KR20230086859A - Method and device for matching companion - Google Patents

Abstract

Provided are a companion matching method and a companion matching device. The companion matching method includes the steps of: obtaining various data through applications provided to a companion; recognizing the data by natural language processing the acquired data, and extracting data about a user with the most similar tendencies to the companion through a preset matching algorithm using the natural language processed data as an input; and recommending the user with the most similar tendencies to the companion by transmitting the extracted data to a terminal used by the companion. The present invention provides convenience, high trust, and strong intimacy to the user.

Description

Companion matching method, companion matching device {METHOD AND DEVICE FOR MATCHING COMPANION}

The present invention relates to a recommended companion matching method and a recommended companion matching device.

In the age of 15 million companions, it is necessary to recommend the best friend according to the characteristics and inclinations of the companion animal or companion owner through a companion-only community. In addition, users can share information such as necessary education, care, and products through exchanges with friends in their neighborhood, friends who raise companion animals similar to mine, and experienced companions or experts, and experience the difficulties of raising companion animals together. are trying to solve Therefore, it is necessary to share daily life with companion animals raised by companions, form a healthier companion culture according to the life cycle of companion animals, and recommend modeling technology that emotional companions can trust.

Publication No. 10-2019-0130180, 2019.11.22

An object to be solved by the present invention is to provide convenience, high trust, and deep intimacy to the user by recommending the most customized user to the companion.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

Companion matching method according to an aspect of the present invention for solving the above-described problems is, through an application serviced to the companion, companion data for the companion, first companion for the first companion animal raised by the companion Obtaining animal data, image data for each of the companion and first companion animal, content data for content uploaded from the application, and SNS data for social networking service (hereinafter referred to as SNS) used by the companion Recognize the companion data, first companion animal data, image data, content data, and SNS data by natural language processing of the data acquisition step, companion data, first companion animal data, image data, content data, and SNS data, Natural language-processed companion data, first companion animal data, image data, content data, and SNS data are used as inputs, and through a preset matching algorithm, among a plurality of users registered in the database, the most similar to the propensity of the companion A data extraction step of extracting user data for a user having an inclination and second companion animal data for a second companion animal raised by the user, and transmitting the user data and the second companion animal data to a terminal used by the owner, and a user recommendation step of recommending to the companion a user with a disposition most similar to that of the companion.

Companion matching device according to another aspect of the present invention for solving the above problems, through an application serviced to the companion, companion data for the companion, first companion for the first companion animal raised by the companion Obtaining animal data, image data for each of the companion and first companion animal, content data for content uploaded from the application, and SNS data for social networking service (hereinafter referred to as SNS) used by the companion Recognize the companion data, first companion animal data, image data, content data, and SNS data by natural language processing of the data acquisition unit, companion data, first companion animal data, image data, content data, and SNS data, Natural language-processed companion data, first companion animal data, image data, content data, and SNS data are used as inputs, and through a preset matching algorithm, among a plurality of users registered in the database, the most similar to the propensity of the companion By transmitting the user data for a user having an inclination and the second companion animal data for a second companion animal raised by the user, and the user data and the second companion animal data to the terminal used by the companion, A user recommendation unit recommending to the companion a user with a disposition most similar to the inclination of the companion is included.

Other specific details of the invention are included in the detailed description and drawings.

According to the present invention, by recommending the most customized user to the companion, it has the effect of providing convenience, high trust, and thick intimacy to the user.

In addition, according to the present invention, companions who raise special animals such as rare species and peculiar constitutions, or who live in areas with relatively little companion animal-related facilities or information, can also use the present invention to develop a By sharing information and services on customized companion animals, the problem of blind spots in information access can be supplemented.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram for explaining a partner matching system according to an embodiment of the present invention.
2 is a flowchart illustrating a partner matching method according to an embodiment of the present invention.
FIG. 3 is a flowchart for explaining the data extraction step shown in FIG. 2 in detail.
4 is a diagram for explaining an embodiment of extracting data.
5 is a diagram exemplarily illustrating extracted data according to an embodiment of the present invention.
6 is a diagram illustrating an embodiment of an application to which an embodiment of the present invention is applied.
7 is a diagram showing another embodiment of an application to which an embodiment of the present invention is applied.
8 is a diagram showing another embodiment of an application to which an embodiment of the present invention is applied.
9 is a diagram illustrating an embodiment of matching a recommended companion in an application to which an embodiment of the present invention is applied.

Like reference numbers designate like elements throughout the specification. This specification does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present invention belongs is omitted. The term 'unit, module, member, or block' used in the specification may be implemented as software or hardware, and according to embodiments, a plurality of 'units, modules, members, or blocks' may be implemented as one component, It is also possible that one 'part, module, member, block' includes a plurality of components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case of being directly connected but also the case of being indirectly connected, and indirect connection includes being connected through a wireless communication network. do.

In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

Throughout the specification, when a member is said to be located “on” another member, this includes not only a case where a member is in contact with another member, but also a case where another member exists between the two members.

Terms such as first and second are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

Expressions in the singular number include plural expressions unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of description, and the identification code does not explain the order of each step, and each step may be performed in a different order from the specified order unless a specific order is clearly described in context. there is.

Hereinafter, the working principle and embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a diagram for explaining a partner matching system according to an embodiment of the present invention.

Referring to FIG. 1 , the partner matching system may include a partner matching device 100 and a user terminal 200 .

The companion matching device 100 may recommend items related to companions and companion animals to the user terminal 200 . In addition, when the companion matching device 100 receives feedback from the user terminal 200, the companion matching device 100 selects items related to companions and companion animals based on the feedback received from the user terminal 200. can be updated And, the partner matching device 100 may provide the updated item to the user terminal 200 . The partner matching device 100 may provide an application to the user terminal 200 .

The partner matching device 100 includes a data acquisition unit 110, a data extraction unit 120, a user registration unit 130, a communication providing unit 140, a feedback execution unit 150, and a user recommendation unit 160. can include

The data acquisition unit 110 may obtain various data from the user terminal 200 through an application. The data acquisition unit 110 may obtain companion data for the companion. The companion may be, for example, a user using the user terminal 200 . When the companion raises a companion animal, the data acquisition unit 110 may acquire first companion animal data for the companion animal raised by the companion. The data acquisition unit 110 may acquire image data for each companion and companion animal. The data acquisition unit 110 may obtain content data for content uploaded from an application. The data acquisition unit 110 may obtain SNS data for the SNS used by the companion.

The data extractor 120 processes the companion data, first companion animal data, image data, content data, and SNS data in natural language (or full text search), and performs companion data, first companion animal data, and image data. , content data, and SNS data can be recognized. Then, the data extractor 120 receives natural language processed companion data, first companion animal data, image data, content data, and SNS data as inputs, and through a preset matching algorithm, a plurality of users registered in the database. Among them, user data for a user having the most similar propensity to the companion and second companion animal data for a second companion animal raised by the user may be extracted.

In one embodiment, the data extractor 120 assigns a weight to each natural language processed data, sets a similarity having a preset range for each of a plurality of users based on the weight assigned, and sets the similarity to the set similarity. Based on this, a user having a degree of similarity higher than a predetermined reference value may be determined as a user having the most similar tendency.

The user registration unit 130 stores the information of the user (or companion) using the user terminal 200 in a database using data obtained from the user terminal 200, so that the user (or companion) can be registered as a new user. You can register as a user.

The communication providing unit 140 may provide chat space information so that a chat is possible between the companion and the recommended user. Alternatively, the communication providing unit 140 may generate and provide community information with characteristics identical to those of the companion. In the characteristic community according to the characteristic community information, the companion, health common sense information, companion animal neutering surgery information, information that informs the health status of the companion animal through the companion animal's excrement, information on how to feed the companion animal's medicine, and companion animal prevention Inoculation information, information on when companion animals' teeth fall out, wild beast owner insurance subscription information, nutritional information, exercise method information, safe walking course information, emergency room information, etc. can be provided. In addition, companions are recommended affiliated stores such as specialized veterinary hospitals, training, pet-friendly cafes, playgrounds, shopping centers, etc. suitable for companion animals around the residence according to the life cycle of the companion animal and the owner's interest, and basic health checkup according to the constitution You can receive customized recommendation services such as kits, assistive devices, home appliances, bedding/furniture, and IoT-related products.

The feedback execution unit 150 may perform feedback on the similarity determination performed by the data extraction unit 120 by reflecting chatting information between the companion and the recommended user in the chatting space to the matching algorithm.

The user recommendation unit 160 may recommend a user with the most similar disposition to the companion by transmitting the user data and the second companion animal data to the user terminal 200 used by the companion. In one embodiment, the user recommendation unit 160 may recommend and match users (ie, neighborhood friends) within a preset radius of the companion's residence.

The data acquisition unit 110, the data extraction unit 120, the user registration unit 130, the communication providing unit 140, the feedback execution unit 150, and the user recommendation unit 160 are within the companion matching device 100. It may be implemented with a memory (not shown) for storing data for an algorithm for controlling the operation of components or a program for reproducing the algorithm, and a processor (not shown) for performing the above-described operation using the data stored in the memory. there is. In this case, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

At least one component may be added or deleted corresponding to the performance of components of the partner matching device 100 shown in FIG. 1 . In addition, it will be easily understood by those skilled in the art that the mutual positions of the components may be changed corresponding to the performance or structure of the system.

Although not shown, the partner matching device 100 may further include a communication unit, a storage unit, a display unit, and an input unit.

The communication unit may include one or more components enabling communication with an external device, and may include, for example, at least one of a short-distance communication module, a wired communication module, and a wireless communication module.

The short-range communication module uses a wireless communication network such as a Bluetooth module, an infrared communication module, a Radio Frequency Identification (RFID) communication module, a Wireless Local Access Network (WLAN) communication module, an NFC communication module, and a Zigbee communication module to transmit signals at a short distance. It may include various short-range communication modules that transmit and receive.

Wired communication modules include not only various wired communication modules such as Local Area Network (LAN) modules, Wide Area Network (WAN) modules, or Value Added Network (VAN) modules, but also USB (Universal Serial Bus) ), high definition multimedia interface (HDMI), digital visual interface (DVI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS).

In addition to the WiFi module and the WiBro module, wireless communication modules include global system for mobile communication (GSM), code division multiple access (CDMA), wideband code division multiple access (WCDMA), and universal mobile telecommunications system (UMTS). ), a wireless communication module supporting various wireless communication schemes such as Time Division Multiple Access (TDMA) and Long Term Evolution (LTE).

The wireless communication module may include a wireless communication interface including an antenna and a transmitter. The wireless communication module may include a wireless communication interface including an antenna and a receiver.

The storage unit includes nonvolatile memory devices such as cache, read only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), and flash memory, or random access memory (RAM). ) or a storage medium such as a volatile memory device or a hard disk drive (HDD, Hard Disk Drive) or a CD-ROM, but is not limited thereto. The storage unit may be a memory implemented as a separate chip from the processor, or may be implemented as a single chip with the processor.

The display part includes a cathode ray tube (CRT), a digital light processing (DLP) panel, a plasma display panel, a liquid crystal display (LCD) panel, and an electro luminescence (electro luminescence: EL) panel, Electrophoretic Display (EPD) panel, Electrochromic Display (ECD) panel, Light Emitting Diode (LED) panel or Organic Light Emitting Diode (OLED) panel, etc. It may be provided, but is not limited thereto.

The input unit includes hardware devices such as various buttons, switches, pedals, keyboards, mice, track-balls, various levers, handles, and sticks for user input. can do. Also, the input unit may include a GUI (Graphical User Interface), ie, a software device, such as a touch pad for user input. The touch pad is implemented as a touch screen panel (TSP) and may form a mutual layer structure with the display unit. When configured with a touch screen panel (TSP) forming a mutual layer structure with a touch pad, the display unit may also be used as an input unit.

The user terminal 200 may be implemented as a computer or portable terminal capable of accessing a device through a network. Here, the computer includes, for example, a laptop, a desktop, a laptop, a tablet PC, a slate PC, etc. equipped with a web browser, and a portable terminal, for example, has portability and mobility. As a guaranteed wireless communication device, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication) -2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminal, smart phone (Smart Phone) based on all types of handhelds It may include a wireless communication device and a wearable device such as a watch, ring, bracelet, anklet, necklace, glasses, contact lens, or head-mounted-device (HMD).

Each component shown in FIG. 1 means software and/or hardware components such as a Field Programmable Gate Array (FPGA) and Application Specific Integrated Circuit (ASIC).

2 is a flowchart illustrating a partner matching method according to an embodiment of the present invention.

Referring to FIGS. 1 and 2, the partner matching method includes data acquisition step (S10), data extraction step (S20), user recommendation step (S30), registration step (S40), communication step (S50), and feedback step. (S60) may be included.

The data acquisition step (S10) is a step in which the companion matching device 100 acquires companion data, first companion animal data, image data, content data, and SNS data through an application serviced to the companion. . The first companion animal data may be data representing a companion animal raised by a companion. The image data may be data representing images for each of the companion and the first companion animal. The content data may be data representing content uploaded from an application provided to the companion.

The SNS data may include data related to SNS posts uploaded by the companion from an application or posts uploaded from another SNS application, and external data. (As an example, images and reviews of pet-friendly cafes)

The SNS data is data of SNS used by the companion. For example, the SNS channel may include Instagram / FB ^TM , Naver Cafe / Blog ^TM , YouTube ^TM , companion animal community, etc. For example, pet-friendly cafe images, reviews, ratings, number of visitors, and cafe information (atmosphere, friendliness, location, contact information, auxiliary facilities, operating hours), etc. may be included.

In addition, the external data that can be included in the SNS data includes research data and reports such as type, species, characteristics, propensity, constitution, personality, and appearance of companion animals around the world, SNS and community data (image and text data related to companion animals), and It may include at least one of the data of the data partner. The data of the above data affiliates are veterinary hospitals (type-specific constitution for aging dogs and elderly cats, disease data, necessary nutrients/inoculation/health checkup information by life cycle), companion animal hairdressers (hair management by breed and seasonal care methods), and Data on at least one of the feed companies (allergens and precautions, recommended nutrients by life cycle, natural raw material information and related ingredients, etc.) can be included.

At this time, examples of recommendation results are companion friend recommendations suitable for my companion animal and me (today's recommendation, personalized recommendation), companion content recommendation suitable for my companion animal and me, and companion meeting suitable for my companion animal and me. It can include recommendations, services, products, regions, information, etc. suitable for companion animals and me by time.

In another embodiment, if the companion does not raise a companion animal, the companion matching device 100 may not acquire the first companion animal data. In this case, in the data acquisition step (S10), adoption intention data indicating whether there is an intention to adopt an animal, animal characteristic data indicating the characteristics of the animal to be adopted, and adoption time data indicating the adoption time may be further acquired. can

In the data extraction step (S20), the companion matching device 100 processes the companion data, first companion animal data, image data, content data, and SNS data in natural language, so that companion data, first companion animal data, and image Recognize data, content data, and SNS data, and the companion matching device 100 inputs natural language-processed companion data, first companion animal data, image data, content data, and SNS data, and pre-set matching This is a step of extracting, through an algorithm, user data for a user having the most similar disposition to a companion among a plurality of users registered in the database and second companion animal data for a companion animal raised by the user.

The user recommendation step (S30) is a step in which the companion matching device 100 transmits user data and second companion animal data to the user terminal 200 to recommend a user with the most similar disposition to the companion to the companion. .

In the registration step (S40), the companion matching device 100 takes natural language processed companion data, first companion animal data, image data, content data, and SNS data as inputs, learns through machine learning, and learns This is the step of registering the partner as a new user in the database based on the data obtained.

The communication step (S50) is a step in which the companion matching device 100 provides chatting space information so that the companion and the recommended user can chat.

The feedback step (S60) is a step in which the companion matching device 100 performs feedback on similarity determination by reflecting chatting information between the companion and the recommended user in the chatting space to the matching algorithm.

The companion matching method of the present invention may be executed by a computer program stored in a computer-readable recording medium in order to perform the companion matching method in combination with a computer, which is hardware.

FIG. 3 is a flowchart for explaining the data extraction step shown in FIG. 2 in detail.

1 to 3, the data extraction step (S20) includes weighting (S200), similarity setting (S210), user determination (S220), database updating (S230). ) may be included.

The step of assigning weights (S200) is a step in which the companion matching device 100 assigns different weights to each of the natural language-processed companion data, first companion animal data, image data, content data, and SNS data. . For example, the companion matching device 100 assigns a first weight to companion data, a second weight to first companion animal data, a third weight to image data, and a third weight to content data. 4 weights are assigned, and a 5th weight is assigned to SNS data. In this case, the N+1th weight (where N is a natural number) may be smaller than the Nth weight. However, it is not limited thereto.

The step of determining the degree of similarity ( S210 ) is a step of determining the degree of similarity having a preset range for each of a plurality of users based on the weight assigned by the companion matching device 100 . The degree of similarity may have, for example, a range of 1 to 100, and the closer the degree of similarity is to 100, the more similar it may be. The companion matching device 100 sets a similarity from 1 to 100 for each of a plurality of users registered in the database. However, it is not limited thereto.

In the step of determining the user (S220), the companion matching device 100 determines a user having a similarity equal to or higher than a preset reference value as a user having the most similar tendency based on the similarity determined for each of a plurality of users. It is a step. For example, it is assumed that a similarity is set for each of a plurality of users stored in a database and a reference value is 90. In this case, the companion matching device 100 determines users having a similarity of 90 or more among a plurality of users as users having the most similar propensity. However, it is not limited thereto.

Updating the database (S230) is a step in which the companion matching device 100 processes the image data to detect companion information and companion animal information, and stores the detected information in the database. This will be described later with reference to FIG. 4 .

4 is a diagram for explaining an embodiment of extracting data.

Referring to FIGS. 1 to 4 , an image group IMG GROUP may include a plurality of images. For example, the image group (IMG GROUP) includes a first image (IMG 1) including companion animals and companions, and a second image (IMG 1) including acquaintances of companions and companion animals or only companion animals. 2), and a third image (IMG 3) including the companion's family and companion animal. However, it is not limited thereto.

In one embodiment, in the data extraction step (S20), the companion matching device 100 analyzes image data through Vision API (Image analysis with Vision API). For example, the companion matching device 100 analyzes the first to third images (IMG 1, IMG 2, and IMG 3) included in the image group (IMG GROUP) using Vision API. do. However, it is not limited thereto. As a result of the analysis, information on the partner's gender, age, emotional state, disposition, and exposure may be detected from the analyzed data (ANALYZED DATA). In addition, information on the type of companion animal (eg, dog breed), emotional state, and propensity may be detected from the analyzed image. However, it is not limited thereto, and information on whether the companion and/or companion animal is introverted, extroverted, or creative may also be detected.

5 is a diagram exemplarily illustrating extracted data according to an embodiment of the present invention.

Referring to FIG. 5, companion data includes personal information, job information, disposition information, hobby information (eg, likes to travel, cares for companion animals, is interested in health, etc.), in-app payment information etc. may be included. Personal information may include, for example, gender, age, family relationship, location (ie, place of residence) of the companion, type of residence, and the like. Occupational information may include, for example, the companion's occupation, the companion's working hours, place of work, income, and the like. However, it is not limited thereto, and information about the companion's experience raising a companion animal may also be included in the companion data.

Companion animal data may include body information, health information, personality information, education information, food information, and the like. Physical information is, for example, type (dog breed in the case of dogs, specifically, raising Maltese, raising old dogs and newly adopted dogs, raising dogs and cats together, raising animals other than dogs and cats, etc.), gender, age , height, size, weight, size, presence or absence of hair, color, mixed race, etc. Health information may include, for example, disease (eg, whether or not the patella is weak), eating habits, amount of exercise, constitution, vaccination status, and the like. Education information may include formal education or not. However, it is not limited thereto.

Content data includes contents planned and produced by the business operator (or management team) that produced the application (for example, everything about cat grooming), reports uploaded to the application, article contents, inquiry contents, review contents, review ratings, etc. can include

The SNS data may include the main customer base, positive words, negative words, emotional words, post content, and images and dates uploaded to the SNS.

6 is a diagram illustrating an embodiment of an application to which an embodiment of the present invention is applied.

Referring to (a) of FIG. 6 , a companion (or an application user) who raises a companion animal may upload at least one image of a companion animal through the application. In addition, the companion can input information about the type of companion animal to raise. For example, the companion can input information about the type of companion animal by selecting one or more of displayed dogs, cats, birds, fish, reptiles/amphibians/insects/, and others. The owner can enter information about the companion animal's name, breed, and gender. The companion can enter an article introducing the companion animal.

Referring to (b) of FIG. 6 , a user using the application does not have a companion animal or a companion who already has a companion animal can input information about which companion animal he or she wants to adopt and whether or not to adopt it. For example, the user may input adoption information by selecting one or more of displayed dogs, cats, birds, fish, reptiles/amphibians/insects/, and others. In addition, the user may input information about breed, gender, and adoption period.

Referring to (c) of FIG. 6 , a user who uses the application does not have a companion animal or a companion who already has a companion animal may input information about a subject of interest to a companion animal. Information on a subject of interest to a companion animal may include, for example, a walk once a day, a neat person, a guardian of many children, a fashionista, and a butler, but is not limited thereto.

The application of the present invention may be a community application that recommends meetings, meetings, contents, etc. of companions based on data such as data and location of companion animals and companions. When the companion uses the application, the application provides basic data (eg, registered companion information, companion animal information, and images, etc.) and log data (eg, companion data recorded while using the application). data), and posting data (eg, images according to posting activity, texts, data on meetings, etc.) (eg, "I'm going to volunteer work together."), characteristic data (eg, type of companion animal, etc.) ), disease data, etc. can be integrated and analyzed to recommend a customized user to the companion using the application. Here, the posting data is a series of activities in which a user posts and manages postings within the service provided by the present invention, a series of activities in communication such as like, follow, chatting, comments, etc., and service usage data (payment, search, hash tag , access time, location, etc.).

As an example of recommendation, there is a recommendation for a 33-year-old male user who is planning adoption as a partner who has newly subscribed to the application of the present invention. As a companion who has been using the application of the present invention for 1 month, there is a recommendation for a 24-year-old female user who has been 3 months since adopting a golden retriever and lives in an apartment located in Seongnam, Gyeonggi-do. There is a recommendation for a 45-year-old woman who has signed up for the application of the present invention for 14 days and is running a companion animal cafe in Seongsu-dong. There is a recommendation for a 33-year-old working woman who has subscribed to the application of the present invention for 3 months and raises a 10-year-old and female Chihuahua and a Korean short cut cat estimated to be 2 years old. There is a recommendation for a 27-year-old woman who has been using the application of the present invention for 4 months, is active in posting activities, and raises rabbits and lizards. However, it is not limited thereto.

7 is a diagram showing another embodiment of an application to which an embodiment of the present invention is applied.

Referring to FIG. 7 , the user may be provided with information about other companions' posts uploaded to the application. For example, the companion can check the user information 310 indicating the nickname, gender, age, and keywords of the user recommended by the application. However, it is not limited thereto. For another example, the companion may check posting information 320 indicating a post posted by a user recommended by the application. The posting information 320 may include photos, texts, hashtags, etc., but is not limited thereto. For another example, the companion may check response information 330 for a post posted by a user recommended by the application. The response information 330 may include, for example, the number of likes and comments, but is not limited thereto. For another example, the companion may check communication information 340 of another user uploaded with respect to a post posted by a user recommended by the application or input the communication information 340 . The communication information 340 may be, for example, commenting, but is not limited thereto.

8 is a diagram showing another embodiment of an application to which an embodiment of the present invention is applied.

Referring to FIG. 8 , the companion can pay for currency used in the application through an in-app payment system provided by the application. In this case, the companion can use the currency acquired through in-app payment to recommend a user with a tendency more similar to that of the companion. For example, a companion, using currency, "recently accessed friends", "recently connected friends", "friends who raise the same species as me", "me and me" included in the personalized recommendation information 400 You can choose friends with similar interests. In the customized recommendation information 400, more weights described above with reference to FIG. 3 may be assigned to items selected by the partner. However, it is not limited thereto, and if the companion receives many buttons for adding friends, etc., the probability of matching the companion with the user may further increase.

9 is a diagram illustrating an embodiment of matching a recommended companion in an application to which an embodiment of the present invention is applied.

Referring to FIG. 9 , the companion may receive recommendations for users having a propensity most similar to that of the companion through an application.

Referring to (a) of FIG. 9, for example, other user's photo, nickname (or name), age, place of residence, existence within a radius of several kilometers, image types in the form of a card including a friend add button, etc. By sequentially listing (410, 420), the companion can be recommended for users.

Referring to (b) of FIG. 9 , for example, card-type image types including photos, nicknames, ages, places of residence, etc. of other users are arranged in a Go type (430), so that the companion can receive recommendations for users. can

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. Instructions may be stored in the form of program codes, and when executed by a processor, create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media in which instructions that can be decoded by a computer are stored. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, and the like.

As above, the disclosed embodiments have been described with reference to the accompanying drawings. Those skilled in the art to which the present invention pertains will understand that the present invention can be implemented in a form different from the disclosed embodiments without changing the technical spirit or essential features of the present invention. The disclosed embodiments are illustrative and should not be construed as limiting.

100: companion matching device
110: data acquisition unit
120: data extraction unit
130: user recommendation unit
140: communication provision unit
150: feedback execution unit
160: user register
200: user terminal

Claims (10)

Companion data for the companion, first companion animal data for the first companion animal raised by the companion, image data for each of the companion and the first companion animal, a data acquisition step of acquiring content data for content uploaded from the application and SNS data for a social networking service (SNS) used by the companion;
The companion data, the first companion animal data, the image data, the content data, and the SNS data are processed in natural language, so that the companion data, the first companion animal data, the image data, the content data, and the Recognize SNS data, take the natural language processed companion data, the first companion animal data, the image data, the content data, and the SNS data as inputs, and through a preset matching algorithm, a plurality of data registered in the database a data extraction step of extracting user data for a user having a propensity most similar to that of the companion and second companion animal data for a second companion animal raised by the user; and
Companion person matching including a user recommendation step of recommending a user with a propensity most similar to that of the companion to the companion by transmitting the user data and the second companion animal data to a terminal used by the companion. method. According to claim 1,
The data acquisition step,
Companion matching method characterized by further acquiring adoption intention data indicating whether there is an intention to adopt an animal, animal characteristic data indicating characteristics of an animal to be adopted, and adoption time data indicating a time to adopt. According to claim 2,
The data extraction step,
assigning different weights to each of the natural language-processed companion data, the first companion animal data, the image data, the content data, and the SNS data;
determining a similarity having a preset range for each of the plurality of users based on an assigned weight; and
Companion matching method comprising the step of determining a user having a similarity equal to or greater than a preset reference value as a user having the most similar propensity based on the similarity determined for each of the plurality of users. According to claim 3,
The data extraction step,
Information on the gender, age, emotional state, disposition, and exposure of the companion is detected through the image data through Vision API, and information on the type, emotional state, and disposition of the first companion animal , and updating the database by storing the detected information in the database. According to claim 4,
The companion data processed in natural language, the first companion animal data, the image data, the content data, and the SNS data are used as inputs to learn through machine learning, and the companion to the database based on the learned data Companion matching method characterized in that it further comprises a registration step of registering the person as a new user. According to claim 5,
Companion matching method characterized in that it further comprises a communication step of providing chatting space information so that chatting is possible between the companion and the recommended user. According to claim 6,
The companion matching method further comprises a feedback step of performing feedback on similarity determination by reflecting chatting information between the companion and the recommended user in the chatting space to the matching algorithm. According to claim 7,
The companion data includes gender, age, family relationship, location where the companion lives, occupation of the companion, working hours of the companion, experience of raising companion animals, hobbies, and inclinations of the companion. ego,
The first companion animal data is data representing type, gender, age, size, weight, disease, eating habits, exercise amount, presence of hair, appearance, personality, color, constitution, mixed blood, education level, and vaccination,
The content data is data representing reports, articles, reviews and ratings, and inquiries uploaded to the application;
Characterized in that the SNS data is data representing the main customer base, positive words, negative words, emotional words, images uploaded to the SNS, and dates. A computer program stored in a computer-readable recording medium in order to perform the matching method of any one of claims 1 to 8 in combination with a computer that is hardware. Companion data for the companion, first companion animal data for the first companion animal raised by the companion, image data for each of the companion and the first companion animal, a data acquisition unit that obtains content data for content uploaded from the application and SNS data for social networking service (SNS) used by the partner;
The companion data, the first companion animal data, the image data, the content data, and the SNS data are processed in natural language, so that the companion data, the first companion animal data, the image data, the content data, and the Recognize SNS data, take the natural language processed companion data, the first companion animal data, the image data, the content data, and the SNS data as inputs, and through a preset matching algorithm, a plurality of data registered in the database a data extraction unit for extracting user data for a user having a propensity most similar to that of the companion and second companion animal data for a second companion animal raised by the user; and
Companion-person matching device including a user recommendation unit for recommending a user with a propensity most similar to that of the companion-person to the companion-person by transmitting the user data and the second companion animal data to a terminal used by the companion-person .

Images