Search

KR-102962720-B1 - Automatic calculation system for the contract of put options by real estate owner using AI big data learning

KR102962720B1KR 102962720 B1KR102962720 B1KR 102962720B1KR-102962720-B1

Abstract

The present invention discloses a technical concept comprising: a contract execution unit that electronically executes a put option exercise contract with a real estate rights holder through a user terminal and electronically executes a fee payment contract through a server of a payment institution for the payment of fees; a data collection unit that defines, selectively acquires, and collects pre-set big data related to whether the real estate rights holder will exercise the put option; an AI learning unit that performs AI learning on the pre-set big data and calculates the exercise probability by selectively acquiring and performing AI learning on pre-set standard-condition information; and a fee calculation unit that quantitatively calculates the agreed fee by selectively reflecting the pre-set standard-condition information selectively acquired by the AI learning unit and the probability of the exercise probability calculated by the AI learning unit into a pre-set standard fee rate.

Inventors

  • 김종구

Assignees

  • 한국자산매입 주식회사

Dates

Publication Date
20260508
Application Date
20250704

Claims (10)

  1. In a system for automatically calculating contract fees for the exercise of a put option, which is the right of a real estate rights holder to sell a real estate property acquired through presale, by collecting and utilizing Big Data using AI (Artificial Intelligence), A contract execution unit that electronically concludes a put option exercise contract with a real estate rights holder through a user terminal and electronically proceeds with concluding a fee payment contract through the server of a payment institution for the payment of the said fee; A data collection unit that defines pre-set big data related to whether the aforementioned real estate right holder will exercise a put option, and selectively acquires and collects the defined pre-set big data; An AI learning unit that performs AI learning on the preset big data acquired and collected by the above data collection unit, and calculates event probability by selectively acquiring preset standard-condition information and performing AI learning; A commission calculation unit that quantitatively calculates an agreed commission by selectively reflecting the preset reference-condition information selectively acquired by the AI learning unit and the exercise probability calculated by the AI learning unit into a preset reference commission rate; and It includes a commission rate security processing unit that securely processes the information on the calculated exercise probability, which is information on the quantitatively calculated put option exercise probability, wherein The above fee rate security processing unit is, A fee information block processing unit (510) that represents the information of the exercise probability of exercising the put option as a binary signal of 1 and 0, arranges it into a binary array, groups a predetermined number of binary codes into one block, and assigns a unique address to each block; A block order reordering unit (520) that generates a function rule for reordering each of the blocks assigned the unique address and reorders the order of each block according to the function rule; and A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by including a block stack processing unit (530) that provides a plurality of stacks capable of stacking sets of the above blocks and sequentially stacks and stores the rearranged blocks in the stacks for every N blocks.
  2. In paragraph 1, the above system is, The above event probability, A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by defining the exercise of the right to purchase the real estate received through distribution as the above real estate right holder.
  3. In Paragraph 2, the above-mentioned contract execution unit is, A customer contract execution unit that electronically concludes a put option exercise contract with the real estate rights holder through the above user terminal; A payer contract conclusion unit that electronically concludes and proceeds with the fee payment contract through the server of the payment institution for the payment of the above fee; and An automatic contract fee calculation system for the exercise of a put option by a real estate right holder using AI big data learning, characterized by including a calculation fee guidance unit that transmits the agreed fee calculated by the above fee calculation unit to the server of the above payment institution for guidance.
  4. In paragraph 2, the data collection unit is, A customer information collection unit that sets the above-mentioned real estate rights holder as a customer and selectively collects and acquires customer information set as part of the above-mentioned pre-set big data; and A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by including a transaction trend information collection unit that sets a pre-set boundary for the real estate received by the real estate right holder, sets pre-set transaction trend information for real estate within the pre-set boundary, and selectively collects and acquires the pre-set transaction trend information as part of the pre-set big data.
  5. In paragraph 4, the data collection unit is, An internal variable collection unit that defines internal economic indicators related to the above real estate and selectively collects and acquires the above internal economic indicators; and A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by further including an external variable collection unit that defines external economic indicators related to the real estate and selectively collects and acquires the external economic indicators.
  6. In paragraph 5, the above AI learning unit is, It includes a minimum standard filtering unit that applies a predetermined standard to real estate satisfying the said predetermined standard, and applies it as the target real estate for the said put option exercise contract and the said commission payment contract conducted by the said contract execution unit, The above predetermined standard value is, A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by satisfying at least one of the following criteria scores as a minimum standard value: i) a preset quantitative score based on administrative district information of the administrative district to which the real estate belongs (eup, myeon, dong, gu, city, or province); ii) the population decline rate of the administrative district to which the real estate belongs; iii) the number of households in an apartment complex if the real estate is an apartment; iv) a quantitative score of the construction company constructing the real estate; v) a quantitative score based on the type, number, and distance of educational institutions adjacent to the real estate; vi) the distance and number of large supermarkets adjacent to the real estate; vii) a quantitative score based on the number and grade of hospitals adjacent to the real estate; or viii) a quantitative score based on public transportation adjacent to the real estate.
  7. In paragraph 6, the above AI learning unit is, A system for automatically calculating contract fees for a real estate right holder’s put option exercise using AI big data learning, characterized by further including a condition information filtering unit that acquires pre-prepared condition information and applies it to the target real estate of the put option exercise contract and the fee payment contract conducted by the contract execution unit depending on whether the pre-prepared condition information is satisfied.
  8. In paragraph 7, the above AI learning unit is, A system for automatically calculating contract fees for the exercise of a put option by a real estate right holder using AI big data learning, characterized by further including an exercise probability calculation unit that, when the real estate is an apartment, calculates the probability of the real estate right holder exercising a put option as a quantitative value based on the pre-set big data learned by the AI learning unit based on the apartment complex to which the real estate belongs.
  9. In Clause 8, the above fee calculation unit is, An automatic contract fee calculation system for a real estate right holder's put option exercise using AI big data learning, characterized by including an exercise probability reflection unit that reflects the put option exercise probability calculated as a quantitative value by the exercise probability calculation unit into the calculation of the agreed fee.
  10. In Clause 9, the above fee calculation unit is, A system for automatically calculating contract fees for a real estate right holder’s exercise of a put option using AI big data learning, characterized by further including a contract fee derivation unit that derives the contract fee calculated by reflecting the exercise probability of the above-mentioned exercise probability in the above-mentioned exercise probability reflection unit.

Description

Automatic calculation system for the contract of put options by real estate owner using AI big data learning The present invention relates to a system for automatically calculating a fee that enables a real estate right holder or a registered right holder to exercise a put option, and more specifically, to a technical field of a system for automatically calculating a fee agreement amount that guarantees the exercise of a put option by a real estate right holder by utilizing AI artificial intelligence and collecting and learning big data. Recently, the surge in contract forfeitures by property rights holders in South Korea's apartment presale market is emerging as a significant social issue. Due to rising interest rates, economic recession, and skyrocketing presale prices, there has been an increase in cases where buyers abandon interim payments or fail to register their ownership after signing a contract. This trend leads to a rise in unsold properties, financial difficulties for construction companies, and a downturn in local economies, acting as a destabilizing factor for the overall housing market. The waiver of real estate rights goes beyond a simple individual abandonment of a contract and directly impacts the trust in the real estate market and the stability of the financial market. As it can lead to a chain of bankruptcies among construction companies and an expansion of non-performing loans in the financial sector, it is urgent to establish a system for proactive risk detection and response. The government and the market urgently need to establish legal and institutional mechanisms to systematically manage risks in the post-contract phase of presales. The current system focuses on regulations and support primarily during the presale phase, resulting in a lack of practical countermeasures against contract cancellations. Furthermore, business models capable of detecting and mitigating post-subscription risks—such as financial linkage models or risk analysis services based on private platforms—are currently insufficient. Due to the absence of coordination between government policies and private solutions, an effective pre-emptive defense mechanism is failing to function. "An apparatus and method for analyzing the feasibility of apartment presale (Publication No. 10-2024-0176666, Patent Document 1)" exists. The invention of Patent Document 1 relates to an apartment presale feasibility analysis device using artificial intelligence, and is configured to preprocess collected data including at least one of regional supply and demand, number of households, unsold units, population, subscription competition rate, and sales price over a certain period, train an artificial intelligence model using training data generated based on the preprocessed collected data, and calculate a presale feasibility grade using the trained artificial intelligence model, wherein the preprocessing is performed by reinforcing missing values in the collected data using the cumulative value of data from adjacent periods. "An apparatus and method for calculating the sale price of a planned real estate development site (Registration No. 10-2686514, Patent Document 2)" exists. In the case of the invention of Patent Document 2, a method for calculating an appropriate sale price of a planned real estate project site, performed by a server, comprises: (a) a step of providing a real estate inquiry interface including a pre-set menu to a user terminal; (b) a step of receiving information of a planned project site including a first exclusive area, a first sale area, a first head of household, and an expected year of occupancy from the user terminal when the user terminal selects to inquire about an appropriate sale price of a planned project site from the real estate inquiry interface, along with information of a comparison complex to be compared with the planned project site; and (c) a step of calculating an appropriate sale price of a planned project site by comparing the information of the planned project site with the information of the comparison complex, wherein the information of the comparison complex includes a second exclusive area, a second sale area, a second head of household, a sale price, and an occupancy year. "A method of cyber real estate distribution on the internet (Publication No. 10-2001-0000085, Patent Document 3)" exists. In the case of the invention of Patent Document 3, the method of internet real estate sales is configured to provide information to visitors by constructing a server that provides information such as real estate sales to visitors who visit a real estate-related website on the internet, a DB which is the content of the server, and a program that implements the website, comprising: a cyber model house programmed to search for video information of the actual real estate to be sold; new sales information that provides information such as sales guides, site overviews, location conditions, and construction s