System and Method for Analyzing of budget settlement based on AI

Abstract

The present invention relates to an artificial intelligence-based budget and settlement analysis system and method that generates reports utilizing budget proposal review and settlement review data by learning various budget and settlement-related materials and various reports analyzed therefrom in a machine learning manner. The system comprises a request receiving unit that receives a budget and settlement analysis request including agency information and period information; a data collection unit that collects budget and settlement-related materials and converts them into big data; a learning unit that analyzes the big data collected by the data collection unit through deep learning techniques and learns using a deep learning algorithm; and a result derivation unit that derives budget and settlement analysis results for a specific agency for a certain period corresponding to the analysis request received by the request receiving unit using the learning results from the learning unit. By means of an artificial intelligence-based budget and settlement analysis system and method, the effect is to provide a system and method capable of automatically generating reports to be used as supporting materials for legislative activities, such as the budget proposal review and settlement review of local governments as well as administrative audits.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence-based budget and settlement analysis system and method, and more specifically, to an artificial intelligence-based budget and settlement analysis system and method that generates reports utilizing budget proposal review and settlement review data by learning from various budget and settlement-related materials and data, such as various reports analyzing such materials, using a machine learning method. Background Technology

[0003] Existing fiscal information systems include the Fiscal Information Management System (FIMSys) of the former Ministry of Planning and Budget, the National Finance Information System (NaFIS) of the former Ministry of Finance and Economy, and local fiscal information systems of local governments.

[0004] NaFIS is a system that provides computerized support for business processes occurring during the execution and settlement of the budget after it has been finalized within financial activities. It integrates and processes accounting tasks such as budget reallocation, budget execution (revenue and expenditure), treasury fund management, and settlement operations.

[0005] FIMSys is a budget information system operated by the Ministry of Planning and Budget as a budget formulation system. Budget formulation refers to the process of estimating the financial resources to be used for government projects and plans and determining the scale of expenditures to support various projects, while budget allocation refers to the first step in executing the budget, which involves allocating the formulated budget to each central government agency.

[0006] Generally, government fiscal activities follow a series of processes: budget formulation, fiscal execution, accounting settlement, and performance evaluation. However, previously, FIMSys and NaFIS operated separately for the budget and accounting sectors. For example, budget formulation was handled by FIMSys, while budget execution and settlement were handled by NaFIS, creating a dual system. Consequently, fiscal information was scattered across various locations, posing a problem in managing and utilizing it.

[0007] Furthermore, the performance evaluation of financial projects and the execution of subsidies to local governments followed a backward process of relying on paperwork due to the lack of a proper system. Although information on the previous year's execution and performance should serve as the basis for budget formulation, the situation prevented the appropriate transmission and utilization of such information.

[0008] The current situation involves staff from the expert committees of local council standing committees or special committees on budget and settlement of accounts individually investigating and analyzing data over a period of about a week to prepare review reports for the purpose of evaluating the performance of financial projects and other institutions, such as local governments. Prior art literature

[0010] KR 10-1182703 B1 The problem to be solved

[0011] The present invention was derived from this technical background and aims to provide an artificial intelligence-based budget and settlement analysis system and method capable of automatically generating reports to be used as materials supporting legislative activities, such as the review of budget proposals and settlements of local governments, as well as administrative audits.

[0012] Furthermore, we aim to provide an AI-based budget and settlement analysis system and method that can assist local governments in efficient budget formulation and execution by enabling a comparative analysis of budgets over a set period at a glance, allowing comparisons with other local government budgets, and deriving prediction results regarding increases or decreases in revenue budgets, population growth, and changes in industrial structure. means of solving the problem

[0014] The present invention for achieving the above objectives includes the following configuration.

[0015] That is, an artificial intelligence-based budget and settlement analysis system according to one embodiment of the present invention includes a request receiving unit that receives a budget and settlement analysis request including institution information and period information; a data collection unit that collects budget and settlement-related data and converts it into big data; a learning unit that analyzes the big data collected by the data collection unit through a deep learning technique and learns using a deep learning algorithm; and a result derivation unit that derives a budget and settlement analysis result for a specific institution for a certain period corresponding to the analysis request received by the request receiving unit using the learning result from the learning unit.

[0016] It also includes a report generation unit that generates the budget and settlement analysis results derived from the above result derivation unit into a report in a preset format.

[0017] Meanwhile, the artificial intelligence-based budget and settlement analysis method includes a request receiving step for receiving a budget and settlement analysis request including agency information and period information; a data collection step for collecting budget and settlement-related data and converting it into big data; a step for analyzing the big data collected in the data collection step through deep learning techniques and learning with a deep learning algorithm; and a result derivation step for deriving a budget and settlement analysis result corresponding to the analysis request received in the request receiving step using the learning result from the learning step.

[0018] It also includes a report generation step that generates the budget and settlement analysis results derived in the above result derivation step into a report in a preset format. Effects of the invention

[0020] According to the present invention, the effect of providing an artificial intelligence-based budget and settlement analysis system and method capable of automatically generating reports to be used as supporting materials for legislative activities, such as the review of budget proposals and settlements of local governments, as well as administrative audits, is derived.

[0021] In addition, we can provide an AI-based budget and settlement analysis system and method that allows for the comparative analysis of budgets over a set period at a glance and comparison with the budgets of other local governments, as well as the derivation of prediction results regarding increases and decreases in revenue budgets, population growth and decline, and changes in industrial structure, thereby assisting local governments in efficient budget formulation and execution. Brief explanation of the drawing

[0023] FIG. 1 is a block diagram illustrating the configuration of an artificial intelligence-based budget and settlement analysis system according to one embodiment of the present invention. FIG. 2 is a flowchart illustrating an artificial intelligence-based budget and settlement analysis method according to one embodiment of the present invention. Specific details for implementing the invention

[0024] It should be noted that the technical terms used in this invention are used merely to describe specific embodiments and are not intended to limit the invention. Furthermore, unless specifically defined otherwise in this invention, the technical terms used in this invention should be interpreted in the sense generally understood by those skilled in the art to which this invention pertains, and should not be interpreted in an overly broad or overly narrow sense.

[0026] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

[0027] FIG. 1 is a block diagram illustrating the configuration of an artificial intelligence-based budget and settlement analysis system according to one embodiment of the present invention.

[0028] An artificial intelligence-based budget and settlement analysis system according to one embodiment of the present invention learns by converting data and information, such as various budget and settlement-related materials of local governments and various reports analyzing such materials, into big data.

[0029] Furthermore, based on learning data, it analyzes the appropriateness, effectiveness, and efficacy of budget formulation and execution results, as well as individual project performance, for a specific local government over a set period, and derives analysis results.

[0030] In addition, by deriving the results of a comparative analysis with other local governments that are pursuing the same or similar individual projects or have a similar financial scale, a report can be automatically generated and printed to be used as supporting material for legislative activities such as the review of the local government's budget and settlement of accounts, as well as administrative audits.

[0031] For example, when a user designates a specific local government and sets a certain period, the AI-based budget and settlement analysis system (10), which is learned through artificial intelligence, automatically collects budget and settlement related materials and data such as financial disclosures, financial operation status, and bill information disclosed on Local Finance 365 and the website of the relevant local government, as well as press releases and various reports that can be collected from the internet network, analyzes them through a deep learning algorithm, and then displays the results of the analysis in the form of a report in a certain format.

[0033] As shown in FIG. 1, a budget and settlement analysis system (10) according to one embodiment includes a communication unit (110), a request receiving unit (120), a big data storage unit (130), a data collection unit (140), a learning unit (150), a result derivation unit (160), and a report generation unit (170).

[0034] The communication unit (110) establishes a communication connection with any internal component or any at least one external terminal through a wired / wireless communication network. Here, wireless internet technologies include Wireless LAN (WLAN), DLNA (Digital Living Network Alliance), Wibro (Wireless Broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), IEEE 802.16, Long Term Evolution (LTE), LTE-A (Long Term Evolution-Advanced), and Wireless Mobile Broadband Service (WMBS). The communication unit (110) transmits and receives data according to at least one wireless internet technology within a range that includes internet technologies not listed above.

[0035] In addition, short-range communication technologies may include Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, and Wi-Fi Direct. Additionally, wired communication technologies may include Power Line Communication (PLC), USB communication, Ethernet, serial communication, and optical / coaxial cables.

[0036] Any at least one external terminal may be one of a user terminal (20), a local government server (30), a media company server (40), or a web server (50). However, it is not limited thereto, and the budget and settlement analysis system (10) according to one embodiment may be interpreted to encompass all technical configurations necessary for collecting data required to perform budget and settlement analysis necessary for budget proposal review or settlement review.

[0037] Accordingly, the budget and settlement analysis system (10) according to one embodiment can automatically collect budget and settlement-related materials and data such as financial disclosures, financial operation status, and bill information disclosed on Local Finance 365 and the website of the relevant local government, as well as press releases and various reports that can be collected from the internet.

[0038] The web server (50) can be implemented with a technical configuration capable of automatically collecting data posted on the web, such as financial disclosures, financial operation status, and bill information disclosed on Local Finance 365 and the website of the relevant local government, as well as press releases and various reports that can be collected from the internet network, by performing web crawling. However, it is not limited to this.

[0039] Local Finance 365 is an internet site containing various data regarding the finances of local governments, managed by the Ministry of Public Administration and Security and provided by a web server (50) where local governments input related data.

[0040] The user terminal (20) can be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or notebook equipped with a web browser. Additionally, the user terminal (20) can be implemented as a terminal capable of connecting to a remote server or terminal via a network. The user terminal (20) may include all kinds of handheld-based wireless communication devices, such as a PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0041] In one embodiment, the user terminal (20) may encompass various types of terminal devices used for business purposes by staff or personnel in charge of the expert committee office at a local council standing committee or special committee on budget and settlement.

[0042] The budget and settlement analysis system (10) can communicate with any at least one external terminal using a network. The network includes a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof, and is a data communication network in a comprehensive sense that enables each network constituent entity shown in FIG. 1 to communicate smoothly with each other, and may include wired internet, wireless internet, and mobile wireless communication networks. In addition, wireless communication may include, for example, wireless LAN (Wi-Fi), Bluetooth, Bluetooth Low Energy, Zigbee, WFD (Wi-Fi Direct), UWB (ultra wideband), infrared communication (IrDA, infrared Data Association), NFC (Near Field Communication), but is not limited thereto.

[0043] The request receiving unit (120) receives a request for budget and settlement analysis that includes agency information and period information. In one embodiment, the request receiving unit (120) may receive an analysis request from various types of user terminals (20) used for business purposes by staff of the expert committee office at a standing committee or special committee on budget and settlement of local councils. However, it is not limited to this, and may receive an analysis request from an entity that wishes to obtain budget and settlement result data.

[0044] The data collection unit (140) collects budget and settlement-related data, converts it into big data, and stores it in the big data storage unit (130).

[0045] In one embodiment, the data collection unit (140) collects data including budget and settlement data in Local Finance 365, local finance disclosure (budget and settlement), local finance operation status (real-time), budget statement (original budget, supplementary budget, final budget), budget proposal detailed project description, settlement statement, settlement review report, administrative affairs audit result report, municipal administration (provincial administration, county administration, district administration) inquiry data, local council meeting minutes, and budget and settlement data of other local governments.

[0046] The data collection unit (140) can include central and local governments, public enterprises, and their affiliated organizations as targets for data collection. In addition, it can share information on the overall national finances, such as revenue, expenditure, assets, and liabilities, in real time.

[0047] To this end, the data collection unit (140) can operate in conjunction with an external linkage system to organically share financial information with local governments and local financial information system utilization agencies.

[0048] In addition, it can be linked with related systems such as local governments, public enterprises, and affiliated organizations.

[0049] The big data storage unit (130) can store various data and computer programs, such as data received / input from an external device and data generated by a budget and settlement analysis system (10) according to one embodiment. The big data storage unit (130) may include volatile memory and non-volatile memory. The big data storage unit (130) may include, for example, flash memory, ROM, RAM, EEROM, EPROM, EEPROM, hard disk, and registers. Alternatively, the big data storage unit (130) may include a file system, a database, and an embedded database.

[0050] The big data storage unit (130) stores training data that an artificial neural network can learn as big data to improve the accuracy of artificial intelligence deep learning modeling.

[0051] In one embodiment, the big data storage unit (130) can store data posted on the web, such as Local Finance 365 web crawled by the web server (50), budget and settlement-related materials and data such as financial disclosures, financial operation status, and bill information disclosed on the homepage of the relevant local government, press releases, and various reports that can be collected from the internet network, by converting them into big data. However, it is not limited thereto.

[0052] The learning unit (150) analyzes big data collected from the data collection unit (140) using deep learning techniques and learns using a deep learning algorithm.

[0053] Artificial intelligence is a technology that implements human intellectual abilities, such as thinking and learning, through computers. Among these, machine learning allows computers to learn autonomously and improve the performance of artificial intelligence. Additionally, deep learning processes information using artificial neural networks similar to human neurons.

[0054] In machine learning, humans must directly provide the features required for learning, but deep learning can extract features on its own and apply them to data learning.

[0055] Machine learning is a field that develops algorithms (processing methods) and techniques that enable the learning unit (150) to learn. It analyzes data using algorithms, learns through analysis, and can make judgments or predictions based on the learned content.

[0056] The learning unit (150) can perform classification, regression, etc. by supervised learning among machine learning learning types.

[0057] Meanwhile, Deep Learning is a field of machine learning that learns data by utilizing an information input layer similar to the neurons of the brain. Deep Learning is based on Artificial Neural Networks (ANNs), which are machine learning algorithms created by mimicking the principles and structure of human neural networks.

[0058] An Artificial Neural Network (ANN) consists of an input layer that receives multiple input data, a hidden layer located between the input layer and the output layer, and an output layer responsible for outputting data.

[0059] To overcome the disadvantages of difficulty in finding optimal parameter values ​​during the learning process, overfitting, and slow training time, a Deep Neural Network (DNN) can be applied to improve the learning results by increasing the number of hidden layers within the model.

[0060] A DNN (Deep Neural Network) refers to a learning method with two or more hidden layers, and the computer can derive an optimal dividing line by repeating the process of generating classification labels, distorting the space, and separating data.

[0061] A learning unit (150) according to one embodiment can analyze big data collected from a data collection unit (140) using a deep learning technique and generate a deep learning model capable of deriving budget and settlement analysis results by repeatedly learning with a deep learning algorithm.

[0062] The learning unit (150) learns an algorithm to determine the appropriateness, effectiveness, and results of budget formulation and execution for a specific local government, as well as to derive the results of analyzing individual project performance.

[0063] For example, an algorithm can be trained to automatically generate reports that can be used as supporting data for legislative activities, such as the review of local government budget proposals and settlements, as well as administrative audits, by producing results of comparative analysis with the budget and settlement details of other local governments that are pursuing individual projects identical or similar to those planned or currently being implemented by a specific institution, such as a specific local government, or have a similar financial scale.

[0064] The result derivation unit (160) derives the results of the budget and settlement analysis for a specific institution over a certain period corresponding to the analysis request received by the request receiving unit (120) using the learning results from the learning unit (150).

[0065] In one embodiment, the result derivation unit (160) can derive a certain result of analyzing the budget and settlement by inputting institution information and period information as input values ​​into a deep learning model learned by the learning unit (150) through machine learning and deep learning.

[0066] In one embodiment, the result derivation unit (160) can derive at least one of the following: a ratio of increase or decrease in finance, a result of predicting future increase or decrease in finance based on analysis results, an ideal budget allocation ratio, a performance level of individual projects, a reliability level of performance of individual projects, a project with a certain ratio of performance level and reliability, a case of budget non-use / transfer / use, a result of revenue increase or decrease ratio for a specific period, a result of predicting revenue increase or decrease ratio, a result of predicting changes in the industrial structure of the local government and future fluctuations, a result of analyzing trends in the number of residents and predicting increases or decreases, and a result of deriving a similar model for the development plan of the local government through analysis of similar local government cases.

[0067] And the result derivation unit (160) can provide the analysis results in a highly readable form by visualizing them as graphs, charts, etc.

[0068] At this time, the result derivation unit (160) can determine the form of the diagram according to the form of the result data during the process of diagramming the analysis results using a graph or chart. For example, the ratio of increase or decrease in finance can be displayed as a line graph or a bar graph, and the ideal budget allocation ratio can be displayed as a pie chart. In addition, it can be output in a format such as a radial graph or a table. However, it is not limited to this and is interpreted to encompass various technical methods that can provide the analysis results in a highly readable form.

[0069] The report generation unit (170) generates the budget and settlement analysis results derived from the result derivation unit (160) into a report in a preset format.

[0070] In one embodiment, the report generation unit (170) can generate and provide a report file in accordance with the report format included in the analysis request received by the request receiving unit (120). That is, the report generation unit (170) can generate a report file in accordance with the format requested by a staff member or person in charge of the expert committee office at a standing committee or special committee on budget and settlement of local councils. The generated file may also be implemented to be uploaded to a specific web space or sent via email or message.

[0071] In addition, in the work aspect, the result derivation unit (160) compares and analyzes the budget and settlement details of a specific institution over different periods in response to the analysis request received by the request receiving unit (120). For example, by setting the period information to 1 year, 5 years, 10 years, 15 years, and 20 years, the budget and settlement details for the same project over 1 year, 5 years, 10 years, 15 years, and 20 years can be provided as a result of comparative analysis so that they can be viewed at a glance.

[0072] Additionally, the result derivation unit (160) can compare and analyze the budget and settlement details between different institutions during the same period in response to the analysis request received by the request receiving unit (120). For example, it can compare and analyze the budget and settlement data of a local government in region A with the budget and settlement data of a local government in region B.

[0073] At this time, the result derivation unit (160) compares and analyzes the budget and settlement details between institutions where the correlation between businesses is above a certain level or the difference in financial scale is below a certain value.

[0074] In this case, the degree of association between projects can be analyzed based on the project application region, target age, or application criteria. For example, if at least two projects targeting pregnant women share the same target group of pregnant women, they can be determined to have a similarity level exceeding a certain threshold.

[0075] Or, in the case of a project targeting children aged 3 to 5, it can be determined that the degree of project correlation between support projects targeting that age group is above a certain level.

[0076] Or, in the case of support measures for small business owners affected by infectious diseases, if the purpose of the project is the same, it can be determined that the degree of correlation is above a certain level even if it is implemented by different local governments, i.e., institutions.

[0077] The criteria or scope for determining the degree of correlation between projects may be arbitrarily set or changed by staff or personnel in charge of the expert committee office at the standing committee or special committee on budget and settlement of the local council.

[0078] That is, the result derivation unit (160) can derive analysis results to facilitate comparative analysis of budget and settlement details regarding the same business operations of different local governments.

[0079] Additionally, by deriving forecast results based on increases or decreases in revenue budgets, population growth, and changes in industrial structure, it can assist local governments in carrying out efficient budget formulation and execution.

[0081] FIG. 2 is a flowchart illustrating an artificial intelligence-based budget and settlement analysis method according to one embodiment of the present invention.

[0082] An artificial intelligence-based budget and settlement analysis method according to one embodiment first receives a request for budget and settlement analysis including agency information and period information from a staff member or expert at a specialized committee or a special committee on budget and settlement of a local council (S200).

[0083] The request receiving stage may receive analysis requests from various types of user terminals used for work by staff of the expert committee office at local council standing committees or special committees on budget and settlement. However, it is not limited to this, and analysis requests may be received from various entities seeking to understand budget and settlement result data.

[0084] And data related to budget and settlement is collected and turned into big data (S210).

[0085] In one embodiment, the big data storage step may convert and store data posted on the web, such as Local Finance 365 web crawled by a web server, budget and settlement-related materials and data such as financial disclosures, financial operation status, and bill information disclosed on the website of the relevant local government, and press releases and various reports that can be collected from the internet, into big data. However, it is not limited thereto.

[0086] Afterwards, the big data collected during the data collection stage is analyzed using deep learning techniques and trained using a deep learning algorithm (S220).

[0087] The learning phase involves learning algorithms to derive analysis results of individual project performance, as well as to judge the appropriateness, effectiveness, and efficacy of budget formulation and execution results for a specific local government over a set period.

[0088] By deriving the results of a comparative analysis of the budget and settlement details of other local governments that are pursuing individual projects identical or similar to those planned by a specific institution, for example, a specific local government, or have a similar financial scale, it is possible to learn an algorithm for automatically generating reports to be used as supporting data for legislative activities such as the review of the local government's budget proposal and settlement of accounts, as well as administrative audits.

[0089] Subsequently, using the learning results from the learning stage, budget and settlement analysis results corresponding to the analysis request received in the request receiving stage are derived (S230).

[0090] The result derivation stage may derive at least one of the following: the expression of fiscal increase / decrease ratios; the expression of predicted future fiscal increase / decrease results based on analysis results; the expression of ideal budget allocation ratios; the expression of individual project performance; the expression of individual project performance reliability; the expression of projects with a certain ratio of performance and reliability; the expression of cases regarding budget non-use, reallocation, or utilization; the expression of revenue increase / decrease ratios for a specific period; the expression of predicted revenue increase / decrease ratios; the expression of changes in the industrial structure of the relevant local government and predictions of future fluctuations; the expression of analysis of resident population trends and predictions of increase / decrease; and the derivation of similar models for development plans for the relevant local government through the analysis of similar local government cases. However, it is not limited to these.

[0091] In addition, the results derivation stage can present the analysis results in a highly readable format by visualizing them using graphs, charts, etc.

[0092] At this stage, during the result derivation phase, the format of the visualization can be determined based on the form of the result data during the process of visualizing the analysis results using graphs or charts. For example, it may be decided to display the ratio of increase or decrease in finances as a line graph or bar graph, and to display the ideal budget allocation ratio as a pie chart. Additionally, the output may be presented in a radial graph or tabular format. However, this is not limited to these methods and is interpreted to encompass various technical approaches that can provide analysis results in a highly readable format.

[0093] In one aspect of the present invention, the result derivation step compares and analyzes the budget and settlement details of a specific institution for different periods in response to the analysis request received by the analysis request step.

[0094] For example, by setting the period information to 1 year, 5 years, 10 years, 15 years, or 20 years, it is possible to provide a comparative analysis result that allows you to view the budget and settlement details for the same project over 5, 10, 15, or 20 years at a glance.

[0095] In another aspect of the present invention, the result derivation step compares and analyzes budget and settlement details between different institutions over the same period in response to an analysis request received by the analysis request step.

[0096] At this stage, the results derivation step involves comparing and analyzing the budget and settlement details of institutions where the correlation between projects is above a certain level or the difference in financial scale is below a certain value.

[0097] The degree of association between projects can be analyzed based on factors such as the project application region, target age, and application criteria. For example, in the case of projects targeting pregnant women, if the target population matches, the similarity can be determined to be above a certain threshold.

[0098] Or, in the case of support measures for a specific social class, if the purpose of achievement is the same, even if they are implemented by different local governments, i.e., institutions, it can be judged that the degree of correlation is above a certain level.

[0099] The criteria or scope for determining the degree of correlation between projects may be arbitrarily set or changed by staff or personnel in charge of the expert committee office at the standing committee or special committee on budget and settlement of the local council.

[0100] In a further aspect of the present invention, the budget and settlement analysis results derived in the result derivation step are generated into a report in a preset format (S240).

[0101] In one embodiment, the report generation step may generate and provide a report file in accordance with the report format included in the analysis request received in the analysis request step. That is, the report generation step may generate a report file in accordance with the format requested by a staff member or person in charge at the expert committee office of a local council standing committee or the special committee on budget and settlement. The generated file may also be implemented to be uploaded to a specific web space or sent via email or message.

[0103] The above-described method may be implemented as an application or in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination.

[0104] The program instructions recorded on the above-mentioned computer-readable recording medium are those specifically designed and configured for the present invention, but may also be those known and available to those skilled in the art of computer software.

[0105] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, and flash memory.

[0106] Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

[0107] Although the invention has been described above with reference to embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as set forth in the following claims. Explanation of the symbols

[0109] 10: Budget and Settlement Analysis System 20: User Terminal 110: Communication unit 120: Request receiving unit 130: Big Data Storage Unit 140: Data Collection Unit 150 : Learning Section 160 : Result Derivation Section 170 : Report Generation Section

Claims

Claim 1 A request receiving unit that receives a request for budget and settlement analysis including institutional information and period information; a data collection unit that collects budget and settlement-related data and converts it into big data; a learning unit that analyzes the big data collected by the data collection unit using deep learning techniques and learns using a deep learning algorithm; and a result derivation unit that uses the learning results from the learning unit to derive budget and settlement analysis results for a specific institution over a certain period corresponding to the analysis request received by the request receiving unit, and graphically outputs the derived analysis results. It includes a report generation unit that generates a report in a pre-configured format to utilize the budget and settlement analysis results derived from the result derivation unit as data supporting legislative activities; the data collection unit collects and converts into big data data including budget and settlement data in Local Finance 365, local finance disclosures related to budget and settlement, status of local finance operations, budget statements including the initial budget, supplementary budget, and final budget, detailed project descriptions for budget proposals, settlement statements, settlement review reports, administrative audit result reports, municipal inquiry materials, local council meeting minutes, and budget and settlement data of other local governments; the learning unit learns using the deep learning algorithm to derive analysis results regarding the appropriateness, effectiveness, efficacy, and individual project performance of budget formulation and execution results for a specific local government over a set period; and the result derivation unit compares and analyzes budget and settlement details between different institutions over the same period in response to an analysis request received by the request receiving unit, and the results of the project correlation analysis It compares and analyzes budget and settlement details among institutions where the degree of correlation is above a certain level or the difference in financial scale is below a certain value, and analyzes the degree of correlation between the above projects based on the project application region, target age, and project application target conditions, and the above learning unit,An algorithm is trained to automatically generate reports that can be utilized as data supporting legislative activities, including the review of local government budget proposals and settlements, as well as administrative audits, by deriving results of comparative analysis with the budget and settlement details of other local governments that are pursuing individual projects identical or similar to those planned or currently being implemented by a specific institution, such as a specific local government, or have a similar financial scale. The result derivation unit compares and analyzes the budget and settlement details of a specific institution over different periods in response to an analysis request received by the request receiving unit, and displays the ratio of financial increase / decrease, the predicted results of future financial increase / decrease based on the analysis results, the ideal budget allocation ratio, the performance of individual projects, the reliability of individual project performance, projects with a certain ratio of performance and reliability, cases of budget non-use / transfer / utilization, results of revenue increase / decrease ratios for a specific period, results of predicted revenue increase / decrease ratios, results of changes in the industrial structure of the relevant local government and predictions of future fluctuations, and analysis of trends in the population and increase / decrease. An AI-based budget and settlement analysis system characterized by displaying prediction results and deriving results of similar models for the development plans of the relevant local government through the analysis of similar local government cases, determining the form of the diagram based on the form of the result data during the process of diagramming the analysis results using graphs or charts, displaying the increase / decrease ratio of finances as a line graph or bar graph, and displaying the ideal budget allocation ratio as a pie chart. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 A request receiving step in which a request for budget and settlement analysis including institutional information and period information is received by a request receiving unit; a data collection step in which budget and settlement-related data is collected and converted into big data by a data collection unit; a learning step in which the big data collected in the data collection step is analyzed through deep learning techniques and learned using a deep learning algorithm by a learning unit; and a result derivation step in which a budget and settlement analysis result corresponding to the analysis request received by the request receiving unit is derived using the learning result from the learning step, and the derived analysis result is graphically represented and output. The method includes a report generation step in which the budget and settlement analysis results derived in the result derivation step are diagrammed and generated into a report in a pre-set format by the report generation unit; the data collection step collects and converts into big data data including budget and settlement data in Local Finance 365, local finance disclosures related to budget and settlement, status of local finance operations, budget statements including the initial budget, supplementary budget, and final budget, detailed project descriptions for budget proposals, settlement statements, settlement review reports, administrative audit result reports, municipal inquiry materials, local council meeting minutes, and budget and settlement data of other local governments; the learning step trains using the deep learning algorithm to derive analysis results regarding the appropriateness, effectiveness, efficacy, and individual project performance of budget formulation and execution results for a specific local government over a set period; and the result derivation step compares and analyzes budget and settlement details between different institutions over the same period in response to the analysis request received in the request receiving step, and the results of the project correlation analysis It compares and analyzes budget and settlement details among institutions where the degree of correlation is above a certain level or the difference in financial scale is below a certain value, and analyzes the degree of correlation between the above projects based on the project application region, target age, and project application target conditions, and the above learning unit,An algorithm is trained to automatically generate reports that can be utilized as data supporting legislative activities, including the review of local government budget proposals and settlements, as well as administrative audits, by deriving results of comparative analysis with the budget and settlement details of other local governments that are pursuing individual projects identical or similar to those planned or currently being implemented by a specific institution, such as a specific local government, or have a similar financial scale. The result derivation step involves comparative analysis of the budget and settlement details of a specific institution over different periods in response to the analysis request received in the request receiving step, and includes the display of financial increase / decrease ratios, predictions of future financial increases / decrease based on analysis results, ideal budget allocation ratios, performance of individual projects, reliability of individual project performance, projects with a certain ratio of performance and reliability, instances of budget non-use / transfer / utilization, results of revenue increase / decrease ratios for a specific period, results of projected revenue increase / decrease ratios, results of changes in the industrial structure of the relevant local government and predictions of future fluctuations, and analysis of trends in resident population changes and predictions of increase / decrease. An AI-based budget and settlement analysis method characterized by deriving results of similar models for the development plan of a local government through the analysis of similar local government cases, determining the form of the diagram based on the form of the result data during the process of diagramming the analysis results using graphs or charts, displaying the above-mentioned increase / decrease ratio of finance as a line graph or bar graph, and displaying the above-mentioned ideal budget allocation ratio as a pie chart. Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 delete

Images