KR102079441B1 - A method and server for providing a service for determining matching fitness of users - Google Patents

Abstract

A method for providing a service for determining matching suitability of a plurality of users according to an embodiment of the present disclosure for realizing the above-described problem is disclosed. Deriving each propensity information for each user by analyzing social networking service (SNS) information of a plurality of users; Processing the derived propensity information into a trained evaluation model to generate evaluation information for each of the plurality of users; And generating matching suitability between the group users by processing evaluation information of each selected group user among the plurality of users and social relation information between the group users as a matching suitability determination model.

Description

A method and server for providing a service for determining the matching suitability of a plurality of users {A METHOD AND SERVER FOR PROVIDING A SERVICE FOR DETERMINING MATCHING FITNESS OF USERS}

The present disclosure relates to a matching service, and more particularly, to a method of providing a service for determining matching suitability between a plurality of users.

Today, people live in constant social interactions in economic, political, legal, moral, and other customs. People in these social relationships have different characteristics. In order to maintain a good social relationship, it is important that the individual's inclinations fit well with each other, and high suitability for the propensity of many people included in the social relationship can have a good effect in the social relationship.

Accordingly, there is an invention that provides various interpretation functions by performing psychological tests of users and comparing psychological test result information in order to determine fitness between members in a social relationship.

However, in the related art, it takes time for a user to directly perform a psychological test, and subjective to his evaluation, the test result may be distorted according to a personality characteristic of a person.

Therefore, there is a demand in the art for a system that collects the user's objectized information more easily and determines the suitability of multilateral propensity through the analysis of the propensity of the user.

KR 10-2014-0053749

The present disclosure is devised in response to the above-described background art, and is to provide a service for determining matching suitability between users.

In one embodiment of the present disclosure for solving the above problems, as a method for providing a service for determining the matching suitability of a plurality of users, by analyzing the Social Networking Service (SNS) information of a plurality of users to each of the propensity information Deriving for each user; Processing the derived propensity information into a trained evaluation model to generate evaluation information for each of the plurality of users; And generating matching suitability between the group users by processing evaluation information of each selected group user among the plurality of users and social relation information between the group users as a matching suitability determination model.

Alternatively, the SNS information may include profile, feed, comment, friends, like, follow, album information and image information associated with the plurality of users. It may include at least one of.

Alternatively, analyzing the SNS information of the plurality of users and deriving the propensity information of each user for each user may include: analyzing the SNS information by at least one of natural language processing and image content analysis; It may include.

Alternatively, the natural language processing may derive nouns and adjectives with respect to the text of the SNS information, analyze the context to derive the emotions of the user, and extract the representative words of the sentences to derive the subject.

Alternatively, the image content analysis may perform place recognition, face recognition, facial expression recognition, and specific object recognition on the image of the SNS information, and position analysis through the place recognition, the number of persons through the face recognition. It may include at least one of counting, analysis of the emotion of the person by recognizing the expression on the person, and image analysis by determining the brand of the object.

Alternatively, the propensity information includes at least one of personality characteristic information, needs information, value information, and taste information, and is derived in at least one of an exponential form and a T / F form. It may be characterized by.

Alternatively, the personality trait information may include information about openness, sincerity, outgoingness, affinity, and emotional ups and downs.

Alternatively, the learned evaluation model is composed of an artificial neural network (Artificial Neural Network), it may be characterized in that it is learned through a supervised learning method.

Alternatively, the supervised learning method may include: deriving learning evaluation information for each user through the survey results of the plurality of users; Labeling the derived learning evaluation information on learning propensity information; Deriving an error by comparing the output of the learning tendency information output from the artificial neural network with the learning evaluation information; And back-propagating the error derived as a result of the comparison to the artificial neural network to update the weight of the artificial neural network.

Alternatively, the survey may be composed of question texts for acquaintances of a plurality of users, and to derive evaluations of each of the plurality of users.

Alternatively, the social relationship information may include information about all kinds of human relationships that may be formed between a plurality of users.

Alternatively, the matching suitability may be provided to the user by including at least one of matching ratio information and comment information according to the matching suitability.

In another embodiment of the present disclosure, a server for providing a service for determining matching suitability of a plurality of users is disclosed. The server includes a processor including one or more cores; And a memory storing program codes executable in the processor, wherein the processor comprises: a propensity information management module configured to analyze SNS information of a plurality of users and derive respective propensity information for each user; An evaluation information management module for processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users; And a matching suitability management module configured to process evaluation information of each selected group user among the plurality of users and social relation information between the group users as a matching suitability determination model to generate matching suitability between the group users.

In yet another embodiment of the present disclosure, a computer program stored on a computer readable storage medium including encoded instructions is disclosed. The computer program, when executed by one or more processors of a computer system, causes the one or more processors to perform the following steps for predicting a figure related to health, wherein the steps include: Deriving each propensity information for each user by analyzing social networking service information; Processing the derived propensity information into a trained evaluation model to generate evaluation information for each of the plurality of users; And generating matching suitability between the group users by processing evaluation information of each selected group user among the plurality of users and social relation information between the group users as a matching suitability determination model.

The present disclosure can provide a service for determining matching suitability between users.

Various aspects are now described with reference to the drawings, wherein like reference numerals are used to refer to like components throughout. In the following examples, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects. However, it will be apparent that such aspect (s) may be practiced without these specific details.
1 is a conceptual diagram illustrating a server for determining matching junctions of a plurality of users according to an embodiment of the present disclosure.
2 is a block diagram of a server for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.
3 illustrates a schematic diagram of an artificial neural network that constitutes a learned evaluation model associated with one embodiment of the present disclosure.
4 is a flowchart of a method for providing a service for determining matching suitability of a plurality of users in accordance with an embodiment of the present disclosure.
5A is an exemplary diagram illustrating a process of determining a matching suitability of two users associated with one embodiment of the present disclosure.
FIG. 5B is an exemplary diagram illustrating the fitness of each user based on the relationship between the boss and the load related to the exemplary embodiment of the present disclosure.
6 is a flow chart of a supervised learning method associated with an embodiment of the present disclosure.
7 is a flowchart illustrating means for determining matching suitability of a plurality of users in accordance with one embodiment of the present disclosure.
8 is a flowchart illustrating a module for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.
9 is a flowchart illustrating logic for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.
10 is a flowchart illustrating a circuit for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.
11 shows a brief general schematic diagram of an example computing environment in which one embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings, wherein like reference numerals are used to refer to like elements throughout. In the present specification, various descriptions are presented to provide an understanding of the present disclosure. However, it will be apparent that such embodiments may be practiced without these specific details. In other instances, well-known structures and devices are provided in block diagram form in order to facilitate describing the embodiments.

As used herein, the terms “component”, “module”, “system” and the like refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component may be, but is not limited to being, a process running on a processor, a processor, an object, an thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a processor and / or thread of execution, and a component can be localized within one computer or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components may for example be signals having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system and / or data over a network such as the other system and the internet via signals and / or signals). May communicate via local and / or remote processes.

In addition, the terms "comprises" and / or "comprising" mean that such features and / or components are present, but exclude the presence or addition of one or more other features, components, and / or groups thereof. It should be understood that it does not. Also, unless otherwise specified or in the context of indicating a singular form, the singular in the specification and claims should generally be construed as meaning "one or more."

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure should not be limited to the embodiments set forth herein but should be construed in the broadest scope consistent with the principles and novel features set forth herein.

1 is a conceptual diagram illustrating a server 100 that provides a service for determining matching junctions of a plurality of users according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users, the network and the user terminal may transmit information through wireless and / or wired interconnection, And can receive.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining a matching suitability of a plurality of users may determine a multiparty matching suitability. In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may derive information on propensity of each of the plurality of users by collecting and analyzing SNS information of the plurality of users. The SNS information collected from the plurality of users may include all kinds of text information and image information posted by the plurality of users through their SNS accounts. The SNS information may include, for example, at least one of a profile, a feed, a comment, friends, like, follow, album information, and image information associated with a plurality of users. It may be one piece of information, and the present disclosure is not limited thereto. In addition, the server 100 that provides a service for determining matching suitability of a plurality of users may derive the propensity information of each of the plurality of users by analyzing the collected SNS information. The propensity information derived from each of the plurality of users may include personality elements (for example, personality characteristic information, need information, value information, taste information, etc.) of the user analyzed through SNS information of the plurality of users in an exponential form and true / Information may be represented in at least one of the false form. In addition, the server 100 that provides a service for determining matching suitability of the plurality of users may generate evaluation information for each of the plurality of users by inputting the propensity information derived from the plurality of users into the learned evaluation model. The evaluation information for each of the plurality of users includes information related to social evaluation of the plurality of users, and may include information related to evaluation of another person or acquaintance with the user. That is, the server 100 that provides a service for determining the matching suitability 530 of the plurality of users may generate evaluation information of each of the plurality of users through the propensity information derived from the SNS information of the plurality of users. In addition, the server 100 may represent social relation information representing all kinds of human relations (eg, a lover relationship, a co-worker relationship, a father-in-law relationship, etc.) or a relationship with an object that may be formed between a plurality of users. And a matching suitability 530 among a plurality of users through a matching suitability determination algorithm based on the generated evaluation information. Matching goodness of fit 530 is a suitability of a predetermined relationship between a plurality of users determined based on a predetermined relationship between the plurality of users (for example, propensity information, evaluation information, etc.) and information about each of the plurality of users It may include information related to. That is, if there are two users with high matching suitability 530 in a particular social relationship (eg, between boss and subordinate), these users may feel comfortable and synergistic when they are in that social relationship. It can also be generated. The matching goodness of fit 530 may include information for predicting the degree of matching between users when several users are in a predetermined social relationship. The matching suitability determination algorithm is a predetermined algorithm that is generated based on a social psychology and a research result of socially known social relations, and is grouped based on social relations and evaluation information of grouped users among a plurality of users. Goodness-of-fit information can be provided. Accordingly, the server 100 that provides a service for determining matching suitability of a plurality of users collects and analyzes information related to the plurality of users from the SNSs of the plurality of users, and analyzes the propensity of the reliable user through the SNS information. Through the information on the multi-party propensity suitability can be provided to the user.

2 is a block diagram of a server for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.

Components of the server 100 that determine the matching suitability of the plurality of users shown in FIG. 2 are exemplary. Only some of the components may configure the server 100 to determine the matching suitability of the plurality of users. Further, in addition to the component, additional component (s) may be included in the server 100 that determines the matching suitability of the plurality of users.

As shown in FIG. 2, the server 100 that determines the matching suitability of the plurality of users includes the network unit 110, the propensity information management module 120, the evaluation information management module 130, and the matching suitability management module 140. ) May be included.

According to an exemplary embodiment of the present disclosure, the network unit 110 may receive information (for example, SNS information, propensity information, evaluation information, and questionnaire information) from at least one of the server 100 and the user terminal 200. Question and answer information and matching suitability, etc.) may be transmitted and received. More specifically, the network unit 110 may include a wired / wireless internet module for network connection. Wireless Internet technologies may include Wireless LAN (Wi-Fi), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), and the like. As a wired Internet technology, a digital subscriber line (XDSL), fibers to the home (FTTH), power line communication (PLC), and the like may be used.

In addition, the network unit 110 may include a short range communication module to transmit and receive data to and from an electronic device including a short range communication module, which is located at a relatively short distance with the user terminal 200. As a short range communication technology, Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, and the like may be used.

According to one embodiment of the present disclosure, the propensity information management module 120 may derive propensity information for each user by analyzing SNS information of a plurality of users. In this case, the propensity information derived from each of the plurality of users may be information representing personality elements of the user analyzed through SNS information of the plurality of users in at least one of an exponential form and True / False form. Specifically, the propensity information may include at least one of propensity characteristic information, need information, value information, and taste information, and the propensity characteristic information may include information about openness, sincerity, extroversion, affinity, and emotional ups and downs. have. Information included in the above-mentioned propensity information is only an example, and the present disclosure is not limited thereto.

The propensity information management module 120 may collect SNS information for each user about SNS activities of a plurality of users. In this case, the SNS information may include all kinds of text information and image information posted by a plurality of users through their SNS account. The SNS information may include, for example, at least one of a profile, a feed, a comment, friends, like, follow, album information, and image information associated with a plurality of users. One may include, but the present disclosure is not limited thereto.

In addition, the propensity information management module 120 may derive the propensity of each of the plurality of users by analyzing the SNS information collected from each of the plurality of users. In this case, the propensity information management module 120 may analyze the SNS information may be at least one method of natural language processing and image content analysis.

The analysis method through natural language processing of the propensity information management module 120 may be an analysis of a text language among SNS information of a plurality of users. In detail, the propensity information management module 120 may determine the atmosphere of the SNS by performing natural language processing and analyzing texts related to SNS activities of a plurality of users. The text associated with the SNS activity may include all kinds of text characters (eg, posts, feeds, comments, etc.) posted by a plurality of users through their SNS. In detail, the propensity information management module 120 may perform natural language processing to extract tokens and phrases, identify a part-of-speech, and make a parsing tree of a dependency of each phrase to perform parsing. In addition, the propensity information management module 120 may perform natural language processing to classify words into text blocks according to a sense of speech, and perform item emotion analysis by identifying emotions for each reference to an item in the text block. In addition, the propensity information management module 120 may perform natural language processing to identify the item in the text and analyze the item by designating a label such as a person, organization, location, event, product, and media. In addition, the natural language processing performed by the propensity information management module 120 may grasp the overall emotion expressed in the text block.

According to an embodiment of the present disclosure, the propensity information management module 120 analyzes the context of the text of the SNS information associated with the plurality of users through natural language processing to derive the emotion of the user, and extract the representative word of the sentence. To derive a topic about the text. For example, if a user posts the text “Happy time at the Eiffel Tower in Paris” on his SNS, the propensity information management module 120 may represent the words “Paris” and “Eiffel Tower”. ', Etc. can be derived to derive the subject of the text, and by analyzing the context, it can be determined that the emotion of the user is' happy'.

According to another embodiment of the present disclosure, the propensity information management module 120 may analyze the image content to analyze the image information among the SNS information of the plurality of users by performing image content analysis. The propensity information management module 120 performs image content analysis to quickly classify images into thousands of categories (e.g., sailing ships, lions, Eiffel towers, flowers, transportation, etc.) and to display individual objects and faces in the images. Detect and read words printed on the image. In addition, the propensity information management module 120 performs image content analysis to analyze the location through location recognition, counting the number of people through face recognition, analyzing the emotions of the person by recognizing facial expressions on the person, and determining the brand of the object. At least one analysis of preference / non-preferred brand determination may be performed. In addition, image content analysis can utilize image search to find topical items such as celebrities, logos, and news events. The analysis method through image content analysis performed by the above-described propensity information management module 120 is merely an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the propensity information management module 120 may analyze SNS information using at least one platform of a National Language API of Google Cloud Platform, Vision API, and Personality Insights of IBM Watson. In addition, the propensity information management module 120 may derive the propensity information of the user in at least one of an exponential form and a True / False form.

According to an embodiment of the present disclosure, the evaluation information management module 130 may include a learning data generation unit 131, a labeling unit 132, a learning unit 133, and an evaluation information generation unit 134. .

According to an embodiment of the present disclosure, the evaluation information management module 130 processes the propensity information of a plurality of users derived through SNS analysis to the learned evaluation information generation unit 134, for each of the plurality of users. Evaluation information can be generated. The evaluation information generator 134 may be configured as an artificial neural network. The artificial neural network 300 constituting the evaluation information generation unit 134 may input the propensity information of each of the plurality of users, and output the evaluation information of each of the plurality of users.

According to an embodiment of the present disclosure, the training data generator 131 may generate training data for training the artificial neural network 300 constituting the evaluation information generator 134. The artificial neural network 300 constituting the evaluation information generator 134 may generate evaluation information including information related to social evaluation of each of a plurality of users and information related to the evaluation of others or acquaintances of the user. Can be.

In addition, the training data generator 131 may include training input data and training label data. In this case, the training input data may be learning propensity information processed as an input of the artificial neural network 300 to train the artificial neural network 300. In addition, the learning label data may be learning evaluation information that is labeled at the output of the artificial neural network 300 to learn the artificial neural network 300. In this case, the learning evaluation information may include information related to the social evaluation of each of the plurality of users and information related to the evaluation of others or acquaintances for the user.

According to an embodiment of the present disclosure, the learning data generator 131 may generate learning evaluation information for each of the plurality of users through the result of the survey. In detail, the learning data generator 131 may generate a survey for deriving learning evaluation information, and may perform the generated survey for acquaintances of a plurality of users. In this case, a survey performed on acquaintances of a plurality of users may be performed in an online manner. For example, a method of performing a survey may be a method of transmitting a survey to terminals of acquaintances of a specific user among a plurality of users, receiving a result thereof, and collecting the received plurality of survey results. . For another example, a method of performing a survey may be a method of initiating a survey on SNSs of a plurality of users and receiving and collecting results from acquaintances of the plurality of users. The evaluation information for learning may be generated by receiving and collecting the result of the survey. The online survey method described above is merely an example, and the present disclosure is not limited thereto.

In addition, in order to generate more reliable evaluation information for learning through a survey, answers from a plurality of acquaintances of a specific user may be required. In detail, the learning data generation unit 131 executes an online survey for a user terminal possessed by a plurality of acquaintances of a specific user, and collects survey results from a user terminal possessed by a plurality of acquaintances, thereby making it more diverse. And generate accurate learning evaluation information.

In addition, the survey may be composed of question text for deriving evaluation information for each of the plurality of users. For example, a response from a specific user's acquaintances with the question ““ Are you a particular user smart? ”Or“ “Are you stupid?” For a specific user from multiple users' acquaintances Learning evaluation information can be obtained. The configuration of the above-described questionnaire, the object of performing the questionnaire, the method of performing the questionnaire, and the contents of the questionnaire are examples only, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the labeling unit 132 may match a label (ie, learning evaluation information) of the learning input data and the learning input data for supervised learning. In this case, the learning input data may include learning propensity information. That is, the labeling unit 132 may match the learning evaluation information derived by performing a survey on acquaintances of a specific user in the learning data generation unit 131 with the learning propensity information. In detail, the labeling unit 132 may match the learning evaluation information of the user corresponding to the learning propensity information, respectively.

According to an embodiment of the present disclosure, the learning unit 133 inputs learning propensity information to the artificial neural network 300 of the evaluation information generating unit 134 to evaluate the learning propensity information output from the artificial neural network 300. An error may be derived by comparing the output of the information generator and the evaluation information for learning (ie, a label). In addition, the learner 133 may propagate the error derived from the comparison result to the artificial neural network 300 to update the weight of the artificial neural network 300 to train the evaluation information generator 134. In the present disclosure, the artificial neural network 300 may be configured as a recurrent neural network (RNN), or may be configured as a long short term memory (LSTM) in which long-term memory problems of the RNNs are solved. The configuration of the artificial neural network 300 described above is merely an example, and the present disclosure is not limited thereto.

If the learning epoch for learning the artificial neural network 300 is less than or equal to a predetermined epoch, the learning unit 133 sets a learning rate of the artificial neural network 300 to a predetermined value or more, and the artificial When the learning epoch for learning the neural network 300 is greater than or equal to a predetermined epoch, the learning rate of the artificial neural network 300 may be set to be equal to or less than a predetermined value. For example, the learning unit 133 verifies the validity of the artificial neural network model by setting the learning rate of 0.8 in the initial 100,000 epochs to speed up the initial learning speed to train the artificial neural network 300, and the 100,000 or more epochs. We can fine tune the learning results by setting a learning rate of 0.2 for.

The learning unit 133 may generate an evaluation model by performing deep learning on the artificial neural network 300 of the evaluation information generator 134 using the evaluation information for learning. The learning unit 133 may train the evaluation information generation unit 134 to output the evaluation information prediction value by using the artificial neural network 300 constituting the evaluation information generation unit 134. In addition, the learner 133 may input learning propensity information into the evaluation information generator 134. The learning unit 133 derives an error by comparing the output of the evaluation information output from the evaluation information generation unit 134 with the evaluation information for learning, and backpropagates the derived error to the evaluation information generation unit 134 to obtain a weight. You can update it. Through the above-described process, the evaluation information generator 134 may be trained to output a value corresponding to the learning evaluation information.

According to an embodiment of the present disclosure, the evaluation information generator 134 may generate evaluation information for each of the plurality of users. In this case, the generated evaluation information may include information related to social evaluation of a plurality of users, and may be information related to evaluation of others or acquaintances of the user. For example, it may include smart, stupid, lazy, diligent, progressive, conservative, positive, negative, and the like, and the present disclosure is not so limited.

In addition, the evaluation information generation unit 134 may generate the evaluation information for each of the plurality of users by inputting the propensity information of each of the plurality of users. In detail, the evaluation information generation unit 134 receives the propensity information of each of the plurality of users, which derives SNS information of the plurality of users by at least one of natural language processing and image content analysis, and evaluates each of the plurality of users. Information can be output. For example, when the index values such as 'intelligence', 'challenge', 'can read frequently', and 'utility' among the indexed propensity information of a specific user among the plurality of users are high, It can be created as "smart and diligent". In another example, when the index values of 'depressed', 'extreme', 'hedonism', 'strong self-consciousness' among the indexed propensity information of a specific user are high, the evaluation information of the specific user is “ It can be created as "dumb and lazy". In more detail, the evaluation information generator 134 may include an artificial neural network 300. Since the artificial neural network 300 is trained to derive evaluation information from the learning unit 133, when inputting propensity information of a specific user among a plurality of users into the artificial neural network 300, the weight of the hidden layer is used. A score value may be output to each output node. In this case, an output node having a high score value among the score values output to each output node may be selected. Here, each output node may be mapped to each evaluation information. That is, each output node may output a different score value by weights of each layer of the hidden layer to the learned artificial neural network, and select an output node by comparing the output score values, Evaluation information of a specific user may be generated according to the mapped evaluation information. The method of outputting the evaluation information by inputting the above-described propensity information is merely an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the matching suitability management module 140 may generate a matching suitability through evaluation information of each of a plurality of users and social relation information between the plurality of users. In detail, the matching suitability management module 140 may output matching suitability for the plurality of users based on evaluation information of each of the plurality of users in the selected group and social relationships of the plurality of users. The social relation may include information on all kinds of human relations and relations with objects that may be formed between a plurality of users. For example, it may include, but is not limited to, workmate relationships, gender relationships, paternal relationships, certain occupations, certain objects, certain movies, certain sports, and the like.

According to an embodiment of the present disclosure, the matching suitability management module 140 may generate a matching suitability between a plurality of users based on evaluation information and social relation information of each of the plurality of users. For example, as shown in FIG. 5A, when generating a matching suitability 530 for two users of a work relationship, the matching suitability management module 140 may execute the first evaluation information (for example, user A 501). The second evaluation information 521 of the user 520 and the user B 502 may be input, and a matching suitability 530 may be generated for the work relationship which is the selected social relationship between the user A 501 and the user B 502. . In addition, the matching suitability management module 140 inputs a user and a specific sport (for example, baseball, soccer, basketball, etc.), and when a social relationship is input as a sport, the matching suitability between the user and the specific sport 530. ) Can be created. The above described matching suitability generating method is merely an example, and the present disclosure is not limited thereto.

In addition, the matching suitability management module 140 may generate a multiparty matching suitability. In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may determine not only matching suitability for two users but also matching suitability for three or more persons as illustrated in FIG. 5A. have. For example, when determining the matching suitability of the three co-workers, the server 100 that provides a service for determining the matching suitability of the plurality of users, the evaluation information and social relation information of each of the three users (work colleagues) Can be used to determine the matching suitability for the three work colleagues. The above-described multiparty matching suitability determination is merely an example, and the present disclosure is not limited thereto.

3 illustrates a schematic diagram of an artificial neural network that constitutes a learned evaluation model associated with one embodiment of the present disclosure.

Throughout this specification, neural networks, network functions, neural networks may be used in the same sense. A neural network may consist of a set of interconnected computing units, which may generally be referred to as "nodes." Such "nodes" may be referred to as "neurouns". The neural network comprises at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more "links".

Within a neural network, one or more nodes connected via a link may form a relationship of input node and output node relatively. The concept of an input node and an output node is relative; any node in an output node relationship for one node may be in an input node relationship in relation to another node, and vice versa. As mentioned above, the input node to output node relationship can be created around the link. More than one output node can be connected to a single input node via a link, and vice versa.

In an input node and output node relationship connected via one link, the output node may be determined based on data input to the input node. Here, the node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are interconnected by each link to one output node, the output node is set to values input to input nodes connected to the output node and to a link corresponding to each input node. The output node value may be determined based on the weight.

As noted above, a neural network is formed by interconnecting one or more nodes via one or more links to form input and output node relationships within the neural network. The characteristics of the neural network may be determined according to the number of nodes and links in the neural network, the relationship between the nodes and the links, and the value of the weight assigned to each of the links. For example, if there are the same number of nodes and links, and there are two neural networks with different weight values between the links, the two neural networks may be recognized as different from each other.

As shown in FIG. 3, the neural network may comprise one or more nodes. Some of the nodes that make up the neural network may construct one layer based on distances from the original input node, for example, a set of nodes with a distance n from the original input node, You can configure n layers. The distance from the original input node may be defined by the minimum number of links that must pass to reach the node from the original input node. However, the definition of such a layer is arbitrary for explanation, and the order of the layer in the neural network may be defined in a manner different from that described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes into which data is directly input without going through a link in relation to other nodes among the nodes in the neural network. Alternatively, in a neural network network, in a relationship between nodes based on a link, it may mean nodes having no other input nodes connected by a link. Similarly, a final output node may refer to one or more nodes that do not have an output node in relationship with other nodes of the neural network. Also, the hidden node may refer to nodes constituting a neural network other than the first input node and the last output node. In the illustration of Fig. 2, the output node is omitted. The neural network according to an embodiment of the present disclosure may be more than the nodes of the hidden layer closer to the output layer than the node of the input layer, and may be a neural network in which the number of nodes decreases as the node progresses from the input layer to the hidden layer.

In an exemplary embodiment of the present disclosure, the neural network may include a multilayer perceptron (MLP), a recurrent neural network (RNN), a convolutional neural network (CNN), and the like. In addition, in an embodiment of the present disclosure, the neural network of the present disclosure may provide long short-term memory (LSTM) to prevent performance degradation due to long range dependency vanishing gradient that may occur as the length of an event increases. It may include. In addition, in an embodiment of the present disclosure, as an optimization technique of the artificial neural network method, stochastic gradient descent (SGD), momentum (Momentum), Adam, AdaGrad, RMSprop, or the like may be used. In addition, if the training data D can be learned only once, the parameters that minimize the error function can be obtained through repeated epochs several times. After checking whether sufficient optimization has been made, it is possible to determine whether to complete the learning phase. have.

Unlike the general feedforward neural network, the RNN can again output the hidden layer to the same hidden layer. The RNN is a neural network that has memory capability by having a feedback structure and calculating the current input data and the data input in the past at the same time. Thus, the RNN can be trained to interpret the current data according to the meaning of the previous data in the data. One of the RNNs, LSTM, is also called a long short term memory network and can learn long-term dependencies. In one embodiment of the present disclosure, the neural network may include not only LSTM, which is one of the RNNs, but also any neural network capable of processing data such as a depth gated RNN, a clockwork RNN, and the like. have.

The artificial neural network 300 shown in FIG. 3 may include one or more hidden layers. The hidden node of the hidden layer can take as input the output of the previous layer and the output of the surrounding hidden nodes. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes of the input layer may be determined based on the number of data fields of the input data, and may be the same as or different from the number of hidden nodes. Input data input to the input layer may be calculated by a hidden node of the hidden layer and may be output by a fully connected layer (FCL) which is an output layer. A description of the specific configuration of the RNN in the artificial neural network is described in US patent applications US15 / 233083 (filed August 10, 2016) and US14 / 810368 (filed July 27, 2015), which are hereby incorporated by reference in their entirety. In more detail).

4 is a flowchart of a method for providing a service for determining matching suitability of a plurality of users in accordance with an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may provide matching suitability information including matching rate information and matching information for a plurality of users. More specifically, the server 100 that provides a service for determining a matching suitability of a plurality of users may provide a multiparty matching suitability based on social relations and evaluation information of a plurality of users in the selected group. In addition, the server 100 that provides a service for determining matching suitability of a plurality of users provides not only matching suitability between users and other users but also matching suitability with various fields such as people and objects, people and movies, and people and sports. can do.

According to an embodiment of the present disclosure, the server 100 that determines the matching suitability of the plurality of users may collect SNS information for each user according to SNS activities of the plurality of users. In this case, the SNS information includes at least one of a profile, a feed, a comment, friends, like, follow, album information, and image information associated with a plurality of users. It may include.

According to an embodiment of the present disclosure, the server 100 that determines the matching suitability of the plurality of users may derive propensity information for each of the plurality of users through analysis of the SNS information of the plurality of users (410). . At this time, the propensity information indicates the personality factor of the user analyzed through the SNS information and can be derived for each user. Specifically, the propensity information may include at least one of propensity characteristic information, need information, value information, and taste information, and the propensity characteristic information may include information about openness, sincerity, extroversion, affinity, and emotional ups and downs. have.

In addition, the server 100 that provides a service for determining the matching suitability of the plurality of users may derive the propensity of each of the plurality of users by analyzing the collected SNS information from the plurality of users. In detail, the method for analyzing SNS information by the server 100 that provides a service for determining matching suitability of a plurality of users may be at least one method of natural language processing and image content analysis.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users performs natural language processing to analyze a tendency toward a plurality of users through analysis of SNS information collected from the plurality of users, respectively. Can be derived. More specifically, the server 100 that provides a service for determining matching suitability of a plurality of users may perform natural language processing to grasp the atmosphere of the SNS through text analysis associated with SNS activities of the plurality of users. The text associated with the SNS activity may include all kinds of text characters (eg, posts, feeds, comments, etc.) posted by a plurality of users through their SNS. In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may perform natural language processing to perform token and syntax analysis on text on an SNS. In addition, the server 100 that provides a service for determining a matching suitability of a plurality of users performs natural language processing to classify words into text blocks according to a sense of speech, and grasp emotions by reference to items in the text block. Emotional analysis can be performed. In addition, the server 100 that provides a service for determining matching suitability of a plurality of users performs natural language processing to identify items in the text and to label them by types such as person, organization, location, event, product, and media. Analyze items. In addition, the natural language processing performed by the server 100 that provides a service for determining matching suitability of a plurality of users may grasp the overall emotion expressed in the text block. That is, the natural language processing performed by the server 100 that provides a service for determining matching suitability of a plurality of users analyzes the context of the text among the SNS information associated with the plurality of users to derive the user's emotion and represent the representative words of the characters. The user's disposition can be derived by extracting the subject of the text. Natural language processing performed by the server 100 that provides a service for determining matching suitability of the plurality of users described above is merely an example, and the present disclosure is not limited thereto.

According to another embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users derives propensity for a plurality of users through image content analysis of SNS information collected from the plurality of users, respectively. can do. The server 100 that provides a service for determining a matching suitability of a plurality of users may perform image content analysis to analyze information on an image among SNS information of the plurality of users. In detail, the server 100 that provides a service for determining a matching suitability of a plurality of users performs image content analysis to classify images on an SNS of a specific user in thousands of categories (eg, sailing boats, lions, Eiffel towers, Quickly sort by flower, transportation, etc., detect individual objects and faces within images, and read words printed on images. In addition, the server 100 that provides a service for determining a matching suitability of a plurality of users performs an image content analysis to analyze the location through place recognition, count the number of people through face recognition, and recognize the person's face through facial expression recognition. At least one of preference / non-preferred brand judgment may be determined through emotion analysis and brand judgment of a specific object. In addition, the server 100 that provides a service for determining a matching suitability of a plurality of users may perform image content analysis to find a topic item such as a celebrity, a logo, and a news event using image search. Image content analysis performed by the server 100 that provides a service for determining matching suitability of the plurality of users described above is merely an example, and the present disclosure is not limited thereto.

According to the exemplary embodiment of the present disclosure, the server 100 that determines the matching suitability of the plurality of users may process the derived plurality of user information with the learned evaluation information generation unit 134 to evaluate each of the plurality of users. Information may be generated (420). In this case, the generated evaluation information may include information related to the social evaluation of each of the plurality of users, and information related to the evaluation of others or acquaintances of the user. For example, it may include smart, stupid, lazy, diligent, progressive, conservative, positive, negative, and the like, and the present disclosure is not so limited.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining a matching suitability of a plurality of users may determine a matching suitability based on evaluation information of each of the plurality of users and social relation information between the plurality of users. May be generated (430). Specifically, the server 100 that provides a service for determining a matching suitability of a plurality of users may determine a matching suitability for the plurality of users based on evaluation information of the plurality of users in the selected group and social relationships of the plurality of users. You can print The social relation may include information on all kinds of human relations and relations with objects that may be formed between a plurality of users. For example, it may include, but is not limited to, workmate relationships, gender relationships, paternal relationships, certain occupations, certain objects, certain movies, certain sports, and the like.

In addition, the server 100 that provides a service for determining matching suitability of a plurality of users may generate a multi-party matching suitability. In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may determine matching suitability for three or more persons as well as matching suitability for two users as illustrated in FIG. 5A. Can be. For example, when determining the matching suitability of the three co-workers, the server 100 that provides a service for determining the matching suitability of the plurality of users, the evaluation information and social relationship information of each of the three users (for example , Co-workers, senior couples, and lover relationships) can be used to determine matching suitability for three co-workers.

5A is an exemplary diagram illustrating a process of determining matching suitability of two users (User A and User B) associated with one embodiment of the present disclosure.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may derive propensity information for each user by analyzing SNS information of the plurality of users. For example, as shown in FIG. 5A, when the matching suitability of two users is determined, the server 100 that provides a service for determining the matching suitability of the plurality of users includes the user A 501 and the user B 502. ), The first propensity information 510 and the second propensity information 511 may be derived. In this case, the first propensity information 510 is based on at least one of profile, feed, comment, friend, like, follow, album information, and image information associated with user A 501 posted on the SNS of user A 501. Can be generated. In addition, the second propensity information 511 may be generated based on the SNS information associated with the user B 502 posted on the SNS of the user B 502.

According to an embodiment of the present disclosure, the server 100 that determines the matching suitability of the plurality of users may generate the respective evaluation information by inputting the propensity information derived from the plurality of users into the evaluation information management module 130. have. In detail, the first tendency information 510 of the user A 501 may be processed by the evaluation information management module to output the first evaluation information 520. The first evaluation information 520 may include information related to social evaluation of the user A 501, and may include information related to evaluation of another person or acquaintance with the user. In addition, the second tendency information 511 for the user B 502 may be processed as an input of the evaluation information management module 130 to output the second evaluation information 521. The second evaluation information 521 may include information related to social evaluation of the user B 502, and may include information related to evaluation of another person or acquaintance with the user.

According to an embodiment of the present disclosure, the matching suitability management module 140 included in the server 100 that determines the matching suitability of the plurality of users may include the first evaluation information 520 and the user B (for the user A 501). The second evaluation information 521 of the user 502 may be input, and the matching suitability 530 may be generated based on the social relationship between the user A 501 and the user B 502. The matching suitability algorithm is a predetermined algorithm that is generated based on research results and social psychology of socially known social relations, and is grouped based on social relations and respective evaluation information of grouped users among a plurality of users. It may provide goodness of fit information between users. For example, the first rating information 520 of user A 501 is ““ smart and lazy ”and the second rating information 521 of user B 502 is“ “smart and diligent”, and If the relationship between the user A 501 and the user B 502 is the relationship between the boss and the work load, as shown in Figure 5b, the goodness of fit between the two users (reference number 541) may be ideal, the matching goodness of fit management module 140 may generate matching goodness of fit 530 as shown in FIG. 5A. For another example, the first rating information 520 of user A 501 is ““ smart and diligent ”and the second rating information 521 of user B 502 is“ “smart and diligent”, And when the relationship between user A 501 and user B 502 is the relationship between the boss and the work load, the fitness between the two users as shown in Figure 5b is "Twisted and intellectual and dispute" (reference numeral 540). ) Is not very good, and the matching suitability management module 140 may determine the matching rate low, and also create a matching suitability 530 by negatively writing a comment about the goodness of fit. The above-described method of generating matching suitability 530 is merely an example, and the present disclosure is not limited thereto.

According to one embodiment of the present disclosure, as shown in FIG. 5A, the matching suitability 530 includes social relationship information 531, matching rate information 532, and comment information 533 according to the matching rate. can do. The information displayed on the matching goodness of fit 530 is exemplary, and only some of the information may be displayed on the matching goodness of fit 530. In addition to the above information, additional information (for example, improvement direction information) may be displayed in matching suitability.

6 is a flow chart of a supervised learning method associated with an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the evaluation information generation unit 134 of the server 100 that determines the matching suitability of a plurality of users may be configured as an artificial neural network 300, the artificial neural network is a map learning method Can be learned.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may generate training data for learning the artificial neural network 300. In addition, the server 100 that provides a service for determining matching suitability of a plurality of users may store training input data and training label data. In this case, the training input data may be learning propensity information processed as an input of the artificial neural network 300 to train the artificial neural network 300. In addition, the learning label data may be compared with the output of the artificial neural network 300 to learn the artificial neural network (300). In this case, the learning evaluation information may include information related to the social evaluation of each of the plurality of users and information related to the evaluation of others or acquaintances for the user.

In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may generate a survey for deriving learning evaluation information, and may generate the survey for acquaintances of a plurality of users. Can be performed. In this case, a survey performed on acquaintances of a plurality of users may be performed in an online manner. For example, a method of performing a survey may be a method of transmitting a survey to terminals of acquaintances of a specific user among a plurality of users, receiving a result thereof, and collecting the received plurality of survey results. . For another example, a method of performing a survey may be a method of initiating a survey on SNSs of a plurality of users and receiving and collecting results from acquaintances of the plurality of users. The evaluation information for learning may be generated by receiving and collecting the result of the survey. In addition, the survey may be composed of question text for deriving evaluation information for each of the plurality of users. For example, a response from a specific user's acquaintances with the question ““ Are you a particular user smart? ”Or“ “Are you stupid?” For a specific user from multiple users' acquaintances Learning evaluation information can be obtained. The configuration of the above-described questionnaire, the object of performing the questionnaire, the method of performing the questionnaire, and the contents of the questionnaire are examples only, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may match a label (ie, learning evaluation information) of the learning input data and the learning input data for supervised learning. Can be. In this case, the learning input data may include learning propensity information. That is, the server 100 that provides a service for determining a matching suitability of a plurality of users matches the learning evaluation information for a specific user to a learning propensity information for a specific user, which is obtained by performing a survey to acquaintances of a specific user. You can. In detail, the server 100 that provides a service for determining matching suitability of a plurality of users may match learning evaluation information of a user corresponding to learning propensity information for each user.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining a matching suitability of a plurality of users may input learning propensity information into the artificial neural network 300 of the evaluation information generator 134 to perform the artificial neural network. An error may be derived by comparing the output of the artificial neural network with respect to the learning propensity information output at 300 and the evaluation information for learning (ie, a label). In addition, the server 100 that provides a service for determining a matching suitability of a plurality of users by back-propagating the error derived as a result of the comparison to the artificial neural network 300 to update the weight of the artificial neural network 300 to generate evaluation information The unit 134 may be trained. In the present disclosure, the artificial neural network 300 may be configured as a recurrent neural network (RNN), or may be configured as a long short term memory (LSTM) in which long-term memory problems of the RNNs are solved. The configuration of the artificial neural network 300 described above is merely an example, and the present disclosure is not limited thereto.

7 is a flowchart illustrating means for determining matching suitability of a plurality of users in accordance with an embodiment of the present disclosure.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may include means for analyzing SNS information of a plurality of users and deriving each propensity information for each user ( 710); Means (720) for processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users; And means 730 for generating a matching suitability by processing evaluation information of each group user among the plurality of users and a social relationship between the group users as a matching suitability determination model.

Alternatively, the SNS information may include profile, feed, comment, friends, like, follow, album information and image information associated with the plurality of users. It may include at least one of.

Alternatively, the means for analyzing the SNS information of the plurality of users and deriving the propensity information of each user for each user may include: means for analyzing the SNS information in at least one of natural language processing and image content analysis; It may include.

Alternatively, the natural language processing may derive nouns and adjectives with respect to the text of the SNS information, analyze the context to derive the emotions of the user, and extract the representative words of the sentences to derive the subject.

Alternatively, the image content analysis may perform place recognition, face recognition, facial expression recognition, and specific object recognition on the image of the SNS information, and position analysis through the place recognition, the number of persons through the face recognition. It may include at least one of counting, analysis of the emotion of the person by recognizing the expression on the person, and image analysis by determining the brand of the object.

Alternatively, the propensity information includes at least one of personality characteristic information, needs information, value information, and taste information, and is derived in at least one of an exponential form and a T / F form. It may be characterized by.

Alternatively, the personality trait information may include information about openness, sincerity, outgoingness, affinity, and emotional ups and downs.

Alternatively, the learned evaluation model is composed of an artificial neural network (Artificial Neural Network), it may be characterized in that it is learned through a supervised learning method.

Alternatively, the supervised learning method, means for deriving learning evaluation information for each user through the survey results for the plurality of users; labeling the derived learning evaluation information in the learning propensity information (Labeling) Means for doing so; Deriving an error by comparing the output of the learning tendency information output from the artificial neural network with the learning evaluation information; And means for updating the weight of the artificial neural network by back-propagating the error derived as a result of the comparison to the artificial neural network.

Alternatively, the survey may be composed of question texts for acquaintances of a plurality of users, and to derive evaluations of each of the plurality of users.

Alternatively, the social relationship information may include information about all kinds of human relationships that may be formed between a plurality of users.

Alternatively, the matching suitability may be provided to the user by including at least one of matching ratio information and comment information according to the matching suitability.

8 is a flowchart illustrating a module for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method for providing a service for determining matching suitability of a plurality of users may be implemented by the following module.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may include a module for analyzing SNS information of a plurality of users and deriving each propensity information for each user ( 810); A module 820 for processing the derived propensity information as a trained evaluation model to generate evaluation information for each of the plurality of users; And a module 830 for generating a matching suitability by processing evaluation information of each group user among the plurality of users and a social relationship between the group users as a matching suitability determination model.

9 is a flowchart illustrating logic for determining matching suitability of a plurality of users according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of providing a service for determining matching suitability of a plurality of users may be implemented by the following logic.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may include logic for deriving each propensity information for each user by analyzing SNS information of the plurality of users. 910); Logic 920 for processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users; And logic 930 for processing matching information of each group user among the plurality of users and social relations between the group users as a matching suitability determination model to generate a matching suitability.

10 is a flowchart illustrating a circuit for determining a matching suitability of a plurality of users according to an embodiment of the present disclosure.

According to an embodiment of the present disclosure, a method of providing a service for determining matching suitability of a plurality of users may be implemented by the following circuit.

According to an embodiment of the present disclosure, the server 100 that provides a service for determining matching suitability of a plurality of users may include a circuit for deriving each propensity information for each user by analyzing SNS information of the plurality of users ( 1010); A circuit 1020 for processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users; And a circuit 1030 for generating a matching suitability by processing evaluation information of each group user among the plurality of users and a social relationship between the group users as a matching suitability determination model.

11 shows a brief general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the invention has been described above generally in terms of computer executable instructions that may be executed on one or more computers, those skilled in the art will appreciate that the invention may be implemented in combination with other program modules and / or as a combination of hardware and software. will be.

In general, modules herein include routines, procedures, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Those skilled in the art will also appreciate that the methods of the present invention may be used in uniprocessor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like (each of which And other computer system configurations, including one or more associated devices.

The described embodiments of the invention can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer readable media. Any medium that can be accessed by a computer can be a computer readable medium, which can be volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. Removable media. By way of example, and not limitation, computer readable media may comprise computer readable storage media and computer readable transmission media.

Computer-readable storage media are volatile and nonvolatile media, temporary and non-transitory media, removable and non-removable implemented in any method or technology for storing information such as computer readable instructions, data structures, program modules or other data. Media. Computer-readable storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage. It includes, but is not limited to, a device or any other medium that can be accessed by a computer and used to store desired information.

Computer-readable transmission media typically embody computer readable instructions, data structures, program modules or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and the like. Includes all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed to encode information in the signal. By way of example, and not limitation, computer readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, or other wireless media. Combinations of any of the above should also be included within the scope of computer readable transmission media.

An exemplary environment 1100 is illustrated that implements various aspects of the present invention, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 connects system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercial processors. Dual processor and other multiprocessor architectures may also be used as the processing unit 1104.

The system bus 1108 may be any of several types of bus structures that may be further interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input / output system (BIOS) is stored in nonvolatile memory 1110, such as ROM, EPROM, EEPROM, etc., and the BIOS provides a basic aid for transferring information between components in the computer 1102, such as during startup. Contains routines. RAM 1112 may also include fast RAM, such as static RAM, for caching data.

Computer 1102 also includes an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) —this internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes, magnetic floppy disk drive (FDD) 1116 (eg, for reading from or writing to removable diskette 1118), and optical disk drive 1120 (eg, CD-ROM Disc 1122 for reading from or writing to or writing from other high capacity optical media such as DVD). The hard disk drive 1114, the magnetic disk drive 1116, and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124, the magnetic disk drive interface 1126, and the optical drive interface 1128, respectively. ) Can be connected. The interface 1124 for external drive implementation includes, for example, at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide nonvolatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. While the above description of computer readable storage media refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate zip drives, magnetic cassettes, flash memory cards, cartridges, It will be appreciated that other types of computer readable media may also be used in the exemplary operating environment and that any such media may include computer executable instructions for performing the methods of the present invention. .

Multiple program modules may be stored in the drive and RAM 1112, including operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or a portion of the operating system, applications, modules and / or data may also be cached in RAM 1112. It will be appreciated that the present invention may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 through one or more wired / wireless input devices, such as a keyboard 1138 and a mouse 1140. Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. These and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, but the parallel port, IEEE 1394 serial port, game port, USB port, IR interface, Etc. can be connected by other interfaces.

A monitor 1144 or other type of display device is also connected to the system bus 1108 via an interface such as a video adapter 1146. In addition to the monitor 1144, the computer generally includes other peripheral output devices (not shown) such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer (s) 1148, via wired and / or wireless communications. Remote computer (s) 1148 may be a workstation, server computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and generally for computer 1102. Although many or all of the described components are included, for simplicity, only memory storage 1150 is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) 1152 and / or a larger network, such as a telecommunications network (WAN) 1154. Such LAN and WAN networking environments are commonplace in offices and businesses, facilitating enterprise-wide computer networks such as intranets, all of which can be connected to worldwide computer networks, such as the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 via a wired and / or wireless communication network interface or adapter 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed therein for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158, connect to a communication server on the WAN 1154, or otherwise establish communications over the WAN 1154. Have the means. The modem 1158, which may be an internal or external and wired or wireless device, is connected to the system bus 1108 via the serial port interface 1142. In a networked environment, program modules or portions thereof described with respect to computer 1102 may be stored in remote memory / storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers can be used.

Computer 1102 is associated with any wireless device or entity disposed and operating in wireless communication, such as a printer, scanner, desktop and / or portable computer, portable data assistant, communications satellite, wireless detectable tag. Communicate with any equipment or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technology. Thus, the communication can be a predefined structure as in a conventional network or simply an ad hoc communication between at least two devices.

Wireless Fidelity (Wi-Fi) allows you to connect to the Internet without wires. Wi-Fi is a wireless technology such as a cell phone that allows a device, for example, a computer, to transmit and receive data indoors and outdoors, ie anywhere within the coverage area of a base station. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, high-speed wireless connections. Wi-Fi may be used to connect computers to each other, to the Internet, and to a wired network (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in unlicensed 2.4 and 5 GHz wireless bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). have.

One of ordinary skill in the art would appreciate that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, It will be appreciated that for purposes of the present invention, various forms of program or design code, or combinations thereof, may be implemented. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. One of ordinary skill in the art may implement the described functionality in various ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The various embodiments presented herein may be embodied in a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable storage media may include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flashes. Memory devices (eg, EEPROM, cards, sticks, key drives, etc.), but are not limited to these. The term “machine-readable medium” includes, but is not limited to, a wireless channel and various other media capable of storing, holding, and / or delivering instruction (s) and / or data.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. Based upon design priorities, it is understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present invention. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the invention. Thus, the present invention should not be limited to the embodiments set forth herein but should be construed in the broadest scope consistent with the principles and novel features set forth herein.

Claims (14)

A method of providing a service for determining matching suitability of a plurality of users performed in one or more processors of a server, the method comprising:
Deriving each propensity information for each user by analyzing social networking service (SNS) information of a plurality of users;
The processor processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users;
Receiving, by the processor, a selection signal for a group user including at least two or more users of the plurality of users and social relation information between the group users from a user terminal; And
The processor processing the evaluation information of each selected group user and the social relation information between the group users based on the selection signal as a matching suitability determination model to generate a matching suitability between the group users;
Including,
The social relation information includes at least one of a human relationship that can be formed by a specific user and another user or a relationship between the specific user and an object,
The matching goodness of fit includes information about the suitability of a predetermined relationship between a particular user and another user,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 1,
The SNS information,
Including at least one of a profile, a feed, a comment, friends, like, follow, album information, and image information associated with the plurality of users,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 1,
Wherein the processor to analyze the SNS information of a plurality of users to derive the propensity information of each user for each user:
Analyzing, by the processor, SNS information in at least one of natural language processing and image content analysis;
Containing,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 3, wherein
The natural language processing,
Deriving nouns and adjectives with respect to the text of the SNS information, Deriving the emotion of the user by analyzing the context, Deriving the subject by extracting the representative words of the sentence,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 3, wherein
The image content analysis,
Performing place recognition, face recognition, facial expression recognition, and specific object recognition on the image of the SNS information;
At least one of the position analysis through the place recognition, the number counting of the person through the face recognition, the analysis of the emotion of the person through the facial recognition of the person, and the image analysis through the brand determination of the object,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 1,
The propensity information is,
Characteristic characteristic information, Needs (Needs) information, Value information, and at least one of the taste information, characterized in that derived from at least one form of the exponential form and T / F form,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 6,
The personality characteristic information,
Including information about openness, integrity, extroversion, affinity and emotional ups and downs,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 1,
The learned evaluation model,
It consists of an Artificial Neural Network,
Characterized in that through the learning method,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 8,
The instruction learning method,
Deriving, by the processor, learning evaluation information for each user through the survey results of the plurality of users;
Labeling the derived learning evaluation information in learning propensity information;
Deriving an error by comparing the output of the learning tendency information output from the artificial neural network with the learning evaluation information by the processor; And
Updating the weight of the artificial neural network by back-propagating the error derived from the comparison to the artificial neural network;
Containing,
A method of providing a service for determining matching suitability of a plurality of users.
The method of claim 9,
The survey,
It consists of question texts targeted to acquaintances of a plurality of users and to derive evaluations of each of the plurality of users,
A method of providing a service for determining matching suitability of a plurality of users.
delete The method of claim 1,
The matching goodness of fit,
Provided to the user, including at least one of comments according to the matching rate and matching suitability,
A method of providing a service for determining matching suitability of a plurality of users.
A server for providing a service for determining matching suitability of a plurality of users,
A processor including one or more cores; And
A memory that stores executable program codes in the processor;
Including,
The processor,
A propensity information management module for analyzing SNS information of a plurality of users and deriving propensity information for each user;
An evaluation information management module for processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users;
A network unit for receiving a selection signal for a group user including at least two or more users of the plurality of users and social relation information between the group users from a user terminal; And
A matching suitability management module configured to process evaluation information of each selected group user and social relation information between the group users based on the selection signal as a matching suitability determination model to generate a matching suitability between the group users;
Including,
The social relation information includes at least one of a human relationship that can be formed by a specific user and another user or a relationship between the specific user and an object,
The matching goodness of fit includes information about the suitability of a predetermined relationship between a particular user and another user,
A server that provides a service for determining matching suitability of a plurality of users.
A computer program stored in a computer readable storage medium containing encoded instructions, wherein the computer program, when executed by one or more processors of a computer system, causes the one or more processors to determine matching suitability of a plurality of users. To perform the following steps to provide a service, said steps:
Deriving each propensity information for each user by analyzing social networking service (SNS) information of a plurality of users;
The processor processing the derived propensity information into a learned evaluation model to generate evaluation information for each of the plurality of users;
Receiving, by the processor, a selection signal for a group user including at least two or more users of the plurality of users and social relation information between the group users from a user terminal; And
The processor processing the evaluation information of each selected group user and the social relation information between the group users based on the selection signal as a matching suitability determination model to generate a matching suitability between the group users;
Including,
The social relation information includes at least one of a human relationship that can be formed by a specific user and another user or a relationship between the specific user and an object,
The matching goodness of fit includes information about the suitability of a predetermined relationship between a particular user and another user,
Computer program stored on a computer readable storage medium.

Images