KR102574972B1 - Method for recommending dog food and server thereof - Google Patents

Abstract

One embodiment of the present invention, the step of receiving the first information including the breed, age and weight of the companion dog; receiving second information including a daily activity amount and daily calorie consumption of the companion dog from a wearable device mounted on the companion dog; inputting the received first information and second information into an AI classification model, and determining at least two or more types of feed as a result of the AI classification model; and controlling the determined two or more types of food to be output to a terminal of the dog owner.

Description

Method for recommending dog food and server thereof {Method for recommending dog food and server thereof}

The present invention relates to a method for recommending food for a companion dog, and more particularly, to a method for recommending the most suitable food for a companion dog when information on the companion dog is collected, and a server for implementing the method. will be.

The size of the industry related to dog products tends to grow along with the increase in the number of single-person households and the change in population structure, which raises the number of people raising companion dogs. In particular, in the case of the dog goods market, including dog food, snacks, toys, and beauty products, changes such as the launch of premium products and the diversification of items through active market entry by large companies and new companies have not only led to quantitative growth of the market, but also In addition, even qualitative growth is appearing, such as an increase in the consumption of high-quality functional products that take into account the health of companion dogs.

Despite the contracted economy due to COVID19, the domestic market for dog supplies is also rapidly expanding. According to the Ministry of Agriculture, Food and Rural Affairs, in 2020, households raising companion dogs accounted for 27.7% of all households, and one out of four households lived with a companion dog, and when converted into population, the number of households raising companion dogs reached 15 million. The pet care market recorded an average annual growth rate of 8.4% from 2016 to 2020.

The domestic dog care market is expected to grow at an average annual rate of 6.1% and reach 3.5 trillion won in 2023. The average cost of raising a companion dog, which is fixedly spent by the companion population raising a companion dog, is 140,000 won per month, and the number of companion population spending more than 250,000 won per month is steadily increasing, accounting for 14.2% of the total. There is an underlying demand for 'canine health care'. Accordingly, the need for a customized dog food recommendation service is emerging.

Republic of Korea Patent Registration No. 10-2320370 (2021.11.02 announcement)

A technical problem to be solved by the present invention is to provide a method for recommending a customized dog food and a server for implementing the method.

A method according to an embodiment of the present invention for solving the above technical problem includes receiving first information including a breed, age, and weight of a companion dog; receiving second information including a daily activity amount and daily calorie consumption of the companion dog from a wearable device mounted on the companion dog; inputting the received first information and second information into an AI classification model, and determining at least two or more types of feed as a result of the AI classification model; and controlling the determined two or more types of pet food to be output to a terminal of the owner of the dog.

In the above method, the receiving of the first information may include receiving the first information from the terminal of the owner.

In the method, in the receiving of the second information, the second information may be received from the wearable device via the terminal of the owner.

The method further includes acquiring third information including allergy information about the companion dog, and the determining of the food includes the received first information, second information, and the obtained third information. By inputting to the AI classification model, as a result of the AI classification model, at least two types of feed may be determined.

In the above method, in the obtaining of the third information, allergy information on the companion dog may be grasped using at least one of the breed and age of the companion dog included in the first information.

In the method, in the obtaining of the third information, allergy information about the companion dog may be grasped based on information received from the terminal of the owner.

In the method, in the step of determining the food, based on the first information and the second information, an evaluation of the activity of the companion dog and an evaluation unrelated to the activity of the companion dog are calculated, and In the step of controlling output to the terminal of the owner, the evaluation of the activity and the evaluation irrelevant to the activity may be controlled to be output to the terminal of the owner of the companion dog together with the information on the pet food.

The method further comprises determining pruritus of the dog based on the information received from the wearable device, and determining the type of allergy of the dog based on the determined pruritus, In the step of determining, the at least two or more types of food may be determined by learning the AI classification model with the received first information, second information, and the identified allergy.

A server according to another embodiment of the present invention for solving the above technical problem includes a memory in which at least one program is stored; and a processor that performs an operation by executing the at least one program, wherein the processor receives first information including the breed, age, and weight of the companion dog, and receives the first information from a wearable device mounted on the companion dog. Receive second information including the daily activity amount and daily calorie consumption of the companion dog, input the received first and second information into an AI classification model, and as a result of the AI classification model, at least two types of food and control such that the determined two or more types of pet food are output to the terminal of the owner of the companion dog.

One embodiment of the present invention may provide a computer readable recording medium storing a program for executing the method.

According to the present invention, it is possible to recommend the most suitable food for a companion dog equipped with a wearable device.

1 is a diagram schematically showing an entire system for implementing an embodiment of the present invention.
2 is a block diagram showing an example of a management server according to the present invention.
3 is a diagram for explaining an example of a process in which a management server receives first information about a dog breed, age, and weight of a companion dog.
4 is a diagram for explaining another example of a process in which a management server receives first information about a dog breed, age, and weight of a companion dog.
5 is a diagram for explaining an example of a process in which a management server receives second information about an activity amount and calories consumed of a companion dog.
6 is a diagram for explaining an example of a process in which a management server receives third information about a dog's allergy.
7 is a diagram conceptually illustrating a process for recommending dog food according to the present invention.
8 is a diagram schematically illustrating an example of a recommended food list displayed on an owner terminal.
9 is a flowchart illustrating an example of a method for recommending a customized dog food according to the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. Effects and features of the present invention, and a method of achieving them will become clear with reference to the embodiments described later in detail together with the drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various forms.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and when describing with reference to the drawings, the same or corresponding components are given the same reference numerals, and overlapping descriptions thereof will be omitted. .

In the following embodiments, terms such as first and second are used for the purpose of distinguishing one component from another component without limiting meaning.

In the following embodiments, singular expressions include plural expressions unless the context clearly indicates otherwise.

In the following embodiments, terms such as include or have mean that features or elements described in the specification exist, and do not preclude the possibility that one or more other features or elements may be added.

When an embodiment is otherwise embodied, a specific process sequence may be performed differently from the described sequence. For example, two processes described in succession may be performed substantially simultaneously, or may be performed in an order reverse to the order described.

1 is a diagram schematically showing an entire system for implementing an embodiment of the present invention.

Referring to FIG. 1 , it can be seen that the entire system 1 according to an embodiment of the present invention has a structure in which a dog owner terminal group 100 and a management server 200 are connected through a communication network 170.

First, the dog owner terminal group 100 includes an owner terminal 110 and a wearable device 115, and the owner terminal 110 and the wearable device 115 are electrically connected through a communication network 170 to communicate. there is. The owner terminal 110 is a terminal used by an owner who owns a companion dog, and means an electronic device equipped with a communication module capable of communicating with the wearable device 115 and the management server 200. Hereinafter, the owner refers to a person who owns a companion dog, and may be referred to as a user according to context.

The owner terminal 110 includes an input device for receiving the owner's input, an output device (display) for visually outputting the input of the owner terminal 110 or the processing result of the terminal, and a communication module capable of communicating with an external device. Since it means a smart device, it is not limited in size or type as long as it includes only the above-described input device, output device, and communication module. For example, although the owner terminal 110 is shown in the form of a smart phone in FIG. 1 , the owner terminal may be a PC, a laptop computer, a netbook, etc. capable of communicating with the management server 200 .

The wearable device 115 is an electronic device that can be mounted on the dog's body to collect the dog's bio signals and periodically or non-periodically transmit the collected bio signals to the owner terminal 110 or the management server 200. means device. Hereinafter, the wearable device 115 will be abbreviated as WD 115. The WD 115 can communicate with the owner terminal 110 through short-range communication such as Bluetooth, Wifi, NFC, and the like, and according to an embodiment, the management server 200 and It is also possible to communicate through the communication network 170 .

In FIG. 1 , the WD 115 is implemented as a collar attached to a dog's neck, but is not limited thereto and may be implemented as a collar attached to various parts such as a dog's ankle or a dog's torso. In addition, although only one WD 115 is shown in FIG. 1, it is not limited thereto, and thus may be a device composed of a plurality of parts according to embodiments.

In FIG. 1, the examination center terminal 130 and the veterinary hospital terminal 150 are shown in the form of a server, but are not limited thereto. In other words, the examination center terminal 130 and the veterinary hospital terminal 150 may be PCs, laptops, netbooks, smart phones, etc. capable of communicating with the management server 200 .

The communication network 170 performs a function of connecting the owner terminal 110, the WD 115, and the management server 200, which are components of the entire system 1 shown in FIG. 1, and includes a data network, a mobile communication network, It may include various wired and wireless communication networks such as the Internet. In particular, in the present invention, the communication network 170 includes not only the mobile communication network currently in use, but also the old-generation mobile communication network that has already been used and discarded, and the next-generation mobile communication network to be used after the infrastructure is built, GSM (Global System for Mobile communications) , Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), CDMA 2000, Long Term Evolution (LTE), Long Term Evolution Advanced (LTE-A), 5-Generation (5G) and It can be one of the 6G mobile communication networks.

Since the communication network 170 is a network implemented by an Internet Service Provider (ISP) that can activate the communication function of the owner terminal 110 and the WD 115 according to the rate plan used by the owner, the entire system 1 of FIG. ), but may be implemented by an ISP base station server and a communication cable for physically and logically implementing the communication network 170.

The owner may receive the WD 115 equipped with a module capable of communicating with the communication company server (eg, USIM) while concluding a communication contract at the communication company agency. After the communication contract is concluded, the WD (115) becomes able to communicate with the management server (200) through the communication network (170) operated by the communication company server, and the dog's biological signals collected by the WD (115) are kept secure. It may be transmitted periodically or non-periodically to the management server 200 in the status. The WD 115 may independently communicate with the management server 200 through the communication network 170 operated by the communication company server without passing through the owner terminal 110 .

According to the present invention, the owner can visit a nearby telecommunications agency, sign a communication contract for the WD (115), and receive a WD (115) capable of communicating with the management server (200) through the communication network (170). , It is possible to receive the benefits of the customized feed recommendation method according to the present invention simply by visiting telecommunications agencies distributed throughout the country. Also, according to embodiments, the WD 115 may be a general communication device that is sold at an electronic device store and can be equipped with a USIM.

The management server 200 may process an operation for determining recommended pet food for the owner's companion dog based on the biosignal received from the WD 115 . The management server 200 physically or logically includes an AI classification model capable of recommending the most suitable food for a companion dog at the present time by synthesizing the basic characteristics and additional characteristics of each companion dog.

Specifically, the management server 200 may determine the current health status and activity of the companion dog and determine whether a new allergy has occurred in the companion dog by receiving and analyzing the biosignal of the companion dog from the WD 115 . The management server 200 may perform an operation to determine at least two or more pet foods suitable for companion dogs according to a series of processes described later, and output the results to the owner terminal 110 .

2 is a block diagram showing an example of a management server according to the present invention.

Referring to FIG. 2 , it can be seen that the management server 200 includes a communication unit 210 , a processor 220 and a DB 230 . Hereinafter, it will be described with reference to FIG. 1 .

The management server 200 according to an embodiment of the present invention corresponds to at least one or more processors, or may include at least one or more processors. Accordingly, the communication unit 210, the processor 220, and the DB 230 included in the management server 200 and the management server 200 may be driven in a form included in a hardware device such as a microprocessor or a general-purpose computer system. can

The name of each module included in the management server 200 shown in FIG. 2 is arbitrarily named to intuitively describe the representative function performed by each module, and when the management server 200 is actually implemented, each module may be given a name different from that described in FIG. 2 .

In addition, the number of modules included in the management server 200 of FIG. 2 may vary depending on the embodiment. More specifically, the management server 200 of FIG. 2 includes a total of three modules, but according to an embodiment, at least two or more modules are integrated into one module, or at least one or more modules are separated into two or more modules. It may be implemented in the form of

The communication unit 210 is a module operable with the same communication protocol as the communication module included in the owner terminal 110 and the WD 115, and implements a communication function. The communication unit 210 may include one or more components that enable wired/wireless communication with an external server or external device. For example, the communication unit 210 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast reception unit (not shown).

The DB 230 stores various data necessary for the management server 200 to operate. As an example, the DB 230 stores an integrated management program for controlling the operation of the management server 200, and the DB 230 may receive and store data received by the communication unit 210. A part of the integrated management program stored in the DB 230 may be distributed in the form of a client and installed in the owner terminal 110 .

The DB 230 includes random access memory (RAM) such as dynamic random access memory (DRAM) and static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and CD-ROM. ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

The processor 220 controls the overall operation of the management server 200. For example, the processor 220 may generally control an input unit (not shown), a display (not shown), the communication unit 210, and the DB 230 by executing programs stored in the DB 230. The processor 220 may control the operation of the management server 200 by executing programs stored in the DB 230.

The processor 220 may include application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, and microcontrollers. It may be implemented using at least one of micro-controllers, microprocessors, and electrical units for performing other functions.

As an example, the processor 220 receives first information including the breed, age, and weight of the companion dog, and second information including the daily activity amount and daily calorie consumption of the companion dog from the wearable device (WD) mounted on the companion dog. Receiving information, inputting the received first information and second information into an AI classification model, determining at least two types of food as a result of the AI classification model, and determining that the two or more types of food are the companion dog's owner terminal (110 ) can be controlled to be output.

In the present invention, the first information, the second information and the AI classification model will be described later with reference to FIGS. 3 to 9. In addition, a process in which the processor 220 determines at least two types of food will be described with reference to FIGS. 3 to 9 .

3 is a diagram for explaining an example of a process in which a management server receives first information about a dog breed, age, and weight of a companion dog.

More specifically, FIG. 3 exemplarily shows a screen that can be implemented by an application installed in the owner terminal 110, and the owner of the companion dog downloads a client from the management server 200 and uses the owner terminal It is installed in (110), a sign-in procedure is performed, and information about a companion dog can be input as shown in FIG. 3.

Hereinafter, for convenience of description, a user is assumed to refer to the same person as the owner of a companion dog. Also, in the present invention, information on the breed, age, and weight of the companion dog is regarded as information included in the first information. That is, in the present invention, the first information refers to information about the basic characteristics of a companion dog.

As shown in FIG. 3 , the user may input information about the weight and age of the companion dog after executing the application installed on the owner terminal 110 . Information on the weight and age of the companion dog entered into the owner terminal 110 is transmitted to the management server 200, stored in the DB 230 of the management server 200, and managed as user metadata. It can be. As shown in FIG. 3 , the user may additionally input information on activity and allergy in addition to the weight and age of the companion dog, which will be described later.

4 is a diagram for explaining another example of a process in which a management server receives first information about a dog breed, age, and weight of a companion dog.

Referring to FIG. 4 , after executing an application installed on the owner terminal 110, the user may input information about the approximate size of the companion dog and the breed of the companion dog. In FIG. 4 , the information on the approximate size of the dog can be valid information when the user does not accurately know the weight of the dog, and the approximate size and breed of the dog, which are information input by the user, are processed as first information. It can be stored in the DB 230 of the management server 200 and utilized.

Information about the approximate size of the dog and the breed of the dog entered into the owner terminal 110 is transmitted to the management server 200, stored in the DB 230 of the management server 200, and the user's metadata ( metadata) can be managed.

5 is a diagram for explaining an example of a process in which a management server receives second information about an activity amount and calories consumed of a companion dog.

The WD 115 described in FIG. 1 can be continuously mounted on at least one part of the dog's body to collect biometric information of the dog in various ways. The dog's bio-signals collected by the WD 115 may be processed into indicators for analyzing the dog's activity level and calories consumed. Hereinafter, in order to distinguish it from the above-mentioned first information, information on the amount of activity and calories consumed of the companion dog that can be obtained from the biosignal collected by the WD 115 will be referred to as second information.

As shown in FIG. 5 , the amount of activity and calories consumed of the companion dog may be measured on a daily basis or a weekly basis. A dog's activity level and calories burned tend to be directly proportional to each other, but depending on the dog's individual characteristics, this is not necessarily the case. For example, if the dog breed is a pit bull terrier, even if the amount of activity calculated from the biosignals collected by the WD (115) is low, the calorie consumption is relatively high due to the high basal metabolic rate unique to the pit bull terrier. can be calculated as high.

Hereinafter, an example of a mathematical formula that the management server 200 refers to in calculating the amount of activity of a companion dog will be described.

Equation 1 is an example of a mathematical formula for the management server 200 to calculate the actual use time. In Equation 1, T _sub is the amount of activity, k _n is the weight for each behavioral characteristic, a _n is the time for the behavioral characteristic, M is the number of behavioral characteristics, and R is the correction value. Depending on the embodiment, the correction value R may be omitted.

Equation 1 best reflects the health state of the companion animal by applying a higher weight to behaviors that are useful in determining the health state of the companion animal and applying a lower weight to behaviors that have little to do with the health state of the companion animal. It can be understood as an equation for calculating the total amount of time for which bio-signals are collected. For example, if a companion animal performs an action with a weight of 1.01 for 1 hour and an action with a weight of 0.98 for 1 hour, the management server 200 determines the amount of activity based on the collected bio-signals as a value for 1.99 hours instead of 2 hours. can be calculated as

In addition, the correction value R is a value that is added separately to increase the accuracy of the amount of activity, and may vary according to the breed of the companion dog. Information on the correction value R is previously stored in the DB 230 of the management server 200 . That is, in the present invention, the correction value R varies depending on the breed of the companion dog, and the breed of the companion dog is information included in the first information as described above, so when calculating the amount of activity in the present invention, the correction value R is essentially If included, the second information including information on the amount of activity and calories burned may be information dependent on the first information.

6 is a diagram for explaining an example of a process in which a management server receives third information about a dog's allergy.

As shown in FIG. 6 , the user can check the screen displayed on the owner terminal 110 and select food that causes an allergic reaction when his/her dog eats it. The information on the allergy of the dog entered into the owner terminal 110 is transmitted to the management server 200, stored in the DB 230 of the management server 200, and metadata of the user and the user's companion dog can be managed as According to the present invention, the user can distinguish and select allergies corresponding to meat, grains, and other groups, so that the user can clearly recognize and exclude food materials that can cause allergies to dogs.

Unlike that shown in FIG. 6, according to another embodiment of the present invention, the management server 200 automatically obtains the third information about the dog's allergy based on the collected first and second information You may. This will be described later in the description of FIG. 7 .

7 is a diagram conceptually illustrating a process for recommending dog food according to the present invention.

In the present invention, the management server 200 learns the AI classification model using additional data in basic data, thereby generating result data indicating that the food suitable for companion dogs is any one of A, B, and C products. A process of calculating and outputting the calculated result data to the owner terminal 110 may be performed.

In FIG. 7 , basic data may be a concept corresponding to the aforementioned first information. The basic data may be information including information about the breed, age, and weight of the companion dog, which is information input by the user to the owner terminal 110. Basic data refers to information about the dog's main physical characteristics.

As an embodiment, the first information may be information for which a total of 100 points is the highest point.

First, a score may be set for the breed of the companion dog input by the user. Basically, when the companion dog is any one of a small dog, a medium dog, and a large dog, 20 points may be given as a score for the dog breed. In the present invention, the size classification of companion dogs determined by dog breeds can utilize the dog breed standards of 344 dog breeds established by the World Canine Federation (FCI) standard. For example, if the dog is a Welsh Corgi, it can be classified as a medium-sized dog.

Subsequently, a score may be set for the age of the companion dog input by the user. When a dog's age is 0-2 years old, it is considered as an infant and gets 40 points. When a dog's age is 3-6 years old, it is considered an adolescent and gets 30 points. If the age exceeds 10 years, 10 points may be awarded each.

Finally, the management server 200 may set a score for the weight of the companion dog based on the previously determined dog breed (size due to the dog breed) and age. As an example, if the companion dog is a small dog and has a weight of 3.0 kg to 6.0 kg, the management server 200 may assign a weight score of 40, which is a score for the average weight. As another example, if the companion dog is a medium-sized dog and weighs more than 21 kg, the management server 200 may assign a weight score of 20, which is a score for obesity.

Table 1 is a table showing criteria for scores that can be set by the management server 200 for the weight of a companion dog by way of example. Referring to Table 1, according to the weight received after the breed of the dog is confirmed and the classification for the size of the dog is completed, it is determined whether the dog's weight status is thin, average, or obese, and the score is determined accordingly. can be known to be

As described above, the management server 200 determines the basic data for the companion dog based on the dog's breed, age, and weight (a total of three factors), and inputs the determined basic data as part of the learning data of the AI classification model. , which determines the type of feed. According to the foregoing, the minimum value of basic data is 40 points (thinness in old age or obesity in old age), and the maximum value of basic data can be 100 points, and since the present invention is not limited to the above example, , the size of basic data may be lower than 40 points or higher than 100 points.

In FIG. 7 , additional data 1 may be a concept corresponding to the aforementioned second information. Additional data 1 may be information about the amount of daily activity and daily consumption of calories of the companion dog calculated based on the bio-signals of the companion animal collected from the WD 115 . Additional data 1 is common in that it is the body information of the companion dog like the basic data, but unlike the basic data, which is received and built by the management server 200 in a way that the user directly inputs into the owner terminal 110, it is installed on the companion dog It is different in that it is information calculated after the dog's bio-signals are collected from the WD 115 located there. The management server 200 may determine a food suitable for the companion dog by using the result of inputting the basic data and the additional data 1 to the AI classification model, and as will be described later, the basic data, the additional data 1, and the additional data 2 are converted to the AI classification model. You can also use the results entered in to determine the food suitable for your dog.

As described above, the management server 200 determines additional data 1 for the companion dog based on the information collected from the WD 115, inputs the determined additional data 1 as part of the learning data of the AI classification model, and decide the type. The management server 200 may set a score for the amount of activity and calories consumed of the companion dog by referring to Tables 2 and 3 described later, and determine the final value of additional data 1 as the sum of the scores.

Referring to Tables 2 and 3, dogs that showed above-average calorie consumption with active movements had a total activity score of 100 (60+40), and dogs that showed less than average calorie consumption for infrequent movements had a total activity score of 40 ( 20 + 20) points.

In FIG. 7 , additional data 2 may be a concept corresponding to third information. In the present invention, the third information may include allergy information of the companion dog and information about the purchase history of the user's food. The dog's allergy information may be directly input by the user to the owner terminal 110, but may be automatically acquired by the management server 200. The management server 200 may estimate the dog's allergy information through the dog's biological signals collected in the WD 115.

For example, as a result of analyzing the biosignals collected from the companion dog equipped with the WD 115, if the companion dog shows movement corresponding to pruritus after eating a specific feed (food), the management server 200 ), it is estimated that the specific food (food) has an allergic factor that causes itching in the companion dog, and the food containing the same ingredient can be excluded from the recommended food list.

In addition, the management server 200 may determine the feed purchase history purchased by the user in the past, and determine a pet food with ingredients similar to those purchased in the past or a similar price range as the recommended feed.

In FIG. 7, additional data 2 has a different attribute from basic data or additional data 1. More specifically, basic data and additional data 1 are data for training an AI classification model in order to select at least two or more recommended foods for companion dogs, and additional data 2 is at least some of the foods included in the list of recommended foods already selected. means data to exclude.

According to FIG. 7 , the management server 200 may finally determine product A, product B, and product C as recommended feed. The management server 200 may provide the user with an opportunity to choose by recommending three types of feed, and the user may raise a companion dog healthily by referring to the nutrient information provided together with the information of the three types of feed. . Here, the nutrient information provided by the management server 200 together with feed information may include information about the reason for recommending nutrients and the function of each nutrient, as shown in Table 4 below.

Table 4 shows an example of nutrient information provided together with feed information as a table. The user can directly check the nutritional components required for the current companion dog, and which component among them causes allergies in the dog, increasing the convenience of parenting. Table 4 shows that, according to the information of the currently entered companion dog, the food ingredients that should be nutritionally included in the dog's recommended food are chicken neck, dry skim milk powder, and anchovy, among which chicken neck can cause allergies only in the companion dog, It clearly indicates that it should be excluded from the recommended feed ingredients.

Table 5 shows an example of a recommended feed list output to the owner terminal 110 by the management server 200 as a table. Table 5 lists a total of four recommended feeds, one of which is classified as an allergy-exempt product, and ultimately becomes a product not recommended to the user.

As shown in Table 5, the management server 200 according to the present invention provides several feeds that are most recommended at the present time along with information on recommended nutrients, thereby guaranteeing the user's choice, and containing allergy-inducing food materials. , If there is a pet food that has been primarily selected and finally excluded, information on the excluded pet food can be provided to the owner terminal 110 together with information on other recommended feeds as shown in Table 5.

8 is a diagram schematically illustrating an example of a recommended food list displayed on an owner terminal.

Referring to FIG. 8, as a result of the AI classification model performed by the management server 200 while determining the recommended food, the owner terminal 110 has a comment on the health condition of the companion dog and at least two types of recommendations. Feed can be output. By checking the information shown in FIG. 8, the user can not only easily know the recommended food, but also intuitively know that the dog's activity level is low and the dog's age is high, so the joints must be thoroughly managed. The convenience of child rearing can be maximized.

9 is a flowchart illustrating an example of a method for recommending a customized dog food according to the present invention.

Since the method according to FIG. 9 can be implemented by the management server 200 described in FIGS. 1 to 8 and the processor 220 included in the management server 200, it will be described with reference to FIGS. 1 to 8. , descriptions overlapping with those described above will be omitted.

The management server 200 may receive first information including the breed, age, and weight of the companion dog (S910).

As an example of step S910, the first information may be received from the owner terminal 110 of an owner who owns a companion dog. An embodiment in which the first information is input to the owner terminal 110 and transmitted to the management server 200 has already been described with reference to FIG. 3 .

The management server 200 may receive second information including daily activity and daily consumption calories of the companion dog from the wearable device (WD, 115) mounted on the companion dog (S930).

As an embodiment of step S930, the management server 200 may receive the second information from the WD 115 via the owner terminal 110. According to this embodiment, the WD 115 does not need to communicate directly with the management server 200 through a communication network, and the second information can be transmitted to the owner terminal 110 through short-range communication with the owner terminal 110 Therefore, it is convenient that the present invention can be implemented even if the WD 115 includes only a module supporting short-range communication such as Bluetooth and Wifi.

The management server 200 may input the received first information and second information into an AI classification model, and determine at least two types of food as a result of the AI classification model (S950).

In step S950, the first information and the second information may be embedded and converted into feature vectors in order to be input to the AI classification model. This can be equally applied to the aforementioned third information (allergy information or information on feed purchase details). The AI classification model is an artificial intelligence classification model that is physically or logically included in the processor 220 of the management server 200, receives vector (matrix) form data, and performs learning based on the input data. , It means a model made to recommend at least two or more foods most suitable for companion dogs, which generated first information and second information. In the present invention, the AI classification model is a model based on deep learning, and according to the internal data processing method, logistic regression, support vector machine, convolutional neural network It may be any one of (CNN: Convolutional Neural Network) and Recurrent Neural Network (RNN).

As an optional embodiment, the management server 200 acquires third information including allergy information for companion dogs, inputs the received first information, second information, and obtained third information into an AI classification model, As a result of the AI classification model, at least two types of feed may be determined. Here, the management server 200 may determine the allergy information on the companion dog based on the information received from the owner terminal 110, or by using at least one of the breed and age of the companion dog included in the first information. there is.

In particular, in this optional embodiment, the management server 200 is able to grasp allergy information that is easy to suffer from according to the breed and age of the dog, using the information stored in the DB 230.

The management server 200 may control the output to the owner terminal 110 of the determined two or more types of dog food (S970).

As an optional embodiment, the management server 200 calculates an evaluation of the activity of the companion dog and an evaluation unrelated to the activity of the companion dog based on the first information and the second information, and the evaluation of the activity and the activity are irrelevant One evaluation can be output through the owner terminal 110 . In this optional embodiment, the evaluation irrelevant to activity may be at least one of the information on the recommended nutrients described in Tables 4 and 5 or the dog's allergy information automatically identified based on the first information. The user can check not only the recommended feed, but also evaluation of activity and evaluation unrelated to activity (dog allergy information that the user was not aware of) at once, so parenting convenience can be increased.

As another optional embodiment, the management server 200 determines the dog's pruritus based on the information received from the WD 115, and identifies the dog's allergy type based on the determined pruritus, At least two kinds of food may be determined by letting the AI classification model learn the first information, the second information, and the type of allergy identified. In this optional embodiment, the management server 200 may determine that the companion dog is feeling itching from the information received from the WD 115 mounted on the companion dog. For example, from the information collected by the sensor of WD 115, if a dog continuously scratches a part of the dog's body with its front or hind paws, or a dog licks a part of the dog's body with its tongue at a high frequency, The management server 200 may determine that the companion dog has pruritus. After determining that the companion dog has pruritus, the management server 200 refers to allergy information for the same breed as the companion dog, or checks the user's food purchase history to find out what can be caused by the food recently paid to the companion dog. It is possible to check allergy information, estimate the dog's allergy from the confirmed information, and reflect the estimated allergy information when calculating the recommended food list, ultimately recommending the most suitable and safe food for the dog. be able to

According to the present invention, a user can conveniently receive food recommendations simply by inputting basic body characteristics of a companion dog through a terminal.

In addition, according to the present invention, the user can be provided with information on activity evaluation and allergy as well as recommended food suitable for the companion dog, so that the convenience of raising the companion dog can be increased.

Embodiments according to the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the medium is a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a ROM hardware devices specially configured to store and execute program instructions, such as RAM, flash memory, and the like.

Meanwhile, the computer program may be specially designed and configured for the present invention, or may be known and usable to those skilled in the art of computer software. An example of a computer program may include not only machine language code generated by a compiler but also high-level language code that can be executed by a computer using an interpreter or the like.

Specific implementations described in the present invention are examples and do not limit the scope of the present invention in any way. For brevity of the specification, description of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted. In addition, the connection of lines or connecting members between the components shown in the drawings are examples of functional connections and / or physical or circuit connections, which can be replaced in actual devices or additional various functional connections, physical connection, or circuit connections. In addition, if there is no specific reference such as “essential” or “important”, it may not be a component necessarily required for the application of the present invention.

In the specification of the present invention (especially in the claims), the use of the term “above” and similar indicating terms may correspond to both singular and plural. In addition, when a range is described in the present invention, it includes an invention in which individual values belonging to the range are applied (unless there is a description to the contrary), and each individual value constituting the range is described in the detailed description of the invention Same as Finally, unless an order is explicitly stated or stated to the contrary for the steps constituting the method according to the present invention, the steps may be performed in any suitable order. The present invention is not necessarily limited according to the order of description of the steps. The use of all examples or exemplary terms (eg, etc.) in the present invention is simply to explain the present invention in detail, and the scope of the present invention is limited due to the examples or exemplary terms unless limited by the claims. it is not going to be In addition, those skilled in the art can appreciate that various modifications, combinations and changes can be made according to design conditions and factors within the scope of the appended claims or equivalents thereof.

100: owner terminal group
110: owner terminal
115: wearable device
170: communication network
200: management server
210: communication department
220: processor
230 DB

Claims (10)

Receiving first information including the breed, age, and weight of the companion dog;
receiving second information including daily activity amount and daily calorie consumption of the dog from a wearable device composed of a plurality of parts mounted on the dog's ankle and torso;
Based on the information received from the wearable device composed of the plurality of parts, pruritus occurring after ingestion of the dog's food is determined, and based on the determined pruritus, the type of allergy of the dog is identified, Acquiring third information including allergy information about the companion dog;
inputting the received first information, second information, and third information into an AI classification model, and determining at least two kinds of feed as a result of the AI classification model; and
and controlling the determined two or more types of food to be output to a terminal of the owner of the dog. According to claim 1,
Receiving the first information,
A method of recommending customized dog food, wherein the first information is received from the terminal of the owner. According to claim 1,
Receiving the second information,
The method of recommending customized dog food, wherein the second information is received from the wearable device via the terminal of the owner. According to claim 1,
The method,
Further comprising obtaining third information including allergy information for the companion dog,
The step of determining the feed is,
The method of recommending customized dog food, wherein the received first information, the second information, and the obtained third information are input to the AI classification model, and at least two types of pet food are determined as a result of the AI classification model. According to claim 4,
Obtaining the third information,
The method of recommending customized dog food, wherein allergy information on the dog is identified using at least one of the breed and age of the dog included in the first information. According to claim 4,
Obtaining the third information,
The method of recommending customized dog food, wherein allergy information on the dog is grasped based on information received from the terminal of the owner. According to claim 1,
The step of determining the feed is,
Calculating an evaluation of the activity of the companion dog and an evaluation unrelated to the activity of the companion dog based on the first information and the second information;
The step of controlling the output to the terminal of the owner of the companion dog,
A method for recommending a customized dog food, wherein the evaluation of the activity and the evaluation irrelevant to the activity are controlled to be output to a terminal of the owner of the dog along with information on the food. delete A computer-readable recording medium storing a program for executing the method according to claim 1. a memory in which at least one program is stored; and
A processor that performs calculations by executing the at least one program,
the processor,
Receiving first information including the breed, age and weight of the companion dog;
Receiving second information including daily activity amount and daily calorie consumption of the dog from a wearable device composed of a plurality of parts mounted on the dog's ankle and torso;
Based on the information received from the wearable device composed of the plurality of parts, pruritus occurring after ingestion of the dog's food is determined, and based on the determined pruritus, the type of allergy of the dog is identified, Acquire third information including allergy information for dogs,
Inputting the received first information, second information, and third information into an AI classification model, and determining at least two types of feed as a result of the AI classification model,
A server for recommending customized dog food, which controls the determined two or more types of food to be output to a terminal of the owner of the dog.

Images