Ai agent system for business trip risk prediction and cost optimization decision support

Abstract

An AI agent system that supports business trip risk prediction and cost optimization decision-making is disclosed. It digitizes and manages a company's business trip regulations and policies, performs rule-based automated decision-making regarding business trip requests, and analyzes and optimizes business trip-related costs for said requests.

Description

Technology Field

[0001] The following description concerns an AI-based decision support solution that predicts risks and proposes cost-saving strategies to optimize a company's business travel processes. Background Technology

[0002] With the advancement of digital and computer technologies, companies are seeking to improve processing efficiency and productivity by adopting digital and network technologies into their business operations. A prime example is the electronic approval system that eliminates paper usage in the office, and these technologies are also being applied to all business processes, including sales, accounting, and human resource management.

[0003] As an example of electronic approval technology, Korean Registered Patent No. 10-0454735 (registered on October 19, 2004) discloses a technology for providing a corporate portal service that integrates electronic approval, knowledge management systems, resource management, document management, and management information systems, enabling access and use through a single unified window such as a web browser.

[0004] The business trip management system within a company has the following problems.

[0005] (1) Inefficiency in planning business trips

[0006] Optimized decision-making is difficult due to the lack of data-driven decision support regarding business trip schedules and costs, as well as the absence of pattern analysis in historical data. Furthermore, cost-effectiveness analysis is performed manually, resulting in excessive time and expense. Consequently, not only is a significant portion of annual business trip expenses spent inefficiently, but the time required for planning also increases, leading to decreased work productivity due to inefficient scheduling.

[0007] (2) Limitations in responding to real-time changes

[0008] Real-time responses to unforeseen situations, such as flight delays and accommodation changes, are inadequate, and automated decision-making support for alternative routes and schedule modifications is lacking. Furthermore, the process for recalculating costs and obtaining approval for schedule changes is complex. Consequently, when unexpected situations arise, additional costs are incurred due to delayed responses; business travelers' work efficiency is reduced; and the workload on managers is increased, leading to the inefficient utilization of human resources.

[0009] (3) Absence of cost optimization mechanism

[0010] Optimization of each cost element, such as airfare, accommodation, and local transportation, is carried out individually, and there is no integrated analysis system for overall cost optimization. Furthermore, there is currently a lack of a function to suggest alternatives for reducing business trip expenses. As a result, total costs sometimes increase due to individual optimization, cost analysis and reporting are time-consuming, and the accuracy of budget management is compromised. The problem to be solved

[0011] We can provide a hybrid rule-based system to innovatively improve a company's business trip management process. means of solving the problem

[0012] A method for optimizing an AI-based business trip plan for a computer device comprising at least one processor, comprising the steps of: digitizing and managing business trip-related regulations and policies of a company by the at least one processor; performing a rule-based automatic decision-making on a business trip request by the at least one processor; and analyzing and optimizing business trip-related costs for the business trip request by the at least one processor.

[0013] According to one aspect, the above-mentioned managing step may include converting travel-related regulations and policies into a standardized form and defining relationships between rules.

[0014] According to another aspect, the managing step may include a step of validating the validity of newly defined or modified rules and detecting whether there are conflicts between rules.

[0015] According to another aspect, the step of performing the above may include a step of verifying the execution results based on rule-based decision-making.

[0016] According to another aspect, the step of performing the above may include identifying and applying relevant rules to the business trip request, but detecting exceptional situations where rule application is impossible and applying alternative rules.

[0017] According to another aspect, the optimization step may include a step of analyzing all cost elements related to the business trip for the business trip request.

[0018] According to another aspect, the optimization step may include the step of collecting real-time price information and historical data, structuring and storing them.

[0019] According to another aspect, the optimizing step may include determining the optimal reservation time for the business trip request and deriving the optimal solution by comparing and analyzing reservation options.

[0020] According to another aspect, the optimization step may include a step of running a prediction model for cost optimization based on real-time data and updating the prediction results.

[0021] According to another aspect, the method may further include the step of detecting and assigning priorities to change business trip-related information occurring in real time by the at least one processor.

[0022] According to another aspect, the processing step may include evaluating the risk regarding the changes related to the business trip and presenting alternative options.

[0023] According to another aspect, the method may further include a step of analyzing business trip-related data and deriving relevant insights by the at least one processor mentioned above.

[0024] According to another aspect, the deriving step may include the step of extracting and converting data from multiple sources and loading it into a data warehouse.

[0025] According to another aspect, the deriving step described above may include performing an analysis of business trip patterns and cost optimization, and predicting future trends through a prediction model.

[0026] The present invention provides a computer device comprising at least one processor implemented to execute a readable command on a computer device, wherein the at least one processor processes the process of digitizing and managing business travel-related regulations and policies of a company; the process of performing rule-based automatic decision-making regarding business travel requests; the process of analyzing and optimizing business travel-related costs regarding business travel requests; the process of detecting business travel-related changes occurring in real time and performing a response to such changes; and the process of analyzing business travel-related data to derive relevant insights. Effects of the invention

[0027] According to embodiments of the present invention, by combining the stability of traditional rule-based systems with the flexibility of artificial intelligence technology, the entire process from planning business trips to settlement can be optimized and automated, and in particular, corporate competitiveness can be strengthened by achieving five core objectives: cost efficiency, work productivity, risk management, data-driven decision-making, and regulatory compliance. Brief explanation of the drawing

[0028] FIG. 1 is a block diagram illustrating an example of the internal configuration of a computer device in an embodiment of the present invention. FIG. 2 illustrates an AI-based business trip management system architecture in one embodiment of the present invention. FIG. 3 illustrates a hybrid cloud architecture for business trip management in one embodiment of the present invention. FIG. 4 illustrates a cloud-native business trip management system architecture in one embodiment of the present invention. FIG. 5 illustrates a configuration diagram of an AI-based business trip planning optimization system in one embodiment of the present invention. FIG. 6 illustrates the detailed configuration of an intelligent rule processing engine in one embodiment of the present invention. FIG. 7 illustrates the detailed configuration of an adaptive cost optimization engine in one embodiment of the present invention. FIG. 8 illustrates the detailed configuration of a variation response process engine in one embodiment of the present invention. FIG. 9 illustrates the detailed configuration of an integrated data analysis engine in one embodiment of the present invention. FIG. 10 illustrates an AI-based business trip planning optimization method in one embodiment of the present invention. FIGS. 11 and 12 illustrate a peripheral module process for AI-based business trip planning optimization in an embodiment of the present invention. Specific details for implementing the invention

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0031] Embodiments of the present invention relate to a technology for optimizing a company's business trip process.

[0032] Embodiments including those specifically disclosed in this specification can support the simultaneous achievement of corporate cost reduction and employee safety by analyzing real-time data using an AI agent to optimize business trip schedules, routes, budgets, etc.

[0033] An AI-based business trip planning optimization system according to embodiments of the present invention may be implemented by at least one computer device, and an AI-based business trip planning optimization method according to embodiments of the present invention may be performed through at least one computer device included in the AI-based business trip planning optimization system. At this time, a computer program according to an embodiment of the present invention may be installed and run on the computer device, and the computer device may perform an AI-based business trip planning optimization method according to embodiments of the present invention under the control of the run computer program. The above-described computer program may be stored on a computer-readable recording medium to be combined with the computer device to execute the AI-based business trip planning optimization method on the computer.

[0034] FIG. 1 is a block diagram illustrating an example of a computer device according to an embodiment of the present invention. For example, an AI-based business trip planning optimization system according to embodiments of the present invention can be implemented by a computer device (100) illustrated in FIG. 1.

[0035] As illustrated in FIG. 1, a computer device (100) may include a memory (110), a processor (120), a communication interface (130), and an input / output interface (140) as components for executing an AI-based business trip planning optimization method according to embodiments of the present invention.

[0036] Memory (110) is a computer-readable recording medium and may include a non-perishable mass storage device such as RAM (random access memory), ROM (read only memory), and a disk drive. Here, a non-perishable mass storage device such as a ROM and a disk drive may be included in the computer device (100) as a separate permanent storage device distinct from memory (110). Additionally, an operating system and at least one program code may be stored in memory (110). These software components may be loaded into memory (110) from a computer-readable recording medium separate from memory (110). This separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, disk, tape, DVD / CD-ROM drive, or memory card. In another embodiment, software components may be loaded into memory (110) through a communication interface (130) rather than a computer-readable recording medium. For example, software components can be loaded into the memory (110) of the computer device (100) based on a computer program installed by files received through the network (160).

[0037] The processor (120) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (120) via memory (110) or a communication interface (130). For example, the processor (120) may be configured to execute instructions received according to program code stored in a recording device such as memory (110).

[0038] The communication interface (130) may provide a function for the computer device (100) to communicate with other devices through a network (160). For example, requests, commands, data, files, etc. generated by the processor (120) of the computer device (100) according to program code stored in a recording device such as memory (110) may be transmitted to other devices through the network (160) under the control of the communication interface (130). Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device (100) through the communication interface (130) of the computer device (100) via the network (160). Signals, commands, data, etc. received through the communication interface (130) may be transmitted to the processor (120) or memory (110), and files, etc. may be stored in a storage medium (the permanent storage device described above) that the computer device (100) may further include.

[0039] The communication method is not limited and may include not only communication methods utilizing communication networks (e.g., mobile communication networks, wired internet, wireless internet, broadcasting networks) that the network (160) may include, but also short-range wired / wireless communication between devices. For example, the network (160) may include any one or more networks such as a PAN (personal area network), LAN (local area network), CAN (campus area network), MAN (metropolitan area network), WAN (wide area network), BBN (broadband network), and the Internet. Additionally, the network (160) may include any one or more network topologies such as a bus network, star network, ring network, mesh network, star-bus network, tree or hierarchical network, but is not limited thereto.

[0040] The input / output interface (140) may be a means for interfacing with an input / output device (150). For example, the input device may include a device such as a microphone, keyboard, camera, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface (140) may be a means for interfacing with a device in which the functions for input and output are integrated into one, such as a touchscreen. The input / output device (150) may be composed of a computer device (100) and a single device.

[0041] Additionally, in other embodiments, the computer device (100) may include fewer or more components than the components of FIG. 1. However, it is not necessary to clearly illustrate most of the prior art components. For example, the computer device (100) may be implemented to include at least some of the input / output devices (150) described above, or may include other components such as a transceiver, a camera, various sensors, a database, etc.

[0042] Below, we will describe specific embodiments of AI agent technology that supports business trip risk prediction and cost optimization decision-making.

[0043] The AI-based business trip planning optimization system according to the present invention may include the following technical features.

[0044] (1) Optimization and efficient management of business trip expenses

[0045] Costs can be reduced by establishing optimal business trip plans through data analysis-based predictive models, and reservations can be made at the optimal time through real-time price monitoring and automated booking systems. Furthermore, analyzing historical business trip data allows for the identification of wasteful spending and the development of improvement strategies.

[0046] (2) Productivity improvement through business process automation

[0047] Processing time can be reduced by automating repetitive and manual business trip-related tasks. In addition, the intuitive interface and automated approval process alleviate the user's workload, while the real-time notification and monitoring system enables rapid decision-making and response.

[0048] (3) Prevention and management of risks related to business trips

[0049] Identify and respond to potential problems in advance through AI-based risk prediction models. Real-time situation monitoring enables the presentation of immediate response measures in the event of unexpected situations, and allows for the automatic detection and control of risk factors such as regulatory violations or budget overruns.

[0050] (4) Data-driven strategic decision support

[0051] It can provide an environment capable of comprehensive analysis by integrating and managing all business trip-related data. Furthermore, by applying advanced analytical techniques, it can derive insights necessary for establishing travel policies and budget planning, and support rapid decision-making by management through customized dashboards and reporting systems.

[0052] (5) Strengthening compliance with business trip regulations

[0053] By systematically reflecting a company's travel regulations and policies into the system, automated verification is possible. It provides an audit system capable of monitoring domestic and international laws and regulatory requirements in real time to verify compliance, and meticulously recording and tracking all travel-related processing details.

[0054] The computer device (100) according to the present embodiment can provide an AI-based business trip planning optimization service to a client by accessing a dedicated application installed on the client or a web / mobile site related to the computer device (100). The computer device (100) may be configured with an AI-based business trip planning optimization system implemented on a computer. For example, the AI-based business trip planning optimization system may be implemented in the form of a program that operates independently, or configured as an in-app of a specific application so that it can operate on said specific application.

[0055] The processor (120) of the computer device (100) may be implemented as a component for performing the following AI-based business trip planning optimization method. Depending on the embodiment, the components of the processor (120) may be optionally included in or excluded from the processor (120). Additionally, depending on the embodiment, the components of the processor (120) may be separated or merged to represent the function of the processor (120).

[0056] These processors (120) and components of the processor (120) can control a computer device (100) to perform steps included in the following AI-based business trip planning optimization method. For example, the processor (120) and components of the processor (120) may be implemented to execute instructions according to the code of an operating system included in memory (110) and the code of at least one program.

[0057] Here, the components of the processor (120) may be representations of different functions performed by the processor (120) according to instructions provided by program code stored in the computer device (100).

[0058] The processor (120) can read necessary instructions from memory (110) in which instructions related to the control of the computer device (100) are loaded. In this case, the read instructions may include instructions for controlling the processor (120) to execute the steps to be described later.

[0059] The steps included in the AI-based business trip planning optimization method described later may be performed in a different order than the one described, and some of the steps may be omitted or additional processes may be included.

[0060] FIG. 2 illustrates an AI-based business trip management system architecture in one embodiment of the present invention.

[0061] Referring to FIG. 2, an AI-based travel management system for manufacturing enterprises may be composed of a client layer (web browser, mobile app, tablet app, etc.), an API gateway and load balancer layer, a core service layer (intelligent rule processing engine, cost optimization engine, variation response engine, data analysis engine, common services (authentication / authorization, logging, monitoring, notification), etc.), and a data layer (relational DB, NoSQL DB, data warehouse, cache storage, data integration layer (ETL / ELT, data pipeline), etc.).

[0062] FIG. 3 illustrates a hybrid cloud architecture for business trip management in one embodiment of the present invention.

[0063] Referring to Fig. 3, a hybrid cloud system for a manufacturing enterprise may be composed of an on-premise IDC including core business systems (ERP system, human resource management system), data storage (Legacy DB, File Storage), and security systems (firewall, VPN Gateway), and a public cloud including travel management services (rule processing engine, cost optimization engine, variation response engine, data analysis engine), cloud services (container service, serverless service), and data services (distributed database, data lake).

[0064] FIG. 4 illustrates a cloud-native business trip management system architecture in one embodiment of the present invention.

[0065] Referring to Fig. 4, the cloud-native travel management system may include a global edge layer (CDN, WAF, DDoS Protection, Route 53), a front-end layer (S3 static web hosting, CloudFront, Lambda@Edge), an API gateway, a microservices layer (ECS / EKS) (Service Mesh (AWS App Mesh), rule processing service, cost optimization service, variation response service, data analysis service, notification service, serverless function (Lambda), etc.), an event message layer (EventBridge, SQS, SNS, Kinesis), and a data layer (Aurora, DynamoDB, ElastiCache, S3, Redshift (data warehouse), etc.).

[0066] FIG. 5 illustrates a configuration diagram of an AI-based business trip planning optimization system in one embodiment of the present invention.

[0067] Referring to FIG. 5, the AI-based business trip planning optimization system according to the present invention may include an intelligent rule engine (200), an adaptive cost optimization engine (300), a change response engine (400), and a data analytics engine (500).

[0068] FIG. 6 illustrates the detailed configuration of an intelligent rule processing engine in one embodiment of the present invention.

[0069] Referring to FIG. 6, the intelligent rule processing engine (200) may include a rule management module (610) and a decision processing module (620).

[0070] First, the rule management module (610) is a core module that digitizes and manages the company's travel-related regulations and policies, and can build and maintain a rule database, manage priorities and dependencies between rules, and process updates.

[0071] The rule management module (610) may include a rule definition submodule (611), a rule verification submodule (612), and a rule database (613).

[0072] The rule definition submodule (611) can convert and store rules in a structured form, define and map relationships between rules, and track and manage change history.

[0073] The rule definition submodule (611) can convert travel-related policies and regulations into a digital format that the system can understand. Additionally, the rule definition submodule (611) can define the priority, scope, and exception conditions of the rules, and can explicitly define and manage the relationships and dependencies between the rules. Furthermore, the rule definition submodule (611) can provide an interface that allows for the addition of new rules and the modification of existing rules.

[0074] The rule verification submodule (612) can verify the validity of the input rules, detect and resolve conflicts between rules, and generate and execute test cases.

[0075] The rule verification submodule (612) can verify the validity of newly defined or modified rules and can automatically check and report whether there are conflicts between rules. In addition, the rule verification submodule (612) can perform tests to verify the consistency and completeness of the rules and store and manage the verified rules in the rule database.

[0076] The rule database (613) serves to systematically store all verified rules. The rule database (613) provides a structure capable of version control and history tracking of rules, has a structure capable of storing and querying relationships between rules, and can provide a high-performance search function for real-time rule application.

[0077] Next, the decision processing module (620) is an execution module that performs rule-based automated decision-making, and can select and apply rules suitable for the current situation, detect exceptional situations, and suggest response measures.

[0078] The decision processing module (620) may include a rule execution submodule (621), an exception handling submodule (622), and a machine learning engine (623).

[0079] The rule execution submodule (621) can drive the rule engine to make decisions, verify and record execution results, and monitor performance indicators.

[0080] The rule execution submodule (621) can identify and apply relevant rules to an input travel request and manage sequential execution according to the priority of the rules. Additionally, the rule execution submodule (621) can perform the function of verifying and recording execution results and can be responsible for monitoring and logging the rule application process.

[0081] The exception handling submodule (622) can identify and classify exception situations, solve problems by applying alternative rules, and establish an exception handling strategy based on learned patterns.

[0082] The exception handling submodule (622) can detect special situations that cannot be handled by general rules, and can identify and apply alternative rules for exception situations. Additionally, the exception handling submodule (622) can record the exception handling history and use it as training data, and can analyze repetitive exception patterns to use for rule improvement.

[0083] The machine learning engine (623) can learn patterns based on accumulated decision data and automatically suggest a method for handling exceptional situations. The machine learning engine (623) can continuously improve the accuracy and efficiency of rule application and derive insights for creating new rules.

[0084] FIG. 7 illustrates the detailed configuration of an adaptive cost optimization engine in one embodiment of the present invention.

[0085] Referring to FIG. 7, the adaptive cost optimization engine (300) may include a cost analysis module (710) and an optimization execution module (720).

[0086] First, the cost analysis module (710) is a module that analyzes all cost elements related to business trips and derives an optimization plan, and can analyze cost patterns based on past data and collect and process real-time price information.

[0087] The cost analysis module (710) may include a data collection sub-module (711), a pattern analysis sub-module (712), and a cost database (713).

[0088] The data collection submodule (711) can collect cost data from various sources, verify and refine the accuracy of the data, and structure and store the collected information.

[0089] The data collection submodule (711) can collect business trip-related cost data such as airline tickets, accommodation, and transportation, and can automatically collect real-time price information and historical data. At this time, the data collection submodule (711) can collect cost processing data from the company's internal accounting system in conjunction.

[0090] The pattern analysis submodule (712) can identify and classify cost patterns, generate and validate prediction models, and derive and suggest optimization opportunities.

[0091] The pattern analysis submodule (712) can analyze the time series patterns of the collected cost data, and can analyze the cost fluctuation factors and their influence to form patterns, and can generate a cost prediction model through a machine learning algorithm.

[0092] The cost database (713) can structure and store all collected cost-related data. The cost database (713) can perform history management and version management of the data, and can store and manage analysis results and prediction models.

[0093] Next, the optimization execution module (720) is an execution module that applies the derived optimization plan to the actual reservation process, and can optimize the timing and method of reservation and monitor the cost reduction effect.

[0094] The optimization execution module (720) may include a reservation optimization sub-module (721), a performance measurement sub-module (722), and a prediction engine (723).

[0095] The reservation optimization submodule (721) can determine and execute the optimal reservation time. Additionally, the reservation optimization submodule (721) can evaluate and suggest alternative options and verify the results of the reservation execution.

[0096] The reservation optimization submodule (721) can determine and execute the optimal reservation time and conditions. At this time, the reservation optimization submodule (721) can derive an optimal solution by comparing and analyzing various reservation options, and can monitor and verify the results of the reservation execution.

[0097] The performance measurement submodule (722) can calculate and report cost reduction effects, evaluate the effectiveness of the optimization strategy, identify improvements, and provide feedback.

[0098] The performance measurement submodule (722) can measure the cost reduction effect of the optimization execution results, evaluate and record the accuracy of the prediction model, and analyze and report the effectiveness of the optimization strategy.

[0099] The prediction engine (723) executes a prediction model for cost optimization, and can update prediction results based on real-time data, analyze prediction errors, and automatically adjust the model.

[0100] FIG. 8 illustrates the detailed configuration of a variation response process engine in one embodiment of the present invention.

[0101] Referring to FIG. 8, the variation response process engine (400) may include a monitoring module (810) and a response execution module (820).

[0102] First, the monitoring module (810) is a module that detects and analyzes all changes related to business trips in real time, and can collect change information from various sources and identify and evaluate risk factors.

[0103] The monitoring module (810) may include an event detection submodule (811), a risk analysis submodule (812), and an event database (813).

[0104] The event detection submodule (811) can detect and classify real-time changes. Additionally, the event detection submodule (811) can assign priorities and determine the processing order, and can send notifications to the relevant system.

[0105] The event detection submodule (811) can detect and classify all business trip-related changes occurring in real time and can monitor external events such as flight delays, cancellations, and changes in accommodation. The event detection submodule (811) can track internal events such as internal schedule changes and budget adjustments.

[0106] The risk analysis submodule (812) can evaluate and classify potential risks, analyze and report impacts, and suggest preventive measures.

[0107] The risk analysis submodule (812) can evaluate the impact and risk of changes detected through the event detection submodule (811). The risk analysis submodule (812) can analyze the impact on achieving the purpose of the business trip and review the feasibility of alternative options.

[0108] The event database (813) serves to store and manage history related to all changes, and can structure data by establishing a classification system by event type and accumulate past response history and results.

[0109] Next, the response execution module (820) is a module that establishes and executes response measures for detected changes, and can generate situational response scenarios and monitor and evaluate the execution results.

[0110] The response execution module (820) may include a scenario management submodule (821), an execution management submodule (822), and an analysis engine (823).

[0111] The scenario management submodule (821) creates and manages response scenarios, and can select the optimal response plan and establish and adjust an execution plan.

[0112] The scenario management submodule (821) can manage standard response scenarios for each situation, select the optimal response plan according to the event type, and determine priorities considering cost and time.

[0113] The execution management submodule (822) executes and tracks response measures, can verify and document results, and can identify and reflect improvements.

[0114] The execution management submodule (822) can coordinate the execution of the selected response scenario, and at the same time, can coordinate collaboration with the relevant departments and systems, record the execution results, and collect feedback.

[0115] The analysis engine (823) can verify the feasibility of the response scenario, predict the impact of the scenario execution, and analyze the execution results to derive improvements.

[0116] FIG. 9 illustrates the detailed configuration of an integrated data analysis engine in one embodiment of the present invention.

[0117] Referring to FIG. 9, the integrated data analysis engine (500) may include a data processing module (910) and an analytics and reporting module (920).

[0118] First, the data processing module (910) is a module that collects, refines, and integrates all business trip-related data, and can standardize data from various sources and manage and guarantee data quality.

[0119] The data processing module (910) may include an ETL submodule (911), a quality control submodule (912), and a data warehouse (913).

[0120] The ETL submodule (911) is responsible for extracting and transforming data, performing quality verification, and loading the quality-verified data into a data warehouse (913).

[0121] The ETL submodule (911) can extract data from various sources such as ERP, electronic approval, and accounting systems, convert and refine the extracted data into a standardized format, and load the refined data into a data warehouse (913).

[0122] The quality control submodule (912) verifies data accuracy, can detect and correct errors, and can monitor quality indicators.

[0123] The quality control submodule (912) can verify the accuracy, completeness, and consistency of the data, detect and correct missing data and erroneous data, and measure and manage data quality metrics.

[0124] The data warehouse (913) plays a role in systematically storing and managing refined data, maintaining data structures for multidimensional analysis, and performing version control of historical data.

[0125] Next, the analysis reporting module (920) is a module that analyzes collected data and derives insights, and can perform multidimensional analysis and generate customized reports.

[0126] The analysis reporting module (920) may include an analysis execution submodule (921), a report generation submodule (922), and an analysis engine (923).

[0127] The analysis execution submodule (921) executes the analysis model and generates results, and can identify trends and patterns and perform predictive analysis.

[0128] The analysis execution submodule (921) can perform business trip pattern analysis and cost optimization analysis. In addition, the analysis execution submodule (921) can execute a prediction model to predict future trends, detect abnormal signs, and analyze the causes.

[0129] The report generation submodule (922) can visualize analysis results by configuring a customized dashboard and can automatically generate periodic reports.

[0130] The report generation submodule (922) configures a customized dashboard for each user, can automatically generate regular / irregular analysis reports, and can provide visualized analysis results.

[0131] The analysis engine (923) can execute statistical analysis and machine learning models, discover patterns through data mining, and process OLAP (Online analytical processing) cubes for multidimensional analysis.

[0132] FIG. 10 illustrates an AI-based business trip planning optimization method in one embodiment of the present invention.

[0133] FIG. 10 illustrates the entire process of the core modules for AI-based business trip planning optimization (intelligent rule processing engine (200), adaptive cost optimization engine (300), variation response process engine (400), and integrated data analysis engine (500)).

[0134] Referring to FIG. 10, the AI-based business trip planning optimization method according to the present invention can support a business trip planning process, a business trip execution and monitoring process, a change response process, a business trip completion and settlement process, etc.

[0135] The business trip planning process can request cost optimization and historical data analysis for business trip application information entered by the user, and provide the user with an optimized cost plan based on the analysis results.

[0136] The business trip execution and monitoring process can request compliance verification as a user's business trip is executed and perform real-time monitoring based on the results of the compliance verification.

[0137] The change response process can establish and propose alternative solutions when changes related to business trips occur.

[0138] The business trip completion and settlement process allows for the overall settlement, including cost settlement and compliance verification, once the completion of a business trip is reported.

[0139] FIGS. 11 and 12 illustrate a peripheral module process for AI-based business trip planning optimization in an embodiment of the present invention.

[0140] As illustrated in FIGS. 11 and 12, the AI-based business trip planning optimization system (intelligent rule processing engine (200), adaptive cost optimization engine (300), change response process engine (400), and integrated data analysis engine (500)) can perform business trip planning and approval processes, business trip reservation and expense processing processes, real-time monitoring and change management processes, business trip completion and settlement processes, and data synchronization and analysis processes through integration with enterprise ERP systems, electronic approval systems, reservation systems, accounting systems, data warehouses, etc.

[0141] Accordingly, according to the embodiments of the present invention, by implementing an AI-based hybrid decision-making system, an advanced decision-making framework can be established by combining the advantages of traditional rule-based systems and machine learning technologies. Furthermore, optimal performance can be achieved through the harmonization of rule-based stability and AI-based flexibility, and the accuracy and efficiency of the system can be automatically improved through continuous learning.

[0142] Furthermore, according to embodiments of the present invention, a real-time monitoring and response system capable of immediately responding to changes in the situation can be established through a real-time adaptive process, changes can be immediately detected and processed through an event-based architecture, and preemptive response through predictive analysis can be enabled to minimize risk.

[0143] Furthermore, according to embodiments of the present invention, by establishing an integrated data analysis system, it is possible to perform comprehensive analysis by integrating data from various sources, derive optimal analysis results by effectively combining real-time data processing and batch processing, and maximize the ability to derive insights by applying advanced analysis techniques.

[0144] Furthermore, according to embodiments of the present invention, as a cost optimization effect, innovative reduction of total costs related to business trips is possible, budget waste can be prevented through prediction-based proactive cost management, and labor cost reduction effects can be created through automated processes.

[0145] In addition, according to embodiments of the present invention, in terms of operational efficiency, manual processing time can be drastically shortened to significantly improve work efficiency, the error rate can be reduced to minimize costs incurred due to rework, and system operating costs can be reduced through an integrated management system.

[0146] Furthermore, according to embodiments of the present invention, the return on investment (ROI) can be maximized to enable the recovery of investment costs within a relatively short period after introduction, long-term cost reduction effects can be created through continuous efficiency improvement, and the total cost of ownership (TCO) can be reduced by minimizing maintenance costs.

[0147] Furthermore, according to embodiments of the present invention, a flexible architecture can be provided that is designed with a modular structure in terms of system scalability, making it easy to add new functions and expand into various business areas, and supports a cloud environment, enabling flexible adjustment of the system scale.

[0148] Furthermore, according to embodiments of the present invention, the structure facilitates the application of the latest AI / ML technologies in terms of technical scalability, enables integration with various technology stacks through an open architecture, and facilitates linkage with external systems through an API-based design.

[0149] Furthermore, according to embodiments of the present invention, in terms of business scalability, it is possible to expand into various business areas other than business trip management, enable multilingual / multicurrency processing to support a global business environment, and provide a flexible structure that allows for the application of various regulations and policies.

[0150] In addition, according to embodiments of the present invention, learning time can be minimized by providing a user-friendly UI / UX as an intuitive interface, access is possible anytime and anywhere by fully supporting a mobile environment, and necessary information can be checked immediately through a customized dashboard.

[0151] In addition, according to embodiments of the present invention, the burden on users can be reduced by automatically applying complex regulations and policies through automated business processing, work efficiency can be maximized by automating repetitive tasks, and decision-making can be supported through smart recommendation functions.

[0152] In addition, according to embodiments of the present invention, all business trip-related tasks can be processed on a single platform through an integrated management environment, important information can be received immediately through a real-time notification function, and the status can be easily assessed through a comprehensive reporting function.

[0153] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0154] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0155] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Additionally, the medium may be various recording or storage means in the form of a single or several hardware combined, and may not be limited to a medium directly connected to a computer system but may exist distributed over a network. Examples of media may 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 media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0156] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0157] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for optimizing an AI-based business trip plan for a computer device comprising at least one processor, the method comprising: a step of digitizing and managing business trip-related regulations and policies of a company by the at least one processor; a step of performing rule-based automatic decision-making on a business trip request by the at least one processor; and a step of analyzing and optimizing business trip-related costs for the business trip request by the at least one processor. Claim 2 In claim 1, the managing step comprises an AI-based business trip planning optimization method that converts business trip-related regulations and policies into a standardized form and defines the relationships between rules. Claim 3 In claim 1, the managing step comprises verifying the validity of newly defined or modified rules and detecting whether there is a conflict between rules, an AI-based business trip planning optimization method. Claim 4 In claim 1, the step of performing the above includes a step of verifying the execution result based on rule-based decision-making, an AI-based business trip planning optimization method. Claim 5 In claim 1, the step of performing the above includes the step of identifying and applying relevant rules to the business trip request, but detecting exceptional situations where rule application is impossible and applying alternative rules, in an AI-based business trip planning optimization method. Claim 6 In claim 1, the optimizing step comprises the step of analyzing all cost elements related to business trip for the business trip request, an AI-based business trip planning optimization method. Claim 7 In claim 1, the optimizing step comprises the step of collecting real-time price information and historical data, structuring and storing them, in an AI-based business trip planning optimization method. Claim 8 In claim 1, the optimizing step comprises the step of determining the optimal reservation time for the business trip request and deriving the optimal solution by comparing and analyzing reservation options, an AI-based business trip planning optimization method. Claim 9 In claim 1, the optimization step comprises the step of executing a prediction model for cost optimization based on real-time data and updating the prediction results, an AI-based business trip planning optimization method. Claim 10 The AI-based business trip planning optimization method according to claim 1, further comprising the step of detecting business trip-related changes occurring in real time by at least one processor and processing them by assigning priorities. Claim 11 In claim 10, the processing step comprises an AI-based business trip planning optimization method that evaluates the risk regarding the changes related to the business trip and suggests alternative options. Claim 12 An AI-based business trip planning optimization method according to claim 1, further comprising the step of analyzing business trip-related data and deriving relevant insights by the at least one processor. Claim 13 In claim 12, the deriving step comprises the step of extracting and converting data from multiple sources and loading it into a data warehouse, an AI-based business trip planning optimization method. Claim 14 In claim 12, the deriving step comprises an AI-based business trip planning optimization method that includes the step of performing business trip pattern and cost optimization analysis and predicting future trends through a prediction model. Claim 15 A computer device comprising at least one processor implemented to execute readable commands on a computer device, wherein the at least one processor processes the process of digitizing and managing business travel-related regulations and policies of an enterprise; the process of performing rule-based automatic decision-making regarding business travel requests; the process of analyzing and optimizing business travel-related costs regarding business travel requests; the process of detecting business travel-related changes occurring in real time and performing a response to the changes; and the process of analyzing business travel-related data to derive relevant insights.

Images