KR20230089513A - Investment attraction flatform system based on artificial intelligence - Google Patents

Abstract

As an investment attraction platform system according to an embodiment for realizing the above object of the present invention, an investment attraction target is registered for an investment attractor, investment attraction information on the investment attraction target, and self-evaluation of the investment attraction target An investment attractor terminal into which first evaluation information is input, an investment expert terminal into which second evaluation information, which is professional evaluation information based on the investment attraction information for an investment attraction registered by an investment expert, is input, and the first evaluation information And an investment platform server that outputs third evaluation information, which is compromised evaluation information, using an artificial intelligence-based valuation model based on evaluation data including the second evaluation information, wherein the valuation model includes, Annual investment attraction information and first evaluation information for an unspecified number of investment attraction targets, annual second evaluation information corresponding to the first evaluation information, and at least one point in time of the investment attraction target It is a result of pre-learning state information based on artificial intelligence, and when the evaluation data is input, the value evaluation information of the investment attraction target according to the year at the time of input and the expected value information by year according to the lapse of time 3 Output evaluation information.

Description

AI-based investment attraction platform system {INVESTMENT ATTRACTION FLATFORM SYSTEM BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to an artificial intelligence-based investment attraction platform system, and more particularly, to provide a guide to investors in investing in companies through the analysis of corporate value evaluation results using artificial intelligence-based big data modeling technology. At the same time, it is about an investment attraction platform system that can secure necessary investment funds even as an investment promoter.

As a conventional method for attracting investment by a company, a method of issuing securities or bonds is well known. However, since it is difficult for start-ups and venture companies to use such investment public offering methods, it is common for most of them to receive loans from banks at high interest rates, or to personally attract investments by mobilizing personal connections. The reason why it is difficult for startups to issue securities or bonds is that there are few channels through which information important to investment decisions, such as the company's own financial information, is disclosed to investors, and ordinary investors avoid investing.

Since ordinary investors do not have specialized tools to analyze or obtain corporate financial information, they prefer the 'fund' type of investment in which direct investment in stocks or bonds is entrusted to professional companies. A fund is an investment method in which an asset management company invests and manages funds collected from investors in stocks and bonds, and then returns the results. In other words, investors do not directly select and invest in stocks or bonds, but a professional asset management company selects them, and the investment is based on funds collected from multiple investors, not individual funds.

Since the investment agency system through the fund is still related to the investment method in the form of stocks or bonds, it cannot escape the aspect of investment that is irrelevant to startups or venture companies that cannot issue stocks or bonds but still need funds. . This is due to the fundamental problem of unbalanced distribution of investment information, in which the work of analyzing and evaluating corporate investment-related information and such investment-related information is concentrated only in some specialized fields and is not open to general investors.

On the other hand, according to government data, it can be seen that interest and attempts to start a business in the domestic market are rapidly increasing recently, but the performance is low. This may mean that the start-up items of startups or venture companies have not reached qualitative maturity. may be

In particular, in the case of lifestyle innovation start-ups, it is necessary to pay attention to the fact that they deal with issues that must be resolved as a social and cultural phenomenon. There is only a low investment rate for lifestyle innovation start-ups.

Therefore, by using big data modeling technology, including professional investors' investment opinions based on several successful cases that can reduce investment risk, there is a gap between the demand for start-up by the general public and the demand for investment by experts in relation to the growth of a start-up culture that is gradually gaining social importance. It can be said that it is expected to contribute to the promotion of a living start-up environment by resolving a significant part of the inevitability of trade arbitration. In addition, if such information is provided to ordinary investors as reliable evaluation results, it is expected that it will be advantageous to both companies and ordinary investors as direct investment by ordinary investors can be activated.

The present invention is to solve the above problems, and in the start-up market, a start-up based on investment opinions of professional investors using artificial intelligence-based big data modeling technology to reduce the risk of investment in start-ups or venture companies. Its purpose is to provide a business valuation model.

Another object of the present invention is to provide general investors or angel investors with the results of valuation of startups or venture companies based on the startup valuation model, so that ordinary people can invest in early-stage companies with reduced investment risk. The goal is to create a sound investment environment and provide an investment attraction platform system that can attract funds from the point of view of companies.

As an investment attraction platform system according to an embodiment for realizing the above object of the present invention, an investment attraction target is registered for an investment attractor, investment attraction information on the investment attraction target, and self-evaluation of the investment attraction target An investment attractor terminal into which first evaluation information is input, an investment expert terminal into which second evaluation information, which is professional evaluation information based on the investment attraction information for an investment attraction registered by an investment expert, is input, and the first evaluation information And an investment platform server that outputs third evaluation information, which is compromised evaluation information, using an artificial intelligence-based valuation model based on evaluation data including the second evaluation information, wherein the valuation model includes, Annual investment attraction information and first evaluation information for an unspecified number of investment attraction targets, annual second evaluation information corresponding to the first evaluation information, and at least one point in time of the investment attraction target It is a result of pre-learning state information based on artificial intelligence, and when the evaluation data is input, the value evaluation information of the investment attraction target according to the year at the time of input and the expected value information by year according to the lapse of time 3 Output evaluation information.

In one embodiment of the present invention, the investment platform server may further include an investor terminal receiving the third evaluation information on an investment attraction desired by the investor from the server.

In one embodiment of the present invention, through the investor terminal, an investor can make a direct investment in an investment attraction target.

In one embodiment of the present invention, at least one of the first evaluation information and the second evaluation information may include data for each evaluation item based on responses to a plurality of questions according to a questionnaire method.

In one embodiment of the present invention, the value evaluation model may pre-learn data for each evaluation item based on correlation between data for each evaluation item and state information for at least one point in time using a data-based deep network. there is.

In one embodiment of the present invention, at least one of the first evaluation information and the second evaluation information may be expressed as a schematized evaluation model.

In one embodiment of the present invention, the valuation model may learn patterns of the valuation model in advance using an image-based deep network.

In one embodiment of the present invention, the valuation model may be created in a separate server outside the investment platform server.

In one embodiment of the present invention, the annual investment attraction information and first evaluation information for an unspecified plurality of investment attraction targets, the annual second evaluation information, and the state information for at least one point in time are It can be sent from the server.

In one embodiment of the present invention, the investment platform server, when the investment attraction target is registered, the investment attraction information about the investment attraction target to an investment professional terminal of at least one investment expert in the field to which the investment attraction target belongs. can transmit.

According to the present invention, by constructing a convergence system applied to the start-up market using the start-up company valuation model implemented with a big data modeling engine, efficient information exchange and transaction between products/services launched by start-ups and end users are possible, By comparing with the relatively reliable value forecast at the idea stage, it is possible to expand the base of access to the life innovation start-up market of ordinary small businesses and the angel market of accelerators (AC) or venture capital (VC).

According to the present invention, in an investment attraction platform system using a value evaluation model based on a big data modeling engine, investment attractors, including early-stage companies such as start-ups, analyze current business values and future companies based on artificial intelligence. Based on value, it is possible to induce investment from investors, and investors can access new items similar to their preferred items based on reliable valuation prospects, pre-discovery of new items, pre-investment estimation, preliminary investment, and development review. Through this, the distribution structure of the startup investment market, which depends on the brokerage structure, can be innovated, and the benefits of both startups and investors can be increased.

1 is a schematic diagram showing the overall configuration of an investment attraction platform system according to an embodiment of the present invention.
Figure 2 is a block diagram for explaining the investment platform server of FIG.
FIG. 3 is a block diagram illustrating the customer module of FIG. 2 .
FIG. 4 is a block diagram illustrating the value evaluation server of FIG. 1 .
5 is an exemplary diagram for explaining an application example of the investment attraction platform system of FIG. 1 .
6 is an exemplary diagram for explaining enterprise value evaluation.
Figure 7 is an exemplary flow chart for explaining the process of the investment attraction method in the investment attraction platform according to an embodiment of the present invention.

Since the present invention may have various changes and various forms, specific embodiments are illustrated in the drawings and described in detail in the text. However, it should be understood that this is not intended to limit the present invention to the specific disclosed form, and includes all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Meanwhile, the meaning of terms described in this application should be understood as follows. Terms such as "first" and "second" are used to distinguish one component from another, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

Expressions in the singular number should be understood to include plural expressions unless the context clearly dictates otherwise, and terms such as “comprise” or “have” refer to an embodied feature, number, step, operation, component, part, or these. It should be understood that it is intended to indicate that a combination exists, and does not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

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

1 is a schematic diagram showing the overall configuration of an investment attraction platform system according to an embodiment of the present invention. Figure 2 is a block diagram for explaining the investment platform server of FIG. FIG. 3 is a block diagram illustrating the customer module of FIG. 2 . FIG. 4 is a block diagram illustrating the value evaluation server of FIG. 1 . 5 is an exemplary diagram for explaining an application example of the investment attraction platform system of FIG. 1 . 6 is an exemplary diagram for explaining enterprise value evaluation.

The investment attraction platform system provided according to one aspect of the present invention is a system that discloses transparent, objective, and reliable investment information for direct investment between an investor and an investment attractor (company). In other words, a company-specific valuation model based on company valuation big data reflecting the opinions of investment experts for each company is created, and the analyzed investment index as an objective and reliable evaluation result using it is provided to investors. Furthermore, this system can provide a direct investment system in which multiple investors and multiple investors can be combined. On the other hand, the investment attraction according to this embodiment is aimed at investment attractors who are early entrepreneurs such as start-ups and venture companies as preliminary founders, individuals or corporations who are difficult to receive investment in reality, but are not limited thereto. For example, since investment may be made for each item, investment may be raised in units of projects of small and medium-sized enterprises or large enterprises.

The system 1000 of the present invention illustrated in FIG. 1 basically includes an investment platform server 10, an investor terminal 20, an investment attractor terminal 30, an investment expert terminal 40, and It includes a value evaluation server 50, and although not shown, a financial institution server and an investment information sharing server may be additionally connected.

In the system of the present invention, an investor terminal 20 used by a plurality of investor members and an investment attractor terminal 30 used by a plurality of investment attractor members are provided through a network 1 capable of wired and wireless two-way data communication, such as the web of the Internet. It can be operated by means of an accessible investment platform server 10 . In addition, the system of the present invention is connected to at least one investment expert terminal 40 through the network 1 in order to receive an investment opinion upon request when an investment expert's opinion is required in the enterprise value evaluation.

The investment platform server 10 may include, for example, a web server that recruits and registers members through a website, inputs and stores member information and investment information, provides a search service, and performs operations such as transferring investment money. can

The investor terminal 20 and the investment attractor terminal 30 are different only in that they are used by the investor member and the investment attractor member, and can access the investment platform server 10 on the same web to input and display information. It may be a computer system having an input/output device, for example, a notebook computer, a desktop computer, a mobile communication terminal having a wireless Internet access function, or a dedicated terminal device.

In other words, the investor terminal 20 and the investment attractor terminal 30 meant in the present invention include communication equipment capable of accessing the server 10 through an interactive data communication network such as the web, a display device, an input device, and an information processing function. Since any system having a back can be used regardless of its size or portability, it is not particularly limited. Like the investor terminal 20 and the investment attractor terminal 30, the investment expert terminal 40 may be a separate computer system having an input/output device, and unlike the investment expert, the investment platform server 10 As an administrator who operates the server, it may be an integrated or separate terminal accessible to the server.

Matters described below as interactions between an investor or investment attractor member and the investment platform server 10 are actually the investor terminal 20 and the investment attractor terminal 30 connected to each other through a two-way data communication network, such as the web of the Internet. ) and the investment platform server 10 based on information exchange, such information exchange technology is obvious to those skilled in the art. Similarly, the investment expert member transmits the evaluation opinion to the server based on the received investment evaluation data in response to the request for evaluation opinion of the investment platform server 10, which can also be understood as information exchange technology.

In this way, information is input, searched, provided on a web page, transmitted through an e-mail, transmitted through a short text message (SMS) to a mobile communication terminal, or traded or transferred in cash or cyber money online such as wired and wireless Internet. Since the techniques and the like are well known in the relevant field, detailed descriptions are omitted for simplicity of description unless closely related to the features of the present invention.

Figure 2 schematically illustrates a specific functional configuration of the investment platform server 10 of the system of the present invention.

Referring to the illustrated configuration, which is non-limiting and merely exemplifies a possible embodiment, the investment platform server 10 includes a customer module 11 for interaction with investment attractor members and investor members, and interaction with investment experts. investment expert management module (12) for investment management, investment module (13) for controlling the investment process, company evaluation module (14) for collecting, evaluating and managing investment information, and searching for investment targets that meet the conditions desired by investors. It may include a matching process module 15 for matching, and an external DB interworking module 16 for sharing information with the outside.

The customer module 11 includes an investment attractor module 11_1 for interaction with investor members and an investor module 11_2 for interaction with investor members.

The investment attractor module (11_1) registers investment attractor members and inputs information such as basic information related to each investment attractor, investment goal or item description desired by each investment attractor, and current company value judged by itself from the investment attractor member. It can be received, processed by the company evaluation module 14, and stored in the basic information database (DB) and investment information DB. On the other hand, since most of the investment attractor members are not objective about the item, value or company evaluation at the current stage, they are provided with information through a questionnaire in the form of a question so that they can receive objective information as much as possible. All or part of the corresponding information is provided to the investment expert terminal 40 so that the investment expert can evaluate the value of the investment.

The basic information DB may include asset information, manpower information, business model information, and the like of an investment attractor, that is, a company. The investment information DB may store information about investment items and companies input by the investment attractor terminal 30 and investment attraction information generated by processing and evaluating them. Afterwards, the operation report submitted while the investment is being executed for a specific investment item and company can be input and stored in the operation report DB, and after the investment is completed, the result report can be input and stored in the result report DB. All histories can be controlled to be stored in the investment attraction history DB.

The investor module 11_2 may register investor members, receive basic information related to each investor from the investor members, and store the information in the member information DB. The member information DB may include investors' personal information. The investment condition DB may store information on investment conditions input by the investor terminal 20, and the investment money DB may store information on funds that may be cash or cyber money used by investor members for investment. In addition, the investor can evaluate the company through the investor terminal 20 for an investment attractor or item that is an investment target of interest, regardless of whether or not the investment is made. The result of this evaluation is provided to the investment inducer as a multi-faceted evaluation, and similarly, it can be transmitted to the value evaluation server 50 to be described later and used as a material for learning. In this case, the corporate evaluation input from the investor may be stored in the investor evaluation DB.

In addition, in one embodiment of the present invention, the customer module 11 has been described as an example of storing and managing the investment inducer and the investor in each member information DB, but is not limited thereto, and can be managed through separate DBs, respectively. there is. In addition, this embodiment has been described as an example of managing information in different modules by dividing an investment inducer and an investor, but is not limited thereto. For example, since an investment inducer can also be an investor, and vice versa, the customer module 11 can register, integrate, and manage customers without distinction. In this case, when the investment inviter and the investor access the server 10 and log in, the customer module 11 checks whether the accessed person is a customer, and if it is confirmed that the customer is a customer, whether the connected person is the investment attractor. Alternatively, depending on whether the investor is an investor, interfaces displayed on the investment attractor terminal 20 and the investor terminal 30 may be switched so as to receive a corresponding service.

The investment expert management module 12 may register investment expert members, receive basic information related to each investment expert from the investment expert members, and store the information in the member information DB. The member information DB may include personal information of an investment expert, information on investment expertise, career, and the like. The investment expert may be provided with information of an investment attractor matched as his/her field of expertise from the server, evaluate the company based thereon, and receive a reward of a certain cost from the server according to the company evaluation. Meanwhile, the corresponding reward may be cash or cyber money.

That is, when the investment attraction target is registered, the investment attraction information on the investment attraction target is transmitted to the investment expert terminal of at least one investment expert in the field to which the investment attraction target belongs, so that the company can be evaluated. On the other hand, a single investment expert may be matched to evaluate a company for one investment attractor, or it may be performed in a multi-faceted evaluation method by assigning several investment experts. That is, in this case, the evaluation may be performed together by experts in the relevant field and experts in other fields.

The investment expert management module 12 may store and manage performance information obtained by each investment expert and store and manage performance-based compensation as reward information. Corresponding reward information may be amount information, and separate account number information may be further added for reward compensation processing.

On the other hand, the investment expert according to this embodiment has been described as an example of managing a large number of people on the system by the platform, but unlike this, it is a limited expert who has a contractual relationship with a certain investment company, for example, AC or VC, or an investment specialist. As an expert, you may be an administrator who operates the system.

The investment module 13 manages the investment process for a specific investment inviter by an investor. The investment may be cash or cyber money. In the present invention, this cyber money includes all points, smart money, mileage, etc. that can be generated offline or online and converted into cash. For example, it may be that a credit card company converts a point for paying a certain percentage of a payment amount to a card user according to details of use of a credit card. Information related to cyber money such as points may be stored in a point management DB. Information related to investment conditions and investment objects, including the investment amount or investment-related period, can be managed in the investment details DB, and the operation of starting, canceling, or completing an investment can be managed in the investment contract management DB. The settlement process at the time of investment cancellation or investment completion can be managed in the investment settlement DB, and the management and control of operation reports or result reports in the permeation process can be managed by the investment process management DB. That is, in this embodiment, the amount of the investor's investment fund is irrelevant, and a small amount of investment is also possible.

The company evaluation module 14 is the result of the self-evaluation model of the company value self-evaluated by the investor based on the investment-related information and company-related basic information provided by the investor, and the investment that is provided with the investment-related information and basic company-related information. Compromise evaluation model results are derived based on the results of the DX evaluation model evaluated by experts. Specifically, based on the value evaluation model based on artificial intelligence, the result of the compromise evaluation model including the present value and future value of the company is derived using the result of the self-evaluation model and the result of the DX evaluation model as input values. On the other hand, the results of the compromise evaluation model can be made by inputting the initial input investment-related information and company-related basic information into the modified evaluation model by providing the DX evaluation model results and feedback opinions of investment experts to the investment inducer. Meanwhile, the enterprise value evaluation according to the present embodiment may be based on change information of the enterprise according to the passage of time in the past, in addition to information input at the current point in time. In addition, since the value evaluation model is the result of learning corporate evaluation data over time from the past of preceding companies, it is based on not only the current corporate value, but also trends over time from the past to the present. It is characterized by being able to evaluate the value of

Specifically, the company evaluation module 14 derives a compromised evaluation model result for each company based on a value evaluation model generated based on artificial intelligence in the valuation server 50 described below. That is, the value evaluation model may use at least one or more of investment-related information, company-related basic information, self-evaluation model results, DX evaluation model results, and modified evaluation model result values obtained through expert feedback as an input value. For example, the primary valuation result is output based on the valuation model according to the input of investment-related information and company-related basic information input from the investment inducer, and thus, the secondary valuation result through the feedback process of the investment inducer. A compromised evaluation model can also be output. That is, the value evaluation model may substitute the investment expert's evaluation in addition to outputting the compromised evaluation model. In this case, the investment expert's opinion has significance as a multi-faceted evaluation, or based on this, the compromise model evaluation result as the final value evaluation result may be modified.

For example, the company evaluation module 14 according to the present embodiment evaluates the investment process and history in order to ensure transparency and objectivity of the investment process, and evaluates the results considering future values, for example, A, B, C and It is possible to provide an evaluation grade expressed as a grade that is distinguished from each other. According to the present invention, the information provided by the investment inviter is not directly delivered to the investor, but the value evaluation information evaluated by the company evaluation module 14 of the investment platform server 10 is delivered. This valuation information is aimed at transparency and objectivity of investment information, and thus provides the advantage that ordinary investors can obtain reliable investment information.

On the other hand, the matching process module 15 matches the investment attraction information processed and generated by the company evaluation module 14 with the investment condition information input by the investor to provide detailed stock information on the recommendation list and each investment list to the investor terminal. provided by

After that, the investor can select a specific investment item or investment inducer as an investment target. When an investment target is selected, an investment-related process such as transferring investment money from an investor's investor account to an investment pool account related to investment attraction information may be initiated by the investment module 13 . Investment execution consists of transferring investment money from the investment pool account to the investment attractor's account. The investment attractor can freely cash out and withdraw the amount transferred to the investment attractor's account.

In one embodiment of the present invention, the investment money used by the investor may be cash, but need not be cash until the investor initiates the investment directly. Therefore, the investment money is all forms of cyber money that can be cashed, such as points generated according to the payment amount of a credit card online or offline, points generated according to the purchase amount of products in offline or online shopping malls, mileage points, smart money, cyber money, etc. All may be included, and in this specification, for convenience of description, these forms excluding cash are collectively referred to as 'cyber money'. This cyber money may be later converted into cash through mediation by, for example, an unshown point provider server or financial institution server connected to the investment platform server 10 .

The investment money may be cash or cyber money existing in an investor's account at which the investment is initiated. Alternatively, the investment money transferred to the investment pool account at the start of the investment may be something expected to be obtained in the future, that is, a gift concept, rather than cash or cyber money that currently exists. That is, it may be a gift cyber money promised to be transferred to the investor account by the investor terminal 20 in the future designated by the investment platform server 10 . In this case, a contract related to cyber money futures trading may be concluded between the investment platform server 10 and the investor.

The external DB interworking module 16 can share information through a shared DB with an external server, for example, a finance-related server that provides financial services based on the company's evaluation information, and the external server also has value for each company. If there is data that has been evaluated, it can be shared. For example, it may consist of all investment history and evaluation information about the current and previous investment process for each investment object and / or for each investment inviter. Meanwhile, data evaluated by the external server may also be transmitted to the value evaluation server 50 and used as data for generating a value evaluation model.

In the system of the present invention, the operation of the investment platform server 10 can be made as follows.

First of all, those who want to attract investment, such as startups or venture companies, can sign up as investment attractor members. When registering as an investment attractor member, enter basic information about the investment attractor, open an investment attractor account, and provide investment attraction information, including current status information, past history information, and detailed information on the investment target to attract investment. enter

The input investment attraction information is analyzed in the company evaluation module 14 based on artificial intelligence and used as value evaluation information that is used as an investment indicator of the investment inviter through an information analysis process. In the information analysis process, for example, investment attraction information is evaluated according to the evaluation criteria of the investment attraction platform system itself, evaluation by investment experts is performed, and, if necessary, there is also a due diligence visit evaluation in which investment experts actually visit and evaluate the workplace of the company concerned. can be done The information can be carried out by the questionnaire method, and the questionnaire method consists of questions for each evaluation item, and the answers to them go through an analysis process based on artificial intelligence. An investment grade that can indicate the degree of investment risk may be set.

Furthermore, a business explanation report (IR data) provided by a member of the investment attraction for the investment target included in the investment attraction information may be included. In this way, since the investment attraction information according to the present invention includes investment briefing report data in which the investor actively explains his or her business, anyone can freely search for and view the investment briefing report data of companies related to the desired item, making it public. The advantage is that a suitable investment briefing session can be prepared, the information is provided to investment experts, and prior to evaluation, corrections or additions to the information can be made through feedback if necessary.

That is, in the system of the present invention, in generating a corporate valuation model, not only the information provided by the investment inducer, but also the evaluation information of the investment expert, for example, the expert's recommendation opinion on the investment target or the investor member's comment. can include This is to enable more objective evaluation through the opinion of a third-party expert, rather than simply including subjective explanations by the investment inducer, and to invest in the relevant investment target or as a consumer. Comments from members of the public who may be interested in attractors may also be included in the evaluation. Accordingly, an advantage of being able to generate more three-dimensional and reliable investment attraction information can be provided.

In addition, according to the present invention, a 'ranking system' may be applied to an investment target included in each investment attraction information. In other words, for each investment target, experts and investor members can not only express their opinions, but also rank them according to the form of popularity vote, and the popularity ranking can be ranked according to this form of vote. This 'ranking system' does not directly guarantee the rate of return for a specific investment target, but it can provide a holistic view of the overall investment environment, and furthermore, it can generate interest among investor members and investment attractor members. Advantages can be provided.

According to the system of the present invention, by generating and storing reliable and transparent investment attraction information, it is easy for an investor to find an investor, and at the same time, an investor can easily find a desired investor.

An investment destination seeking investment attraction information may be a general investor member or may be an external investment information sharing server connected to the investment platform server 10 . The investment information sharing server may be a system of a public institution supporting entrepreneurship.

Using the system of the present invention, an investment destination, that is, an investment information sharing server or an investor member looking for a company to invest in, actively provides investment attraction information under the conditions, for example, 'item: education, entrepreneurship: 3 years, number of people: less than 10 people'. You can find the investor you want by searching. In this way, the process of investors finding investors can be more 'automated'. That is, the investor member or the investment information sharing server may set desired keywords (for example, conditions such as 'item: education, entrepreneurship: 3 years, number of people: less than 10 people') in advance. In this case, the investment platform server 10 may select investment attraction information corresponding to the previously stored or newly generated and stored investment attraction information corresponding to the set keyword. Selected investment attraction information may be transmitted from the investment platform server 10 to the investment information sharing server or transmitted to investor members via e-mail or SMS text message.

In the system of the present invention, an ordinary investor, which may be, for example, an individual, may sign up as an investor member. When registering as an investor member, basic information about the investor, that is, member information including personal information is entered, an investor account is opened, and each investor member is provided with a personal web page (My Page). Of course, dedicated pages may also be provided to investment attractor members.

Investor members may generally be individuals wishing to invest directly. However, the present invention need not be limited to this type of investor membership. For example, companies and organizations that specialize in investment, such as financial institutions or investment companies, can also act as investor members in the system according to the present invention. Therefore, although investor members are assumed as general individuals below, the investor members of this system should be understood as a broad concept encompassing all types of individuals and organizations who want to invest directly with their own capital.

Investor members must select a specific investment target for investment. For selection, a matching process is performed. In the matching process, the investor member can input desired investment conditions and perform a search. Accordingly, when a matched investment target is searched for, a list of recommended stocks is listed, and detailed valuation information on the investment target selected by the investor member can be viewed. Through this process, investor members can decide to invest in a specific investment target.

The valuation server 50 is configured to collect and process data for generating an artificial intelligence-based enterprise valuation model from the investment platform server 10, create a valuation model, and manage it. The value evaluation server 50 includes an evaluation data collection module 51 , an evaluation feedback module 52 , an evaluation model creation module 53 and an evaluation model management module 54 .

The evaluation data collection module 51 is. The collected data is converted into big data and managed, and involved in generating an artificial intelligence-based value evaluation model to be trained in the evaluation model creation module 53. The collected data is the valuation information on the enterprise value of the preceding company at the initial stage of the company, for example, self-assessment information directly evaluated by the preceding company and DX evaluation information evaluated by experts at that time, and It includes company status information and information on changes in company value accordingly. It does not matter whether the preceding company is a company registered in the investment platform server 10 . That is, data on prior companies for learning may be provided from, for example, at least one or more specialized investment institutions or an external server such as a public server that registers and manages venture companies.

Self-assessment information and DX evaluation information include investment-related information and company-related basic information input from investment promoters and investment experts as a result or basic information thereof. That is, information on the current state of the company at the time of collection and evaluation information of at least one expert based on the current state information are included. In addition, investors may also conduct corporate evaluations, and such corporate evaluations may be treated as non-professional opinions and collected. In addition, the corresponding information includes keywords (for example, conditions such as 'item: education, business establishment: 3 years, number of people: less than 10 people').

For example, as shown in (a) of FIG. 6, the self-assessment information may consist of items including technology, marketability, competency level, prospect level, and preparation level illustrated in a pentagonal model. For example, in most cases, investment attractors are not objective about the item for the company, or the value or company evaluation at the current stage. Here, not only answer information according to each question, but also analysis results for related questions may be provided. That is, the evaluation model shown in (a) of FIG. 6 may be generated by analyzing the answers to these questions. The corresponding information is classified by item or by year of establishment, and information by company is accumulated and collected based on the same or similar classification criteria. In other words, even for the same company, information on the current state of the company is collected regularly or irregularly, and accordingly, not only information on the state of affairs at a specific point in time, but also the process of changing the state of each company over time. information is collected cumulatively.

For example, as shown in (b) of FIG. 6, the DX evaluation information includes basic platform satisfaction, data governance platform satisfaction, overall platform success prospect level, DI promotion capability level, and market governance platform satisfaction illustrated by the DX evaluation model. It may consist of items containing. That is, the DX evaluation model shown in FIG. 6 (b) may be generated by analyzing the feedback for each evaluation item input by the investment expert. The relevant information is accumulated and collected by matching with the information entered by the investor or the self-evaluation model. That is, even for the same company, value evaluation information from investment experts is continuously collected by matching information on the current state of the company collected regularly or irregularly. Items by location of the DX evaluation model may correspond to items by location of the self-evaluation model based on information input from the investment inducer, and may be included in each other.

The evaluation feedback module 52 compares the result of the self-evaluation model evaluated by the investment inviter with the result of the DX evaluation model evaluated by the expert. It is configured to collect feedback information, such as correction of.

On the other hand, if there is a difference between the items evaluated by the investment attractor and the items evaluated by the expert, for example, when information is collected by the questionnaire method, the questions with errors in judgment are checked and delivered to the investment attractor. By doing so, it induces the investment inducer to modify the information that is the basis of the evaluation or the evaluation items. Sending information such as a corresponding error check and receiving modified evaluation information may be performed in the company evaluation module 14 of the investment platform server 10 .

Even if the items of the self-evaluation model evaluated by the investor and the DX evaluation model evaluated by the expert are different, the difference in the numerical range can be determined because each item is inclusive with each other, and the numerical range is Based on the big data information for each company, it can be determined whether or not it is within the error range. That is, if the difference in the numerical range of a specific item is greater than the error range, the answer to the question that has a high correlation to the numerical change of the item among the answers of the investment attractor to the question is checked and presented to the investment attractor. The correlation of numerical changes can be extracted based on big data analysis for each company. For example, the importance or relevance of each question may be pre-determined according to the resulting corporate value based on the difference in answers to each question, where the resulting corporate value is based on the success of the final investment and achievement of the target value. can

Accordingly, when the answer to each question checked as feedback information from the investment attractor terminal is modified, the self-evaluation model is modified based on this. Also, unlike this, when basic data or data for value evaluation of a company are added as feedback information of an investment inducer, the DX evaluation model determined by an investment expert may be modified accordingly. That is, the evaluation feedback module 52 refers to an operation of transforming input data in order to secure high accuracy even for variant data in order to increase the accuracy of the model in the learning stage. In a broad sense, it may be included in preprocessing. there is.

That is, investment-related information, company-related basic information, self-evaluation model results, DX evaluation model results, and modified evaluation model results are learned by mapping labels containing information for each evaluation item corresponding to learning data in the database. can be stored as data.

The evaluation model generation module 53 generates a value evaluation model that outputs the result of the compromised evaluation model for each company based on the self-evaluation model and the investment expert's DX evaluation model based on artificial intelligence.

The value evaluation model includes annual investment attraction information and self-evaluation information for an unspecified number of investment attraction targets, annual DX evaluation information corresponding to the self-evaluation information, and at least one or more of the investment attraction targets over time. It is the result of pre-learning state information about the point of view based on artificial intelligence.

In other words, the valuation model takes as input values information about the valuation of the preceding company's corporate value at the initial stage of the business, for example, self-assessment information directly evaluated by the preceding company and DX evaluation information evaluated by experts at that time and time. company status information according to the flow of the company and the company value change information, etc. accordingly, the company's valuation information, the trade-off valuation information, the trade-off valuation model based on it, and the company value change information over time to be output. That is, the value information expected at a future point in time is included, and when the evaluation data is input, the value assessment information of the investment attraction target according to the year at the time of input and the expected value information by year according to the lapse of time are included. Valuation information is output.

For example, as information to be learned, at least one of the self-assessment information and the DX evaluation information may include data for each evaluation item based on responses to a plurality of questions according to the questionnaire method. At this time, the value evaluation model, Data for each evaluation item based on a correlation between data for each evaluation item and state information for at least one time point may be learned in advance using a data-based deep network.

Alternatively, as shown in FIG. 6, at least one of the self-evaluation information and the DX evaluation information may be expressed as a schematized evaluation model, that is, a self-evaluation model and a DX evaluation model. In this case, the value evaluation model, The pattern of the evaluation model can be learned in advance using an image-based deep network. That is, the evaluation is performed based on the pattern of the input evaluation model, and as a result of this, the compromise value evaluation information can also be output as a patterned model. In this case, the investment value can be calculated by the area of the pattern created by digitizing the evaluation model for each item.

That is, the value evaluation model may use at least one or more of investment-related information, company-related basic information, self-evaluation model results, DX evaluation model results, and modified evaluation model result values obtained through expert feedback as an input value.

The evaluation model generation module 53 learns the learning data stored in the database through artificial intelligence. In this embodiment, the evaluation model generation module 53 uses an artificial neural network to which a typical error backpropagation learning algorithm is applied for learning will be described as an example. The learning structure of the artificial neural network may include an input layer, an output layer, and at least one hidden layer formed between the input layer and the output layer.

In this embodiment, at least one of the investment-related information for each company, the basic information related to the company, the self-evaluation model result, the DX evaluation model result, and the result value of the modified evaluation model made through expert feedback is used as an input value and a regular annual or annual basis for each company. In the case of non-regular events (occurrence of a J-curve in sales or success in attracting investment), the input value corresponding to the time of occurrence can be learned. That is, the event at that time is input and learned as the status information of the company, and based on the accumulated big data, the cause of the event and the difference compared to other companies are extracted as factors for each evaluation item, and other cases Reliability can be output as the degree of influence of the factor compared to . That is, by using a data-based deep network, data for each evaluation item is learned in advance based on the correlation between data for each evaluation item and state information for at least one point in time, and even in the case of an initial company, if it has a specific factor for each evaluation item, Values can be assessed taking into account future events.

On the other hand, here, the past and present data at different viewpoints for each company also have meaning as data augmentation of the evaluation data for each company according to the year. By doing so, it is possible to predict the current state from the output result or the future state from the past and present states.

For example, the compromised valuation model, which is the output of the valuation model shown in FIG. Corresponding synchronic compromised results and diachronic results according to the passage of time by year after the corresponding point can be output together. In addition, by extracting the value evaluation factor for the occurrence of a specific event, the occurrence of the specific event may be predicted based on the presence or absence of the value evaluation factor at the time of input. That is, the compromised valuation model is a model, and not only synchronic results but also diachronic results may be reflected, and may be individually output as several models.

Learning by the artificial neural network can be repeated as many times as selected by applying the gradient descent method. For optimal learning, the learning structure with the minimum error value is selected by applying MAPE (Mean Absolute Percentage Error) among artificial neural network techniques, decision tree techniques, and automatic machine learning techniques. After the repeated learning of the learning factors is completed by the evaluation model generation module 53, a value evaluation model is generated.

Meanwhile, in this embodiment, learning through an artificial neural network has been described as an example, but is not limited thereto. It is obvious that the decision tree technique and the automatic machine learning technique can be applied as artificial intelligence techniques. Specifically, the decision tree techniques may include techniques such as decision trees, random forests, and gradient boosting.

In addition, the automatic machine learning technique includes a technique in which artificial intelligence automatically adjusts hyperparameters such as the number of hidden layers and the number of neurons in an artificial neural network, a decision tree technique, and an existing artificial intelligence technique including artificial neural networks Connecting multiple layers It may include stacking and ensemble techniques that learn by doing, or techniques that use the above-described staking, ensemble, and automatic tuning for hyperparameters at the same time.

For example, the evaluation model generation module 53 may be composed of a plurality of modules, and each module performs learning by applying a decision tree technique, artificial neural network, automatic machine learning, etc., respectively, and these modules It is also possible to select and apply the optimal model by comparing each generated value evaluation model. In this case, an optimal model can be selected and applied by applying MAPE (mean absolute percentage error) and RMSE (root mean square error) based on the valuation of the actual preceding company at a specific point in time and the change in valuation.

In addition, in the data learning method, it can be based on various methods such as machine learning or supervised learning, and in performing machine learning, various artificial neural network models such as CNN, RNN, and combinations thereof can be applied. can Meanwhile, in the data learning method, image-based data learning may be performed as well as a learning method for a series of data. For example, in the self-evaluation model and the DX evaluation model shown in FIG. An image of a pentagonal figure can be output.

On the other hand, the items of the compromised valuation model of the output of the value valuation model are shown in (c) of FIG. 6 as being composed of some of the items of the self-evaluation model and the investment expert's DX valuation model, but are not limited thereto, and each item It is possible to reconstruct the item name by information or replace the dominant sub-item among the sub-items of a specific item with the item name. In addition, the value evaluation model according to this embodiment has been exemplified as being based on the investment attraction information and self-assessment information of the investment inviter and the DX evaluation information of the investment expert, but is not limited thereto. For example, the valuation model includes a first valuation model that outputs valuation information of an investment expert based on artificial intelligence-based investment attraction information and self-assessment information of an investment promoter, and a first valuation model that outputs the investment expert's evaluation information and correction. It may be configured as a second value evaluation model that outputs compromised evaluation information based on the self-assessment information. That is, the accumulated investment experts' DX evaluation information can be learned based on artificial intelligence, and final compromise evaluation information can be output only with investment attraction information and self-evaluation information without additional investment experts' evaluation opinions.

The evaluation model management module 54 is configured to update the valuation model by recollecting regular or irregular evaluation data of the investment attractor registered as a member in the investment platform server 10 . The corresponding data includes information about a point in time. For example, in the process of recollecting evaluation data, if evaluation data that exceeds the diachronic valuation output based on the valuation model at a previous point in time is collected, a specific factor of the output is tracked and the valuation model Weight is given to the specific factor in learning of .

5 is an exemplary diagram for explaining an application example of the investment attraction platform system of FIG. 1 . Referring to FIG. 5, the Tucha platform server is exemplified by the "Yang Yang's PICK" operating platform, and startup customers connected to it correspond to investment attractors, and investor (expert) customers correspond to general investors or professional investors. In other words, professional investors can proceed with investment at the same time as giving a valuation opinion. In addition, the general purchase customers shown in FIG. 5 are customers who use the services provided by startups and correspond to the general public, but they can also invest in startups as prospective investors and become prospective investors, so the platform system can be added as a member, and from these information, consumer information can be analyzed. Specifically, in learning the value evaluation model, consumer information for each service/product can be input, and compared with the customer information that the investor is targeting, a compromise evaluation model in which matching or feedback according to size is the result. may be reflected in In other words, consumer information by unspecified number of services/products is learned, and when investment attraction information is input to the valuation model, expected consumer information is output, and feedback information or value evaluation results are compromised by comparing with targeting customer information. A type evaluation model can be output. In other words, the operation and management of the system is performed in "KEAF", and the value evaluation model is also created in KEAF, and the evaluation of the company is performed separately in the core-solution startup evaluation system.

According to the present invention, in an investment attraction platform system using a value evaluation model based on a big data modeling engine, investment attractors, including early-stage companies such as start-ups, analyze current business values and future companies based on artificial intelligence. Based on value, it is possible to induce investment from investors, and investors can access new items similar to their preferred items based on reliable valuation prospects, pre-discovery of new items, pre-investment estimation, preliminary investment, and development review. Through this, the distribution structure of the startup investment market, which depends on the brokerage structure, can be innovated, and the benefits of both startups and investors can be increased.

Figure 7 is a schematic flow chart for explaining the process of the investment attraction method in the investment attraction platform according to an embodiment of the present invention.

Referring to Figure 7, a schematic flow chart for explaining the process of the investment attraction platform method according to an embodiment of the present invention is illustrated. The specific investment process is explained. After going through the matching process 150, when an investor selects a specific investment target and decides to invest (1301), an investment contract is concluded between the investor and the investment attractor who submitted the item (1302).

When an investment contract is concluded, the contracted investment amount is transferred from the investor account opened to the investor member to the investment pool account opened for the investment object. In the investment pool account, a small amount of investment may be transferred and accumulated from the investor accounts of a plurality of investor members who have decided to invest in the investment object. The accumulated investment can then be transferred from the investment pool account to the investment attractor's account and executed.

In the present invention, the investment platform server 10 may be provided so that the investment attractor can withdraw the investment money from the investment pool account to the investment attractor account at least once. That is, when the investment money is invested from the investment pool account to the investment inducer at once, the investment execution is completed with one transfer. Furthermore, when the investment money from the investment pool account is divided and invested over a certain period of time to the investment inducer, the investment execution 1308 may be performed by dividing and transferring the money in multiple times.

On the other hand, before the investment is executed (1308), the investment platform server 10 monitors the real-time cumulative amount of the investment transferred to the investment pool account, and whether the accumulated amount satisfies the investment start condition determined according to the investment attraction information. Determine (1304). Accordingly, if certain conditions, for example, investment start conditions such as whether a certain period of time has elapsed after the investment contract, but the cumulative investment amount has not reached 30% of the total investment amount (YES in 1305), the contract is terminated (1306) and the settlement is made. It operates to transfer the investment money transferred to the investment pool account back to the original investor account (1307). That is, only when the investment start condition is satisfied, the investment attractor withdraws the investment money transferred to the investment pool account to the investment attractor account, that is, the investment is executed (1308).

Here, the investment pool account may be a virtual account that is automatically generated one by one for each investment target. The investment pool account, which is a virtual account, is a kind of fund or pool in which investments deposited from the accounts of a number of investor members are gathered. Unlike the direct transfer of investment money from investors to investment inviters, by setting up such a virtual intermediate investment pool account, a device is provided to make the execution of investment money more transparent and safe. That is, the process of withdrawing money from the investment pool account may be managed by a third party, such as the investment platform server 10 or other external administrators, other than investors and investment attractors. Such a service providing protection by a third party is commonly known as 'escrow'.

In general, 'escrow' means that a neutral third party or institution, in the capacity of a representative of both parties, keeps the deposit or guarantee related to the sale or all the property and documents corresponding to it until the contract terms are terminated. According to the present invention, the investment pool account may refer to a virtual account that stores the investment between the investor and the attractor for the period until the actual execution of the investment after the investment contract.

Characteristically, in order to secure the transparency of the investment process, the investment platform server 10 receives an operation report including operation details of the withdrawn investment from the investment attractor (1309) and provides it to the investor to receive an evaluation of the operation report. (1310). Then, according to this evaluation, permission to withdraw additional investment money from the investment attractor terminal 30 is approved or rejected (1311). If the investment is subsequently rejected (NO), the contract may be terminated (1312) and a settlement procedure (1313) may be performed.

If it is determined (YES) that the investment will continue thereafter in step 1311, it is determined whether the investment completion condition is satisfied (1314). Investment completion conditions include whether the total amount of investment attracted has been executed or whether the contracted investment period has all elapsed. If there is still investment money that has been attracted but has not been executed, or if the investment period has not yet elapsed (NO), the step 1311 of determining whether to continue the investment from the step of executing the investment 1308 may be repeated. When the investment completion condition is met (YES), the investment attractor evaluates the investment execution result profit or loss (1315), and generates a result report and transmits it to the investment platform server 10 (1316). The investment platform server 10 may end the investment process for the investment object by allowing the investment attractor to transfer the profits according to the result report and distributing the profits to the investors (1317).

In the system of the present invention, the types of investment objects proposed by the investment promoter and selectable by the investor do not need to be particularly limited. The investment target may be, for example, in the form of including at least a part of a business project that the investor who proposed the investment target is performing or is planning to carry out, or the investment attractor, the company or individual itself, may be the investment target, and bonds It may be an intellectual property, such as a product or a patent.

In another embodiment of the present invention, members using this system, that is, investment attractor members and investor members, may be divided into a plurality of classes and each have differential authority. Members may be called various names such as, for example, general members, special members, regular members, temporary members, free members, paid members, and the like. In the present invention, the name of the member is irrelevant, but only the characteristic that the authority differs according to the level is important. The authority according to the level will be related to the degree of information access and the scope of investment activities. Membership levels can be determined and assigned based on each member's past career and will and history data using this system.

In the system of the present invention, each investor member is also supported to advertise widely, eg on the web, for investments in which he or she is or is not investing but believes to be promising. To this end, the investment platform server 10 may provide each investor member with a means for posting and advertising at least one piece of investment attraction information selected by the investor member on a website. Such a means may be a system that supports posting on a personal blog site of an investor member, and/or a free bulletin board of a portal site, for example. In addition to this, investor members may be supported to send investment information to acquaintances through e-mail. A personal blog site may be provided by the investment platform server 10 to each member. When investors are attracted according to the advertisements of these members themselves, a predetermined reward, such as cyber money that can be used as investment money in this system, may be given.

Since the information related to the investment target or investment attraction advertised by the investor members is transmitted through the web or e-mail, it may include a hyperlinked certification mark to the web page containing the investment attraction information provided by the investment platform server 10. can This authentication mark is a kind of icon, and may be configured to include text and/or images including simple information related to the fact that investment is made by this system and the investment target. The investment process described above is only an example, and is not limited thereto.

As described above, the investment platform system of the present invention is characterized as a system that helps ordinary investors make direct investments in companies safely with a small amount based on reliable investment information. To this end, this system outputs value evaluation data reflecting the opinions of investment experts based on artificial intelligence based on the investment-related information submitted by the company, carefully evaluates the investment and makes it easy for general investors to understand the evaluation results. The advantage of being able to establish an open market for investment information and an open investment attraction market that reduces the risk of investment and maximizes returns by transparently disclosing the operation status of the investment process and allowing it to be appropriately evaluated. Provided.

The investment process using the artificial intelligence-based investment attraction platform system according to an embodiment of the present invention described above is an application basically installed in the terminal (this may include a program included in a platform or operating system basically installed in the terminal) ), or an application (that is, a program) installed directly in the master terminal through an application providing server such as an application store server, an application, or a web server related to the corresponding service. In this sense, the investment process using the investment attraction platform system according to the present invention according to an embodiment of the present invention described above is implemented as an application (ie, a program) that is basically installed in the terminal or directly installed by the user, and is implemented in the terminal, etc. can be recorded on a computer-readable recording medium.

The above description of the present invention is for illustrative purposes, and those skilled in the art can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

1000: investment attraction platform system
10: investment platform server
20: investor terminal
30: investment attractor terminal
40: investment expert terminal
50: Valuation server

Claims (10)

As an investment attraction platform system,
An investment attractor terminal in which an investment attraction target is registered, and first evaluation information, which is a self-assessment of the investment attraction information and investment attraction target for the investment attraction target, is input;
An investment expert terminal into which second evaluation information, which is professional evaluation information based on the investment attraction information for a registered investment attraction target by an investment expert, is input; and
Based on the evaluation data including the first evaluation information and the second evaluation information, an investment platform server that outputs third evaluation information, which is compromised evaluation information, using an artificial intelligence-based value evaluation model,
The value evaluation model is based on annual investment attraction information and first evaluation information for an unspecified number of investment attraction targets, annual second evaluation information corresponding to the first evaluation information, and investment attraction targets over time. It is the result of pre-learning state information for at least one point in time based on artificial intelligence. When the evaluation data is input, the value evaluation information of the investment target according to the year at the time of input and the expected value by year according to the lapse of time Investment attraction platform system, characterized in that for outputting the third evaluation information containing information. According to claim 1,
An investment attraction platform system further comprising an investor terminal receiving the third evaluation information on an investment target desired by an investor from the investment platform server. According to claim 2,
Through the investor terminal, the investment attraction platform system, characterized in that the direct investment in the investment attraction target by the investor is made. According to claim 1,
At least one of the first evaluation information and the second evaluation information includes data for each evaluation item based on responses to a plurality of questions according to a questionnaire method. According to claim 4,
The valuation model is an investment attraction platform system, characterized in that for pre-learning data for each evaluation item based on correlation between data for each evaluation item and state information for at least one point in time using a data-based deep network. According to claim 1,
At least one of the first evaluation information and the second evaluation information is an investment attraction platform system, characterized in that expressed in a schematized evaluation model. According to claim 6,
The valuation model is an investment attraction platform system, characterized in that the pattern of the valuation model is pre-learned using an image-based deep network. According to claim 1,
The valuation model is an investment attraction platform system, characterized in that generated in a separate server outside the investment platform server. According to claim 1,
The annual investment attraction information and first evaluation information for an unspecified plurality of investment attraction targets, the annual second evaluation information, and the state information on at least one time point are transmitted from an external server. Investment attraction platform system. According to claim 1,
When the investment attraction target is registered, the investment platform server transmits the investment attraction information about the investment attraction target to an investment professional terminal of at least one investment expert in the field to which the investment attraction target belongs. platform system.
.

Images