Removal annuity record management system

Abstract

The invention provides a retirement annuity record management system. According to the embodiment of the invention, the retired pension record management system receives a retired pension management request of a first user side, generates a first asset plan by using pension amount information containing the retired pension management request, sends the first asset plan to the first user side, receives execution completion information of the first asset plan, and sends the execution completion information to the first user side. And calculating a first return rate of the first asset plan according to preset time, if the first return rate is lower than a first threshold value, updating the first asset plan, and generating a second asset plan.

Description

Technical Field

[0001] This invention relates to a retirement annuity record management system, and more specifically, to a business system for retirement annuity operation and management institutions. The retirement annuity record management system can utilize optimized reference models and experience from securities / banking institutions to provide an operational / marketing management system and various customer services. Background Technology

[0002] Retirement pensions are a type of pension system that workers can receive upon retirement. This refers to an asset received by a worker after a period of service, either upon retirement or through regular payments over a period of time after retirement. Retirement pensions are an important means of helping workers maintain financial stability in preparation for old age.

[0003] Retirement pensions can be mainly divided into the following two types:

[0004] 1. Defined Benefit Plan (DB): The annuity received by the employee upon retirement is predetermined. Pension payments are calculated based on the employee's length of service, average wage, etc., and the company is responsible for managing the employee's pension fund. The company is obligated to pay the agreed-upon amount upon the employee's retirement.

[0005] 2. Defined Contribution Plan (DC): The annuity received by the worker upon retirement is not predetermined. The worker or company contributes a certain amount to the retirement account annually, and the outcome of investment activities determines the amount received upon retirement. The worker can directly choose how their retirement assets are used; the amount received after retirement depends on the investment results.

[0006] The retirement annuity system is an important financial tool to help workers mitigate income volatility that may result from long-term work and maintain a stable retirement life. Summary of the Invention

[0007] The problem that the invention aims to solve

[0008] One of the technical challenges that this invention aims to address is to provide a retirement pension record management system that generates asset plans using pension amount information.

[0009] Another technical problem that this invention aims to solve is to provide a retirement pension record management system that adjusts asset plans based on a target rate of return.

[0010] Another technical challenge that this invention aims to address is to provide a retirement pension record management system that acquires stocks according to an asset plan and stores stock price information in conjunction with the asset plan.

[0011] The technical problems to be solved by this invention are not limited to those described.

[0012] means for solving problems

[0013] According to a specific embodiment of the present invention, the retirement annuity record management system comprises one or more processors; and, when run by the one or more processors, memory containing one or more stored commands, wherein the commands for operations performed by the one or more processors are stored. The one or more processors receive a retirement pension management request from a first user terminal, generate a first asset plan using information including the pension amount in the retirement pension management request, send the first asset plan to the first user terminal, complete a first asset yield plan based on the first user terminal, and calculate the first asset yield based on a first point in time. In some cases, a second asset plan can be generated by updating the first asset plan.

[0014] As an implementation example, the one or more processors receive a modification request for the first asset plan from the first user terminal, generate a third asset plan that updates the first asset plan in response to the modification request, and send the third asset plan to the first user terminal. They also receive execution completion information based on the third asset plan from the first user terminal, and calculate a higher rate of return and a higher rate of return for the third asset plan based on the rates of return of the second and third asset plans, according to a pre-set time point. Further, relevant information can be sent to the first user terminal.

[0015] As one embodiment, the one or more processors can send the second asset plan to the first user terminal, receive the execution completion information of the second asset plan from the first user terminal, calculate the fourth rate of return and the fifth rate of return of the first asset plan at a preset time point, compare the fourth rate of return and the fifth rate of return, and send the information of the asset plan with the higher value to the first user terminal.

[0016] As an example, if the one or more processors calculate a first rate of return based on the first asset plan at a preset time point, they can compare a preset target rate of return with the first rate of return. If the target rate of return is higher than the first rate of return, the first asset plan can be updated to generate a fourth asset plan. If the target rate of return is lower than the first rate of return, the processor can prompt the user as a first terminal to maintain the first asset plan.

[0017] As an example, if the one or more processors receive the execution completion information of the first asset plan, the one or more processors will receive a stock purchase request from the first user terminal, send a stock purchase order to the securities company server according to the stock purchase request, receive a stock purchase completion signal from the securities company server, and include the stock purchase and purchase quantity in the first asset plan according to the stock purchase completion signal, and periodically receive stock price information from the securities company server to update the first asset plan.

[0018] According to one or more processors of the present invention; and a retirement pension record management method using a retirement pension record management system when running on said one or more processors, comprising one or more memories storing commands for operations performed by said one or more processors; a step of receiving a retirement pension management request from a first user terminal via said one or more processors; a step of generating a first asset plan via said one or more processors using pension amount information including the retirement pension management request; a step of sending the first asset plan to the first user terminal via said one or more processors; a stage of receiving execution completion information based on the first asset plan from the first user terminal via said one or more processors; a stage of calculating a first rate of return based on the first asset plan at a preset time point via said one or more processors; and a step of updating the first asset plan to generate a second asset plan if the first rate of return is lower than a first threshold via said one or more processors.

[0019] According to an embodiment of the present invention, one or more processors; and a computer program stored in a computer-readable recording medium, executed by the one or more processors, can execute commands executed by the one or more processors on a computer containing storage in one or more memory, including the following steps: receiving a retirement pension management request from a first user terminal by the one or more processors; generating a first asset plan using pension amount information including the retirement pension management request by the one or more processors; sending the first asset plan to the first user terminal by the one or more processors; receiving execution completion information according to the first asset plan from the first user terminal by the one or more processors; calculating a first rate of return according to the first asset plan at a preset time point by the one or more processors; and, according to the one or more processors, if the first rate of return is lower than a first threshold, it can be stored in a computer-readable recording medium so as to perform a step of generating a second asset plan by updating the first asset plan.

[0020] Invention Effects

[0021] The retirement annuity record management system according to a Japanese embodiment of the present invention can provide a means for customers to formulate and manage asset plans.

[0022] Furthermore, the retirement annuity record management system according to a daily embodiment of the present invention can adjust asset plans based on a target rate of return.

[0023] Furthermore, the retirement annuity record management system according to a Japanese embodiment of the present invention can acquire stocks according to an asset plan and store stock price information in conjunction with the asset plan. Attached Figure Description

[0024] Figure 1 This is an example diagram of a retirement annuity record management system according to an embodiment of the present invention.

[0025] Figure 2 This is an example diagram showing the server configuration according to an embodiment of the present invention.

[0026] Figure 3 These are drawings illustrating a learning neural network according to an embodiment of the present invention.

[0027] Figure 4 This is a flowchart illustrating a retirement annuity record management method procedure according to an embodiment of the present invention.

[0028] Figure 5 This is an example diagram of a device configuration according to an embodiment of the present invention.

[0029] Explanation of reference numerals in the attached figures

[0030] 100: Retirement Annuity Record Management System; 110-1110-n: User Terminal

[0031] 120: Server 130: Database

[0032] 122: Processor 124: Memory

[0033] 126: Transceiver 127: Input Layer

[0034] 128: Neural Network 129: Output Layer Detailed Implementation

[0035] The following sections will describe the implementing examples in detail with reference to the accompanying drawings. However, various modifications may be made to the implementing examples, and therefore the scope of the patent application is not limited or restricted by these implementing examples. All modifications, equivalents, or substitutions to the implementing examples should be understood to be included within the scope of the claims.

[0036] The specific structural or functional descriptions of the implementation examples are merely illustrative and can be modified and implemented in various forms. Therefore, the implementation examples are not limited to a particular starting form, and the scope of this list includes changes, equivalents, or alternatives contained in the technical ideas.

[0037] The terms "first" or "second" can be used to describe various components, but these terms should only be interpreted as distinguishing one component from others. For example, the first component can be named the second component, and similarly, the second component can be named the first component.

[0038] When it is said that a component is "connected" to another component, it may be directly connected to or connected to another component, but it must be understood that there may be other components in between.

[0039] The terminology used in the embodiments is for illustrative purposes only and should not be construed as an attempt to limit. Singular expressions include plural expressions unless the meaning is clearly different in the context. In this description, terms such as “comprising” or “owning” should be understood to specify the presence of the features, numbers, steps, actions, components, parts, or combinations thereof listed in the list, without excluding the possibility of the presence or addition of one or more other features or numbers, steps, actions, components, parts, or combinations thereof.

[0040] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the embodiments pertain. Terms as defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and should not be construed as having an ideal or overly formal meaning unless explicitly defined in this application.

[0041] Furthermore, when describing the embodiments with reference to the attached figures, the same components will be assigned the same reference numerals regardless of the graphic symbols used, and repeated descriptions will be omitted. When describing embodiments, detailed descriptions of relevant disclosed technologies will be omitted if it is believed that such detailed descriptions might unnecessarily obscure the essential points of the embodiments.

[0042] Implementation examples can be achieved through various products such as personal computers, laptops, tablets, smartphones, televisions, smart home appliances, smart cars, self-service machines, and wearable devices.

[0043] Figure 1 This is an example diagram of a retirement annuity record management system according to an embodiment of the present invention.

[0044] like Figure 1As shown, the retirement annuity record management system 100 may include multiple user terminals 110-1, ..., 110-n, a server 120, and a database 130. According to one example, the database 130 is considered to be configured independently of the server 120, but is not limited to this; the database 130 may also be within the server 120. For example, the server 120 may contain multiple artificial intelligence models to execute machine learning algorithms. According to a real-time example, the multiple user terminals 110-1, ..., 110-n, the server 120, and the database 130 can communicate with each other via a network N.

[0045] Server 120 can receive retirement pension management requests from a first user terminal. According to a real-time example, server 120 can receive retirement pension management requests entered by the first user through a first user terminal 110-1 via network N. For example, the retirement pension management request might contain information about the first user's current pension holdings, pension target amount, and pension amount during the pension contribution period.

[0046] Server 120 can generate a first asset plan using pension amount information including a retirement pension management request. According to a real-time example, server 120 can generate a first asset plan using the pension amount information contained in a retirement pension management request received from a first user terminal 110-1. For example, if the first user currently holds 100 million won, the target pension amount is 300 million won, and the pension contribution period is 20 years, server 120 can generate a first asset plan with an annual interest rate of 10%. Server 120 can also generate the first user's first asset plan using product yields from various financial institutions stored in database 130.

[0047] Server 120 can send the first asset plan to the first user terminal. As an example, server 120 can send the generated first asset plan to the first user terminal 110-1 via network N.

[0048] Server 120 can receive execution completion information of the first asset plan from the first user terminal. According to one implementation example, server 120 can receive execution completion information input by the first user terminal 110-1 after the first user has confirmed the first asset plan and made an investment according to the first asset plan. For example, if the first asset plan includes investment information for a specific stock project, when the first user completes the acquisition of that stock project through the first user terminal 110-1, server 120 can receive execution completion information from the first user terminal 110-1 via network N.

[0049] Server 120 can calculate the first rate of return based on the first asset plan at a preset time point. According to a daily implementation example, server 120 can calculate the first rate of return of the first asset plan at a preset time point (e.g., 1 month, 6 months, 1 year, etc. from the date of receiving the execution completion information). For example, server 120 can calculate the first rate of return (20%) based on the first asset plan, using the difference between the initial stock purchase price (e.g., 10,000 Korean won) and the price per share at a preset time (6 months after receiving the execution completion information) (e.g., 12,000 Korean won), as shown in Formula 1.

[0050] [Mathematical Expression 1]

[0051]

[0052] The server (120) can update the first asset plan to generate a second asset plan when the first yield is lower than a first threshold. According to one implementation example, if the calculated first yield (e.g., 8%) is lower than the first threshold (e.g., 10%), the server (120) can update the first asset plan to generate a second asset plan to include items with a higher yield. According to other implementation examples, the server (120) can instruct a first user terminal (110-1) to maintain the first asset plan when the calculated first yield (e.g., 12%) is higher than the first threshold (e.g., 10%).

[0053] Furthermore, the server (120) can receive modification requests for the first asset plan from the first user terminal. According to one example, the server (120) can receive modification requests for the first asset plan from the first user terminal (110-1) via a network (N). For example, the modification request might include a request to change the stock items included in the first asset plan to other stock items.

[0054] The server (120) can generate a third asset plan that updates the first asset plan to reflect the modification request. According to one implementation example, the server (120) can generate a third asset plan that updates the first asset plan to reflect the received modification request.

[0055] The server (120) can send the third asset plan to the first user terminal. According to one example, the server (120) can send the generated third asset plan to the first user terminal (110-1) via the network (N).

[0056] The server (120) can receive information from the first user terminal regarding the completion of the operation according to the third asset plan. According to one implementation example, the server (120) can receive execution completion information input by the first user terminal (110-1) after the first user terminal (110-1) confirms the third asset plan and makes an investment according to the third asset plan, and receive this information from the first user terminal (110-1) via the network (N). For example, if the third asset plan contains investment information for a specific stock project, when the first user completes the acquisition of that stock project through the first user terminal (110-1), the first user terminal (110-1) can receive the execution completion information from the first user terminal (110-1) via the network (N).

[0057] The server (120) can calculate the second rate of return of the first asset plan and the third rate of return of the third asset plan at preset time points. According to a daily embodiment, the server (120) can calculate the second rate of return of the first asset plan and the third rate of return of the third asset plan at preset time points (e.g., 1 month, 6 months, 1 year, etc., from the initial purchase time of the third asset plan). For example, the server (120) can calculate the second rate of return using mathematical formula 2 and calculate the third rate of return using mathematical formula 3.

[0058] [Mathematical Expression 2]

[0059]

[0060] [Mathematical Expression 3]

[0061]

[0062] The server (120) can send asset plan information with a higher value to the first user terminal by comparing the second rate of return and the third rate of return. According to one example, the server (120) can compare the calculated second rate of return and the third rate of return. If the second rate of return is higher than the third rate of return, the server (120) sends the information of the second rate of return to the first user terminal (110-1) via the network (N). If the third rate of return is higher than the second rate of return, the server (120) sends the information of the third rate of return to the first user terminal (110-1) via the network (N).

[0063] Furthermore, the server (120) can send a second asset plan to the first user terminal. According to a real-time example, the server (120) can send the second asset plan generated by updating the first asset plan to the first user terminal (110-1) via the network (N).

[0064] The server (120) can receive information from the first user terminal confirming the completion of the operation according to the second asset plan. According to one implementation example, the server (120) can receive execution completion information input by the first user terminal (110-1) via the first user terminal (110-1), and then receive, via the network (N), information confirming the investment made by the first user under the second asset plan by the first user terminal (110-1). For example, if the second asset plan contains investment information for a specific stock project, when the first user completes the acquisition of that stock project through the first user terminal (110-1), the first user terminal (110-1) can receive execution completion information via the network (N).

[0065] The server (120) can calculate the fourth rate of return of the first asset plan and the fifth rate of return of the second asset plan at preset time points. According to a typical embodiment, the server (120) can calculate the fourth rate of return of the first asset plan and the fifth rate of return of the second asset plan at preset time points (e.g., 1 month, 6 months, 1 year, etc., from the initial purchase date of the stocks, according to the second asset plan). For example, the server (120) can calculate the fourth rate of return using mathematical formula 4 and calculate the fifth rate of return using mathematical formula 5.

[0066] [Mathematical Expression 4]

[0067]

[0068] [Mathematical Expression 5]

[0069]

[0070] Server 120 can send asset plan information with the higher value to the first user terminal by comparing the fourth yield and the fifth yield. According to one example, server 120 can compare the calculated fourth yield with the fifth yield; if the fourth yield is higher than the fifth yield, the server 120 sends the fourth yield information to the first user terminal 110-1 via network N; if the fifth yield is higher than the fourth yield, the server 120 sends the fifth yield information to the first user terminal 110-1 via network N.

[0071] Furthermore, if server 120 calculates the first rate of return based on the first asset plan at a preset time point, it can compare the preset target rate of return with the first rate of return. According to a typical embodiment, server 120 can calculate the first rate of return of the first asset plan based on the preset target rate of return and a preset time point (e.g., 1 month, 6 months, 1 year, etc. from the initial stock purchase time point according to the first asset plan).

[0072] Server 120 can update the first asset plan to generate a fourth asset plan if the target rate of return is higher than the first rate of return. According to one implementation example, if the target rate of return of server 120 is higher than the first rate of return, the first asset plan can be updated to generate a fourth asset plan. For example, if the target rate of return (e.g., 10%) is higher than the calculated first rate of return (e.g., 8%), server 120 can generate a fourth asset plan to update the first asset plan to include projects with higher rates of return.

[0073] Server 120 can instruct the first user terminal to maintain the first asset plan if the target rate of return is lower than the first rate of return. According to one implementation example, if the target rate of return (e.g., 10%) is lower than the calculated first rate of return (e.g., 12%), server 120 can instruct the first user terminal 110-1 to maintain the first asset plan.

[0074] Furthermore, if server 120 receives completion information for the first asset plan, it can receive stock purchase requests from the first user terminal. According to one implementation example, if server 120 receives completion information for the first asset plan from the first user terminal 110-1, it can receive stock purchase requests for the first asset plan from the first user terminal 110-1 via network N.

[0075] Server 120 can send a stock purchase order to the securities company server based on a stock purchase request. According to a real-time example, server 120 can send a stock subscription order to the securities company server via network N based on a stock subscription request received from the first user terminal 110-1.

[0076] Server 120 can receive a stock acquisition completion signal from the securities company's server. According to a real-time example, server 120 can receive a signal from the securities company's server via network N indicating that a stock acquisition order has been completed.

[0077] Server 120 can store the stock purchase price and quantity in the first asset plan based on the stock purchase completion signal. According to a real-time example, server 120 can store the stock purchase price and quantity in the first asset plan based on the stock purchase completion signal. For example, server 120 can store the stock purchase price (e.g., 10,000 Korean won per share) and the purchase quantity (e.g., 10,000 shares) in the first asset plan based on the stock purchase completion signal.

[0078] Server 120 can periodically receive stock price information from the securities company's server and update the first asset plan. According to a real-time example, server 120 can periodically (e.g., once a month, once a year, etc.) receive stock price information from the securities company's server, update the stock acquisition price stored in the first asset plan, and store it in database 130.

[0079] Network N enables wireless or wired communication between multiple user terminals 110-1, ..., 110-n, server 120, database 130, etc. For example, network N can communicate wirelessly using methods such as LTE (long-term evolution), LTE-A (LTE Advanced), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless Broadband), WiFi (wireless fidelity), Bluetooth, NFC (near field communication), GPS (Global Positioning System), or GNSS (global navigation satellite). For example, network (N) can also communicate wiredly using methods such as USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), or POTS (plain old telephone service).

[0080] Database 130 can store various types of data. The data stored in database 130 can be data acquired, processed, or used by at least one component of multiple user terminals 110-1, ..., 110-n and server 120, including software (e.g., programs). Database 130 can contain volatile and / or non-volatile memory. As a one-off example, database 130 can store retirement pension management requests, first to fourth asset plans, first to fifth yields, etc.

[0081] In this invention, Artificial Intelligence (AI) refers to the technology of mimicking human learning, reasoning, and perceptual abilities and implementing them in computers. This may include concepts such as machine learning and symbolic logic. Machine learning (ML) is an algorithmic technique that automatically classifies or learns the features of input data. Artificial intelligence technology uses machine learning algorithms to analyze input data, learn from the analysis results, and make judgments or predictions based on those results. Furthermore, technologies that utilize machine learning algorithms to simulate the cognitive and judgmental functions of the human brain can also be understood as falling within the scope of artificial intelligence. For example, this may include technical fields such as language understanding, visual understanding, reasoning / prediction, knowledge representation, and action control.

[0082] Machine learning can mean using experience in processing data to train neural network models. Through machine learning, computer software can improve its data processing capabilities. Neural network models are built by modeling the correlations between data, which can be expressed by multiple parameters. The process of a neural network model extracting and analyzing features from given data, deriving correlations between data, and repeating these processes to optimize the model's parameters can be considered machine learning. For example, a neural network model can learn the mapping (correlation) between inputs and outputs to obtain data as input / output pairs. Alternatively, a neural network model can learn relationships by deriving regularities between given data given input data.

[0083] Artificial intelligence (AI) learning models, or neural network models, can be designed to replicate the structure of the human brain on a computer. They can contain multiple network nodes that simulate neurons in a human neural network and have weights. These multiple network nodes can mimic the synaptic activity of neurons, which transmit signals through synapses, thus creating interconnections. In AI learning models, multiple network nodes reside at different depths and can exchange data based on convolutional connections. AI learning models can be, for example, Artificial Neural Networks (ANNs) or Convolutional Neural Networks (CNNs). As an implementation example, AI learning models can perform machine learning in the manner of supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms used for machine learning can include decision trees, Bayesian networks, support vector machines, artificial neural networks, Ada-boost, perceptron, genetic programming, clustering, and more.

[0084] CNNs (Multilayer Perceptrons) are designed to use minimal preprocessing. A CNN consists of one or more synthetic multiplication layers and ordinary artificial neural network layers placed on top, further utilizing weights and pooling layers. Thanks to this structure, CNNs can fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs have shown good performance in video and speech processing. CNNs can also be trained using standard inverse propagation. CNNs are easier to train than other feedforward artificial neural network techniques and use fewer parameters.

[0085] A convolutional network is a type of neural network that contains a set of nodes with a set of parameters. With the increase in the size of available training data and the availability of computing power, as well as the development of algorithms such as distinguishing linear units and descent training, many computer vision tasks have seen significant improvements. In today's large datasets (such as datasets usable for many tasks), overfitting is not critical, and increasing the network size can improve test accuracy. Optimal use of computing resources becomes a limiting factor. For this reason, distributed, scalable implementations of deep neural networks can be used.

[0086] Figure 2 This is an example diagram showing the server configuration according to an embodiment of the present invention.

[0087] like Figure 2 As shown, server 120 may include one or more processors 122, one or more memory modules 124, and transceivers 126. As an example, at least one of these components in server 120 may be omitted, or other components may be added to server 120. Additionally or alternatively, some components may be integrated and implemented, or implemented as singular or multiple objects. At least some of the components inside and outside server 120 are interconnected via system bus, GPIO (general purpose input / output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface), and can transmit and receive data and / or signals.

[0088] One or more processors 122 can drive software (such as commands, programs, etc.) to control at least one component of server 120 connected to processor 122. Furthermore, processor 122 can perform various operations related to this invention, including calculations, processing, data generation, and manipulation. Additionally, processor 122 can load data from or store data in one or more memory locations 124.

[0089] One or more processors 122 may receive retirement pension management requests from a first user terminal. According to a real-world example, processor 122 may receive a retirement pension management request input by the first user through a first user terminal (e.g., 110-1) via transceiver 126. For example, the retirement pension management request may contain information about the first user's current pension holdings, pension target amount, and pension amount during the pension contribution period.

[0090] One or more processors 122 can generate a first asset plan using pension amount information contained in a retirement pension management request. According to a real-time example, processor 122 can generate a first asset plan using pension amount information contained in a retirement pension management request received from a first user terminal 110-1. For example, if the first user currently holds 100 million Korean won, the target pension amount is 300 million Korean won, and the pension contribution period is 20 years, processor 122 can generate a first asset plan with an annual interest rate of 10%. Processor 122 can also generate the first user's first asset plan using product yields from various financial institutions stored in memory 122.

[0091] One or more processors 122 can send the first asset plan to the first user terminal. According to a real-time example, processor 122 can send the generated first asset plan to the first user terminal 110-1 via transceiver 126.

[0092] One or more processors 122 can receive execution completion information of a first asset plan from a first user terminal. According to a real-time example, processor 122 can receive execution completion information input by a first user terminal 110-1 after the first user terminal 110-1 has confirmed the first asset plan and made an investment according to the first asset plan. For example, if the first asset plan includes investment information for a specific stock project, when the first user completes the acquisition of that stock project through the first user terminal 110-1, processor 122 can receive execution completion information from the first user terminal 110-1 via transceiver 126.

[0093] One or more processors 122 can calculate a first rate of return based on a first asset plan at a preset time point. According to a typical embodiment, the processor 122 can calculate the first rate of return of the first asset plan at a preset time point (e.g., 1 month, 6 months, 1 year, etc., from the date of receiving the execution completion information). For example, the processor 122 can calculate the first rate of return (20%) based on the first asset plan, using the difference between the initial stock purchase price (e.g., 10,000 Korean won) and the stock price at a preset time (6 months after receiving the execution completion information) (e.g., 12,000 Korean won), as shown in Formula 1.

[0094] One or more processors 122 can update a first asset plan to generate a second asset plan when a first yield is lower than a first threshold. According to a daily implementation example, if the calculated first yield (e.g., 8%) is lower than a first threshold (e.g., 10%), processor 122 can update the first asset plan to generate a second asset plan to include projects with higher yields. According to other implementation examples, processor 122 can instruct a first user terminal 110-1 to maintain the first asset plan when the calculated first yield (e.g., 12%) is higher than a first threshold (e.g., 10%).

[0095] One or more memory modules 124 may store the retirement pension management request, the first to fourth asset plans, the first to fifth rates of return, etc. Additionally, one or more memory modules 124 may store commands executed by one or more processors 122 during runtime.

[0096] According to a real-world example, server 120 may also include transceiver 126. Transceiver 126 can enable wireless or wired communication between server 120 and various external servers, databases, client devices, and / or other devices. For example, transceiver 126 can perform GPS-like communication based on technologies such as eMBB (enhanced Mobile Broadband), URLLC (Ultra-Reliable Low-Latency Communication), MMTC (Quality Machine Type Communication), LTE (Long Term Evolution), LTE-A (LTE Advance), UMTS (Universal Mobile Telecommunications System), GSM (Global System for Mobile Communications), CDMA (Code Division Multiple Access), WCDMA (Wideband Communication System), WiBro (Wireless Broadband), WiFi (Fidelity), Bluetooth (Near Field Communication System), and GPS (Global Positioning System). For example, transceiver (126) can also perform wired communication via USB (universal serial bus), HDMI (high definition multimedia interface), RS-232 (recommended standard 232), or POTS (plain old telephone service).

[0097] According to a real-time example, one or more processors 122 can control transceiver 126 to obtain information from various external servers and databases 130. The information obtained from the various external servers and databases 130 can be stored in one or more memories 124.

[0098] According to one example, server 120 can be a variety of devices. For example, server 120 can be a portable communication device, a computer device, or a combination of one or more of said devices. The server 120 of the present invention is not limited to said devices.

[0099] According to the present invention, various embodiments of server 120 can be combined with each other. Each embodiment can be combined in a number of cases, and the combined embodiments of server 120 also fall within the scope of the present invention. Furthermore, according to the present invention, internal and external components of server 120 can be added, modified, replaced, or deleted according to the embodiments. In addition, the internal and external components of server 120 can also be implemented as hardware components.

[0100] Figure 3 These are drawings illustrating a learning neural network according to an embodiment of the present invention.

[0101] As Figure 3 As shown, the learning device can learn a neural network 128 to generate an asset allocation plan from retirement pension management requests. According to one example, the learning device could be a server 120 or other independent entities, but is not limited to these.

[0102] The neural network 128 includes an input layer 127 that takes training samples as input and an output layer 129 that outputs the training output. It can learn based on the difference between the training output and the label. Here, the label can be defined based on the asset allocation plan corresponding to the retirement pension management request. The neural network 128 is defined by an activation function, which consists of groups of multiple nodes connected together, activating the weights and nodes between the connections.

[0103] The learning device can learn neural networks using either Gradient Descent (GD) or Stochastic Gradient Descent (SGD) techniques. The learning device can utilize the output and labels of the neural network to design a loss function.

[0104] The learning device can calculate the training error using a predefined loss function. The loss function can predefine labels, output, and parameters as input variables, where the parameters can be set by the weights in the neural network 128. For example, the loss function can be designed in the form of MSE (Mean Square Error), entropy, etc., and various techniques or methods can be used to design the loss function.

[0105] The learning device can use backpropagation to identify the weights that influence training errors. These weights represent the relationships between nodes in a neural network. The learning device can then use SGD (Signal-Growth Divide) based on the labels and outputs to optimize the weights found through backpropagation. For example, the learning device can use SGD to update the weights of a loss function defined based on the labels, outputs, and weights.

[0106] According to the daily implementation example, the learning device can acquire training retirement pension management requests (e.g., information such as the first user's current holdings, pension target amount, and pension amount during the pension joining period) and generate an asset allocation plan for the training recipient. The learning device can acquire each pre-tagged piece of information (first tag) in the training retirement pension management request, where the first tag represents a predefined asset allocation plan in the training retirement pension management request.

[0107] Based on real-time examples, the learning device can generate a first training feature vector based on the compositional, logical, and pattern features of training retirement pension management requests. Extracting features from training retirement pension management requests can be done in various ways.

[0108] According to a real-time example, the learning device can apply a first training feature vector to neural network 128 to obtain a training output. The learning device can learn neural network 128 based on the training output and the first label. The learning device can calculate the training errors corresponding to the training output and learn neural network 128 by optimizing the connections between nodes in neural network 129 to minimize these training errors. Server 120 can use the learned neural network 128 to generate an asset allocation plan from a retirement pension management request.

[0109] Figure 4 This is a flowchart illustrating a retirement annuity record management method according to an embodiment of the present invention. Figure 4 In the flowcharts, process steps, method steps, algorithms, etc., are described sequentially, but these processes, methods, and algorithms can be configured to run in any suitable order. In other words, the steps of the processes, methods, and algorithms described in the various embodiments of the present invention do not necessarily have to be executed in the order described in the present invention. Furthermore, even if some steps are interpreted as being executed asynchronously, these steps can be executed simultaneously in other embodiments. Moreover, the process examples described in the figures do not imply that the example processes exclude other changes and modifications to them, nor do they imply that the example processes or any of their steps are necessary for one or more of the various embodiments of the present invention, nor do they imply that the example processes are desirable.

[0110] like Figure 4As shown, in step S410, a retirement pension management request will be received. For example, refer to... Figures 1 to 3 The server 120 in the retirement annuity record management system 100 can receive retirement annuity management requests input by a first user through a first user terminal 110-1 via network N. For example, the retirement annuity management request may contain information about the first user's current pension amount, pension target amount, and pension amount during the pension contribution period.

[0111] In step S420, a first asset plan will be generated. For example, refer to... Figures 1 to 3 The server 120 in the retirement pension record management system 100 can generate a first asset plan using pension amount information including a retirement pension management request. According to a real-time example, the server 120 can generate the first asset plan using the pension amount information contained in the retirement pension management request received from the first user terminal 110-1. For example, if the first user currently holds 100 million won, the target pension amount is 300 million won, and the pension contribution period is 20 years, the server 120 can generate a first asset plan with an annual interest rate of 10%. The server 120 can also generate the first user's first asset plan using the product yields of various financial institutions stored in the database 130.

[0112] In step S430, the first asset plan is sent. For example, refer to... Figures 1 to 3 The server 120 of the retirement annuity record management system 100 can send the first asset plan to the first user terminal. According to one example, the server 120 can send the first asset plan generated in stage S420 to the first user terminal 110-1 via network N.

[0113] In step S440, execution completion information will be received. For example, refer to... Figures 1 to 3 The server 120 of the retirement annuity record management system 100 can receive execution completion information of the first asset plan from the first user terminal. According to one implementation example, the server 120 can receive execution completion information entered by the first user terminal 110-1 after the first user has confirmed the first asset plan and made an investment according to the first asset plan. For example, if the first asset plan includes investment information for a specific stock project, when the first user completes the acquisition of that stock project through the first user terminal 110-1, the server 120 can receive the execution completion information from the first user terminal 110-1 via network N.

[0114] In stage S450, the first rate of return is calculated. For example, refer to... Figures 1 to 3The server 120 of the retirement pension record management system 100 can calculate the first rate of return of the first asset plan at a preset time point. According to a daily implementation example, the server 120 can calculate the first rate of return of the first asset plan at a preset time point (e.g., 1 month, 6 months, 1 year, etc. from the date of receiving the execution completion information). For example, the server 120 can calculate the first rate of return (20%) based on the first asset plan, using the difference between the initial purchase price per share (e.g., 10,000 Korean won) and the price per share (e.g., 12,000 Korean won) at a preset time (6 months after receiving the execution completion information), as shown in Formula 1.

[0115] In step S460, a second asset plan is generated. For example, if referring to... Figure 1 or Figure 3 In the retirement annuity record management system 100, server 120 can update the first asset plan to generate a second asset plan when the first rate of return falls below a first threshold. According to one implementation example, if the calculated first rate of return (e.g., 8%) is lower than the first threshold (e.g., 10%), server 120 can update the first asset plan to generate a second asset plan to include items with a higher rate of return. According to other implementation examples, server 120 can instruct first user terminal 110-1 to maintain the first asset plan when the calculated first rate of return (e.g., 12%) is higher than the first threshold (e.g., 10%).

[0116] Figure 5 This is an example diagram of a device configuration according to an embodiment of the present invention.

[0117] According to one example, device 501 includes processor 502 and memory 503. According to a real-time example, device 501 could be the server or terminal. The processor may contain... Figures 1 to 4 At least one of the aforementioned devices, or through Figures 1 to 4 At least one of the methods described above. Memory 503 may store information related to the method or store programs implementing the method. Memory 503 may be volatile memory or non-volatile memory.

[0118] Processor 502 can run programs and control device 501. The program code executed by processor 502 can be stored in memory 503. Device 501 is connected to external devices (such as personal computers or networks) via I / O devices (not shown in the figure) and can exchange data.

[0119] The implementation examples described above can be implemented using hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the implementation examples can be implemented using one or more general-purpose computers or special-purpose computers, such as processors, controllers, ALUs (arithmetic logic units), digital signal processors, microcomputers, programmable gate arrays (FPGAs), programmable logic units (PLUs), microprocessors, or any other device that executes and responds to instructions. The processing device can execute an operating system (OS) and one or more software applications executed on said operating system. Furthermore, the processor can access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, a processing unit is sometimes interpreted as using "one," but those skilled in the art will recognize that a processing unit can contain multiple processing elements and / or multiple types of processing elements. For example, a processing unit can contain multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, can be configured.

[0120] The method according to the embodiments can be executed by various computer means, implemented in the form of program commands, and recorded in a computer-readable medium. The computer-readable medium may contain program commands, data files, data structures, etc., individually or in combination. The program commands recorded on the medium may be specifically designed and configured for the embodiments, or may be available after notification to each computer software vendor. Examples of computer-readable recording media include specially configured hardware devices for storing and executing program commands on magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floppy disks; ROMs; RAMs; and flash memory. Examples of program commands include not only machine code generated by a compiler, but also code in high-level languages ​​executable by a computer, such as interpreters. The hardware device may be configured to run as one or more software modules to perform the operations in the examples, and its scope may also be as described.

[0121] Software can comprise computer programs, code, instructions, or a combination thereof, and can configure processing units to operate on demand, or to instruct processing units independently or collectively. Software and / or data can be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by processing equipment or to provide commands or data to processing equipment. Software is distributed across network-connected computer systems and can be stored or run in a distributed manner. Software and data can be stored on one or more computer-readable recording media.

[0122] As described above, although the implementation examples are illustrated in limited drawings, various technical modifications and variations can be applied based on this foundation if you have general knowledge in this technical field. For example, the described techniques can be performed in a different order than the described method, and / or the components of the described system, structure, device, circuit, etc., can be combined or combined in a different form than the described method, or suitable results can be obtained even if they are replaced or substituted by other components or homogeneous objects.

[0123] Therefore, other implementations, other embodiments, and those equivalent to the scope of the patent application are also within the scope of the following claims.

Claims

1. A retirement annuity record management system, wherein, The retirement annuity record management system includes: More than one processor; and One or more memory locations, when run by the one or more processors, store commands that require the one or more processors to perform operations. The one or more processors receive retirement pension management requests from the first user terminal. A first asset plan is generated using information including the pension amount in the retirement pension management request. Send the first asset plan to the first user terminal. Receive execution completion information according to the first asset plan from the first user terminal. At a predetermined time point, the first rate of return is calculated based on the first asset plan. If the first yield is lower than the first threshold, then the first asset plan is updated to generate a second asset plan.

2. The retirement annuity record management system according to claim 1, wherein, The one or more processors receive a modification request for the first asset plan from the first user terminal. Based on the modification request, a third asset plan is generated to update the first asset plan. Send the third asset plan to the first user terminal. The first user terminal receives completion information regarding the execution of the third asset plan. The second rate of return of the first asset plan and the third rate of return of the third asset plan are calculated at preset time points. By comparing the second rate of return with the third rate of return, information about the asset plan can be better sent to the first user terminal.

3. The retirement annuity record management system according to claim 1, wherein, The one or more processors send the second asset plan to the first user terminal. The first user terminal receives completion information regarding the execution of the second asset plan. The fourth rate of return for the first asset plan and the fifth rate of return for the second asset plan are calculated at preset time points. The fourth yield is compared with the fifth yield in order to send information about the asset plan to the first user terminal.

4. The retirement annuity record management system according to claim 1, wherein, Of the one or more processors If the first rate of return is calculated based on the first asset plan at a preset time point... Compare the preset target rate of return with the first rate of return. If the target rate of return is higher than the first rate of return, then the first asset plan is updated to generate a fourth asset plan. If the target rate of return is lower than the first rate of return, redirect it to the first user terminal to maintain the first asset plan.

5. The retirement annuity record management system according to claim 1, wherein, Of the one or more processors If the completion information of the first asset plan is received, Upon receiving the stock purchase request from the first user client, Based on the stock subscription request, a stock subscription order is sent to the securities company's server. A stock purchase completion signal was received from the brokerage's server. Based on the stock purchase completion signal, the stock purchase price and quantity are stored in the first asset plan. The system periodically receives stock price information from the securities company's server to update the first asset plan.

Images