KR20230050010A - Bus lines assessment system based on digital twin - Google Patents

Abstract

The present invention relates to a bus line assessment system based on digital twin which provides a response defined based on a pre-prepared assessment indicator for a query input to assess bus lines for each stakeholder (i.e., bus users, bus operators, bus operation management institutions, local civil organizations related to bus line assessment, etc.) in relation to bus line assessment through machine learning using big data based on a current operating environment and new operating environment changing differently from the current operating environment, under a digital twin bus operating environment equivalent to the current bus operating environment including road maps having real bus lines formed and traffic facilities. When a response to a query for bus line assessment for each stakeholder in relation to bus line assessment is provided according to the present invention, an optimized bus line policy decision can be made by reflecting assessment opinions of all stakeholders, and in particular, the system can be utilized in an optimized bus line policy decision by easily performing minor simulations for minor bus lines under a new operating environment changing differently from the current operating environment. The system comprises a big data DB for learning, a traffic digital twin model, and a bus line assessing the digital twin model.

Description

{Bus lines assessment system based on digital twin}

The present invention relates to a bus route evaluation system, and more particularly, to a digital twin-based bus route evaluation system.

When determining a bus route policy for a specific region, reflect the evaluation opinions of all interested parties related to the bus route (e.g., bus users, bus operators, bus operator management organizations, local community groups related to bus route evaluation, etc.) in advance There is a difficult problem.

For example, bus users tend to value bus usage time, bus usage cost, and bus convenience, bus operators tend to value business profitability, and bus operator management organizations or local community groups related to bus route evaluation Since there is a tendency to place importance on the optimization of bus routes, it is difficult to determine bus route policies by reflecting the evaluation opinions of all stakeholders related to bus routes.

The above problems become a fundamental cause of continuously causing dissatisfaction of interested parties after bus route policy is decided.

KR 10-2223800 B1

The present invention is to solve the above conventional problems, and an object of the present invention is the current operation under the digital twin bus operating environment having equivalence with the current bus operating environment including road maps and traffic facilities in which actual bus routes are formed. Through machine learning using environment-based big data and new operating environment-based big data that changes differently from the current operating environment, stakeholders related to bus route evaluation (e.g., bus users, bus operators, bus operating company management agencies, bus routes It is to suggest an optimal alternative by providing a digital twin-based bus route evaluation system that provides defined responses based on pre-prepared evaluation indicators to queries entered for bus route evaluation by evaluation-related local community groups, etc.).

In order to achieve the object of the present invention as described above, the digital twin-based bus route evaluation system according to the present invention, the current bus route collected under the current bus operating environment including the road map and traffic facilities in which the actual bus route is formed Relevant data and actual traffic situation data collected under the current bus operating environment are stored as big data based on the current operating environment used as big data for learning to provide answers to bus route evaluation queries, and as a result of simulation of the traffic digital twin model The collected new bus route-related data and new traffic situation-related data are stored as new operating environment-based big data that is used as big data for learning to provide responses to bus route evaluation queries, and the current operating environment-based big data stored as big data for learning a big data DB for learning that manages update and deletion of data and big data based on the new operating environment; Under the digital twin bus operating environment having equivalence with the current bus operating environment including the road map and traffic facilities in which the actual bus route is formed, the current operating environment-based big data is used for building a traffic digital twin, and the current operating environment is used. A traffic digital twin model designed to perform a simulation to collect new bus route-related data and new traffic situation-related data under a new operating environment that changes differently from the environment; And a bus route evaluation digital twin that provides answers defined based on previously prepared evaluation indicators to queries input for bus route evaluation through machine learning using the current operating environment-based big data and the new operating environment-based big data. It is characterized in that it consists of; model.

In the digital twin-based bus route evaluation system according to the present invention, the traffic digital twin model collects new bus route-related data and new traffic situation-related data for local bus routes under a new operating environment that is changed differently from the current operating environment. It is characterized in that it performs a local simulation that does.

In the digital twin-based bus route evaluation system according to the present invention, the bus route evaluation digital twin model provides a customized user interface for query input and response confirmation for bus route evaluation for each interested party related to bus route evaluation. to be

In the digital twin-based bus route evaluation system according to the present invention, the bus route evaluation digital twin model has a function to respond to all queries and response performance within a few seconds to minutes, and the digital twin bus operating environment is an actual bus route It is characterized in that it has an accuracy within the operating environment and a predetermined error range.

In the digital twin-based bus route evaluation system according to the present invention, the bus route evaluation digital twin model is characterized in that it provides a response to a query for bus route evaluation by utilizing graph machine learning.

According to the present invention, when responses are provided to questions for bus route evaluation for each interested party related to bus route evaluation, it is possible to determine an optimized bus route policy by reflecting the evaluation opinions of all interested parties, especially unlike the current operating environment. Local simulation of local bus routes can be easily performed under a new operating environment that is changed and used to determine optimized bus route policies.

1 is an embodiment showing the configuration of a digital twin-based bus route evaluation system according to the present invention.
Figure 2 is a chart showing the form of questions and evaluation indicators related to bus routes for each interested party according to the present invention.
3 is an embodiment showing a response to a query provided as a graph machine learning result of a bus route evaluation digital twin model.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings.

The digital twin-based bus route evaluation system according to the present invention described below is not limited to the following embodiments, and anyone with ordinary knowledge in the relevant technical field without departing from the subject matter of the technology claimed in the claims It has the technical spirit to the extent that it can be implemented by changing it.

Referring to FIG. 1, the digital twin-based bus route evaluation system 100 according to the present invention includes a learning big data DB 110, a traffic digital twin model 120, and a bus route evaluation digital twin model 130. do.

The digital twin-based bus route evaluation system 100 according to the present invention can be installed in the cloud for determining a bus route policy for a specific area.

The big data DB 110 for learning includes data related to current bus routes collected under the current bus operating environment including traffic facilities and road maps where actual bus routes are formed, and data related to actual traffic conditions collected under the current bus operating environment. Stored as big data based on the current operating environment used as learning big data to provide responses to bus route evaluation queries, and new bus route-related data and new traffic conditions collected as a result of the simulation of the traffic digital twin model 120 Save the data as new operating environment-based big data that is used as big data for learning to provide answers to questions about bus route evaluation.

It is preferable to understand that the big data DB 110 for learning is a database system that manages update and deletion of the big data based on the current operating environment and the big data based on the new operating environment stored as big data for learning.

The traffic digital twin model 120 converts the big data based on the current driving environment into the traffic digital twin bus operating environment having equivalence with the current bus operating environment including road maps and traffic facilities in which actual bus routes are formed. It is designed to be used for twin construction and to perform simulation to collect new bus route-related data and new traffic situation-related data under a new operating environment that is changed differently from the current operating environment.

The traffic digital twin model 120 may perform local simulation to collect new bus route-related data and new traffic condition-related data for local bus routes under a new operating environment that is changed differently from the current operating environment.

The traffic digital twin model 120 is manufactured using Digital Twin technology, and is a simulation model that includes a computer processor, a memory unit (or memory unit), an input device, an output device, etc., and is mounted on a computing device. (or program), and the computing device is preferably capable of wired or wireless communication with an external device.

The bus route evaluation digital twin model 130 is based on evaluation indicators prepared in advance for queries input for bus route evaluation through machine learning using the current operating environment-based big data and the new operating environment-based big data. Provides a defined response.

For reference, in the diagram shown in FIG. 2, users (e.g., bus users), operators (e.g., bus operators), managers (e.g., bus operator management organizations), and social groups (e.g., bus operators), who are interested parties related to bus route evaluation, For local community organizations related to bus route evaluation), examples of bus route-related question forms and evaluation indexes according to each person's understanding point of view are given.

The bus route evaluation digital twin model 130 queries for bus route evaluation for each interested party related to bus route evaluation (eg, bus users, bus operators, bus operator management organizations, bus route evaluation related local community groups, etc.) Provide customized user interfaces for input and response confirmation (eg, interfaces for bus users, interfaces for bus operators, interfaces for bus operator management agencies, interfaces for community groups related to bus route evaluation, etc.).

The bus route evaluation digital twin model 130 has a function of responding to all queries (eg, q queries) and response performance within several seconds to minutes, and the digital twin bus operating environment is determined from the actual bus route operating environment. It is desirable to have an accuracy within an error range (eg, a%).

The bus route evaluation digital twin model 130 provides a response to a query for bus route evaluation using graph machine learning.

The bus route evaluation digital twin model 130 is manufactured using Digital Twin technology, and includes a computer processor, a memory unit (or storage unit), an input device, an output device, etc., and is mounted on a computing device. It is preferable to understand it as a simulation model (or program), and it is preferable that the computing device is capable of wired or wireless communication with an external device.

In the digital twin-based bus route evaluation system 100 according to the present invention, the digital twin technology used in the traffic digital twin model 120 and the bus route evaluation digital twin model 130 provides dynamic analysis in real time. By performing simulation using a digital twin model that maintains the sameness and consistency as possible real physical model or real sensor information model, future phenomena such as real physical model or real sensor information model are predicted and real physical model or real sensor information model It is known as a technology that can control.

The digital twin-based bus route evaluation system 100 according to the present invention configured as described above operates as follows.

Before determining the bus route policy for a specific region, the learning big data DB (110) is the current bus route-related data collected under the current bus operating environment including the road map and traffic facilities in which the actual bus route is formed. (e.g., bus user's transportation card usage information, information provided by bus operating companies, information provided by bus operating company management organizations, information provided by local community groups related to bus route evaluation, etc.) and information collected under the current bus operating environment The data related to actual traffic conditions is stored as big data based on the current operating environment, which is used as big data for learning to provide answers to questions about bus route evaluation.

The big data based on the current operating environment stored in the learning big data DB 110 can be updated or deleted as needed when determining a bus route policy.

As described above, once the big data based on the current operating environment is stored, the traffic digital twin model 120 has a digital twin bus having equivalence with the current bus operating environment including the road map and traffic facilities in which the actual bus route is formed. Under the operating environment, the current operating environment-based big data is used for building a traffic digital twin, and a simulation is performed to collect new bus route-related data and new traffic situation-related data under a new operating environment that changes differently from the current operating environment. .

For example, the traffic digital twin model 120 provides new bus route-related data and new data under a new operating environment, such as changing the signal system of a bus route differently from the current operating environment or installing a dedicated bus lane, in order to determine a bus route policy. Simulations can be performed to collect data related to traffic conditions.

In particular, at this time, the traffic digital twin model 120 uses new bus route-related data and new traffic situation-related data for a local bus route selected from among all bus routes for a specific region under a new operating environment that is changed differently from the current operating environment. It is possible to perform a local simulation to collect

As described above, after new bus route-related data and new traffic situation-related data are collected as a result of the simulation of the traffic digital twin model 120, the new big data manager 130 performs the new bus route-related data and new traffic data. Situation-related data is stored as new operating environment-based big data that is used as big data for learning to provide answers to questions about bus route evaluation.

The new operating environment-based big data stored in the new big data manager 130 can be updated or deleted as necessary when determining a bus route policy.

After the new operating environment-based big data is stored as described above, the bus route evaluation digital twin model 130 is digitally equivalent to the current bus operating environment including road maps and traffic facilities in which actual bus routes are formed. Under the twin bus operating environment, answers defined based on previously prepared evaluation indicators are provided to queries input for bus route evaluation through machine learning using the current operating environment-based big data and the new operating environment-based big data. .

FIG. 3 shows that the bus route evaluation digital twin model 130, prior to policy decision on the Jeju Island bus route, is used by stakeholders related to the bus route evaluation (e.g., bus users, bus operators, bus operator management organizations, bus route evaluations). Relevant local community organizations, etc.) after inputting an inquiry for the evaluation of the corresponding bus route, and then immediately providing a response to the inquiry within a few seconds or within a few minutes is an embodiment.

In FIG. 3, the section (or link) of the bus route is indicated by alphabets, and the response defined based on the evaluation index prepared in advance utilizes a 10-point scale method to understand each section (or link) of the bus route by interested parties. Satisfaction was expressed as a number.

In this case, the bus route evaluation digital twin model 130 is a customized user interface (eg, interface for bus users, interface for bus operators, bus operation It is desirable to provide interfaces for business management agencies, interfaces for local community groups related to bus route evaluation, etc.).

As described above, if responses to questions for bus route evaluation are provided for each interested party related to bus route evaluation according to an embodiment of the present invention, it is possible to determine an optimized bus route policy by reflecting the evaluation opinions of all interested parties. .

In particular, according to an embodiment of the present invention, local simulation for a local bus route selected from among all bus routes for a specific region can be easily performed under a new operating environment that changes differently from the current operating environment, and can be used to determine an optimized bus route policy. there is.

100: Digital twin-based bus route evaluation system
110: Big data DB for learning
120: Transportation digital twin model
130: Bus route evaluation digital twin model

Claims (5)

The current bus route-related data collected under the current bus operating environment, including road maps and traffic facilities where actual bus routes are formed, and actual traffic situation-related data collected under the current bus operating environment are provided in response to bus route evaluation queries. Provides new bus route-related data and new traffic situation-related data collected as a result of simulation of the traffic digital twin model (120) in response to bus route evaluation queries. Learning big data DB (110 )and;
Under the digital twin bus operating environment having equivalence with the current bus operating environment including the road map and traffic facilities in which the actual bus route is formed, the current operating environment-based big data is used for building a traffic digital twin, and the current operating environment is used. A traffic digital twin model 120 designed to perform a simulation to collect new bus route-related data and new traffic situation-related data under a new operating environment that changes differently from the environment; and
A bus route evaluation digital twin model that provides defined responses based on pre-prepared evaluation indicators to queries input for bus route evaluation through machine learning using the current operating environment-based big data and the new operating environment-based big data. (130);
Digital twin-based bus route evaluation system, characterized in that consisting of. The method of claim 1, wherein the traffic digital twin model 120 performs local simulation to collect new bus route-related data and new traffic situation-related data for local bus routes under a new operating environment that is changed differently from the current operating environment. Digital twin-based bus route evaluation system, characterized in that. The method of claim 1, wherein the bus route evaluation digital twin model 130 is based on digital twin, characterized in that it provides a customized user interface for query input and response confirmation for bus route evaluation for each interested party related to bus route evaluation. Bus route evaluation system. The method of claim 1, wherein the bus route evaluation digital twin model 130 has a function of responding to all queries and a response performance within several seconds to several minutes, and the digital twin bus operating environment has a predetermined error with the actual bus route operating environment. Digital twin-based bus route evaluation system, characterized in that it has accuracy within the range. The digital twin-based bus route evaluation system according to claim 1, wherein the bus route evaluation digital twin model (130) provides a response to a query for bus route evaluation by utilizing graph machine learning.

Images