KR102169382B1 - Artificial Intelligence-Based Personalized Expert Cross Matching and Proposal System - Google Patents

Abstract

The present invention relates to a personalized expert cross-matching and suggestion system using an AI model and, more specifically, to a system for providing expert information or content information optimized for each user based on an area of concern of a user collected from personal information uploaded by a user or social network service (SNS) of a user, and a method thereof.

Description

Artificial Intelligence-Based Personalized Expert Cross Matching and Proposal System}

The present invention relates to a personalized expert mutual matching and proposal system using an artificial intelligence model, and more particularly, based on the personal information uploaded by the user and the user's interests collected from the user's SNS (Social Network Service), etc. It relates to a system device and method that provides expert information or content information optimized to each user.

“C-Professional” is a word that refers to people who have C (chief) in their titles such as senior management, senior executive, CEO/CFO, etc. As a former/current executive of a major company, they have expertise, competence, experience and leadership in each field. It refers to an individual who has achieved more than the management level in major conglomerates and foreign companies.

The number of young C-Professional retirees is rapidly increasing thanks to changes in the job market and socio-cultural trends. However, most retirees do not have enough preparations for life after retirement, and they have a lot of difficulties in finding their own identity separated from public relations such as expectations and social norms of others, and there are not many successful cases.

As the number of retired executives who fall under C-Professional is on an increasing trend, the lifestyle-related service market is expected to continue to increase after retirement, and related sectors are from about 6.7 billion in 2022 to 14 billion within 10 years. It is expected to achieve growth in scale.

Korean Patent Registration No. 10-1493736

An object of the present invention is to provide a method and a system for providing a personalized expert mutual matching service.

The technical problems to be achieved in the present invention are not limited to the technical problems mentioned above, and other technical problems that are not mentioned will be clearly understood by those of ordinary skill in the technical field to which the present invention belongs from the following description. I will be able to.

An aspect of the present invention is a method of providing a service for mutually matching experts in each field based on artificial intelligence, including primary input information input by a user and primary external information collected from an external data server. Receives primary personal information to the user terminal and transmits it to the central server, extracts and analyzes key elements of primary personal information collected by the central server, and weights according to the combination of key elements through machine learning. Each calculation, including the step of predicting the user's interests by artificial intelligence based on the second personal information analyzed by applying a weight to the first personal information, and suggesting a community and program that shares the interests, the user And calculating the synergy effect of the community and programs, and the primary external information includes the user's personal SNS content, search engine search history, shopping mall search and purchase history, online book purchase history, offline book purchase history, and active activity. It provides a method of providing a customized mutual matching service based on artificial intelligence, which is one or more selected from the group consisting of online community activity details.

Specifically, in the step of predicting the user's field of interest by artificial intelligence based on the analyzed secondary personal information by applying a weight to the primary personal information, an individual weight calculated by machine learning is applied to the primary personal information. It analyzes and generates personalized information request content for each individual based on the primary personal information analyzed by the artificial intelligence-based prediction unit, the user secondly inputs necessary personal information corresponding to the information request content, and the first analyzed Comprising a new second weight by comparing and analyzing the personal information and the newly input secondary personal information, and finally calculating the user's interest field by applying the newly calculated second weight. It may be a method of providing an intelligence-based customized mutual matching service.

In addition, in an embodiment of the present invention, a community that shares interests derived by artificial intelligence is selected, the interests and objectives of the community itself are vectorized as community information, and detailed interests of each member constituting the community And capability information is analyzed and vectorized, the vectorized information is reprocessed through machine learning to be compatible with the contents listed in the database, and the optimal value between the community and the database is calculated using the reprocessed information. It proposes matching, compares the results proposed by artificial intelligence using only the information of each member of the community and the results calculated by vectorizing the community's own information, and re-adjusts the results in the order that the discrepancy between individual results and community results is small. It provides a customized mutual matching service method based on artificial intelligence, including the step of suggesting community and program matching to users.

With respect to the method for vectorizing the information in the present invention, any technology used in the relevant technical field may be used, and the type or format thereof is not limited.

In the present invention, the "vectorization" refers to expressing a word or document as numerical data in order to allow a computer to recognize a certain word or document. As an example of this method, TF-IDF (Term Frequency Inverse Document Frequency) can be applied, and programs such as word2vec, which are commercially used, can be used.

In addition, an embodiment of the present invention recognizes in advance a possibility that a community or program will occur in the user's interest field through prediction based on artificial intelligence, determines whether the community or program is suitable for the user, The decision is made by calculating the synergy effect using the vector similarity to which the weight is applied, which will be described later, and by comparing the determined community or program's request level with the user's personal information, proactively suggesting the development of the skills necessary for the user, based on artificial intelligence. Provides a customized mutual matching service method.

Another aspect of the present invention is an artificial intelligence-based customized expert mutual matching system, including a central server for sending and receiving a database and a user terminal, and recommending customized experts, programs, and communities based on the various data and information. And, the central server, the user terminal recognition management unit for recognizing the user terminal; A user information registration unit for storing information received from a user terminal in a central server; A user information extraction unit for recognizing the registration information received and stored by the user information registration unit, and extracting key elements including a plurality of keywords included in the registration information; A user information analysis unit for analyzing a plurality of keywords and key elements extracted by the information extraction unit; A machine learning unit that combines the core elements according to a specific subject and calculates a user-customized weight for each combination; A user information management unit that manages personal information for each user, weights for combinations of key elements, and prediction results based on artificial intelligence; And an artificial intelligence-based prediction unit that predicts the user's interest field by artificial intelligence based on the personal information reconstructed by reflecting the user-customized weight calculated through machine learning. System.

According to the present invention, based on the user's behavior patterns collected through personal information input by the user, the user's personal SNS (Social Network Service), and search history, the user was not aware of it through machine learning and artificial intelligence algorithms. It is possible to provide customized programs optimized for individual users by exploring the underlying areas of interest.

In addition, the system of the present invention can form a community by matching retired executives who are experts in each field according to similar interests or fields of interest, as well as selecting a target program that meets the internal capabilities and purpose of the formed community or Can suggest the creation of.

Furthermore, according to the present invention system, it is possible to preemptively propose programs that require users by pre-searching various target groups, programs, lectures, etc. that require the above expert (retired executive) community. Furthermore, it is possible to compare the required capabilities and objectively evaluated current user's capabilities and interests to match with experts in the fields to be supplemented and prepared.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and other effects not mentioned can be clearly understood by those of ordinary skill in the art from the following description. will be.

1 is a view for explaining a system for artificial intelligence-based customized expert mutual matching according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining a method of providing personalized expert mutual matching based on artificial intelligence according to an embodiment of the present invention.
3 is a flowchart illustrating a method of deriving an interest field of a user by collecting necessary information and a search history of a user according to an embodiment of the present invention.
4 is a diagram illustrating a method of matching a target program with a community formed according to an embodiment of the present invention.
5 is a block diagram showing the configuration of a user terminal according to the present invention.
6 is a block diagram showing the configuration of a central server for artificial intelligence-based matching according to the present invention.
It should be noted that throughout the drawings, like reference numbers are used to show the same or similar elements, features, and structures.

In order to clarify the features and advantages of the problem solving means of the present invention, the present invention will be described in more detail with reference to specific embodiments of the present invention shown in the accompanying drawings.

However, in the following description and the accompanying drawings, detailed descriptions of known functions or configurations that may obscure the subject matter of the present invention will be omitted. In addition, it should be noted that the same components are indicated by the same reference numerals as possible throughout the drawings.

The terms or words used in the following description and drawings should not be construed as being limited to their usual or dictionary meanings, and the inventor may appropriately define the concept of terms for describing his or her invention in the best way. It should be interpreted as a meaning and concept consistent with the technical idea of the present invention based on the principle that there is. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are only the most preferred embodiments of the present invention, and do not represent all the technical ideas of the present invention, so various alternatives that can be substituted for them at the time of application It should be understood that there may be equivalents and variations.

In addition, terms including ordinal numbers such as first and second are used to describe various elements, and are only used for the purpose of distinguishing one element from other elements, and to limit the elements. Not used. For example, without departing from the scope of the present invention, a second component may be referred to as a first component, and similarly, a first component may be referred to as a second component.

In addition, terms used in the present specification are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In addition, terms such as "comprises" or "have" described herein are intended to designate the presence of features, numbers, steps, actions, components, parts, or a combination thereof described in the specification, but one or a combination thereof. It is to be understood that the above other features, or the possibility of the presence or addition of numbers, steps, actions, components, parts, or combinations thereof, are not preliminarily excluded.

In addition, terms such as "unit", "group", and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware or software or a combination of hardware and software. In addition, "a or an", "one", "the" and similar related words are different from this specification in the context of describing the present invention (especially in the context of the following claims). Unless otherwise indicated or clearly contradicted by context, it may be used in a sense encompassing both the singular and the plural.

In addition to the above terms, specific terms used in the following description are provided to aid understanding of the present invention, and the use of these specific terms may be changed in other forms without departing from the technical spirit of the present invention.

In addition, embodiments within the scope of the present invention include computer-readable media having or transferring computer-executable instructions or data structures stored in the computer-readable media. Such computer-readable media may be any available media accessible by a general purpose or special purpose computer system. By way of example, such computer readable media may be in the form of RAM, ROM, EPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, or computer executable instructions, computer readable instructions, or data structures. It may include, but is not limited to, physical storage media such as any other media that may be used to store or deliver certain program code means, and may be accessed by a general purpose or special purpose computer system. .

In addition, the present invention relates to a personal computer, a laptop computer, a handheld device, a multiprocessor system, a microprocessor-based or programmable consumer electronics, a network PC, a minicomputer, a mainframe computer, a mobile phone, a PDA, a pager. It can be implemented in a network computing environment having various types of computer system configurations including (pager) and the like. The invention may also be practiced in a distributed system environment where both local and remote computer systems linked through a network with a wired data link, a wireless data link, or a combination of wired and wireless data links perform tasks. In a distributed system environment, program modules may be located in local and remote memory storage devices.

In addition, it will be appreciated that each block of the process flow diagrams and combinations of the flow chart diagrams may be executed by computer program instructions. Since these computer program instructions can be mounted on the processor of a general purpose computer, special purpose computer or other programmable data processing equipment, the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates a means to perform functions. These computer program instructions can also be stored in computer-usable or computer-readable memory that can be directed to a computer or other programmable data processing equipment to implement a function in a particular way, so that the computer-usable or computer-readable memory It is also possible to produce an article of manufacture containing instruction means for performing the functions described in the flowchart block(s). Computer program instructions can also be mounted on a computer or other programmable data processing equipment, so that a series of operating steps are performed on a computer or other programmable data processing equipment to create a computer-executable process to create a computer or other programmable data processing equipment. It is also possible for instructions to perform processing equipment to provide steps for executing the functions described in the flowchart block(s).

In addition, each block may represent a module, segment, or part of code that contains one or more executable instructions for executing the specified logical function(s). In addition, it should be noted that in some alternative execution examples, functions mentioned in blocks may occur out of order. For example, two blocks shown in succession may in fact be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order depending on the corresponding function.

In describing the embodiments of the present disclosure in detail, examples of a specific system will be the main target, but the main subject matter to be claimed in this specification is the scope disclosed in the present specification to other communication systems and services having a similar technical background. It can be applied within a range that does not deviate greatly, and this will be possible at the judgment of a person skilled in the art.

Now, a method of providing a personalized expert mutual matching service based on artificial intelligence according to an embodiment of the present invention will be described in earnest.

1 is a view for explaining a system for artificial intelligence-based customized expert mutual matching according to an embodiment of the present invention.

Referring to FIG. 1, a system for artificial intelligence-based customized expert mutual matching according to an embodiment of the present invention includes a communication network 100, a user terminal 200, a central server 300, a database 400, and user information. It may include an external data server 500 and an external data server 600 related to needs for professional manpower.

Here, the user terminal 200 may be interlocked with the central server 300 and the external data server 500 related to user information through the communication network 100. In this case, the communication network 100 may be a wireless communication network. For example, the wireless communication network may be a wireless communication network using LTE (Long Term Evolution), 5G (5 Generation), and WiFi.

Meanwhile, the central server 300 and the database 400 may be linked through a wireless communication network, but may be linked through a wired communication network. In addition, various types of data may be transmitted and received between the central server 300 and the database 400 in a form in which a wired/wireless communication network is combined.

Here, examples of various data transmitted and received between the user terminal 200, the central server 300, the database 400, the external data server 500 related to user information, and the external data server 600 related to the needs for professional manpower are It may be according to the embodiments of the present invention described later.

The user terminal 200 of the present invention refers to a user's device capable of transmitting and receiving various data via the communication network 100 according to the user's manipulation. The user terminal 200 may perform voice or data communication through the communication network 100 and may transmit and receive information through the central server 300 and the communication network 100. For this, the user terminal 200 of the present invention may include various modules for transmitting and receiving data to and from the central server 300, and specifically, the control module 210, the input module 220, and the output module 230 And it may include a communication module 240. The control module may include a memory for storing programs and protocols, and a microprocessor for calculating and controlling by executing various programs.

The user terminal 200 preferentially accesses an application (hereinafter,'app') providing device (not shown) connected to the communication network 100, for example, an app store, and provides an app for a customized matching service from the corresponding app store. It can be received and installed.

In addition, the user terminal 200 may be implemented in various forms. For example, the user terminal 200 described herein is a mobile terminal such as a smart phone, a tablet PC, a personal digital assistant (PDA), a portable multimedia player (PMP), and an MP3 player. Of course, a fixed terminal such as a smart TV or a desktop computer may be used.

In addition, the user terminal 200 of the present invention can not be listed all because the deformation of the portable device is very diverse according to the convergence trend of the digital device. However, a unit of the same level as the above-mentioned units is used in the present invention. If it is a device that can be used as the user terminal 200 according to the present invention, and can download and install an app related to the artificial intelligence-based customized mutual matching service according to the present invention, any device is the user terminal 200 according to the embodiment of the present invention. Can be used as.

The central server 300 transmits and receives various data and information to and from the database 400 and user terminal 200 for providing an artificial intelligence-based customized expert mutual matching service according to an embodiment of the present invention, and transmits and receives the various data and information. Based on this, it is a server device for recommending customized experts, programs, and communities.

The database 400 is provided with a communication module 450 capable of interworking with the central server 300 and an external data server 600 related to the needs of professionals, and an external expert DB 401, related to travel and experience. It may include an activity DB 402, a personal care program DB 403, and an external needs-related DB 410. The external needs-related DB 410 communicates periodically with the external data server 600 related to the needs for the professional manpower, so that the needs for the professional manpower can be continuously updated and stored in real time, and by communicating with the central server again, the trend and It can analyze patterns, predict demand proactively using artificial intelligence, and upload itself to external needs-related DB 410.

The external data server 500 related to user information is for searching not only the expressed interests but also the latent interests by obtaining and analyzing the details of activities performed by the user consciously and unconsciously. User's personal SNS server (500-1), search engine server (500-2), shopping mall server (500-3), online/offline book purchase history management server (500-) by delegating necessary authority through the installed app. 4) It is possible to acquire user-related information in all fields in which personal interests may be expressed, such as the server 500-5 of an active online community, and transmit/receive to the user terminal 200 and the central server 300.

The external data server 600 related to the needs for professional manpower is for transmitting and receiving data on all related fields in which demand for the professional manpower may occur, and if the above demand can be confirmed, the type is specifically limited. no. For example, the demand for the professional manpower may be confirmed through online announcements, official documents, newspaper advertisements, and SNS, and when such demand is classified and categorized by content, the job search server (600-1), external lecture related It may be subdivided into a server 600-2, a server related to urban regeneration 600-3, and a server related to marketing 600-4, but is not limited thereto.

When interest or demand for the above-described professional manpower is confirmed or expected, such information may be obtained and transmitted and received to the database 400 and the central server 300.

Now, a detailed operation process of the devices disclosed in FIG. 1 will be described through FIGS. 2 to 6.

FIG. 2 is a diagram for explaining a method of providing personalized expert mutual matching based on artificial intelligence according to an embodiment of the present invention. Referring to FIG. 2, a user inputs primary input information into the user terminal 200 (S205), and the primary input information is for converting a propensity including his/her own history and a field of interest into vector data. Background, investment type and scale, asset management method, religion, interest, education degree, desire, interest, motto, creed, etc. may be made.

Together with the primary input information, primary external information, which is user information obtained from the external data server 500, is transmitted to the central server 300 through the user terminal 200 (S210).

Under the premise that the basic information directly entered by the user is an area of explicit interest recognized by the user, it is intended to produce higher quality results including potential areas of interest by acquiring and analyzing the details of activities that the user consciously and unconsciously performs. As a result, the user delegates the necessary authority through the app installed on the user terminal 200, so that the user's personal SNS content, search engine search history, shopping mall search and purchase history, online/offline book purchase history, active online community activity history User-related information in all fields in which personal interests may be expressed, such as, may be obtained from the external data server 500.

The primary input information and primary external information are collectively referred to as primary personal information.

The primary personal information collected by the central server 300 is extracted and analyzed for each key element for each information, and goes through a step (S215) of calculating a separate weight according to the combination of each key element through machine learning. .

Specifically, in step S215, it is checked whether the terminal is authorized by the user terminal recognition management unit 310 that recognizes the user terminal 200, and the user information registration unit 320 stores information received from the user terminal. Thereafter, the user information extraction unit 330 recognizes the registration information received and stored by the user information registration unit 320 and extracts a key element including a plurality of keywords included in the registration information. At this time, since the registration information may include not only the content directly input by the user, but also the content queried through the external server 500, the form may be a word, a sentence, or a voice recording file. After recognizing nouns, adjectives, investigations, adverbs, verbs, etc., the extracted keywords are reinterpreted from complex sentences into formalized patterned sentences through formalization and patterning functions according to subject, object, and verb. Through this, keywords are extracted mainly for nouns that are repeatedly spoken.

Thereafter, the user information analysis unit 340 analyzes a plurality of keywords and key elements extracted by the user information extraction unit 330, and the machine learning unit 350 combines the key elements according to a specific subject. User-customized weights are calculated. For example, if the user's religion is “Christian”, even though he likes “climbing,” the interest in “Temple Stay” is expected to be low, so a low weight may be given to the field. If you are interested in “real estate investment” and “child education”, it is expected that the interest in “real estate trends by school district” will be high, so a high weight can be given to the field.

In addition, even if you do not express interest explicitly, you can predict potential interests of users by analyzing personal search history, reading list, tone of favorite news, activity radius, personal relationships, and frequently used vocabulary or language. In addition, a separate weight can be calculated and assigned to the corresponding field.

That is, the system of the present invention collects and classifies data in all fields that can be obtained for an individual user, and combines the number of all possible cases for each key element included in each data, so that each combination of a myriad of key elements It is characterized in that the weight can be calculated through machine learning.

Based on the personal information reconstructed by reflecting the user-customized weight calculated through machine learning, the user's interest field is predicted by artificial intelligence from the artificial intelligence-based prediction unit 370 provided in the central server (S220), and the field of interest is determined. A program or community to be shared may be suggested to the user, and a synergy effect between the user and the corresponding program or community may be calculated through artificial intelligence (S225).

Specifically, in the present invention, the “synergy effect” is vectorized by applying individual weights for the user's explicit interests and potential interests based on the vectorized personal information of the user used to select a program and/or community. It may be calculated by comparing the result of vectorization of the core elements of the corresponding community or program.

In the present invention, the “individual weight” refers to a second-order weight finally calculated through two-step machine learning, and details thereof will be described later.

As for the specific criterion for determining the synergy effect, the similarity of the field of interest calculated by applying individual weights based on the user's personal information and the result of vectorizing the core elements of the program or community to be judged was compared. Specifically, when the vector similarity between the weighted explicit interest field and the program/community is 85% or higher, and the vector similarity between the potential interest field and the program/community is 70% or higher, the synergy effect between the user and the corresponding community/program is It can be judged as good, and when the vector similarity with the explicit field of interest is 50 to 85%, and the vector similarity with the potential field of interest is 45 to 70%, it can be judged that it does not produce any synergistic effect. If the vector similarity to and less than 50% or the vector similarity to potential interests is less than 45%, it causes stress similar to referencing something you don't like, so it may have a negative effect on the user, resulting in an inverse synergy effect. .

In other words, the present invention compares the vectorized result by applying individual weights for the user's explicit interests and potential interests based on the user's vectorized personal information and the vectorized results of the core elements of the corresponding community or program. By additionally going through the synergy calculation process, it is possible to overcome the limitations of the conventional mechanical matching method, and to the user, “I can easily meet people who are well suited to me without knowing why”, and “I take care of my needs that I did not know. It is characterized by being able to give a feeling of satisfaction, as if it seemed to know me better than me.

Now, through FIG. 3, an example of predicting a user's interest field by artificial intelligence in steps S205 to S220 of FIG. 2 will be described.

Referring to FIG. 3, the user inputs basic information related to the user in the user terminal 200 (S305), and collects the user's activity information from the external data server 500 (S310). The information input in S305 is referred to as primary input information, and the information collected in S310 is referred to as primary external information, and the first input information and primary external information are collectively referred to as primary personal information.

After the collected primary personal information is separated by the core elements constituting the personal information in the central server 300, the machine learning unit 350 calculates a weight for each when the core elements are combined according to each subject. Then, the collected information is analyzed by reflecting the calculated user-customized weight (S315).

Based on the personal information analyzed by reflecting the user-customized weight, the artificial intelligence-based prediction unit 370 generates customized information request contents to the user, and the user secondly inputs necessary personal information corresponding to the information request contents. It goes through a step (S320).

The information request content generated by artificial intelligence for acquiring the secondary personal information may be a request in a way that asks ``the user who likes climbing as a Christian, what his preference for temple stay is'' based on the above example. Also, it may include a'question process in which the user has not explicitly expressed interest, but re-evaluates the user's preference for the area of interest predicted by analyzing the activity details', and is not limited to any form or content. The above-described examples are merely examples, and are not limited thereto.

Thereafter, after the secondary personal information corresponding to the information request content is inputted by the artificial intelligence, the weight is newly corrected and calculated by comparing and analyzing the primary personal information analyzed in step S315 with the secondary input personal information. By generating the second weight and applying the second weight for each individual case (combination of each key element), the user's interest field is finally calculated. As described above, machine learning can be used in the weight calculation process.

That is, through the system of the present invention, it is possible to more clearly distinguish detailed areas of interest by weight among areas of interest that the user has explicitly and consciously recognized, as well as search for potential areas of interest that are inherent without the user's knowledge. It is characterized by being able to provide customized programs optimized for individual users.

In FIG. 4, a method of matching a selected community and a target program between users sharing an interest field according to an embodiment of the present invention will be described.

Referring to FIG. 4, a community that shares an area of interest derived by artificial intelligence is selected (S405), vectorizes key elements related to the common interest field and purpose of the community itself, and detailed interest for each member of the community The field and competency information is analyzed and vectorized (S410).

Thereafter, the vectorized information for each individual community goes through a step of reprocessing through machine learning so that the information registered in the database 400 is compatible with each other (S415).

In the present invention, the core elements constituting the personal information of each individual user constituting the community and the core elements constituting the information of the community itself are vectorized, and this is again applied to both internal and external DBs through machine learning. By reprocessing, it is possible to solve the problem of information fragmentation and a wide error range, which may have occurred in the conventional method of primarily comparing vector similarities.

Specifically, by calculating the optimal value when mutual matching is attempted based on the reprocessed community information and the contents of the previously registered database, we propose matching a community or program with excellent synergy effects (S420), and finally, the user By comparing the results predicted by artificial intelligence based only on the information of the AI and the results calculated by vectorizing the community's own information, the result of the comparison is readjusted in the order of the smallest gap between the individual results and the community results. -Program matching can be proposed (S425). The synergy effect is as described above.

In addition, in an embodiment of the present invention, by preemptively predicting the necessity of a professional manpower using artificial intelligence-based prediction, and conversely, by providing the user with the possibility of creating a community or program in an area of interest, the user It can help you prepare for the necessary preparations for participation in the program, or it can help you develop additional skills that are required.

This will be described with a specific example as follows. As an example, suppose a user who worked as an executive of a civil engineering company wants to continue his career in a related field even after retirement. The central server 300, which received the above-described field of interest, started to search for the existence of related content from the information collected from the database 400 of the present invention system and the external data server 600 related to the needs for professional manpower. As a result, it succeeded in extracting and analyzing the contents that there is a possibility that a large-scale artificial forest creation project will start in the near future. In this case, whether the relevant content belongs to the user's interest field (whether civil engineering and landscaping correspond to similar fields that the user thinks), competency (whether there is a license related to landscape, etc.) It can be determined by the unit 350 and the artificial intelligence-based prediction unit 370. After it is determined that it is suitable for the user as a result of the judgment, the program can be presented to the user based on the content necessary to participate in the project in the future. Specifically, it is possible to match external experts related to acquiring the qualification requirements necessary for large-scale landscaping projects, and linking with programs such as education necessary for this. In addition, a method such as recommending community organization by grouping members with high relevance to the project among other professional personnel registered in the system may be possible.

Another embodiment relates to the creation of a new program that is proactively proposed by artificial intelligence from the beginning. Specifically, in the process of searching and analyzing the database 400 and the external data server 600 through machine learning, the number of personal broadcasters with expertise is increasing thanks to the rising trend of online video transmission platforms such as YouTube, further differentiating them. In order to do this, it is assumed that it has succeeded in analyzing the need for senior retired executives who can encompass the product planning stage and overall product design. In the above circumstances, the system of the present invention provides the results of this analysis to retired executives who served as product planning team leaders and retired executives at the general designer level, and preemptively suggests establishing a project team to meet market needs. , It may be possible to provide an external expert (photographing expert, editing expert, columnist, etc.) accompanying this from the DB 401. The above examples are intended to aid understanding of the present invention and are not intended to limit the embodiments of the present invention to any form.

5 to 6 are block diagrams showing the configuration of an apparatus for implementing the embodiment of the present invention.

5 is a block diagram illustrating a configuration of a user terminal 200 for implementing the above-described embodiment of the present invention.

Referring to FIG. 5, the user terminal 200 may include a control module 210, an input module 220, an output module 230, a communication module 240, and the like.

The input module 220 receives various information such as number and character information, and transmits a signal input in connection with setting various functions and controlling the functions of the user terminal 200 to the control module 210. In addition, the input module 220 may be configured to include at least one of a keypad and a touch pad that generate an input signal according to a user's touch or manipulation. In this case, the input module 220 is configured in the form of a single touch panel (or touch screen) together with the output module 230 to simultaneously perform input and display functions. In addition, the input module 220 may use any type of input means that may be developed in the future, in addition to input devices such as a keyboard, a keypad, a mouse, and a joystick. Particularly, the input module 220 according to the present invention detects input information input from a user and transmits it to the control module 210.

The output module 230 displays information on a series of operation states and operation results that occur while performing a function of the user terminal 200. In addition, the output module 230 may display a menu of the user terminal 200 and user data input by the user. Here, the output module 230 is a liquid crystal display (LCD), an ultra-thin liquid crystal display (TFT-LCD, Thin Film Transistor LCD), a light emitting diode (LED), an organic light emitting diode (OLED). OrganicLED), an active organic light emitting diode (AMOLED, Active Matrix OLED), a retina display, a flexible display, and a three-dimensional display. In this case, when the output module 230 is configured in the form of a touch screen, the output module 230 may perform some or all of the functions of the input module 220.

The communication module 240 may transmit and receive data to and from the central server 300 and the external server 500 through the communication network 100. In addition, the communication module 240 includes an RF transmission unit for up-converting and amplifying a frequency of a transmitted signal, an RF receiving unit for low-noise amplifying and down-converting a received signal, and a communication protocol according to a specific communication method. And data processing means. The communication module 240 may include at least one of a wireless communication module (not shown) and a wired communication module (not shown). And, the wireless communication module is a configuration for transmitting and receiving data according to a wireless communication method, and when the user terminal 200 uses wireless communication, any one of a wireless network communication module, a wireless LAN communication module, and a wireless fan communication module is used. Thus, data can be transmitted and received with the central server 300. Here, the communication module 240 may include a plurality of communication modules. When a plurality of communication modules are included in the communication module 240, one communication module may perform communication in a Personal Area Network (PAN) method including Bluetooth. The present invention may include a first communication module 241 for communicating with the central server 300 and a second communication module 242 for communicating with the external server 500, but is not limited thereto.

In addition, the other communication module communicates with the central server 300 through the communication network 100. Here, the other communication module may use a wireless communication method such as WLAN (Wireless LAN), Wi-Fi, Wibro, Wimax, and High Speed Downlink Packet Access (HSDPA).

The control module 210 may be an operating system (OS) and a process device that drives each component.

Therefore, the control module 210 of the user terminal 200 controls to transmit the signal received through the input module 220 to the central server 300 through the communication module 240, and through the communication module 240 The received beacon, Wi-Fi, a base station signal, or information transmitted from the central server 300 may be controlled to be exposed through the output module 230.

In addition, the control module 210 of the user terminal 200 may control the overall operation process of the user terminal 200 according to an embodiment of the present invention. In other words, the entire operation process of the user terminal 200 according to the embodiments of the present invention described above based on FIGS. 1 to 4 may be controlled by the control module 210.

6 is a block diagram showing the configuration of a central server 300 for implementing embodiments of the present invention.

6, a user terminal recognition management unit 310, a user information registration unit 320, a user information extraction unit 330, a user information analysis unit 340, a machine learning unit 350, a user information management unit 360 , It may include an artificial intelligence-based prediction unit 370 and/or a database management unit 380.

The user terminal recognition management unit 310 may recognize the user terminal 200 to indicate whether or not an authorized terminal has been recognized, or may receive user terminal recognition information indicating that it has been detected.

The user information registration unit 320 stores information received from the user terminal. Thereafter, the user information extraction unit 330 recognizes the registration information received and stored by the user information registration unit 320 and extracts a key element including a plurality of keywords included in the registration information.

The information analysis unit 340 analyzes a plurality of keywords and key elements extracted by the information extraction unit 330, and the machine learning unit 350 combines the key elements according to a specific subject and weights them. Is calculated.

The user information management unit 360 may play a role of managing personal information for each user, a weight for a combination of each key element, and a prediction result based on artificial intelligence.

In addition, the machine learning unit 350 generates a key element from the personal information of the user or a combination of the key elements by using machine learning on big data stored in the database and information received from the user terminal. Can be newly created or its weight can be determined. In addition, the machine learning unit learns the artificial intelligence-based prediction unit 370 using big data stored in the database of the central server 300 as an input variable. Specifically, a deep learning technique, which is a field of machine learning, is used. Using this, learning can be performed so that an accurate correlation can be derived. In addition, various models, such as a recurrent neural network (RNN), a deep neural network (DNN), and a dynamic recurrent neural network (DRNN), may be used as an artificial intelligence network model used for such learning.

The database management unit 380 may include a separate control module 381 and a communication module 382, and the communication module 382 is for communicating with the database 400, and the communication module 382 performs a function. The communication network to perform is preferably a wireless communication method such as WLAN (Wireless LAN), Wi-Fi, Wibro, Wimax, and High Speed Downlink Packet Access (HSDPA), but is limited thereto. Depending on the system implementation method, wired communication methods such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coaxial Cable), FTTC (Fiber to The Curb), FTTH (Fiber To The Home) are used. May be.

The control module 381 may be an operating system (OS) and a process device that drives each component.

As explained above, the specification includes details of a number of specific implementations, but these should not be construed as limiting to the scope of any invention or claimable, but rather, which may be specific to a particular embodiment of a particular invention. It should be understood as a description of features. Certain features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination. Furthermore, although features operate in a particular combination and may be initially described as so claimed, one or more features from a claimed combination may in some cases be excluded from the combination, and the claimed combination may be a subcombination. Or sub-combination variations.

Likewise, although operations are depicted in the drawings in a specific order, it should not be understood that such operations must be performed in that particular order or sequential order shown, or that all illustrated operations must be performed in order to obtain a desired result. In certain cases, multitasking and parallel processing can be advantageous. In addition, separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the program components and systems described are generally integrated together into a single software product or packaged in multiple software products. You should understand that you can.

Specific embodiments of the subject matter described herein have been described. Other embodiments are within the scope of the following claims. For example, the operations recited in the claims may be performed in a different order while still achieving desirable results. As an example, the process depicted in the accompanying drawings does not necessarily require that particular depicted order or sequential order to obtain desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

The present description presents the best mode of the present invention, and provides examples for describing the present invention and for enabling those skilled in the art to make and use the present invention. The thus written specification does not limit the present invention to the specific terms presented. Accordingly, although the present invention has been described in detail with reference to the above-described examples, those of ordinary skill in the art can make modifications, changes, and modifications to these examples without departing from the scope of the present invention.

Therefore, the scope of the present invention should not be determined by the described embodiments, but should be determined by the claims.

100: communication network 200: user terminal 300: central server
400: database
500: external data server related to user information
600: External data server related to the needs of professionals

Claims (6)

In a method of providing a service that matches experts in each field based on artificial intelligence,
(a) Receive primary personal information including primary input information entered by the user and primary external information collected from an external data server to the user terminal and transmit it to the central server,
(b) Extracting and analyzing key elements of the primary personal information collected by the central server,
(c) Calculate each weight according to the combination of each key element through machine learning,
(d) Predict the user's area of interest by artificial intelligence based on the analyzed secondary personal information by applying weight to the primary personal information,
(e) including proposing communities and programs that share areas of interest,
(f) calculating synergies between users and communities and programs,
The primary external information in step (a) above is one or more from the group consisting of the user's personal SNS content, search engine search history, shopping mall search and purchase history, online book purchase history, offline book purchase history, and active online community activity history. Selected,
Predicting the user's interest field by artificial intelligence based on the secondary personal information analyzed by applying a weight to the primary personal information in step (d),
(d-1) Analysis by applying individual weights calculated by machine learning to primary personal information,
(d-2) Create personalized information request content based on the primary personal information analyzed by the artificial intelligence-based prediction unit,
(d-3) The user secondly inputs necessary personal information that meets the information requested above,
(d-4) A new second weight is calculated by comparing and analyzing the previously analyzed primary personal information and newly input secondary personal information,
(d-5) including the step of finally calculating the user's interest field by applying the newly calculated second weight,
The synergistic effect of step (f) is,
Comparing the similarity between the explicit interest field and potential interest field calculated by applying individual weights based on the result of vectorizing the program or community core elements subject to judgment and the user's personal information,
When the vector similarity between the weighted explicit interest field and the program or community is 85% or more, and the vector similarity with the potential interest field is 70% or more, it is judged that the synergy effect is good,
When the vector similarity to the explicit field of interest is 50 to 85% and the vector similarity to the potential field of interest is 45 to 70%, it is judged that no other synergistic effect is produced,
If the vector similarity with the explicit interest field is less than 50% or the vector similarity with the potential interest is less than 45%, it is judged as an inverse synergy effect,
A method of providing customized mutual matching services based on artificial intelligence. delete The method of claim 1,
The step (f) calculating the synergy effect of the user, the community, and the program,
(f-1) A community that shares an area of interest derived by artificial intelligence is selected,
(f-2) Vectorize the community's own interests and purposes as community information,
(f-3) Analyzing and vectorizing detailed information on the interests and capabilities of each member of the community,
(f-4) Reprocessing each of the vectorized information through machine learning to be compatible with the contents listed in the database,
(f-5) Proposing matching of communities or programs with excellent synergy effects when attempting mutual matching based on the reprocessed information and the contents of the previously registered database,
(f-6) Using only the information of each member of the community, the results proposed by artificial intelligence and the results calculated by vectorizing the community's own information are compared,
(f-7) Comprising the step of rearranging in the order of high similarity between individual results and community results as a result of comparison, and finally suggesting community and program matching to users,
A method of providing customized mutual matching services based on artificial intelligence. delete delete In the artificial intelligence-based customized expert mutual matching system, it includes a central server for recommending customized experts, programs, communities, etc., based on data and information transmitted and received, and transmitted and received with a database and a user terminal,
The central server,
A user terminal recognition management unit that recognizes a user terminal;
A user information registration unit for storing information received from a user terminal in a central server;
A user information extraction unit for recognizing the registration information received and stored by the user information registration unit, and extracting key elements including a plurality of keywords included in the registration information;
A user information analysis unit for analyzing a plurality of keywords and key elements extracted by the information extraction unit;
A machine learning unit that combines the core elements according to a specific subject and calculates a user-customized weight for each combination;
A user information management unit that manages personal information for each user, weights for combinations of key elements, and prediction results based on artificial intelligence; And
Including; artificial intelligence-based prediction unit,
The artificial intelligence-based prediction unit,
By applying the individual weights calculated by the machine learning unit to the primary personal information input to the user information management unit, a personalized information request content is created, and newly calculated based on the secondary personal information input based on the information request content. Predict the user's interest field by applying the second order weight,
Calculate the synergy effect of users and communities and programs that share the predicted interests,
The synergy effect is by comparing the similarity between the explicit interest field and potential interest field calculated by applying individual weights based on the result of vectorizing the core elements of the program or community to be judged and the user's personal information,
When the vector similarity between the weighted explicit interest field and the program or community is 85% or more, and the vector similarity with the potential interest field is 70% or more, it is judged that the synergy effect is good,
When the vector similarity to the explicit field of interest is 50 to 85% and the vector similarity to the potential field of interest is 45 to 70%, it is judged that no other synergistic effect is produced,
It is characterized in that it is determined as an inverse synergistic effect if the vector similarity with the explicit interest field is less than 50% or the vector similarity with the potential interest is less than 45%,
Artificial intelligence-based customized expert mutual matching system.

Images