KR102172532B1 - Method and system for calculating price influence based on disclosure and media - Google Patents

Abstract

The present invention relates to a method for calculating a price impact on an investment item based on public announcement and media, and a system for performing the same. A method for calculating a price influence according to an embodiment of the present invention includes: collecting information on investment products for at least one investment product; Performing keyword analysis based on the collected investment product information; Matching the keywords of the announcement or news collected in real time for a specific investment product with the result of the keyword analysis performed; And determining a price influence of the public announcement or news collected in real time on the specific investment product based on the matching result.

Description

Method and system for calculating price influence based on disclosure and media}

The present invention relates to a method for calculating a price impact on an investment item based on public announcement and media, and a system for performing the same.

With the rapid development of various networks or the Internet in recent years, the types of media are diversified, and the types of information handled through the media are also diversifying. Accordingly, investment stocks, such as stocks, futures, and cryptocurrency, which are sensitive to the media, are also increasing, and on the contrary, the good or bad news of investment stocks are often spread through the media.

In addition, it is common that the prices of investment stocks increase in case of good news, and decrease in case of bad news.

In other words, it is not an exaggeration to say that recent investment stocks are closely related to media as well as disclosures that have had an impact from the past. Therefore, disclosure and media-related information are likely to be used as very important auxiliary indicators for successful investment item selection and purchase/sell timing decisions.

However, from an individual's point of view, it is not only difficult to collect massive amounts of public announcements and media-related information, and it is even more difficult to analyze their impact on price fluctuations of investment stocks.

The present invention is to provide a method and a system for performing systematic price impact analysis based on public announcements and media.

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

In order to solve the above technical problem, a method for calculating a price influence degree according to an embodiment of the present invention includes: collecting investment product information for at least one investment product; Performing keyword analysis based on the collected investment product information; Matching the keywords of the announcement or news collected in real time for a specific investment product with the result of the keyword analysis performed; And determining a price influence of the public announcement or news collected in real time on the specific investment product based on the matching result.

For example, the matching may include extracting at least one key keyword based on a noun from the public announcement or news collected in real time; Determining at least one keyword matching the result of the performed keyword analysis among the extracted at least one key keyword; And counting the matched at least one keyword.

For example, the determining of the price influence may include, for each of the aggregated at least one keyword, based on an individual score and a combination score with other keywords included in the announcement or news collected in real time. It may include determining a price impact.

For example, the determining of the price impact may be performed by considering the ratio of the total quantity of the specific investment product related to the quantity information when quantity information is included in the announcement or news collected in real time. I can.

For example, the investment product information may include news and disclosure information between the present and the past predetermined time points for the at least one investment product; And price change information over a period of time.

For example, the performing of the keyword analysis may include extracting at least one keyword from news and announcement information between the present and the past predetermined time point; And assigning a score to the extracted keywords based on price fluctuations between a certain period of time from a time when news or announcements including the extracted keywords are published.

For example, a method of calculating a price influence may include: after determining the price influence, tracking a price change for the specific product; And correcting the result of the keyword analysis performed based on the tracked price change.

In addition, an apparatus for calculating a price influence according to an embodiment of the present invention includes: an information collection unit that collects investment product information for at least one investment product; A keyword analysis unit that performs keyword analysis based on the collected investment product information; A keyword matching unit that matches keywords of public announcements or news collected in real time by the information collection unit for a specific investment product with a result of the performed keyword analysis; And a price influence calculator configured to determine a price influence degree of the public announcement or news collected in real time on the specific investment product based on the matching result.

Through the method and system for calculating the price influence according to at least one embodiment of the present invention configured as described above, it is possible to easily know the systematic price influence by information.

In addition, individual investors can predict the volatility of investment items through the result of calculating the price impact, and can be used as a subsidiary tool for successful investment.

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

1 is a flow chart showing an example of a process of calculating a price influence according to an embodiment of the present invention.
2 shows an example of a real-time information analysis process according to an embodiment of the present invention.
3 is a block diagram showing an example of a configuration of an apparatus for calculating a price influence according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present invention. However, the present invention may be implemented in various forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary. In addition, parts denoted by the same reference numerals throughout the specification refer to the same components.

In one embodiment of the present invention, in measuring the price impact of investment products by analyzing news and disclosures, keywords are extracted from information related to investment product data in the past and present, and according to the correlation between the extracted keywords and price fluctuations. It is proposed to calculate the price influence by matching scores to keywords included in news/announcements in real time by assigning scores for each keyword.

For example, news is broadcast or video media such as over-the-air/cable TV based on IP (Internet Protocol) networks, audio broadcasts such as radio or cast content, Internet news media, Internet posts such as blogs, and social network services ( SNS) posts, community posts, etc., but is not limited thereto.

In addition, investment products may include stocks, futures, virtual currency, spots, real estate, etc., but these are illustrative and are not necessarily limited thereto, and it is sufficient as long as an investment object.

First, a process of calculating a price influence degree based on real-time information according to an embodiment will be described with reference to FIG. 1.

1 is a flow chart showing an example of a process of calculating a price influence according to an embodiment of the present invention.

Referring to FIG. 1, in order to calculate the price impact according to the present embodiment, product information may be first collected (S110), and keyword extraction may be performed by analyzing big data on the collected information.

Here, the product information includes news, disclosure, and price change information on the investment product of interest between the present and a certain past point in time. News collection may use data crawling and indexing techniques widely used in search engines, or may be collected by using investment product names as search words in one or more search engines, or use one or more preset source addresses, and combinations thereof. It is possible.

Here, the preset one or more source addresses may be homepages of broadcasters or Internet news media, or addresses of blogs or SNS accounts of influential individuals or groups even if they are not news media.

Of course, such a collection method is exemplary, and the present embodiment is not limited to any method as long as it is possible to collect news information.

Meanwhile, keyword extraction may include a process of collecting and filtering metadata.

Here, the process of collecting metadata may mean a process of acquiring at least one of body text, images, videos, comments, views, hashtags, and preferences (likes, number of shares, number of recommendations, publishers, etc.). In addition, the filtering process may be a process of removing keywords whose price influence is less than a certain level in the process of analyzing duplicate information and previous keywords by determining whether the keywords extracted from the meta data overlap with previously collected data.

Next, keyword analysis may be performed on the keyword extracted from the collected information (S120). The keyword analysis process may include a process of analyzing an effect on price for each extracted keyword alone and an effect on price when combined with other keywords. The degree of influence on the price may be determined through a process of matching price fluctuations between a certain period of time from the time when news or disclosure including the corresponding keyword is released for each single/combined keyword.

For example, the price change rate for each period may be determined by analyzing price fluctuations for different periods such as within 1 hour, within 1 day, and within 1 week from the time when the single keyword "orders" appears in the news or public announcement. Based on this, as a price change appears within a short period of time from the time when the keyword appears in news or disclosure, and the greater the rate of change, a higher score may be given to the keyword.

As another example, the keyword combination score is a score based on a combination of other keywords included in the same news or public announcement, "contract" + "contract" is given + points, and "contract" + "no trade" is given- Can be.

When a score for a keyword is provided, real-time information analysis may be performed (S130). This process will be described with reference to FIG. 2. 2 shows an example of a real-time information analysis process according to an embodiment of the present invention.

Referring to FIG. 2, the real-time information analysis process (S130) may include a noun-oriented core keyword extraction process (S131), an extracted core keyword comparison process (S133), and a matching keyword aggregation process (S135).

Specifically, the noun-centered core keyword extraction process (S131) is a process of extracting the noun-centered key keywords from information such as published news or public announcements. Except that real-time information is an object, the logic of the process is the above-described product information. It can be similar to the collection process.

The extracted core keyword comparison process (S133) may be a process of inquiring the keyword extracted in the core keyword extraction process (S131) in the keyword list for which the score was calculated in the keyword analysis process (S120).

The matching keyword aggregation process (S135) may be a process of matching one or more keywords matched to a keyword list for which a score is calculated among keywords extracted as a result of the comparison process (S133).

Returning to FIG. 1 again, when real-time information analysis is completed, a price influence degree on real-time information may be determined based on the analyzed information (S140). The price influence may be expressed in a range of scores (eg, between -100 and +100 points), and may be determined based on a single score and a combination score of each of the aggregated matching keywords.

At this time, the score for each keyword may be additionally assigned a proportional weight to the quantity of real-time information. For example, when the amount is included in the news, a weight may be assigned through a proportionality of the related total quantity information, such as capital stock, annual sales, quarterly sales, etc. of the investment product. As another example, when the number of shares is included in the news, a weight may be assigned through a proportionality of the investment product relative to the total issued shares.

The shape of the finally determined price influence can have the following scores.

If the worst score is -100, a combination of keywords such as "CEO + (Appointment or Abuse or Imprisonment)" or "Quarterly + Consecutive + Deficit" may correspond to this. In addition, if the best score is 100 points, "50 billion won (% weight of sales) + (supply or supply/demand or sales) + contract + contract" or "paid increase + decision + 20 million shares (% weight of total issued shares) Keyword combinations such as may correspond to this.

After the price influence is determined, a tracking analysis may be performed on the news or disclosure (S150). The tracking analysis process may refer to a process of monitoring a price change of a related investment product for a certain period of time after a corresponding news or disclosure, and correcting a score for a keyword assigned through past information through current information. For example, the keyword "recession" has had a significant negative impact in the past, so even if the score is set high, the effect on the product may be negligible if it is no longer new due to a long-term economic downturn. The score fluctuation according to the tracking analysis result may be reflected back to the score for each keyword determined in the keyword analysis process 120 to be reflected in information analysis (S130) and influence determination (S140) of other real-time news that occur later.

Therefore, according to the price influence calculation method described above with reference to FIGS. 1 and 2, not only is the effect on the product price calculated by analyzing keywords included in news or public announcements based on big data, but also due to real-time tracking of news. The calculation accuracy can be continuously corrected.

Meanwhile, in the mechanical implementation, each process shown in FIGS. 1 and 2 may be implemented as one software module or a hardware module, and one step may be implemented by two or more modules, or two It is obvious to those skilled in the art that the above steps may be implemented in one module.

For example, as shown in FIG. 3, the price influence calculation device 200 according to the present embodiment includes an information collection unit 210 that first collects product information S110 and real-time news/disclosures, and the collected product information and real-time Keyword analysis unit 220 that performs keyword analysis (S120, S131) and tracking analysis (S150) based on news/disclosure, keyword score list determined based on product information collected by collecting key keywords extracted from real-time news/disclosure The keyword matching unit 230 for matching (S133) and aggregation (S135) with the keywords included in the keyword matching unit 230, the price influence calculating unit for determining the final price influence (S140) based on the aggregation result of the keyword matching unit 230 ( 240) and the output unit 250 for outputting the price influence information in a predetermined form.

Here, the output unit 250 may be in the form of a communication module that outputs a digital signal corresponding to a price influence to another device or a logical address according to a preset protocol, may be a display device that outputs visual information, or a print medium B may be a sound output means, but this is illustrative and is not limited thereto.

In addition, the detailed operation process of the module/functional unit corresponds to each process described with reference to FIGS. 1 and 2, and redundant descriptions will be omitted.

The present invention described above can be implemented as a computer-readable code in a medium on which a program is recorded. The computer-readable medium includes all types of recording devices storing data that can be read by a computer system. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SDD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. There is this.

Therefore, the detailed description above should not be construed as restrictive in all respects and should be considered as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (8)

Collecting investment product information for at least one investment product;
Performing keyword analysis based on the collected investment product information;
Matching the keywords of the announcement or news collected in real time for a specific investment product with the result of the keyword analysis performed; And
And determining a price influence of the public announcement or news collected in real time on the specific investment product based on the matching result,
The matching step,
Extracting at least one key keyword based on a noun from the public announcement or news collected in real time;
Determining at least one keyword matching the result of the performed keyword analysis among the extracted at least one key keyword; And
Comprising the step of counting the matched at least one keyword,
The step of determining the price influence,
For each of the aggregated at least one keyword, including the step of determining the price influence based on an individual score and a combination score with other keywords included in the public announcement or news collected in real time, Calculation method. delete delete The method of claim 1,
The step of determining the price influence,
When quantity information is included in the public announcement or news collected in real time, a price influence calculation method is performed by considering a ratio of the total quantity of the specific investment product related to the quantity information. The method of claim 1,
The above investment product information,
News and public announcement information between the present and the past predetermined time points for the at least one investment product; And
A method of calculating price impact, including information on price changes over a period of time. The method of claim 5,
The step of performing the keyword analysis,
Extracting at least one keyword from news and public announcement information between the present and the past predetermined time point; And
And assigning a score to the extracted keywords based on price fluctuations between a certain period of time from the time of publication of the news or disclosure including the extracted keywords. The method of claim 1,
After the step of determining the price influence,
Tracking a price change for the specific product; And
And correcting the result of the keyword analysis performed based on the tracked price change. An information collection unit that collects investment product information for at least one investment product;
A keyword analysis unit that performs keyword analysis based on the collected investment product information;
A keyword matching unit that matches keywords of public announcements or news collected in real time by the information collection unit for a specific investment product with a result of the performed keyword analysis; And
And a price influence degree calculator configured to determine a price influence degree of the public announcement or news collected in real time on the specific investment product based on the matching result.

Images