JP7670549B2 - Digital twin analysis device, digital twin analysis system, digital twin analysis method, and program - Google Patents

Description

This disclosure relates to a digital twin analysis device, a digital twin analysis system, a digital twin analysis method, and a program.

In recent years, there has been a movement to utilize data while reducing the cost of acquiring data by using external data, including open data. Patent Document 1 discloses a technology for generating a simulation model of a power system, including a model that reproduces each of a number of subsystems included in the power system, based on data on electrical quantities in each of the subsystems, and for executing a simulation based on the collected data and the simulation model.

JP 2019-154201 A

However, the data obtained from an external source used in the invention described in Patent Document 1 may not meet the desired performance or reliability due to differences in the design philosophy of the digital twin, etc. It is also possible that the reliability of the data itself is low. This poses the problem that errors and delays in judgment may occur in the digital twin if there are deficiencies in the external data. When using other data, a mechanism is required to use data with high performance, reliability, and reliability compared to the data to be used.

One example of the objective of the present disclosure is to provide a digital twin analysis device that makes it possible to stabilize the operation of a digital twin even when using data obtained from an external source.

The digital twin analysis device of the present invention in one aspect of the present disclosure includes a data receiving means for receiving input of data to be analyzed, an evaluation index storage means for storing an evaluation index for evaluating the accuracy of the data received by the data receiving means, a data evaluation means for evaluating the accuracy of the received data based on the evaluation index stored in the evaluation index storage means, a data analysis means for performing analysis using data selected based on the accuracy evaluated by the data evaluation means, and an output means for outputting the results of the analysis by the data analysis means.

A digital twin analysis system according to one aspect of the present disclosure includes a sensor unit, a digital twin analysis device, and a control unit that controls the system based on the results of analysis by the digital twin analysis device. The digital twin analysis device includes a data reception means that receives input of data acquired from the sensor unit, an evaluation index storage means that stores an evaluation index for evaluating the accuracy of the data received by the data reception means, a data evaluation means that evaluates the accuracy of the received data based on the evaluation index stored in the evaluation index storage means, a data analysis means that performs analysis using data selected based on the accuracy evaluated by the data evaluation means, and an output means that outputs the results of the analysis by the data analysis means.

In one aspect of the digital twin analysis method of the present disclosure, a computer receives input of data to be analyzed, evaluates the accuracy of the received data based on stored evaluation indicators, performs analysis using data selected based on the evaluated accuracy, and outputs the analyzed results.

A program in one aspect of the present disclosure causes a computer to execute a process of accepting input of data to be analyzed, a process of evaluating the accuracy of the accepted data based on stored evaluation indices, a process of analyzing using data selected based on the evaluated accuracy, and a process of outputting the analysis results.

One example of the effect of this invention is that it stabilizes the operation of the digital twin even when using data obtained from an external source.

FIG. 1 is a block diagram showing the configuration of a digital twin analysis device in the first embodiment. FIG. 2 is a diagram showing a hardware configuration in which a digital twin analysis device in the first embodiment is realized by a computer device and its peripheral devices. FIG. 3 is a diagram illustrating an example of data stored in a storage device in the first embodiment. FIG. 4 is a diagram showing an example of evaluation indexes stored in the evaluation index storage unit in the first embodiment. FIG. 5 is a diagram showing an example of a database relating to data sources in the first embodiment. FIG. 6 is a flowchart showing the operation of the first embodiment. FIG. 7 is a block diagram showing the configuration of the second embodiment. FIG. 8 is a flowchart showing the operation of the second embodiment. FIG. 9 is a flowchart showing the operation of the second embodiment. FIG. 10 is a block diagram showing a configuration of a modified example of the second embodiment. FIG. 11 is a diagram illustrating an example of data stored in a storage device in the modified example of the second embodiment. FIG. 12 is a diagram showing an example of evaluation indexes stored in the evaluation index storage unit in the modified example of the second embodiment.

Next, the embodiment will be described in detail with reference to the drawings.

[First embodiment]
Fig. 1 is a block diagram showing the configuration of a digital twin analysis device 100 according to a first embodiment. The digital twin analysis device 100 shown in Fig. 1 includes a data receiving unit 101, an evaluation index storage unit 102, a data evaluation unit 103, a data analysis unit 104, and an output unit 105.

FIG. 2 is a diagram showing an example of a hardware configuration in which the digital twin analysis device 100 in the first embodiment of the present disclosure is realized by a computer device 500 including a processor. As shown in FIG. 2, the digital twin analysis device 100 includes a CPU (Central Processing Unit) 501, memories such as a ROM 502 and a RAM 503, a storage device 505 such as a hard disk that stores a program 504, a communication I/F (Interface) 508 for network connection, and an input/output interface 511 for inputting and outputting data. In addition, the digital twin analysis device 100 is connected to an input device 509 and an output device 510 via a bus 512. In this embodiment, the data reception unit 101 receives the data to be analyzed via the communication I/F (Interface) 508 for network connection.

The CPU 501 runs an operating system to control the entire digital twin analysis device 100 according to the first embodiment. The CPU 501 also reads programs and data from a recording medium 506 mounted in, for example, a drive device 507 into memory. The CPU 501 also functions as part of the data receiving unit 101, evaluation index storage unit 102, data evaluation unit 103, data analysis unit 104, and output unit 105 in the first embodiment, and executes processing or commands in the flowchart shown in FIG. 6, which will be described later, based on the program.

The recording medium 506 is, for example, an optical disk, a flexible disk, a magnetic optical disk, an external hard disk, or a semiconductor memory card. The semiconductor memory card, which is part of the recording medium, is a non-volatile storage device in which the program is recorded. The program may also be downloaded from an external computer (not shown) that is connected to a communication network.

The input device 509 is realized, for example, by a mouse, a keyboard, built-in key buttons, etc., and is used for input operations. The input device 509 is not limited to a mouse, a keyboard, or built-in key buttons, but may be, for example, a touch panel. The output device 510 is realized, for example, by a display, and is used to check the output.

As described above, the first embodiment shown in FIG. 1 is realized by the computer hardware shown in FIG. 2. However, the means for realizing each part of the digital twin analysis device 100 in FIG. 1 is not limited to the configuration described above. In addition, the digital twin analysis device 100 may be realized by a single physically combined device, or may be realized by two or more physically separated devices connected by wire or wirelessly. For example, the input device 509 and the output device 510 may be connected to the computer device 500 via a network.

The data reception unit 101 is a means for receiving input of data to be analyzed by the digital twin analysis device 100 and storing it in the storage device 505. The data received as input by the data reception unit 101 is, for example, sensor data obtained by detecting a signal from an external sensor or analyzing an image from an external camera. The data reception unit 101 inputs sensor data acquired from a sensor used for analysis at regular intervals (for example, every 30 minutes), links the sensor data to information accompanying the sensor data, and stores the data in the storage device 505. FIG. 3 is a diagram showing an example of data stored in the data reception unit 101. As shown in FIG. 3, for example, the data reception unit 101 links the sensor data to an evaluation flag, acquisition date and time, generation date and time, category, data source, and sensor data, and stores the sensor data in the storage device 505. The evaluation flag is set to ON for data evaluated as having accuracy by the data evaluation unit 103 described later, and set to OFF for data evaluated as not having accuracy by the data evaluation unit 103. When storing sensor data in the storage device 505, the evaluation flag is stored as OFF. The acquisition date and time indicates the date and time when the sensor data was obtained, and the generation date and time indicates the date and time when the sensor data was generated. The category indicates the classification of the data, such as power demand, weather information, or power supply, and the data source indicates the name of the organization that sensed the data or generated the data.

The evaluation index storage unit 102 is a means for storing an evaluation index for evaluating the accuracy of the received data. The evaluation index can be set based on, for example, the generation interval, the range of sensor data, the maximum difference of sensor data, the existence time of sensor data, or the reliability of sensor data. The generation interval is the difference between the generation time of acquired sensor data and the generation time of previously acquired sensor data, and if the generation interval is within a predetermined time, it is evaluated as having accuracy, and if the generation interval is longer than the predetermined time, it is evaluated as not having accuracy. FIG. 4 is a diagram showing an example of the evaluation index stored in the evaluation index storage unit 102. As shown in FIG. 4, in the case of sensor data being weather information such as temperature, humidity, or illuminance, for example, the generation interval is within 10 minutes, so the evaluation index is the difference between the generation time of acquired sensor data and the generation time of previously acquired sensor data, and if the generation interval is within 10 minutes, it is evaluated as having accuracy of the data, and if the generation interval is longer than 10 minutes, it is evaluated as not having accuracy of the data. In addition, the range of sensor data is an index of the range of values that the sensor data can take, which is set in advance, and if the sensor data is within the range of possible values, it is evaluated as having accuracy, and if the sensor data is outside the range of possible values, it is evaluated as not having accuracy. The maximum difference of sensor data is calculated by taking the difference between the acquired sensor data and the sensor data acquired last time. If it is within a preset maximum difference, it is evaluated as having accuracy, and if it is greater than the maximum difference, it is evaluated as not having accuracy. The existence time of sensor data is calculated by taking the difference between the time the sensor data was generated and the current time. If it is within a preset existence time, it is evaluated as having accuracy, and if it is greater than the existence time, it is evaluated as not having accuracy. The reliability of sensor data is calculated by statistically processing the frequency of past sensor data with or without accuracy, and if the ratio of cases where there is accuracy is higher than a preset value, it is evaluated as having accuracy, and if the ratio of cases where there is accuracy is lower than the set value, it is evaluated as not having accuracy.

The evaluation index can also be set according to the evaluation level of the data source. The evaluation level of the data source is primary data if the data is directly obtained from the sensor, and secondary data if another system utilizes data sensed by the sensor. The evaluation index storage unit 102 can evaluate the accuracy of the data source according to the evaluation level, for example, by determining whether the acquired sensor data is primary data or not. FIG. 5 is a diagram showing an example of a database related to a data source. As shown in FIG. 5, the database uses the name of the sensing institution (ministry, organization, company, etc.) as a key, and stores the registration date and time. For example, the sensor data received by the data receiving unit 101 may be compared with the data source stored in the database of the data source, and if the difference is less than a certain value, it may be evaluated as having accuracy, and if the difference is more than a certain value, it may be evaluated as not having accuracy. However, the evaluation index used in this embodiment is not limited to these.

The data evaluation unit 103 is a means for evaluating the accuracy of the received data based on the evaluation index stored in the evaluation index storage unit 102. When data to be analyzed is input from the data receiving unit 101, the data evaluation unit 103 refers to the evaluation index storage unit 102 and determines whether the accuracy of the data is higher than the evaluation index. If the data evaluation unit 103 determines that the accuracy of the data is higher than the evaluation index, it evaluates the data as accurate data and turns on a flag linked to the data stored in the storage device 505. On the other hand, if the data evaluation unit 103 determines that the data is equal to or lower than the evaluation index, it evaluates the data as inaccurate data and turns off a flag linked to the data stored in the storage device 505.

The data analysis unit 104 is a means for performing analysis using data selected based on the accuracy evaluated by the data evaluation unit 103. The data analysis unit 104 performs analysis using only data that has been evaluated as having accuracy by the data evaluation unit 103. When the data analysis unit 104 detects that an operation to start data analysis has been performed from the input device 509, it refers to the storage device 505 and performs data analysis using a digital twin using data for which a flag linked to the data is on. The data analysis unit 104 does not use data for which the flag is off in the data analysis using a digital twin.

Here, an example of an analysis method performed by the data analysis unit 104 will be described, but the analysis method performed in this embodiment is not limited to this. The data analysis unit 104 executes a simulation of the system to be applied using digital twin technology in a virtual space. A digital twin is a solution for predicting what will happen in the real space by collecting information acquired in real time and reproducing a situation that may actually occur in a virtual space such as a computer using technology such as AI (Artificial Intelligence) and executing a simulation. In this embodiment, an analysis is performed by reproducing in a virtual space what may occur when the control contents of an operating system are executed in the real space, and executing a simulation. Next, the data analysis unit 104 outputs the analysis results to the output unit 105.

The output unit 105 is a means for outputting the results of the analysis performed by the data analysis unit 104. When the analysis results are input from the data analysis unit 104, the output unit 105 displays information about the analysis results so that the information can be confirmed via the output device 510 or the like. The output unit 105 may transmit information about the analysis results to a system that requires the information.

The operation of the digital twin analysis device 100 configured as described above will be explained with reference to the flowchart in Figure 6.

Figure 6 is a flowchart showing an overview of the operation of the digital twin analysis device 100 in the first embodiment. Note that the processing according to this flowchart may be executed based on program control by the processor described above.

As shown in FIG. 6, first, the data reception unit 101 receives and stores the input of data to be analyzed (step S101). Next, the data evaluation unit 103 evaluates the accuracy of the received data based on the evaluation index stored in the evaluation index storage unit 102 (step S102). Here, when the accuracy of the data is higher than the evaluation index by referring to the evaluation index storage unit 102 (step S103; YES), the data evaluation unit 103 turns on the evaluation flag linked to the data stored by the data reception unit 101 (step S104). On the other hand, when the accuracy of the data is lower than the evaluation index by referring to the evaluation index storage unit 102 (step S103; NO), the data evaluation unit 103 turns off the evaluation flag linked to the data stored by the data reception unit 101 (step S105). Next, the data analysis unit 104 performs analysis using only the data evaluated to be accurate by the data evaluation means (step S106). And finally, the output unit 105 outputs the result analyzed by the data analysis unit 104 (step S107). This completes the digital twin analysis device 100's status information management operations.

Next, the effects of the first embodiment of the present disclosure will be described. The digital twin analysis device 100 in the above-described embodiment can provide a digital twin analysis device or the like that makes it possible to stabilize the operation of a digital twin even when using data acquired from an external source. The reason for this is that if the accuracy of the data is higher than the evaluation index by the data evaluation unit 103, the data is evaluated as having accuracy and is used when analyzing the digital twin. On the other hand, if the accuracy of the data is equal to or lower than the evaluation index, the data is evaluated as not having accuracy and is not used when analyzing the digital twin. By having the data analysis unit 104 use only the sensor data evaluated as having accuracy by the data evaluation unit 103 for analysis, errors in data analysis by the digital twin analysis device 100 can be reduced and erroneous judgments and erroneous control can be suppressed.

[Second embodiment]
Next, a second embodiment of the present disclosure will be described in detail with reference to the drawings. Below, to the extent that the description of this embodiment is not unclear, the description of the contents that overlap with the above description will be omitted. The second embodiment is a power system control system including a digital twin analysis device 110.

FIG. 7 is a block diagram showing the configuration of a power system control system 11 equipped with a digital twin analysis device 110 according to a second embodiment of the present disclosure. Referring to FIG. 7, the power system control system 11 in this embodiment includes a sensor unit 210, a digital twin analysis device 110, and a power generation adjustment unit 310. The digital twin analysis device 110 is significantly different from the digital twin analysis device 100 of the first embodiment in that it includes a data management unit 114 and a data control unit 116 instead of the output unit 105. The description of the same parts as in the first embodiment will be omitted, and the second embodiment will be described focusing on the different parts. The digital twin analysis device 110 according to the second embodiment includes a data reception unit 111, an evaluation index storage unit 112, a data evaluation unit 113, a data management unit 114, a data analysis unit 115, and a data control unit 116. The data stored in the storage device 505 by the data reception unit 111 in this embodiment is the data shown in FIG. 3. The data stored in the evaluation index storage unit 112 is the data shown in FIG. 4.

In the power system control system 11 of this embodiment, in addition to the digital twin analysis device 110, the external sensor unit 210 is composed of a demand sensor 211 that senses power usage data and meteorological information data, a supply sensor 212 that senses the amount of power supply, and a power generation amount adjustment unit 310 that controls the amount of power generation. The demand sensor 211 collects power usage data from a smart meter that senses the amount of power usage installed in each home. The demand sensor 211 also collects meteorological information such as temperature and weather related to the demand for power using a temperature sensor, a humidity sensor, an illuminance sensor, etc. These data collected by the demand sensor 211 are stored in the storage device 505 by the data reception unit 111. The supply sensor 212 also detects the amount of power generated and supplied by the power plant, and the data of the detected supply amount is stored in the storage device 505 by the data reception unit 111. The power generation amount adjustment unit 310 is configured to control a system for adjusting the amount of power generation in the power plant.

In this embodiment, the digital twin analysis device 110 predicts the amount of electricity demand based on information obtained from the demand sensor 211, and also takes into account the amount of supply obtained from the supply sensor 212, and calculates the amount of electricity required through analysis by the data analysis unit 115, and the data control unit 116 controls the power generation adjustment unit 310 based on the calculated result.

Specifically, the data analysis unit 115 uses a neural network, graph AI, or other machine learning algorithm to generate a trained model showing the relationship between the sensor data obtained from the sensor unit 210 acquired as training data and the required amount of power, which is a result showing the correct label of the training data. When performing learning, the data analysis unit 115, for example, receives sensor data to be analyzed from the data reception unit 111, and optimizes the model by verifying the trained model for the required amount of power, and generates a virtual space by a digital twin. Next, the data analysis unit 115 calculates the required amount of power using the trained model corresponding to the combination of the supply and demand data acquired from the demand sensor 211 and the supply sensor 212 and the required amount of power. As described above, the data analysis unit 115 trains the model using the virtual space by the digital twin and calculates the required amount of power. However, the method of calculating the required amount of power by the data analysis unit 115 in this embodiment is not limited to this.

Furthermore, in addition to the functions and operations of the data evaluation unit 103 in the first embodiment, the data evaluation unit 113 in this embodiment differs in that it reevaluates the accuracy of the data stored in the storage device 505 before the data analysis unit 115 analyzes the data. Then, it outputs the presence or absence of accuracy to the data management unit 114. Then, the data analysis unit 115 performs analysis using only data that has been evaluated as having accuracy through the reevaluation. The analysis operations performed by the data analysis unit 115 are similar to the analysis operations of the data analysis unit 104 in the first embodiment, and therefore will not be described here.

In addition, in this embodiment, the data management unit 114 is a means for managing the data stored in the data storage means based on the accuracy evaluated by the data evaluation means. When the data management unit 114 receives information from the data evaluation unit 113 that the data is accurate, it leaves the data stored in the storage device 505 saved. When the data management unit 114 acquires information that belongs to the same category as data already stored in the storage device 505, it updates the data to be stored. On the other hand, when the data management unit 114 receives information from the data evaluation unit 113 that the data is not accurate, it deletes the data stored in the storage device 505.

The components in each embodiment of the present disclosure described above can be implemented not only as hardware components, but also as program-controlled computers and firmware, as in the computer device shown in FIG. 2.

Next, the operation of the power system control system 11 will be described with reference to the flowcharts shown in Figures 8 and 9. Note that the processing according to these flowcharts may also be executed based on program control by the CPU described above.

Figure 8 is a flowchart showing an overview of the operation of digital twin analysis (receiving input of sensor data) in the power system control system 11 in the second embodiment. As shown in Figure 8, first, the data receiving unit 111 receives and stores the input of data to be analyzed (step S201). Next, the data evaluation unit 113 evaluates the accuracy of the received data based on the evaluation index stored in the evaluation index storage unit 112 (step S202). Here, when the accuracy of the data is higher than the evaluation index by referring to the evaluation index storage unit 112 (step S203; YES), the data evaluation unit 113 evaluates that the data is accurate and ends the flow. On the other hand, when the accuracy of the data is lower than the evaluation index by referring to the evaluation index storage unit 112 (step S203; NO), the data evaluation unit 113 evaluates that the data is not accurate, and the data management unit 114 deletes the stored data (step S204), and ends the flow.

FIG. 9 is a flowchart showing an overview of the operation (data analysis) of digital twin analysis in the power system control system 11 in the second embodiment. As shown in FIG. 9, the data evaluation unit 113 evaluates the accuracy of the data before the data analysis unit 115 analyzes the data. Here, the data evaluation unit 113 refers to the evaluation index storage unit 112 and if the accuracy of the data is higher than the evaluation index (step S205; YES), it evaluates that the data is accurate, and the data analysis unit 115 performs analysis using the data (step S206). On the other hand, the data evaluation unit 113 refers to the evaluation index storage unit 112 and if the accuracy of the data is equal to or lower than the evaluation index (step S205; NO), it evaluates that the data is inaccurate, and the data management unit 114 deletes the data and ends the flow (step S207). Next, the data control unit 116 controls the system based on the analysis result of the data analysis unit 115 (step S208). With the above, the power system control system 11 ends the operation of power system control.

Next, the effects of the second embodiment of the present disclosure will be described. In this embodiment, even when the system is closed within its own system, such as a power system control system, the operation of the system can be stabilized by evaluating the accuracy (authenticity) of the sensor data. Furthermore, in the second embodiment, before the data analysis unit 115 analyzes the data, the accuracy of the data stored in the storage device 505 is reevaluated. This further improves the accuracy of the data used in the digital twin analysis device, making it possible to provide a digital twin analysis device 110 with stable operation.

Furthermore, in the second embodiment, when the data management unit 114 receives information from the data evaluation unit 113 that the data is not accurate, the data management unit 114 deletes the data stored in the storage device 505. This makes it possible to prevent a large amount of sensor data from accumulating in the storage device 505. Note that the data management unit 114 may delete the data after a certain period of time has passed, rather than deleting the data immediately after receiving the information from the data evaluation unit 113 that the data is not accurate.
[Modification of the second embodiment]
Next, a modified example of the second embodiment of the present disclosure will be described in detail with reference to the drawings. Below, to the extent that the description of this embodiment is not unclear, the description of the contents that overlap with the above description will be omitted. The second embodiment is a traffic congestion alleviation system equipped with a digital twin analysis device 120. The digital twin analysis device 120 has the same configuration and function as the above-mentioned digital twin analysis device 110, but has a different external sensor unit and system to which it is applied. FIG. 10 is a block diagram showing the configuration of a traffic congestion alleviation system 12 equipped with a digital twin analysis device 120 according to a modified example of the second embodiment of the present disclosure. Referring to FIG. 10, the traffic congestion alleviation system 12 in this embodiment includes a sensor unit 220, a digital twin analysis device 120, and a traffic light control unit 320. The digital twin analysis device 120 in this embodiment includes a data reception unit 121, an evaluation index storage unit 122, a data evaluation unit 123, a data management unit 124, a data analysis unit 125, and a data control unit 126.

In the traffic congestion alleviation system 12 in this embodiment, in addition to the digital twin analysis device 120, the external sensor unit 220 is composed of a traffic volume sensor 221, a parking lot sensor 222, and a traffic light control unit 320 to be controlled. The traffic volume sensor 221 is a sensor that senses traffic volume, and if there are multiple organizations sensing traffic volume, it is composed of multiple traffic volume sensors. For example, one traffic volume sensor 221 is a traffic volume sensor managed by the Ministry of Land, Infrastructure, Transport and Tourism, and the other traffic volume sensor 221 is a traffic volume sensor provided by a private company such as NEXCO. The parking lot sensor 222 is, for example, a sensor that senses the full or empty status of a parking lot in a city. The data input by the data reception unit 121 is not limited to data from the sensor, and may also include, for example, processed data analyzed from sensor data held by an external digital twin. The traffic light control unit 320 is part of a system that controls traffic lights in a city, and can control traffic lights installed in the city using digital twin technology.

In this embodiment, the digital twin analysis device 120 uses sensor data acquired from the traffic volume sensor 221 and the parking lot sensor 222 to detect cars arriving at an intersection and calculate the traffic volume. Based on the calculated traffic volume, the data control unit 126 controls the traffic light control unit 320 in real time to control the traffic lights and prevent sudden traffic congestion. In addition to controlling a single traffic light, it is thought that traffic congestion can be further alleviated by detecting the traffic volume of the entire city and controlling the traffic lights of the entire city. In other words, a system can be conceived in which the traffic network and traffic lights of the entire city are modeled using a digital twin, the current traffic volume is captured as sensor data, and the traffic lights are controlled to alleviate traffic congestion in the entire city. This embodiment can be applied as a system that alleviates traffic congestion in the entire city by reproducing the traffic network and traffic lights of the entire city in a virtual space using a digital twin.

FIG. 11 is a diagram showing an example of data stored in the storage device 505 in a modified example of the second embodiment. In FIG. 11, data in the category of traffic volume is data acquired by the traffic volume sensor 221, and data in the category of parking lot is data acquired by the parking lot sensor 222. The data receiving unit 121 inputs the sensor data and information associated with the sensor data as shown in FIG. 11 from the traffic volume sensor 221 and the parking lot sensor 222, and stores them in the storage device 505.

12 is a diagram showing an example of evaluation indices stored in the evaluation index storage unit 122 in a modified example of the second embodiment. As shown in FIG. 12, the data whose category is traffic volume is data whose evaluation index for evaluating accuracy is "generation interval of 5 minutes or less". The data whose category is parking lot is data whose evaluation index for evaluating accuracy is "generation interval of 30 minutes or less". The data evaluation unit 123 evaluates the accuracy of the data stored in the evaluation index storage unit 122 and assigns on (ON) or off (OFF) to the evaluation flag. The data management unit 124 manages the data stored in the storage device 505 based on the accuracy evaluated by the data evaluation unit 123. That is, the data management unit 124 deletes data evaluated by the data evaluation unit 123 as not being accurate. In addition, when the data management unit 124 acquires information belonging to the same category as data already stored in the storage device 505, it updates the data to be stored. The data analysis unit 125 performs data analysis by using only data that satisfies these evaluation indices when analyzing the digital twin. The data control unit 126 controls the traffic light control unit 320 based on the results calculated by the data analysis unit 125.

As in the present embodiment described above, even when applied to a system that controls traffic lights in a city, the operation of the system can be stabilized by evaluating the accuracy of the sensor data. The invention according to this embodiment also works effectively when using sensor data from other sensor systems and other digital twin systems other than those described above, and can stabilize the operation of the system.

The present invention has been described above with reference to each embodiment, but the present invention is not limited to the above-mentioned embodiment. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

For example, although multiple operations are described in sequence in the form of a flow chart, the order of description does not limit the order in which the multiple operations are performed. Therefore, when implementing each embodiment, the order of the multiple operations can be changed to the extent that does not interfere with the content. For example, in the modified example of the second embodiment described above, the data control unit 126 controls the traffic light control unit 320 based on the results calculated by the data analysis unit 125, but the results calculated by the data analysis unit 125 may be distributed as traffic congestion forecast information to a website or car navigation device for users who are traveling by car within the city.

100, 110, 120 Digital twin analysis device 101, 111, 121 Data reception unit 102, 112, 122 Evaluation index storage unit 103, 113, 123 Data evaluation unit 104, 115, 125 Data analysis unit 105 Output unit 114, 124 Data management unit 116, 126 Data control unit 210, 220 Sensor unit

Claims (8)

A data receiving means for receiving an input of data to be analyzed;
an evaluation index storage means for storing an evaluation index for evaluating the accuracy of the data received by the data receiving means;
a data evaluation means for evaluating the accuracy of the received data based on the evaluation index stored in the evaluation index storage means;
a data analysis means for performing an analysis using the data selected based on the accuracy evaluated by the data evaluation means;
an output means for outputting the results of the analysis by the data analysis means;
Including,
A digital twin analysis device , wherein the evaluation index is set based on an evaluation level by a data source . The digital twin analysis device according to claim 1, wherein the data analysis means performs analysis using only the data that is evaluated as having accuracy by the data evaluation means. The digital twin analysis device according to claim 1 or 2, wherein the data evaluation means evaluates the data as having accuracy if the evaluation index of the data is higher than the evaluation index stored in the evaluation index storage means, and evaluates the data as having no accuracy if the evaluation index of the data is equal to or lower than the evaluation index stored in the evaluation index storage means. The digital twin analysis apparatus according to any one of claims 1 to 3 , further comprising: a data control means for controlling an operating system based on the results of analysis by the data analysis means. The data receiving means stores the input data,
A data management unit that manages the data stored by the data reception unit based on the accuracy evaluated by the data evaluation unit,
The digital twin analysis device according to any one of claims 1 to 4 , wherein the data management unit deletes data that is evaluated by the data evaluation means as having no accuracy from the data stored by the data receiving means. A sensor unit;
Digital twin analysis equipment and
A control unit that controls a system based on the results of analysis by the digital twin analysis device,
The digital twin analysis device includes a data receiving means for receiving input of data acquired from the sensor unit;
an evaluation index storage means for storing an evaluation index for evaluating the accuracy of the data received by the data receiving means;
a data evaluation means for evaluating the accuracy of the received data based on the evaluation index stored in the evaluation index storage means;
a data analysis means for performing an analysis using the data selected based on the accuracy evaluated by the data evaluation means;
output means for outputting the results of the analysis performed by the data analysis means;
A digital twin analysis system , wherein the evaluation index is set based on an evaluation level by a data source . The computer
Accepts input of data for analysis;
Evaluating the accuracy of the received data based on the stored evaluation index;
performing an analysis using the data selected based on the assessed accuracy;
A digital twin analysis method for outputting the analyzed results,
A digital twin analysis method , wherein the evaluation index is set based on an evaluation level by a data source . A process for accepting input of data for analysis;
evaluating the accuracy of the received data based on the stored evaluation index;
performing an analysis using the data selected based on the assessed accuracy;
A process of outputting the analyzed results;
A program for causing a computer to execute the following:
The evaluation index is set based on an evaluation level by a data source .

Images