KR102576191B1 - Method for matching system for senior user - Google Patents

Abstract

A control method of a matching system between senior users according to an aspect of the present invention includes obtaining, by the server, a recommendation request signal for requesting a matching target recommendation; The server determines whether user information of the first user who has requested to recommend a matching target is deficient because the server uses the first matching target recommendation algorithm that recommends matching targets based on additional information in addition to interest information of the first user. doing; The server uses the first matching object recommendation algorithm based on a result of determining whether or not the deficient state or the second matching object recommendation algorithm recommends a matching object based on the interest information of the first user. selecting user information of at least one second user to be matched with the first user from user information of the second user, and generating the selected user information as recommended user information; and providing, by the server, the recommended user information to the user device.

Description

Control method of matching system between senior users {Method for matching system for senior user}

The present invention relates to a control method of a matching system between senior users, and more particularly, to a method for recommending other users to be matched based on user interest information or selecting one of the user's location information, preferred age information, and preferred appearance information. Based on the above, it recommends other users to be matched, provides chat script information based on the chat history to two users who are matched and chats, and the similarity of the facial image with the user's facial image captured by the user's device is the criterion A control method of a matching system between senior users capable of registering only facial images exceeding a facial image similarity in user information.

Currently, the number of single-person households in Korea as well as foreign countries is gradually increasing. According to the announcement of the National Statistical Office, there are about 5 million single-person households in Korea as of 2018, and the difficulty of living as a single-person household is psychological anxiety. and loneliness were rated the most.

In particular, Korea not only has the fastest aging rate in the world, but also the rate of increase in single-person households among the aging population is rapidly increasing. As of 2021, the elderly population aged 65 or older in Korea accounts for 16.5% of the total population, reaching 8,537,000 people.

Accordingly, socio-cultural research on the aging society to which seniors, the elderly population, belong, continues. According to the research results, enjoying active and productive leisure activities during the increased leisure time in old age has an impact on health satisfaction and social solidarity. Relieve negative emotions such as loneliness and depression of seniors through friendship and exchange activities where you can feel the positive emotions.

According to other research results, seniors valued relationships with people in society/workplace and preferred meeting and communicating with various people, expressing their thoughts and opinions, and exerting their influence. They are also active, and show no hesitation in establishing relationships and communicating with others through clubs and SNS.

In other words, it is being investigated that social communication is necessary to overcome social isolation, loneliness, and depression caused by the loss of social roles and physical aging of seniors.

Recently, seniors no longer simply mean extending lifespan in an old state to the extent that it is not enough to be characterized as 'frailty', and the youth of health, appearance, and nutritional status are showing longer-lasting aspects than before.

In other words, recent seniors have a desire for 'successful aging' in which they achieve self-realization through exchanges with others, without being supported by others in good health and without being economically short.

Therefore, there is a demand for a technology capable of satisfying the seniors' desire for social communication and forming a community among the seniors.

Korean Patent Registration No. 10-2335043

The present invention intends to provide a matching platform with a matching success rate by recommending users with similar interests by recommending other users to be matched based on user interest information.

In addition, the present invention recommends other users to be matched based on at least one of the user's location information, preferred age information, and preferred appearance information, thereby recommending a user who meets the user's preference, so that the matching success rate increases through the matching platform. want to provide

In addition, the present invention provides a matching platform with a matching success rate by inducing smooth chatting by providing chatting script information based on chatting details to two users who are matched and chatting.

In addition, the present invention registers only facial images in which the facial image similarity with the user's facial image captured by the user device exceeds the reference facial image similarity in user information, thereby preventing the act of registering other people's facial images in user information. there is.

The objects of the present invention are not limited to the above-mentioned objects, and other objects and advantages of the present invention not mentioned above can be understood by the following description and will be more clearly understood by the embodiments of the present invention. It will also be readily apparent that the objects and advantages of the present invention may be realized by means of the instrumentalities and combinations indicated in the claims.

A control method of a matching system between senior users according to an aspect of the present invention for solving the above problems includes obtaining, by the server, a recommendation request signal for requesting a recommendation of a matching target; The server determines whether user information of the first user who has requested to recommend a matching target is deficient because the server uses the first matching target recommendation algorithm that recommends matching targets based on additional information in addition to interest information of the first user. doing; The server uses the first matching object recommendation algorithm based on a result of determining whether or not the deficient state or the second matching object recommendation algorithm recommends a matching object based on the interest information of the first user. selecting user information of at least one second user to be matched with the first user from user information of the second user, and generating the selected user information as recommended user information; and providing, by the server, the recommended user information to the user device.

Preferably, in the generating of the recommended user information, if the server determines that the user information of the first user is not deficient, the user information of one or more second users to be matched among the user information of a plurality of second users. selecting user information using the first matching target recommendation algorithm; and when the server determines that the user information of the first user is deficient, the user information of one or more second users to be matched from among the user information of a plurality of second users is used by the second matching target recommendation algorithm. and selecting; may include.

Preferably, in the step of selecting using the second matching target recommendation algorithm, the server classifies the user information of the first user into a plurality of user groups based on a plurality of interest information included in the user information of the first user. including in any one of the user clusters; and selecting, by the server, user information of at least one second user to be matched from among user information of a second user included in a user cluster including user information of the first user.

Preferably, in the step of selecting using the first matching target recommendation algorithm, the server performs the user real-time location information included in the user information of the first user and the user real-time location information included in the user information of the plurality of second users. calculating position difference information indicating a position difference between each position information; calculating, by the server, age difference information by calculating an age difference between preferred age information included in the user information of the first user and age information included in the user information of the plurality of second users; and calculating, by the server, appearance similarity information indicating a degree of appearance similarity between preferred appearance information included in the user information of the first user and user appearance information included in the user information of the plurality of second users. can

Preferably, in the step of selecting using the first matching target recommendation algorithm, the matching success rate of each of the plurality of second users is determined by the server using at least one of the location difference information, the age difference information, and the appearance similarity information. Calculating; and selecting, by the server, user information of a second user within a preset rank in order of the matching success rate.

Preferably, the server may further include generating chat script information based on matched chat history information between the first user and the second user.

Preferably, the user device generates a first user face image of the first user by using a camera photographing function when a camera authentication request requesting facial authentication with a camera photographed image is input from the first user; transmitting, by the user device, an image registration request signal requesting registration of a second user's face image with user information of the first user to the server; And the server calculates a facial image similarity between the first user facial image and the second user facial image when the image registration request signal is received, and based on whether the facial image similarity exceeds a reference facial image similarity The method may further include determining whether to register the second user's face image in the user information of the first user.

Preferably, the step of determining whether to register the second user's face image with the user information of the first user may include, if the facial image similarity exceeds a reference facial image similarity, the server converts the second user's facial image to the first user's user information. registering the user information of the first user; and not registering, by the server, the second user's face image in the user information of the first user if the facial image similarity does not exceed the reference facial image similarity.

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

According to the control method of the system according to the present invention, by recommending other users to be matched based on the user's interest information, the matching success rate of the matching platform can be improved by recommending users with similar interests.

In addition, the present invention recommends other users to be matched based on one or more of the user's location information, preferred age information, and preferred appearance information, thereby increasing the matching success rate of the matching platform by recommending users who satisfy the user's preferences. can improve

In addition, the present invention can improve the matching success rate of the matching platform by inducing smooth chatting by providing chatting script information based on chatting details to two users who are matched and chatting.

In addition, the present invention registers only facial images in which the facial image similarity with the user's facial image captured by the user device exceeds the reference facial image similarity in user information, thereby preventing the act of registering other people's facial images in user information. there is.

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 configuration diagram of a system according to an embodiment of the present disclosure.
2 is a configuration diagram of a first user device, a server, and a second user device included in a system according to an embodiment of the present disclosure.
3 is a flowchart of a method for controlling a system according to an embodiment of the present disclosure.
4 is an exemplary view of how a first user device acquires interest information according to an embodiment of the present disclosure.
5 is an exemplary view of how a first user device acquires a first user's face image according to an embodiment of the present disclosure.
6 is an exemplary view of how a first user device obtains a face image of a second user according to an embodiment of the present disclosure.
7 is an exemplary view of a state in which a server provides chatting inducement information according to an embodiment of the present disclosure.
8 is an exemplary view of a state in which a server provides chatting script information according to an embodiment of the present disclosure.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, only these embodiments are intended to complete the disclosure of the present invention, and are common in the art to which the present invention belongs. It is provided to fully inform the person skilled in the art of the scope of the invention, and the invention is only defined by the scope of the claims.

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and "units" or "modules" may be combined into smaller numbers of components and "units" or "modules" or may be combined into additional components and "units" or "modules". can be further separated.

The spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe a component's correlation with other components. Spatially relative terms should be understood as including different orientations of elements in use or operation in addition to the orientations shown in the drawings. For example, if you flip a component that is shown in a drawing, a component described as "below" or "beneath" another component will be placed "above" the other component. can Thus, the exemplary term “below” may include directions of both below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a configuration diagram of a system according to an embodiment of the present disclosure.

As shown in FIG. 1 , a system according to an aspect of the present invention may include a plurality of user devices 100 and 300 and a server 200 .

At this time, the plurality of user devices 100 and 300 may be divided into a first user device 100 and a second user device 300 .

Specifically, the first user device 100 is a device controlled by a first user requesting matching with another user, and the second user device 200 is a device for a candidate group of second users to be matched with the first user. It may be a device controlled by the included second user.

In this case, when the second user requests matching with another user, the second user device 300 may become the first user device 100 . That is, the first user device 100 and the second user device 300 are not determined between the plurality of user devices 100 and 300 and may be changed according to a user's request.

Hereinafter, the present invention will be described by taking, for example, that there is one first user device 100 and a plurality of second user devices 300 .

Meanwhile, in the present specification, matching may mean that information, messages, and data are transmitted and received so that two users communicate through a system according to an aspect of the present invention.

To this end, the first user device 100 and the second user device 300 send an information registration request signal for requesting registration of user information of each user (first user and second user) to the user information list to the server 200. can be sent to

Here, the user information includes one or more of user name information, user age information, user gender information, user address information, interest information, user real-time location information, preferred age information, preferred appearance information, and first and second user facial images. can do.

The server 200 may register the user information received along with the information registration request signal in the user information list.

Thereafter, when the server 200 receives a recommendation request signal for requesting recommendation of a matching target from the first user device 100, the server 200 selects a user information of a plurality of second users based on user information registered in the user information list. User information of one or more second users to be matched with the first user may be selected to generate recommended user information, and the generated recommended user information may be transmitted to the first user device 100 .

The first user device 100 is a device that receives various information and data from the above-described first user and transmits and receives various information, data, and signals with the server 200, such as a smartphone, a tablet PC, and a personal computer ( PC), TV, console device, set-top box, other control devices, etc., and preferably, the first user device 100 can be implemented as a smart phone.

The second user device 300 is a device that receives various information and data from the above-described second user and transmits and receives various information, data, and signals with the server 200, such as a smartphone, tablet PC, or personal computer (PC). , TV, console device, set-top box, other control devices, etc., and preferably, the second user device 300 can be implemented as a smart phone.

Accordingly, the server 200 may provide application data of a mobile version so that the platform service according to the present invention is implemented in a smartphone.

Meanwhile, a user according to the present invention may be a senior user aged 40 years or older.

2 is a configuration diagram of a first user device, a server, and a second user device included in a system according to an embodiment of the present disclosure.

Referring to FIG. 2 , the first user device 100 may include a memory 110, an input unit 120, a display 130, a processor 140, and a communication unit 150.

The memory 110 may store various programs and data necessary for the operation of the first user device 100 . The memory 110 may be implemented as a non-volatile memory 110, a volatile memory 110, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD).

The processor 140 may control overall operations of the first user device 100 using various programs stored in the memory 110 . The processor 140 may include a RAM, a ROM, a graphic processing unit, a main CPU, first through n interfaces, and a bus. At this time, the RAM, ROM, graphic processing unit, main CPU, first to n interfaces, etc. may be connected to each other through a bus.

RAM stores O/S and application programs. Specifically, when the first user device 100 is booted, the O/S may be stored in RAM, and various application data selected by the user may be stored in RAM.

The ROM stores instruction sets for system booting. When a turn-on command is input and power is supplied, the main CPU copies the O/S stored in the memory 110 to the RAM according to the command stored in the ROM, and executes the O/S to boot the system. When booting is completed, the main CPU copies various application programs stored in the memory 110 to RAM, and executes the application programs copied to RAM to perform various operations.

The graphic processing unit uses a calculation unit (not shown) and a rendering unit (not shown) to create a screen including various objects such as items, images, and text. Here, the calculation unit may be configured to calculate attribute values such as coordinate values, shape, size, color, etc. of each object to be displayed according to the layout of the screen by using a control command received from the input unit. And, the rendering unit may be configured to generate screens of various layouts including objects based on the attribute values calculated by the calculation unit. The screen created by the rendering unit may be displayed within the display area of the display 130 .

The main CPU accesses the memory 110 and performs booting using the OS stored in the memory 110 . And, the main CPU performs various operations using various programs, contents, data, etc. stored in the memory 110 .

The first through n interfaces are connected to the various components described above. One of the first through n interfaces may be a network interface connected to an external device through a network.

Meanwhile, the processor 140 may include one or more cores (not shown) and a graphic processor (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals to and from other components. can

Processor 140 according to one embodiment performs a method described in connection with the present invention by executing one or more instructions stored in memory 110 .

For example, the processor 140 acquires new training data by executing one or more instructions stored in the memory 110, performs a test on the acquired new training data using the learned model, and the test result, First training data in which the labeled information is obtained with accuracy equal to or higher than a predetermined first reference value is extracted, the extracted first training data is deleted from the new training data, and learning is performed using the new training data from which the extracted training data is deleted. The model can be re-trained.

Meanwhile, the processor 140 includes RAM (Random Access Memory, not shown) and ROM (Read-Only Memory) for temporarily and/or permanently storing signals (or data) processed in the processor 140. , not shown) may be further included. In addition, the processor 140 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

The memory 110 may store programs (one or more instructions) for processing and control of the processor 140 . Programs stored in the memory 110 may be divided into a plurality of modules according to functions.

The input unit 120 may receive various types of information from a user. To this end, the input unit 120 may have various input interfaces. For example, the input unit 120 may include a keyboard, mouse, and touch module.

The display 130 is a configuration for visually outputting various information, and may be implemented as a Liquid Crystal Display (LCD), Plasma Display Panel (PDP), Organic Light Emitting Diodes (OLED), Transparent OLED (TOLED), Micro LED, etc. However, it is not limited thereto, and other types of conventionally known displays may be included.

As an example, the display 130 may be implemented in the form of a touch screen capable of detecting a user's touch manipulation, or may be implemented as a flexible display capable of being folded or bent.

The communication unit 150 may communicate with the server 100 . In particular, the communication unit 150 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, a wireless communication chip, an NFC chip, and a low energy Bluetooth chip (BLE chip). At this time, the Wi-Fi chip, the Bluetooth chip, and the NFC chip perform communication in a LAN method, a WiFi method, a Bluetooth method, and an NFC method, respectively. In the case of using a Wi-Fi chip or a Bluetooth chip, various connection information such as an SSID and a session key is first transmitted and received, and various information can be transmitted and received after communication is connected using this. The wireless communication chip refers to a chip that performs communication according to various communication standards such as IEEE, ZigBee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and 5th Generation (5G).

Referring to FIG. 2 , the server 200 may include a memory 210 , a processor 220 and a communication unit 230 .

The memory 210 may store various programs and data necessary for the operation of the server 200 . The memory 210 may be implemented as a non-volatile memory 210, a volatile memory 210, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD).

The processor 220 may control overall operations of the server 200 using various programs stored in the memory 210 . The processor 220 may include a RAM, a ROM, a graphic processing unit, a main CPU, first through n interfaces, and a bus. At this time, the RAM, ROM, graphic processing unit, main CPU, first to n interfaces, etc. may be connected to each other through a bus.

RAM stores O/S and application programs. Specifically, when the server 200 is booted, O/S is stored in RAM, and various application data selected by the user may be stored in RAM.

The ROM stores instruction sets for system booting. When a turn-on command is input and power is supplied, the main CPU copies the O/S stored in the memory 210 to the RAM according to the command stored in the ROM, and executes the O/S to boot the system. When booting is completed, the main CPU copies various application programs stored in the memory 210 to RAM, and executes the application programs copied to RAM to perform various operations.

The main CPU accesses the memory 210 and performs booting using the OS stored in the memory 210 . In addition, the main CPU performs various operations using various programs, contents, data, etc. stored in the memory 210 .

The first through n interfaces are connected to the various components described above. One of the first through n interfaces may be a network interface connected to an external device through a network.

Meanwhile, furthermore, the processor 220 may control the artificial intelligence model. In this case, of course, the processor 220 may include a dedicated graphics processor (eg, GPU) for controlling the artificial intelligence model.

Meanwhile, the artificial intelligence model according to the present invention may be a model based on supervised learning or unsupervised learning. Furthermore, the artificial intelligence model according to the present invention may include a support vector machine (SVM), a decision tree, a neural network, and the like, and methodologies to which they are applied.

As an embodiment, the artificial intelligence model according to the present invention may be an artificial intelligence model based on convolutional deep neural networks (CNN) learned by inputting training data. However, it is not limited thereto, and it goes without saying that various artificial intelligence models can be applied to the present invention. For example, models such as a deep neural network (DNN), a recurrent neural network (RNN), and a bidirectional recurrent deep neural network (BRDNN) may be used as an artificial intelligence model, but are not limited thereto.

At this time, convolutional deep neural networks (CNNs) are a type of multilayer perceptrons designed to use a minimum of preprocessing. A convolutional neural network consists of one or several convolutional layers and general artificial neural network layers placed on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, convolutional neural networks can fully utilize input data with a two-dimensional structure. Also, convolutional neural networks can be trained via standard back-propagation. Convolutional neural networks are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

In addition, deep neural networks (DNNs) are artificial neural networks (ANNs) consisting of a plurality of hidden layers between an input layer and an output layer.

At this time, the structure of the deep neural network may be composed of a perceptron. Perceptron consists of several inputs, one processor, and one output value. The processor multiplies each of a plurality of input values by a weight, and then sums all the input values multiplied by the weight. Then, the processor substitutes the summed value into the activation function and outputs one output value. If a specific value is desired as an output value of the activation function, a weight value multiplied with each input value may be modified, and an output value may be recalculated using the corrected weight value. At this time, each perceptron may use a different activation function. In addition, each perceptron accepts the outputs passed from the previous layer as inputs, and then obtains the outputs using the activation function. The obtained output is passed as input to the next layer. Through the process as described above, several output values can finally be obtained.

Recurrent Neural Network (RNN) refers to a neural network in which the connections between units constituting an artificial neural network constitute a directed cycle. Unlike feed-forward neural networks, recurrent neural networks can utilize the memory inside the neural network to process arbitrary inputs.

Deep Belief Networks (DBN) is a generative graphical model used in machine learning. In deep learning, it means a deep neural network consisting of multiple layers of latent variables. There are connections between layers, but there is no connection between units within a layer.

Due to the characteristics of a generative model, the deep trust neural network can be used for prior learning, and after learning initial weights through prior learning, the weights can be fine-tuned through backpropagation or other discrimination algorithms. This characteristic is very useful when there is little training data, because the smaller the training data, the stronger the influence of the initial weight values on the resulting model. The pre-learned initial value of the weight becomes closer to the optimal weight than the arbitrarily set initial value of the weight, which enables the performance and speed of the fine-tuning step to be improved.

The above-described artificial intelligence and its learning method are described for illustrative purposes, and the artificial intelligence and its learning method used in the above-described embodiments are not limited. For example, all kinds of artificial intelligence technologies and learning methods that can be applied by a person skilled in the art to solve the same problem can be used to implement the system according to the disclosed embodiment.

Meanwhile, the processor 220 may include one or more cores (not shown) and a graphic processing unit (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals to and from other components. can

Processor 220 according to one embodiment performs a method described in connection with the present invention by executing one or more instructions stored in memory 210 .

For example, the processor 220 acquires new training data by executing one or more instructions stored in the memory 210, performs a test on the acquired new training data using the learned model, and the test result, First training data in which the labeled information is obtained with accuracy equal to or higher than a predetermined first reference value is extracted, the extracted first training data is deleted from the new training data, and learning is performed using the new training data from which the extracted training data is deleted. The model can be re-trained.

Meanwhile, the processor 220 includes RAM (Random Access Memory, not shown) and ROM (Read-Only Memory) that temporarily and/or permanently store signals (or data) processed in the processor 220. , not shown) may be further included. In addition, the processor 220 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

The memory 210 may store programs (one or more instructions) for processing and control of the processor 220 . Programs stored in the memory 210 may be divided into a plurality of modules according to functions.

The communication unit 230 may communicate with the first user device 200 . In particular, the communication unit 230 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, a wireless communication chip, an NFC chip, and a low energy Bluetooth chip (BLE chip). At this time, the Wi-Fi chip, the Bluetooth chip, and the NFC chip perform communication in a LAN method, a WiFi method, a Bluetooth method, and an NFC method, respectively. In the case of using a Wi-Fi chip or a Bluetooth chip, various connection information such as an SSID and a session key is first transmitted and received, and various information can be transmitted and received after communication is connected using this. The wireless communication chip refers to a chip that performs communication according to various communication standards such as IEEE, ZigBee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and 5th Generation (5G).

Referring to FIG. 2 , the second user device 300 may include a memory 310, an input unit 320, a display 330, a processor 340, and a communication unit 350.

The memory 310 may store various programs and data necessary for the operation of the second user device 300 . The memory 310 may be implemented as a non-volatile memory 310, a volatile memory 310, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD).

The processor 340 may control overall operations of the second user device 300 using various programs stored in the memory 310 . The processor 340 may include a RAM, a ROM, a graphic processing unit, a main CPU, second through n interfaces, and a bus. At this time, the RAM, ROM, graphic processing unit, main CPU, second to n interfaces, etc. may be connected to each other through a bus.

RAM stores O/S and application programs. Specifically, when the second user device 300 is booted, the O/S is stored in the RAM, and various application data selected by the user may be stored in the RAM.

The ROM stores instruction sets for system booting. When a turn-on command is input and power is supplied, the main CPU copies the O/S stored in the memory 310 to the RAM according to the command stored in the ROM, and executes the O/S to boot the system. When booting is completed, the main CPU copies various application programs stored in the memory 310 to RAM, and executes the application programs copied to RAM to perform various operations.

The graphic processing unit uses a calculation unit (not shown) and a rendering unit (not shown) to create a screen including various objects such as items, images, and text. Here, the calculation unit may be configured to calculate attribute values such as coordinate values, shape, size, color, etc. of each object to be displayed according to the layout of the screen by using a control command received from the input unit. And, the rendering unit may be configured to generate screens of various layouts including objects based on the attribute values calculated by the calculation unit. The screen created by the rendering unit may be displayed within the display area of the display 330 .

The main CPU accesses the memory 310 and performs booting using the OS stored in the memory 310 . And, the main CPU performs various operations using various programs, contents, data, etc. stored in the memory 310 .

The second through n interfaces are connected to the various components described above. One of the second through n interfaces may be a network interface connected to an external device through a network.

Meanwhile, the processor 340 may include one or more cores (not shown) and a graphic processor (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals to and from other components. can

Processor 340 according to one embodiment performs a method described in connection with the present invention by executing one or more instructions stored in memory 310 .

For example, the processor 340 acquires new training data by executing one or more instructions stored in the memory 310, performs a test on the acquired new training data using the learned model, and the test result, Extract the second training data in which the labeled information is obtained with accuracy equal to or higher than a predetermined second reference value, delete the extracted second training data from the new training data, and learn using the new training data from which the extracted training data is deleted. The model can be re-trained.

Meanwhile, the processor 340 includes RAM (Random Access Memory, not shown) and ROM (Read-Only Memory) temporarily and/or permanently storing signals (or data) processed in the processor 340. , not shown) may be further included. In addition, the processor 340 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

The memory 310 may store programs (one or more instructions) for processing and control of the processor 340 . Programs stored in the memory 310 may be divided into a plurality of modules according to functions.

The input unit 320 may receive various types of information from a user. To this end, the input unit 320 may have various input interfaces. For example, the input unit 320 may include a keyboard, mouse, and touch module.

The display 330 is a component for visually outputting various information, and can be implemented with a Liquid Crystal Display (LCD), Plasma Display Panel (PDP), Organic Light Emitting Diodes (OLED), Transparent OLED (TOLED), Micro LED, etc. However, it is not limited thereto, and other types of conventionally known displays may be included.

As an example, the display 330 may be implemented in the form of a touch screen capable of detecting a user's touch manipulation, or may be implemented as a flexible display capable of being folded or bent.

The communication unit 350 may communicate with the server 300 . In particular, the communication unit 350 may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, a wireless communication chip, an NFC chip, and a low energy Bluetooth chip (BLE chip). At this time, the Wi-Fi chip, the Bluetooth chip, and the NFC chip perform communication in a LAN method, a WiFi method, a Bluetooth method, and an NFC method, respectively. In the case of using a Wi-Fi chip or a Bluetooth chip, various connection information such as an SSID and a session key may be first transmitted and received, and various information may be transmitted and received after communication is connected using the same. The wireless communication chip refers to a chip that performs communication according to various communication standards such as IEEE, ZigBee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), and 5th Generation (5G).

3 is a flowchart of a method for controlling a system according to an embodiment of the present disclosure.

As shown in FIG. 3 , in the control method of a matching system between senior users according to an aspect of the present invention, the server 200 obtains a recommendation request signal requesting a matching target recommendation from the first user device 100. Step (S1) may be performed.

Subsequently, the server 200 determines whether the user information of the first user who requested the recommendation of the matching target is in a deficiency state because the server 200 uses the first matching target recommendation algorithm that recommends the matching target based on additional information in addition to the interest information of the first user. The step (S2) of determining whether or not may be performed.

Thereafter, the server 200 uses a first matching object recommendation algorithm based on a result of determining whether or not the user is in a deficiency state or a second matching object recommendation algorithm that recommends a matching object based on the interest information of the first user. A step (S3) of selecting one or more second user user information to be matched with the first user among the user information of the second user and generating the selected user information as recommended user information may be performed.

Finally, the server 200 may perform step S4 of providing recommended user information to the user device.

Before performing step S1, the server 200 may obtain user information from each of the first user device 100 and the second user device 300.

To this end, the first user device 100 and the second user device 300 provide user name information, user age information, user gender information, user address information, interest information, user real-time location information, preferred age information, and preferred appearance information. and a UI capable of receiving or acquiring each of the first and second user face images.

4 is an exemplary view of how a first user device acquires interest information according to an embodiment of the present disclosure.

Referring to FIG. 4 , the first user device 100 may receive interest information of the user from the first user, acquire the interest information, and transmit the acquired interest information to the server 200 .

At this time, the first user device 100 may display a plurality of interest candidate information (A) on the screen and acquire interest candidate information (A') selected and input by the user as interest information (A').

Here, the first user device 100 may obtain a preset number of interest information (A'). For example, the preset number may be four.

Meanwhile, the first user device 100 may also obtain ranking information of each interest information A'. Specifically, the first user device 100 may obtain, as ranking information, the order in which the interest information A' is selected and inputted by the user.

Here, the ranking information may indicate that the user is more interested in the ranking information as the ranking information is higher.

5 is an exemplary view of how a first user device acquires a first user's face image according to an embodiment of the present disclosure, and FIG. It is an exemplary view of how to acquire a facial image.

Referring to FIGS. 5 and 6 , when a camera authentication request (C) requesting face authentication with a camera-photographed image is input from the first user, the first user device 100 uses a camera-photographed function to determine the identity of the first user. By capturing the face, a face image of the first user of the first user may be generated.

To this end, the first user device 100 may provide a UI (D) capable of capturing the face of the first user when a camera authentication request (C) is input.

At this time, the first user device 100 may transmit the first user face image to the server 200 .

Thereafter, the first user device 100 transmits an image registration request signal requesting registration of a second user face image different from the first user face image to the user information of the first user together with the second user face image, and the server 200 ) can be sent.

Then, when the image registration request signal is received, the server 200 calculates a facial image similarity between the first user facial image and the second user facial image, and based on whether the facial image similarity exceeds the reference facial image similarity, the second user facial image similarity is calculated. It is possible to determine whether to register the user's face image in the user information of the first user.

Specifically, the server 200 may register the corresponding second user's face image in user information of the first user only when the facial image similarity exceeds the reference facial image similarity.

Conversely, when the facial image similarity does not exceed the reference facial image similarity, the server 200 may not register the corresponding second user's facial image in user information of the first user.

Here, the first user's face image is an image captured through the shooting UI (D) of the application provided by the server 200 according to the present invention, and the second user's face image is previously stored in the first user device 100. could be an image.

Meanwhile, the server 200 may calculate the above-described facial image similarity using various algorithms or artificial intelligence models for calculating similarity between two images.

Various algorithms or artificial intelligence models that calculate the similarity between these two images adjust the ratio, angle, size, and position of the two images, extract only the region of interest, and extract facial feature points (landmarks) to compare the two images. can

For example, the server 200 may calculate facial image similarity using the “Dlib” model.

Meanwhile, when the first user face image is newly received, the server 200 recalculates the facial image similarity between each of the previously registered second user facial images and the first user facial image, and the recalculated facial image similarity is the reference facial image. A face image of the second user having a similarity or less may be deleted from user information.

Through this, only the second user's face image (B) whose face image similarity with the first user's face image exceeds the reference face image's similarity may be registered in the user information.

Meanwhile, when a recommendation request signal for requesting recommendation of a matching target is received from the first user device 100, the server 200 recommends a matching target based on additional information in addition to the interest information of the first user. Since the algorithm is used, it may be determined whether the user information of the first user who requested the recommendation of the matching target is in a deficient state.

Specifically, the server 200 determines that the user information of the first user is in a deficient state when the user information of the first user does not include real-time user location information, preferred age information, and preferred appearance information, and When the user information includes at least one of user real-time location information, preferred age information, and preferred appearance information, it may be determined that the user information of the first user is not deficient.

Here, the preferred age information may be information representing the preferred age of a second user for whom the first user is recommended as a matching target, and the preferred appearance information may be information representing the preferred appearance of the second user for whom the first user is recommended as a matching target. there is.

For example, the preferred appearance information may be a person image indicating a preferred appearance of the first user.

Thereafter, if it is determined that the user information of the first user is not deficient, the server 200 converts user information of one or more second users to be matched from among the user information of a plurality of second users to a first matching target recommendation algorithm. can be used to select.

Conversely, if the server 200 determines that the user information of the first user is deficient, the user information of one or more second users to be matched from among the user information of a plurality of second users is selected using a second matching target recommendation algorithm. can be selected.

Here, the second matching object recommendation algorithm is an algorithm that recommends a matching object based on interest information of a first user and a plurality of second users, and the first matching object recommendation algorithm is additional user information in addition to the interest information of the first user. It may be an algorithm that recommends a matching target based on information.

When it is determined that the user information of the first user is deficient, the server 200 converts the user information of the first user to any one user among a plurality of user groups based on a plurality of interest information included in the user information of the first user. can be included in clusters.

Thereafter, the server 200 may select at least one user information of a second user to be matched from user information of a second user included in a user cluster including user information of the first user.

In this case, the server 200 may randomly select at least one user information of the second user to be matched from among the user information of the second user included in the user cluster including the user information of the first user.

The server 200 may generate interest information of each of the first user and the second user as a unique embedding vector for each user, and cluster the unique embedding vector for each user into three user clusters in order to generate the aforementioned user clusters.

At this time, the server 200 generates a unique embedding vector, and the rank of interest information may be reflected.

On the other hand, when the server 200 determines that the user information of the first user is not in a deficient state, the server 200 determines the real-time location information of the user included in the user information of the first user and the user information included in the user information of a plurality of second users. Position difference information indicating a position difference between each of the real-time position information is calculated, and age difference information is calculated by calculating the age difference between the preferred age information included in the user information of the first user and the age information included in the user information of a plurality of second users. and may calculate appearance similarity information indicating a degree of appearance similarity between preferred appearance information included in user information of the first user and user appearance information included in user information of a plurality of second users.

At this time, the server 200 excludes the second user whose position difference indicated by the position difference information exceeds the reference position difference from the matching target, and excludes the second user whose age difference indicated by the age difference information exceeds the reference age difference from the matching target, , the second user whose appearance similarity indicated by the appearance similarity information is less than the reference appearance similarity may be excluded from the matching target.

Through this, the server 200 may exclude a second user who is located too far away, has a preferred age and age difference, or has a preferred appearance and appearance that is too different from the matching target.

Meanwhile, the server 200 calculates the similarity between the preferred appearance information (personal image of the preferred appearance) included in the user information of the first user and the face image of the second user included in the user information of the second user, as the above-described appearance similarity information. can be calculated with

Thereafter, the server 200 may calculate a matching success rate of each of the plurality of second users by using at least one of location difference information, age difference information, and appearance similarity information.

Specifically, the server 200 calculates a matching success rate such that the shorter the position difference indicated by the position difference information is, the higher the matching success rate is, and calculates the matching success rate such that the smaller the age difference indicated by the age difference information is, the higher the matching success rate is, and the foreign affairs similarity information The matching success rate may be calculated so that the matching success rate increases as the appearance similarity is higher.

Thereafter, the server 200 may select user information of the second user within preset ranks in order of matching success rate.

The user information of the second user, which has been changed through the above process, is generated as recommended user information by the server 200, and the server 200 may provide the recommended user information to the first user device 100.

Hereinafter, a process of matching a first user and a second user to chat will be described.

At this time, the first user selects any one recommended user information among the recommended user information received by the first user device 100, and the server 200 sends the second user device 300 corresponding to the selected recommended user information. User information of the first user may be transmitted together with the chatting request signal.

Thereafter, the second user device 300 may display user information of the first user on the screen along with a chatting request notification message indicating that the chatting request has been received.

Subsequently, the second user device 300 may transmit a chatting request acceptance signal to the server 200 when a chatting request acceptance input for accepting the chatting request is input from the second user.

When the chatting acceptance signal is received, the server 200 may open a chatting room in which chatting messages are transmitted and received between the first user device 100 and the second user device 300 .

7 is an exemplary view of a state in which a server provides chatting inducement information according to an embodiment of the present disclosure.

When the chat room is opened, the server 200 analyzes the user information of each of the first user and the second user to generate chat induction information (E) for inducing the first user and the second user to start a chat, and the generated chat The guidance information (E) may be transmitted to the first user device 100 and the second user device 300 .

At this time, the server 200 may generate a chatting phrase based on one of the first user's interest information and the second user's interest information as the chatting inducement information (E).

As shown in FIG. 7, if there is overlapping interest information between the interest information of the first user and the interest information of the second user, a chatting phrase based on the overlapping interest information is generated as chat inducement information (E). can

Accordingly, the first user device 100 and the second user device 300 can transmit and receive chatting messages (F, G) on the subject of a common interest between the first user and the second user or an interest of either side of the two users. can

Meanwhile, the server 200 according to another embodiment checks the last time when the chatting message is last transmitted and received from the first user device 100 and the second user device 300, and the data from the last time to the current time The time is generated as an elapsed time, and if the elapsed time exceeds the standard elapsed time, chatting inducement information (E) may be regenerated and transmitted to the first user device 100 and the second user device 300.

At this time, the server 200 according to another embodiment checks whether or not the last transmitted/received chatting message includes content requesting termination or standby of the chatting, and determines whether or not to end or wait for the chatting in the last transmitted/received chatting message. Only when the requested content is not included, the chatting inducement information E may be regenerated and transmitted to the first user device 100 and the second user device 300 .

Through this, when a situation in which it is difficult to continue chatting due to lack of chatting material occurs, a new chatting topic may be suggested.

8 is an exemplary view of a state in which a server provides chatting script information according to an embodiment of the present disclosure.

The first user device 100 may transmit a script request signal requesting chatting script information to the server 200 .

At this time, when the preset phrase (H) is input as a chatting message, the first user device 100 may determine that chatting script information is requested from the first user and transmit a script request signal to the server 200 .

Also, when a preset phrase is input as a chatting message, the corresponding chatting message may not be transmitted to another user's user device (the second user device 300).

Here, the preset phrase is a phrase input by the user to request chatting script information, and may be, for example, “HELP”.

On the other hand, when the chat script request signal is received, the server 200 generates chat script information (H1, ..., H3) based on the chat history information between the first user and the second user, and provides the generated chat script information 1 can be transmitted to the user device 100.

At this time, a plurality of chatting scripts may be included in the chatting script information H1, ..., H3.

Here, the chat script may indicate an example of a chat message suitable for transmission based on chat details between users.

When the chatting script information is received, the first user device 100 displays a plurality of chatting scripts included in the chatting script information on the screen, and when one of the chatting scripts is selected and input by the first user from among the plurality of chatting scripts, the corresponding chat script information is received. Chat scripts can be sent as chat messages.

Meanwhile, the server 200 may extract core keywords from chatting messages transmitted and received during a preset chatting period prior to the time at which the script request signal is received, and search the extracted core keywords from the conversation data set.

In this case, the server 200 may extract, as a key keyword, a keyword having the highest number of appearances among a plurality of keywords included in chatting messages transmitted and received during the chatting period.

Thereafter, the server 200 may configure a plurality of chatting scripts by processing the searched conversation data set, and generate the plurality of chatting scripts as chatting script information.

At this time, the server 200 may search for core keywords in the subject-specific conversation data set and emotional empathy conversation data set of 40 or more people.

Here, the emotional empathy conversation data set may be a conversation data set composed of conversations that emotionally empathize with the first conversation.

Meanwhile, the server 200 searches for words included in the junior use word data set in each of the chatting messages transmitted and received between the first user (first user device) and the second user (second user device) during the chatting period, and If a word included in the used word data set is found in a chat message transmitted and received between the first user and the second user during the chatting period, the user of the user who is the chatting partner of the user who sent the corresponding chat message among the first user and the second user A junior notification message may be sent to the device.

For example, when the server 200 searches for a word included in the junior use words data set among chatting messages sent from the first user to the second user during the chatting period, the chatting partner of the first user who sent the corresponding chatting message. The junior notification message may be transmitted to the second user device of the second user.

Here, the data set of words used by juniors may be a data set composed of words that senior users do not use in chatting and only non-senior junior users use in chatting.

Here, a senior user is a user whose age is included in a preset age range, a junior user is a user whose age is not included in a preset age range, and the preset age range may be set to 40 years or older, but is changed can be set.

Meanwhile, the junior notification message may be a message informing that a conversation partner may not be a senior.

Meanwhile, each of the user devices (first user device and second user device) calculates the chatting input rate of each user (first user and second user), and if the calculated chatting input rate exceeds the standard chatting input rate, A senior non-use notification message notifying that a corresponding user using the user device may not be a senior may be transmitted to the server 200 .

Through the above-described junior notification message and senior non-use notification message, it is possible to monitor a case in which a non-senior user chats or uses a corresponding platform.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Also, different embodiments of the present invention may complement each other or be combined.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), assembler (assembler), may be implemented in a programming or scripting language such as Python (Python). Functional aspects may be implemented in an algorithm running on one or more processors.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: first user device
200: server
300: second user device

Claims (8)

In the control method of a system including a plurality of user devices and servers,
obtaining, by the server, a recommendation request signal requesting a recommendation of a matching target from a first user device controlled by a first user among the plurality of user devices;
The server determines whether user information of the first user who has requested to recommend a matching target is in a deficient state in order to use the first matching target recommendation algorithm that recommends matching targets based on additional information in addition to interest information of the first user. judging;
The server uses the first matching object recommendation algorithm based on a result of determining whether or not the deficient state or the second matching object recommendation algorithm recommends a matching object based on the interest information of the first user. selecting user information of at least one second user to be matched with the first user from among user information of the second user of the second user, and generating the selected user information as recommended user information; and
Including; providing, by the server, the recommended user information to the user device;
The step of determining whether the deficiency state is,
The server determines that the user information of the first user is in a deficient state when the user information of the first user has no real-time user location information, preferred age information, and preferred appearance information, and Determining that the user information of the first user is not deficient when at least one of the user real-time location information, the preferred age information, and the preferred appearance information is included in the information;
The control method of the system,
opening, by the server, a chatting room in which a chatting message is transmitted and received between a second user device controlled by a second user corresponding to the recommended user information selected by the first user and the first user device;
The server analyzes user information of each of the first user and the second user who controls the second user device to generate chatting inducement information for inducing chatting to start, and the first user device and the second user device sending to;
The server checks the last time at which the chatting message is finally received from the first user device and the second user device, generates an elapsed time from the last time to the current time as an elapsed time, and the elapsed time If the reference elapsed time is exceeded, it is checked whether a chatting message last transmitted and received between the first user device and the second user device includes content requesting the end of chatting or standby, and the first user device If the chatting message last transmitted and received between the user device and the second user device does not include content requesting termination of chatting or standby, regenerating the chatting inducement information and transmitting the chatting information to the first user device and the second user device. step;
generating, by the server, chatting script information based on matched chat history information between the first user and the second user;
The first user device calculates a chatting input rate for an input chat, and if the chatting input rate exceeds the standard chatting input rate, a senior non-use notification message notifying that the first user may not be a senior is sent. sending to the server; and
The second user device calculates a chatting input rate for an input chat, and if the chatting input rate exceeds a standard chatting input rate, the second user controlling the second user device may not be a senior Transmitting a senior non-use notification message notifying the server; further comprising,
Generating the chat script information,
extracting, by the server, a key keyword from a chatting message transmitted and received during a preset chatting period prior to the time at which the script request signal is received when the chatting script request signal is received; and
The server searches for the extracted core keyword in a conversation data set, processes the searched conversation data set, configures a plurality of chat scripts, and generates chat script information;
The chat inducement information is
A chatting phrase based on a subject of interest of each of the second users chatting with the first user by controlling the first user and the second user device, the control method of the system.
According to claim 1,
The step of generating the recommended user information
When the server determines that the user information of the first user is not deficient, the user information of one or more second users to be matched from among the user information of a plurality of second users is selected using the first matching target recommendation algorithm. to select; and
When the server determines that the user information of the first user is in a deficient state, the user information of one or more second users to be matched from among the user information of a plurality of second users is selected by using the second matching target recommendation algorithm. Step of screening; including, the control method of the system.
According to claim 2,
The step of selecting using the second matching target recommendation algorithm
including, by the server, user information of the first user in one user cluster among a plurality of user clusters based on a plurality of pieces of interest information included in the user information of the first user; and
The server randomly selects, by the server, user information of one or more second users to be matched from among the user information of the second user included in the user cluster including the user information of the first user. control method.
According to claim 2,
The step of selecting using the first matching target recommendation algorithm
calculating, by the server, location difference information indicating a location difference between user real-time location information included in the user information of the first user and user real-time location information included in the user information of the plurality of second users;
calculating, by the server, age difference information by calculating an age difference between preferred age information included in the user information of the first user and age information included in the user information of the plurality of second users; and
Calculating, by the server, appearance similarity information indicating a degree of appearance similarity between preferred appearance information included in the user information of the first user and user appearance information included in the user information of the plurality of second users; How to control the system.
According to claim 4,
The step of selecting using the first matching target recommendation algorithm
calculating, by the server, a matching success rate of each of the plurality of second users by using at least one of the location difference information, the age difference information, and the appearance similarity information; and
Including, by the server, selecting user information of a second user within a preset rank in order of the matching success rate;
Calculating the matching success rate
calculating a matching success rate so that the matching success rate increases as the position difference indicated by the position difference information becomes shorter;
calculating a matching success rate such that the matching success rate increases as the age difference indicated by the age difference information decreases; and
and calculating a matching success rate so that the higher the appearance similarity indicating the appearance similarity information, the higher the matching success rate.
delete According to claim 1,
generating, by the user device, a first user's face image of the first user by using a camera photographing function when a camera authentication request requesting facial authentication with a camera photographed image is input from the first user;
transmitting, by the user device, an image registration request signal requesting registration of a second user's face image with user information of the first user to the server; and
When the image registration request signal is received, the server calculates a facial image similarity between the first user facial image and the second user facial image, and determines whether the facial image similarity exceeds a reference facial image similarity. Determining whether to register a second user's face image with the user information of the first user; further comprising a control method of the system.
According to claim 7,
The step of determining whether to register the second user's face image with the user information of the first user
registering, by the server, the facial image of the second user in user information of the first user when the facial image similarity exceeds the reference facial image similarity; and
and not registering, by the server, the facial image of the second user in the user information of the first user if the facial image similarity does not exceed a reference facial image similarity.