KR20230092847A - Method for determining target company to be invested regarding a topic of interest and apparatus thereof - Google Patents

Abstract

Provided is a method for determining a target company to be invested for a topic of interest. According to an embodiment of the present disclosure, the method for determining a target company to be invested, comprises the steps of: obtaining a keyword associated with a topic of interest; and determining at least one target company to be invested among a plurality of investment candidate companies associated with the keyword. The step of determining the target company to be invested includes the steps of: searching for the keyword in a document set associated with each company included in the investment candidate companies; and determining a first investment candidate company associated with an essential document where the keyword is searched, as the target company to be invested, based on a result of the search.

Description

METHOD FOR DETERMINING TARGET COMPANY TO BE INVESTED REGARDING A TOPIC OF INTEREST AND APPARATUS THEREOF}

The present disclosure relates to a method and apparatus for determining an investment target company for a topic of interest. More specifically, it relates to a method for determining a company related to a topic of interest among a plurality of investment candidate companies based on a set of documents associated with investment candidate companies, and an apparatus for performing the device.

An Exchange Traded Fund (hereinafter referred to as "ETF") is a product designed so that returns are linked to the movement of the price of a specific index such as the KOSPI and KOSDAQ or a specific asset such as gold, bonds and crude oil. , means a fund that is listed on an exchange and traded like a stock. Since ETFs are based on a portfolio composed of a number of stocks, they not only have diversified investment effects, but also are in the spotlight of many investors because they are easy to acquire, hold, and dispose of like stocks.

When designing an ETF product, the most important and difficult task is to accurately select the investment stocks to be incorporated into the portfolio. Accordingly, in the prior art, the selection of investment stocks was entirely performed by experts, and the topics of ETF products were not diverse due to difficulties in selecting investment stocks. In other words, the topics of ETF products were limited to some fields where investment items could be accurately selected. For example, as shown in FIGS. 1 and 2, based on a portfolio (1) composed of multiple affiliates, an ETF product that tracks the index of a specific group company, and a portfolio (3) composed of representative companies in a specific industry sector ETF products that follow the value of a specific industry sector were the main topics of ETF products.

However, the needs of investors toward ETF products linked to various topics are continuously increasing, and it is impossible to satisfy the needs of investors in the conventional way. For example, when designing ETF products related to topics such as "secondary batteries," "inter-Korean economic cooperation," and "fine dust," which are issues across society, what companies, even experts, are related to the topics listed above? It's difficult to pinpoint exactly what it is. In addition, according to the conventional method, since the portfolio of ETF products is determined according to the subjective judgment of experts, the objectivity and reliability of the ETF portfolio cannot be guaranteed.

Therefore, a method that can objectively and accurately determine companies related to various fields, topics, issues, etc. is required.

Korean Patent Publication No. 10-2014-0018532 (published on February 13, 2014)

A technical problem to be solved through embodiments of the present disclosure is to provide a method for determining a target company for investment in a topic of interest and an apparatus for performing the method.

Another technical problem to be solved through embodiments of the present disclosure is to provide a method for constructing an investment portfolio for a topic of interest and an apparatus for performing the method.

Another technical problem to be solved through the embodiments of the present disclosure is to provide a method for accurately calculating a score of relevance between an investment candidate company and a topic of interest using a document related to the investment candidate company, and a device for performing the method. is to do

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

In order to solve the above technical problem, a method for determining a company to be invested in a topic of interest according to an embodiment of the present disclosure includes acquiring a keyword associated with the topic of interest and among a plurality of investment candidate companies associated with the keyword. It may include determining at least one investment target company. At this time, the step of determining the investment target company includes the step of searching for the keyword in a document set associated with each company included in the plurality of investment candidate companies, and essential documents for which the keyword is searched based on the search result. A step of determining a related first investment candidate company as the investment target company may be included.

In one embodiment, the document set may include a pre-set essential document set and an auxiliary document set, and the step of determining the first investment candidate company as the investment target company may be associated with an auxiliary document for which the keyword is searched. Excluding the second investment candidate company from the investment target may be included.

In one embodiment, the essential documents may be included in a document set including public disclosure documents, IR documents, news documents, and securities company reports.

In one embodiment, the step of determining the first investment candidate company associated with the essential document from which the keyword is searched as the investment target company based on the result of the search, the occurrence position of the keyword in the essential document and a pre-specified position Comparing and determining the first investment candidate company as the investment target company based on a result of the comparison.

In one embodiment, the pre-designated location may be a pre-designated section in a document associated with the first investment candidate company.

In one embodiment, the step of determining the first investment candidate company as the investment target company based on the result of the comparison may include, when the appearance location of the keyword does not match the pre-designated location, the first investment candidate Excluding the company from the investment target may be included.

In one embodiment, the method for determining an investment target company for a topic of interest according to an embodiment of the present disclosure includes the step of building an investment portfolio for the topic of interest by determining an investment weight for the investment target company. can include more.

In one embodiment, the step of building the investment portfolio includes determining the investment proportion based on a difference between a time when the topic of interest is issued and a time when a document related to the investment target company is generated. can be done with

In one embodiment, the step of determining the first investment candidate company associated with the essential document for which the keyword is searched as the investment target company based on the search result, the time when the topic of interest is issued and the first investment candidate company The method may further include comparing a value change point of , and adding the first investment candidate company to the investment target companies based on a result of the comparison.

In one embodiment, the step of determining a first investment candidate company associated with an essential document for which the keyword is searched for as the investment target company based on a result of the search, a financial indicator associated with the financial soundness of the first investment candidate company In response to a determination that the predetermined condition is not satisfied, the step of excluding the first investment candidate company from the investment target company may be included.

1 and 2 are exemplary diagrams for explaining the limitations of a conventional ETF portfolio.
3 is a block diagram showing a system for providing an investment portfolio according to an embodiment of the present disclosure.
4 is an exemplary diagram for explaining an investment portfolio providing interface that may be referenced in some embodiments of the present disclosure.
5 and 6 are block diagrams illustrating an apparatus for determining an investment target company according to an embodiment of the present disclosure.
7 and 8 are exemplary diagrams for explaining concepts of essential keywords and supplementary keywords that may be referred to in some embodiments of the present disclosure.
9 is a diagram for explaining a filtering-based search method according to an embodiment of the present disclosure.
10 is an exemplary view for explaining the concept of an essential document and an auxiliary document that may be referred to in some embodiments of the present disclosure.
11 is a hardware configuration diagram illustrating an apparatus for determining a company to be invested according to an embodiment of the present disclosure.
12 and 14 are flowcharts for explaining a method of determining investment target companies for a topic of interest according to an embodiment of the present disclosure.
15 to 17 are diagrams for explaining a relevance score calculation method according to an embodiment of the present disclosure.
18 to 20 are flowcharts illustrating a method for determining an investment proportion according to some embodiments of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Advantages and features of the present disclosure, and methods of achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms, only the present embodiments make the present disclosure complete, and those of ordinary skill in the art to which the present disclosure belongs It is provided to fully inform the person of the scope of the disclosure, and the disclosure is only defined by the scope of the claims.

In adding reference numerals to components of each drawing, it should be noted that the same components have the same numerals as much as possible even if they are displayed on different drawings. In addition, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those of ordinary skill in the art to which this disclosure belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined. Terminology used herein is for describing the embodiments and is not intended to limit the present disclosure. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase.

Also, terms such as first, second, A, B, (a), and (b) may be used in describing the components of the present disclosure. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term. When an element is described as being “connected,” “coupled to,” or “connected” to another element, that element is directly connected or connectable to the other element, but there is another element between the elements. It will be understood that elements may be “connected”, “coupled” or “connected”.

As used herein, "comprises" and/or "comprising" means that a stated component, step, operation, and/or element is the presence of one or more other components, steps, operations, and/or elements. or do not rule out additions.

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

3 is a block diagram of an investment portfolio providing system according to an embodiment of the present disclosure.

As shown in FIG. 3, the investment portfolio provision system is a system that determines and provides investment target companies (or investment stocks) and investment portfolios for a topic of interest. Note that the term "topic" may be used interchangeably with terms such as subject, issue, field, sector, and the like in the technical field.

An investment portfolio providing system according to an embodiment may include an investment target company determining device 100 and at least one data source 30 . However, this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some components may be added or deleted as needed. In addition, it should be noted that each component of the investment portfolio providing system shown in FIG. 3 represents functionally differentiated functional elements, and a plurality of components may be implemented in a form integrated with each other in an actual physical environment. Of course, in an actual physical environment, each of the above components may be implemented in a form of being separated into more subdivided detailed functional elements.

In the investment portfolio providing system, the investment target company determining device 100 is a computing device that determines an investment target company for a given topic of interest and builds an investment portfolio based on the determined investment target company. Here, the computing device may be a notebook, a desktop, or a laptop, but is not limited thereto and may include any type of device equipped with a computing function. Hereinafter, for convenience of description, the investment target company determining device 100 will be abbreviated as the determining device 100 .

More specifically, the decision device 100 collects documents related to investment candidate companies from at least one data source 30 . In addition, the decision device 100 determines an investment candidate company associated with a topic of interest as an investment target company based on the collected documents. Furthermore, the decision device 100 may build an investment portfolio by determining the investment proportion of each investment target company.

According to an embodiment, the decision device 100 searches a document set associated with the investment candidate company with a keyword associated with the topic of interest, and calculates a relevance score between the topic of interest and the investment candidate company based on the search result. The relevance score may be understood as an index indicating the degree to which a specific company is associated with the topic of interest. Also, the determining device 100 determines an investment target company from among investment candidate companies based on the relevance score. According to this embodiment, related companies can be objectively and accurately derived based on keyword search results even for topics that are difficult to clearly derive related companies, such as “secondary battery” and “inter-Korean economic cooperation”. In addition, by building an investment portfolio based on the related companies, a highly reliable and accurate investment portfolio for a topic of interest can be automatically built. The investment portfolio can be used in various financial products such as ETFs and index funds, thereby satisfying the needs of various investors and activating the investment market.

According to an embodiment, the decision device 100 may provide an investment portfolio service to the user terminal 10 . The investment portfolio service is a service that provides or recommends a list and/or an investment portfolio of companies related to a topic of interest (ie, investment target companies) to the user. For example, as shown in FIG. 4 , the decision device 100 may provide an investment portfolio 57 for a topic of interest through a web-based user interface 50 . At this time, a topic of interest and document information (e.g. news, public announcements, etc.) related to the topic of interest are provided through the first area 51 of the user interface 50, and information about the topic of interest is provided in the second area 53. An investment portfolio 57 may be provided, but the scope of the present disclosure is not limited thereto. According to this embodiment, investment activities of investors can be encouraged by providing investment portfolios for various topics of interest to investors. Accordingly, the effect of activating the investment market can also be achieved.

A method of providing the investment portfolio service may vary according to embodiments.

In one embodiment, the decision device 100 may provide an investment portfolio service in an on-demand manner. That is, the decision device 100 may provide an investment portfolio in response to a request of the user terminal 10 . At this time, the request may include a topic of interest.

In one embodiment, the decision device 100 may provide an investment portfolio service in a subscription manner. That is, the decision device 100 may periodically or irregularly provide an investment portfolio to subscribers. Depending on the embodiment, the decision device 100 may analyze the collected news data, extract an issue topic at the current time, and provide the issue topic to the user terminal 10 . Of course, an investment portfolio along with the issue topic may also be provided to the user terminal 10 .

In one embodiment, an investment portfolio service may be provided based on a combination of the foregoing embodiments.

A detailed description of the configuration and operation of the decision device 100 will be described in more detail with reference to the drawings below in FIG. 5 .

In the investment portfolio providing system, at least one data source 30 is a repository providing various data related to investment candidate companies. The various types of data may be text-type documents, but the scope of the present disclosure is not limited thereto. For example, the various types of data may be data in the form of voice, video, or image. In this case, text data may be obtained from non-text based data through speech recognition (e.g. speech-to-text), image analysis, and the like.

The data source 30 may include a web server (eg, a web server of a portal site) providing various news articles on politics, economy, and industry trends.

According to one embodiment, data collected from the data source 30 may include public disclosure documents (eg, business reports), investor relations (IR) documents, securities company reports, news documents, and the like. However, the scope of the present disclosure is not limited thereto.

In the investment portfolio providing system, the user terminal 10 is a terminal on the side of a user (e.g. investor) using the investment portfolio service provided by the decision device 100 . The user terminal 10 may be implemented in any device.

Each component of the investment portfolio providing system shown in FIG. 3 may communicate through a network. Here, the network is a local area network (LAN), a wide area network (Wide Area Network; WAN), a mobile communication network (mobile radio communication network), all types of wired / wireless networks such as Wibro (Wireless Broadband Internet) can be implemented

So far, the investment portfolio providing system according to an embodiment of the present disclosure has been described with reference to FIGS. 3 and 4 . Hereinafter, the configuration and operation of the decision device 100 will be described by searching for FIGS. 5 to 7 .

5 is a block diagram illustrating a decision device 100 according to an embodiment of the present disclosure.

Referring to FIG. 5 , the decision device 100 includes a collection unit 110, a topic determination unit 120, a keyword acquisition unit 130, a scoring unit 140, an investment target company determination unit 150, and a portfolio construction unit. (160). However, only components related to the embodiment of the present disclosure are shown in FIG. 5 . Accordingly, those of ordinary skill in the art to which this disclosure belongs may know that other general-purpose components may be further included in addition to the components shown in FIG. 5 . In addition, it should be noted that each component of the decision device 100 shown in FIG. 5 represents functionally differentiated functional elements, and a plurality of components may be implemented in a form integrated with each other in an actual physical environment.

In addition, it should be noted that not all components shown in FIG. 5 are essential components of the decision device 100 . That is, the decision device 100 may be implemented in a form in which some of the components shown in FIG. 5 are omitted. For example, the decision device 100 may be implemented with only components other than the portfolio builder 160 . Hereinafter, each component of the decision device 100 will be described.

The collection unit 110 collects various documents related to investment candidate companies from the data source 30 . Any method of collecting the various documents may be used.

As shown in FIG. 5, the various documents may include a disclosure document 31, an IR document 33, a news 35, a securities company report 37, etc., but the scope of the present disclosure is not limited thereto no.

The investment candidate company refers to a company to be calculated as a relevance score. The criterion for determining the investment candidate company may vary according to the embodiment. In one embodiment, the investment candidate company may be a company listed on the KOSPI or KOSDAQ. In another embodiment, the investment candidate company may be a company within a specific sector. In another embodiment, the investment candidate companies may be companies (e.g. blue chip companies) whose financial indicators related to financial soundness (e.g. debt-to-asset ratio, trading volume, market capitalization, etc.) satisfy designated conditions.

Next, the topic determining unit 120 determines a topic of interest as a criterion for determining a company to be invested in. A method in which the topic determiner 120 determines the topic of interest may vary according to embodiments.

In one embodiment, a topic provided from the user terminal 10 may be determined as a topic of interest. Specifically, the decision device 100 may determine an investment target company in response to being provided with the topic of interest and build an investment portfolio. In addition, the decision device 100 may provide an on-demand investment portfolio service by providing the built investment portfolio to the user terminal 10 .

In another embodiment, the topic determiner 120 may extract an issue topic by analyzing the aforementioned documents 31 to 37 and the like, and may determine the issue topic as a topic of interest. For example, the topic determiner 120 determines a topic mentioned in a plurality of IR documents, a topic mentioned in a plurality of news, a topic of a news article with a high update frequency, a topic of a news article with a large number of comments, and a top ranked real-time topic. A topic related to a search term may be determined as an issue topic. For another example, the topic determiner 120 may construct a plurality of clusters by clustering periodically collected documents, and select an issue cluster from among the plurality of clusters based on the number of documents belonging to the clusters. Also, the topic determiner 120 may determine a topic for the issue cluster as a topic of interest. In this embodiment, the decision device 100 may provide an issue topic whenever an issue topic is extracted or periodically, and provide an investment portfolio for the issue topic to the user terminal 10 . At this time, the decision device 100 may provide the investment portfolio only to users who have applied for subscription services.

Next, the keyword acquisition unit 130 acquires keywords (or keyword sets) associated with the topic of interest. Keywords associated with the topic of interest are used as search keywords for the collected documents (e.g. 31 to 37).

In some embodiments, keywords associated with the topic of interest may include two types of keywords. Hereinafter, for convenience of understanding, the above two types of keywords will be described.

The first type of keywords are mandatory keywords. The essential keyword refers to a keyword that a candidate investment company must necessarily associate with in order to be determined as an investment target company. Here, that a specific company is associated with a specific keyword means that a document related to the specific company includes the specific keyword. For example, when a document associated with a first investment candidate company does not include a required keyword, the first investment candidate company may be excluded from the investment target company even if the related document includes an auxiliary keyword. The concept of the essential keyword will be further explained with reference to examples shown in FIGS. 6 and 7 .

The second type of keywords are auxiliary keywords. The auxiliary keyword refers to a keyword that is auxiliaryly used to more accurately determine an investment target company.

The essential keyword or the auxiliary keyword may be subdivided into a primary keyword, a secondary keyword, ??, and an n-order keyword according to importance. At this time, weights may be differentially assigned according to the order of keywords, which will be described later.

A method for the keyword acquirer 130 to obtain a required keyword and/or an auxiliary keyword may vary according to embodiments.

In one embodiment, the required and auxiliary keywords associated with the topic of interest may be preset. The keyword acquisition unit 130 may obtain the preset keyword from a file or receive input from a user interface, but the scope of the present disclosure is not limited thereto. Preferably, the preset keywords are set by an expert related to a corresponding topic.

In one embodiment, the keyword acquisition unit 130 may automatically generate essential keywords and auxiliary keywords based on a representative keyword representing a topic of interest. For example, the keyword acquisition unit 130 determines a keyword located within a first distance from the representative keyword as an essential keyword on a pre-constructed ontology, and determines a keyword located within a second distance from the representative keyword (or the essential keyword). A keyword located within a certain distance from the keyword may be determined as an auxiliary keyword. At this time, the second distance is, of course, a longer distance than the first distance. For another example, the keyword acquisition unit 130 may perform a portal search or document search with the representative keyword, and may determine keywords appearing together in the searched document as essential keywords and auxiliary keywords. In this case, a keyword having a relatively high frequency of occurrence may be determined as an essential keyword, and a keyword having a relatively low frequency may be determined as an auxiliary keyword. For example, when the representative keyword is a technology-related keyword (e.g. secondary battery), the keyword acquisition unit 130 searches technical documents such as patents and papers to accurately determine essential keywords and auxiliary keywords.

In one embodiment, essential keywords related to the topic of interest are set in advance, and the keyword acquisition unit 130 may automatically generate auxiliary keywords based on the essential keywords. For a method of automatically generating the auxiliary keyword, refer to the above-described embodiment.

In one embodiment, the keyword acquisition unit 130 may acquire essential keywords and auxiliary keywords based on a combination of the foregoing embodiments.

Meanwhile, in some embodiments, the keyword acquisition unit 130 may further perform an extension function for the acquired keyword. Specifically, when a required keyword or an auxiliary keyword is acquired as a search keyword, the keyword acquisition unit 130 may add synonyms, related keywords, and the like to each keyword as search keywords. By doing so, a precise search can be performed, and companies related to the topic of interest can be accurately selected.

Next, the scoring unit 140 calculates a relevance score between the investment candidate company and the topic of interest. As shown in FIG. 6 , the scoring unit 140 may include a weight determination unit 141 , a search unit 143 and a score calculation unit 145 .

The weight determination unit 141 determines weights based on various criteria. For example, the weights include weights according to keyword types, weights according to document types, weights according to keywords, weights according to keyword appearance positions in documents, weights according to document creation time, weights according to topics of interest, and the like. can do. It can be understood that the weight is used to more accurately calculate the relevance with the topic of interest. A more detailed description of the weight will be described later with reference to FIGS. 15 to 17 .

Next, the search unit 143 searches for documents related to investment candidate companies using the keyword obtained by the keyword acquisition unit 130 and provides the search result to the score calculation unit 145 .

According to an embodiment, a document that does not include a required keyword among the related documents may be excluded from a search result. For example, as shown in FIG. 7 , documents B and F (61, 63) may be excluded from the search results even though they contain primary and secondary auxiliary keywords. When independent keywords are composed of multiple orders, such as first and second orders, documents that do not include independent keywords of all orders among the related documents may be excluded from the search results. For example, as shown in FIG. 8 , documents B, E, and F (71, 73, and 75) may be excluded from the search results because they do not include the first and second required keywords. According to this embodiment, investment candidate companies that are not related to important keywords (ie, essential keywords) for the topic of interest are excluded from investment target companies, so that companies related to the topic of interest can be accurately selected.

According to an embodiment, the search unit 143 may perform a search using a filtering method. Specifically, as shown in FIG. 9, the search unit 143 filters the given document set 81 with essential keywords 83 and then searches the filtered documents 85 with auxiliary keywords (87). can be performed. By doing so, computing resources required for search can be reduced and efficient search can be performed.

Meanwhile, in some embodiments, technical ideas inherent in essential keywords and auxiliary keywords may also be applied to types of documents. For example, as shown in FIG. 10 , a disclosure document is set as a required document, and keywords (e.g. required, secondary keywords) associated with a topic of interest do not appear in the disclosure documents associated with companies b and f (241, 243) as search results. Let's assume it didn't. Then, companies b and f (241, 243) may be excluded from investment target companies regardless of their relevance scores.

In some embodiments, technical ideas inherent in mandatory keywords and supplementary keywords may also be applied to the occurrence location of keywords in a document. For example, assume that the business summary section of the business report is set as a required occurrence position, and keywords (e.g. required, secondary keywords) related to the topic of interest do not appear in the business summary section of the business report issued by the first company as a search result. Then, the first company may be excluded from the investment target company regardless of the relevance score.

Next, the score calculation unit 145 assigns a relevance score to investment candidate companies associated with a specific keyword by using the search result. For example, when a specific keyword is searched for in the disclosure document, the score calculation unit 145 may assign a relevance score to the investment candidate company that issued the disclosure document. For another example, when a specific keyword is searched for in the news, the score calculation unit 145 may assign a relevance score to the investment candidate company mentioned in the news. At this time, the relevance score given to each investment candidate company may be a value proportional to the frequency of occurrence of the specific keyword, but the scope of the present disclosure is not limited thereto.

In addition, the score calculation unit 145 calculates a final relevance score for each investment candidate company by summing the assigned relevance scores. At this time, the score calculation unit 145 may calculate the final relevance score by reflecting the weight determined by the weight determination unit 141, which will be described later with reference to FIGS. 15 to 17.

Next, the investment target company determining unit 150 determines an investment target company from among a plurality of investment candidate companies based on the final relevance score. In order to exclude duplicate descriptions, a detailed description of the method for determining the investment target company will be described later with reference to FIGS. 12 and 13 .

Next, the portfolio building unit 160 builds an investment portfolio for a topic of interest by determining an investment weight for the determined investment target company. The method of determining the investment ratio may vary depending on the embodiment, and a description thereof will be described later with reference to FIGS. 18 to 20.

Each component of FIGS. 5 and 6 may mean software or hardware such as a Field Programmable Gate Array (FPGA) or an Application-Specific Integrated Circuit (ASIC). However, the components are not limited to software or hardware, and may be configured to be in an addressable storage medium or configured to execute one or more processors. Functions provided within the components may be implemented by more subdivided components, or may be implemented as a single component that performs a specific function by combining a plurality of components.

11 is a hardware configuration diagram illustrating a decision device 100 according to an embodiment of the present disclosure.

Referring to FIG. 11, the determination device 100 includes one or more processors 101, a bus 105, a communication interface 107, and a memory 103 that loads a computer program executed by the processor 101. and a storage 109 for storing the computer program 109a. However, only components related to the embodiment of the present disclosure are shown in FIG. 11 . Accordingly, those of ordinary skill in the art to which this disclosure belongs may know that other general-purpose components may be further included in addition to the components shown in FIG. 11 .

The processor 101 controls the overall operation of each component of the decision device 100 . The processor 101 includes a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present disclosure. It can be. Also, the processor 101 may perform an operation for at least one application or program for executing a method according to embodiments of the present disclosure. The investment target company determining device 100 may include one or more processors.

Memory 103 stores various data, commands and/or information. The memory 103 may load one or more programs 109a from the storage 109 to execute a method for determining a company to be invested according to embodiments of the present disclosure. An example of the memory 103 may be a RAM as shown in FIG. 11, but the scope of the present disclosure is not limited thereto. When the computer program 109a is loaded into the memory 103, the modules shown in FIGS. 5 and 6 may be implemented in the form of logic on the memory 103.

The bus 105 provides communication between components of the decision device 100 . The bus 105 may be implemented in various types of buses such as an address bus, a data bus, and a control bus.

The communication interface 107 supports wired and wireless Internet communication of the decision device 100 . Also, the communication interface 107 may support various communication methods other than Internet communication. To this end, the communication interface 107 may include a communication module well known in the art of the present disclosure.

The storage 109 may non-temporarily store the one or more programs 109a. The storage 109 may be non-volatile memory, such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc., a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.

Computer program 109a may include instructions that when loaded into memory 103 cause processor 101 to perform methods in accordance with some embodiments of the present disclosure. The instruction is a series of instructions grouped on the basis of function, and refers to a component of a computer program and executed by a processor.

For example, the computer program 109a may perform an operation of obtaining a required keyword and an auxiliary keyword associated with a topic of interest, and the required keyword among the investment candidate companies based on a result of searching for a document set related to the investment candidate company with the required keyword. assigning a first relevance score to a company related to the second relevance score to a company associated with the auxiliary keyword among the investment candidate companies based on a result of searching all or part of the document set with the auxiliary keyword; and determining one or more investment target companies for the topic of interest based on a relevance score assigned to the investment candidate company.

So far, the configuration and operation of the decision device 100 according to an embodiment of the present disclosure have been described with reference to FIGS. 5 to 11 . Hereinafter, a method for determining an investment target company for a topic of interest according to an embodiment of the present disclosure will be described in detail with reference to FIG. 12 and subsequent drawings.

Each step of a method for determining an investment target company according to an embodiment of the present disclosure, which will be described below, may be performed by a computing device. For example, the computing device may be the decision device 100 . However, for convenience of explanation, the description of the operating subject of each step included in the method for determining the investment target company may be omitted. In addition, each step of the method for determining the investment target company may be implemented as instructions of a computer program executed by a processor.

12 is a flowchart illustrating a method of determining investment target companies for a topic of interest according to an embodiment of the present disclosure. However, this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.

Referring to FIG. 12 , the method for determining a company to be invested starts in step S100 of acquiring a keyword associated with a topic of interest. In this case, keywords associated with the topic of interest may include essential keywords and auxiliary keywords.

According to an embodiment, prior to this step ( S100 ), the decision device 100 may further perform a step of determining a topic of interest. For a description of this, refer to the description of the topic determiner 120.

In step S200, the decision device 100 performs a search with the acquired keyword in the previously collected document set, and calculates a relevance score between the topic of interest and the investment candidate company using the search result. In this case, documents that do not include essential keywords in the document set may be excluded from the search results. Therefore, investment candidate companies that are not related to the essential keywords are excluded from the investment target companies. A detailed description of this step (S200) will be described in detail with reference to FIGS. 15 to 17.

In step S300, the determining device 100 determines an investment target company for a topic of interest from among a plurality of investment candidate companies based on the relevance score calculated in step S200. For example, the determining device 100 may determine an investment candidate company having a relevance score equal to or greater than a threshold value as an investment target company. For another example, the determining device 100 may determine top n investment candidate companies having a high relevance score (where n is a natural number equal to or greater than 1) as investment target companies. Here, the value of n may be a predetermined fixed value or a variable value that changes according to circumstances. For another example, the investment target company may be determined based on a combination of the above examples. That is, the decision device 100 may determine investment candidate companies corresponding to the top n investment candidate companies having a high relevance score (where n is a natural number equal to or greater than 1) and having the relevance score equal to or greater than a threshold value as investment target companies. there is. In this way, the method by which the decision device 100 determines the investment target company may vary according to embodiments.

Meanwhile, according to an embodiment of the present disclosure, as shown in FIG. 13 , the decision device 100 may exclude or add a specific company from investment target companies according to a predetermined condition (S310 and S330). Although FIG. 13 illustrates that steps S310 and S330 are performed in order, steps S310 and S330 may be performed regardless of the order shown in FIG. 13 . Also, only some of steps S310 and S330 may be performed.

In a specific example, the decision device 100 responds to determining that a financial indicator (e.g., debt-to-asset ratio, transaction volume, market capitalization, etc.) associated with the financial soundness of the first company does not satisfy a pre-specified condition, and the first company Companies can be excluded from the investment target companies.

For another example, the decision device 100 may compare a time when the topic of interest is issued and a time when the value of the first company changes, and add the first company to the investment target companies based on the comparison result. That is, when determining that a correlation exists between the topic of interest and the asset value (eg stock price index) of the first company, the decision device 100 may add the first company to the investment target company. For example, as shown in FIG. 14, the decision device 100 extracts a topic 201 by analyzing various news articles, and determines a time point T ₁ at which the topic 201 was issued based on a news date. there is. In addition, the decision device 100 compares the timing of changes in the asset value (203, eg stock price, etc.) of the company (a) with the timing (T ₁ ) of the issue of the topic 201, thereby determining the topic 201 and the company (a). It is possible to determine whether there is a relationship between If it is determined that there is a relationship, the decision device 100 may add the company (a) to the investment target companies. According to this example, even a company that is actually related to the topic of interest but whose relationship is not revealed in the document can be accurately selected as an investment target company.

Referring back to FIG. 12 , in step S400 , the decision device 100 builds an investment portfolio by determining the investment portion of the investment target company. A detailed description of this step (S400) will be described later with reference to FIGS. 18 to 20. In some embodiments, the investment portfolio construction step (S400) may be omitted.

For reference, among the above-described steps (S100 to S400), step (S100) is performed by the keyword acquisition unit 130, step (S200) is performed by the scoring unit 140, and step (S300) is an investment target It may be performed by the enterprise determination unit 150 . Also, step S400 may be performed by the portfolio building unit 160 .

So far, a method for determining investment target companies for a topic of interest according to an embodiment of the present disclosure has been described with reference to FIGS. 12 to 14 . Hereinafter, the relevance score calculation method according to an embodiment of the present disclosure, which is performed in step S200, will be described in detail with reference to FIGS. 15 to 17.

15 is a flowchart illustrating a relevance score calculation method according to an embodiment of the present disclosure. In particular, FIG. 15 illustrates a case in which a search keyword is composed of an independent keyword, a primary auxiliary keyword, and a secondary auxiliary keyword as an example. For convenience of understanding, although FIG. 15 illustrates that steps S210 to S230 are performed in order, it should be noted that each step S210 to S230 may be performed regardless of the order shown in FIG. 15 . It will be described below with reference to FIG. 15 .

As shown in FIG. 15 , the decision device 100 searches a document set given each keyword and assigns a relevance score to an investment candidate company associated with each keyword using the search result. In more detail, the determining device 100 assigns a first relevance score to the investment candidate company associated with the essential keyword by using the search result for the essential keyword (S210). Similarly, the decision device 100 searches a document set with a primary secondary keyword and a secondary secondary keyword, and additionally assigns a relevance score to an investment candidate company associated with each keyword by using the search result (S230 and S250). ). In this case, the assigned relevance score may be a value proportional to the frequency of occurrence of the search keyword in the corresponding document, but the scope of the present disclosure is not limited thereto.

Next, in step S270, the decision device 100 calculates a final relevance score for the investment candidate company by reflecting various weights on the relevance score. In this case, the weight may be a basic weight or an additional weight. In addition, the method of reflecting the weight may be any method such as a method of multiplying a relevance score by a weight or a method of giving additional points. A weight reflected in the relevance score may vary according to embodiments.

In the first embodiment, the weight may be a weight for each keyword type, at least some of which are differentially determined according to the type of keyword. For example, as shown in FIG. 16, a first weight 211 is applied to investment candidate companies associated with essential keywords, and a second weight 213 is applied to investment candidate companies associated with primary secondary keywords. A third weight 215 may be applied to investment candidate companies associated with the auxiliary keyword. In this case, the first weight 211 may be set to a greater value than the second weight 213 , and the second weight 213 may be set to a greater value than the third weight 215 . Since the types of keywords can be classified based on the importance of keywords for the topic of interest, the weight according to the present embodiment can be understood as a weight according to the importance of keywords. According to this embodiment, a company closely associated with a topic of interest may be determined as a company to be invested, since an investment candidate company related to a keyword with high importance will be determined as an investment target company.

In the second embodiment, at least some of the weights may be keyword weights that are differentially determined for each keyword. That is, even if they are keywords of the same type (e.g. required keywords), a first weight may be applied to investment candidate companies associated with the first required keyword, and a second weight may be applied to investment candidate companies associated with the second required keyword. In some examples, the keyword weight may be determined based on a similarity between a representative keyword indicating a topic of interest and the corresponding keyword. For example, a keyword weight for a specific keyword may be determined based on a distance between the representative keyword and a specific keyword on a given ontology, but the scope of the present disclosure is not limited thereto. In some examples, additional weight (or additional points) may be assigned only to specific keywords. For example, when a dictionary is provided in which keywords closely related to topics of interest are defined, additional weight (or additional points) may be given only to investment candidate companies associated with keywords included in the dictionary. According to the present embodiment, a company associated with a topic of interest may be more accurately determined by using a more subdivided weight for each keyword than in the first embodiment described above.

In the third embodiment, the weight may be a weight for each document type, at least some of which are differentially determined according to the document type. For example, as shown in FIG. 16 , when a keyword is searched for in a disclosure document, a first weight 217 may be applied to a candidate investment company associated with the disclosure document. Also, when a keyword is searched in an IR document, a second weight 219 may be applied to investment candidate companies associated with the IR document. According to this embodiment, a relevance score may be more accurately calculated by reflecting the importance or reliability of a document.

In the 3-1 embodiment, the weight for each first document type for the first topic of interest may be different from the weight for each second document type for the second topic of interest. For example, when the topic of interest is a topic related to a specific technology or a specific product, such as “secondary battery”, a higher weight may be set for a public announcement document (eg, a business report) than a news article. However, when the topic of interest is a topic related to a social issue and not related to a specific technology or product, such as “inter-Korean economic cooperation,” the related keyword will hardly appear on the disclosure document. Accordingly, in such a case, a higher weight may be set for the news article than for the publication document. In one example, when a topic of interest corresponds to a recent issue (ie, an issue within a certain point in time based on the present), the decision device 100 may automatically adjust a weight for each document type. For example, the decision device 100 may adjust a weight for a news article to a higher value and a weight for an announcement document to a lower value. In another example, when essential keywords rarely appear in documents of the first type, the determination device 100 adjusts the weight for the document of the first type to a lower value, and sets the weight for the document of the other type to a relative value. can be adjusted to a higher value.

In the fourth embodiment, at least some of the weights may be differentially determined based on an appearance position of a specific keyword in a document. For example, as shown in FIG. 17, even if the keyword A 227 appears in two business reports 221 and 231, a higher weight will be applied to the investment candidate company that issued the business report A 221. can This is because a company in which the keyword A (227) appears in the business summary (223) will be more closely related to the topic of interest than a company in which the keyword A (227) appears in the business background (225, 235). In this embodiment, an additional weight or additional points may be assigned based on the occurrence position of the specific keyword in the document. For example, when a specific keyword appears at the beginning of a specific document or appears in a main section such as “summary” or “summary”, additional weight or additional points may be given to investment candidates associated with the specific document.

In the fifth embodiment, at least some of the weights may be differentially determined based on a creation time of a document in which a specific keyword is searched for. Alternatively, additional weight or additional points may be assigned based on the occurrence position of a specific keyword in the document. For example, when a specific document is created recently, it is highly likely that the first investment candidate company currently associated with the specific document is a company more closely related to the topic of interest. Accordingly, additional weight or additional points may be assigned to the first investment candidate company.

In the sixth embodiment, when a specific keyword continuously appears in a document related to a specific investment candidate company, additional weight or additional points may be assigned to the specific investment candidate company. For example, when a specific keyword continuously appears in related documents of a first investment candidate company generated during a certain period of time, additional weight or additional points may be assigned to the first investment candidate company.

In the seventh embodiment, at least some of the weights may be determined differently according to the source (or reliability) of the retrieved document. For example, it is assumed that a specific keyword appears in the first news article and the second news article, and the first news article is published by a more reputable news agency. In this case, a higher weight may be assigned to the first investment candidate company associated with the first news article. Alternatively, additional weight or additional points may be assigned to the first investment candidate company.

In an eighth embodiment, a final relevance score may be calculated by reflecting weights or additional points according to a combination of the above-described embodiments.

So far, the relevance score calculation method according to an embodiment of the present disclosure has been described with reference to FIGS. 15 to 17 . According to the above-described method, a relevance score between a topic of interest and an investment candidate company can be accurately calculated by reflecting various types of weights. Accordingly, companies associated with the topic of interest can be accurately selected.

Hereinafter, a method for determining an investment ratio according to some embodiments of the present disclosure will be described with reference to FIGS. 18 to 20 .

18 to 20 are flowcharts illustrating a method for determining an investment proportion according to some embodiments of the present disclosure. Hereinafter, description will be made with reference to FIGS. 18 to 20 .

In the first embodiment, as shown in FIG. 18 , the determining device 100 may determine the investment proportion based on the relevance score of the investment target company (S410). For example, the determining device 100 may determine the investment weight of the investment target company based on the relative ratio of the relevance score. According to this embodiment, the proportion of investment may be determined based on a reasonable criterion of relevance to a topic of interest.

In the second embodiment, as shown in FIG. 19 , the determining device 100 may determine the investment proportion of the investment target company based on the market capitalization or market cap proportion of the investment target company (S430). According to this embodiment, an investment portfolio that well follows the average index of investment target companies can be constructed.

In the third embodiment, as shown in FIG. 20 , the decision device 100 determines the investment proportion of the investment target company based on the difference between the time when the topic of interest is issued and the time when the document related to the investment target company is created. It can (S450). For example, as the difference between the time when the topic of interest is issued as an issue and the time when the relevant document of the first investment target company is generated increases, the investment proportion of the first investment target company may decrease. In the opposite case, the investment proportion of the first investment target company may be increased. According to this embodiment, a highly reliable investment portfolio can be constructed based on a substantial correlation between a topic of interest and a target company for investment.

In the fourth embodiment, the investment proportion of the investment target company may be determined based on a combination of the above embodiments. For example, the investment proportion of each investment target company may be determined by considering both the relevance score and the market capitalization of the investment target company.

So far, a method for determining an investment ratio according to some embodiments of the present disclosure has been described with reference to FIGS. 18 to 20 . According to the above-described method, a highly reliable investment portfolio for a topic of interest can be constructed by determining the investment portion of the investment target company under a reasonable standard.

So far, several embodiments of the present disclosure and effects according to the embodiments have been described with reference to FIGS. 1 to 20 . The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

The concept of the present disclosure described with reference to FIGS. 1 to 20 so far may be implemented as computer readable code on a computer readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disc, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). can The computer program recorded on the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet, installed in the other computing device, and thus used in the other computing device.

In the above, even though all components constituting the embodiments of the present disclosure have been described as being combined or operated as one, the present disclosure is not necessarily limited to these embodiments. That is, within the scope of the purpose of the present disclosure, all of the components may be selectively combined with one or more to operate.

Although actions are shown in a particular order in the drawings, it should not be understood that the actions must be performed in the specific order shown or in a sequential order, or that all shown actions must be performed to obtain a desired result. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be understood as requiring such separation, and the described program components and systems may generally be integrated together into a single software product or packaged into multiple software products. It should be understood that there is

Although the embodiments of the present disclosure have been described with reference to the accompanying drawings, those skilled in the art to which the present disclosure pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present disclosure. can understand that Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. The protection scope of the present disclosure should be construed by the claims below, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present disclosure.

Claims (10)

A method for determining an investment target company for a topic of interest in a computing device,
acquiring keywords associated with the topic of interest; and
Determining at least one investment target company from among a plurality of investment candidate companies associated with the keyword,
The step of determining the investment target company,
Retrieving the keyword from a document set associated with each company included in the plurality of investment candidate companies; and
Determining a first investment candidate company associated with an essential document for which the keyword is searched for as the investment target company based on a result of the search,
How to decide which companies to invest in your topic of interest. According to claim 1,
The document set,
It includes a set of pre-set essential documents and a set of auxiliary documents,
The step of determining the first investment candidate company as the investment target company,
Excluding a second investment candidate company associated with an auxiliary document for which the keyword is searched for from the investment target,
How to decide which companies to invest in your topic of interest. According to claim 1,
The essential document is included in a set of documents including public documents, IR documents, news documents and securities company reports,
How to decide which companies to invest in your topic of interest. According to claim 1,
Determining a first investment candidate company associated with an essential document for which the keyword is searched for as the investment target company based on a result of the search,
Comparing an appearance position of the keyword in the essential document with a predetermined position; and
Determining the first investment candidate company as the investment target company based on the result of the comparison,
How to decide which companies to invest in your topic of interest. According to claim 4,
The predetermined location is
A pre-designated section in a document associated with the first investment candidate company,
How to decide which companies to invest in your topic of interest. According to claim 4,
Determining the first investment candidate company as the investment target company based on the result of the comparison,
Excluding the first investment candidate company from the investment target when the appearance location of the keyword does not match the pre-specified location,
How to decide which companies to invest in your topic of interest. According to claim 1,
Further comprising the step of building an investment portfolio for the topic of interest by determining the proportion of investment in the investment target company,
How to decide which companies to invest in your topic of interest. According to claim 7,
The step of building the investment portfolio,
Determining the investment proportion based on a difference between a time when the topic of interest is issued and a time when a document related to the investment target company is generated.
How to decide which companies to invest in your topic of interest. According to claim 1,
Determining a first investment candidate company associated with an essential document for which the keyword is searched for as the investment target company based on a result of the search,
Comparing a time when the topic of interest became an issue and a time when the value of the first investment candidate company changed; and
Further comprising the step of adding the first investment candidate company to the investment target company based on the result of the comparison.
How to decide which companies to invest in your topic of interest. According to claim 1,
Determining a first investment candidate company associated with an essential document for which the keyword is searched for as the investment target company based on a result of the search,
Excluding the first investment candidate company from the investment target company in response to determining that a financial metric associated with the financial soundness of the first investment candidate company does not satisfy a pre-specified condition,
How to decide which companies to invest in your topic of interest.

Images