Data rationality verification method, system and storage medium based on semantic integrity

Abstract

The present invention discloses a data rationality verification method, system and storage medium based on semantic integrity, which constructs a city simulation model based on digital twins; obtains dynamic data and static data in the model; extracts data based on relationships, entities and attributes of the dynamic data and static data based on the CNN semantic analysis algorithm, builds a graph based on the extracted data to form a city knowledge graph; obtains model data in real time within a preset time period, performs data classification and data integrity calculation analysis on the model data based on the city knowledge graph, and obtains data integrity and data rationality; generates a data adjustment plan based on the data integrity and data rationality. The present invention can make full use of the semantic information in the model, verify data consistency and integrity, and improve the accuracy and stability of the model.

Description

Technical Field

[0001] The present invention relates to the field of data analysis, and more specifically, to a method, system and storage medium for verifying data rationality based on semantic integrity. Background Art

[0002] With the development of information technology, digital twin technology is gaining widespread application across various fields, providing a bridge between the physical and digital worlds. However, because digital twin system models involve diverse and complex data, accurately and efficiently verifying the rationality of model data and ensuring that it accurately reflects the state of the physical world has always been a challenge facing the industry. Especially in complex environments such as urban infrastructure construction, data consistency and accuracy play a decisive role in the effectiveness of the model.

[0003] Therefore, there is an urgent need for a data rationality verification method based on semantic integrity. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and proposes a data rationality verification method, system and storage medium based on semantic integrity.

[0005] A first aspect of the present invention provides a method for verifying data rationality based on semantic integrity, comprising:

[0006] Build a city simulation model based on digital twins;

[0007] Obtaining dynamic data and static data in the model;

[0008] Based on the CNN semantic analysis algorithm, the dynamic data and static data are extracted based on relationships, entities, and attributes, and a graph is constructed based on the extracted data to form a city knowledge graph;

[0009] Within a preset time period, the model data is acquired in real time, and the model data is subjected to data classification and data integrity calculation and analysis based on the city knowledge graph to obtain data integrity and data rationality;

[0010] A data adjustment plan is generated based on the data integrity and data rationality.

[0011] In this solution, the construction of a city simulation model based on digital twins is specifically as follows:

[0012] Obtain the target city's area, outline, transportation roads, and infrastructure information;

[0013] Perform visual modeling based on the city information to form a city model;

[0014] Conduct digital twin-based traffic simulation analysis based on city information and build a digital twin-based traffic model;

[0015] The city model and the traffic model are integrated to form a city simulation model based on visualization and digital twins.

[0016] In this solution, the acquisition of dynamic data and static data in the model is specifically as follows:

[0017] Obtain urban dynamic data through monitoring devices in the target city;

[0018] Based on the urban simulation model, obtain urban static data;

[0019] The urban static data includes the scale, shape, and location information of urban roads, urban tunnels, and urban platforms;

[0020] The dynamic data includes traffic flow, pedestrian flow, vehicle type statistics, pedestrian flow distribution, and vehicle distribution information on various roads in the city.

[0021] In this solution, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic and static data, and a graph is constructed based on the extracted data to form a city knowledge graph. The previous steps include:

[0022] Build a semantic analysis model based on CNN algorithm;

[0023] Obtain historically collected city data from the system database;

[0024] Dividing the historically collected city data into a training data set, a validation data set, and a test data set according to a preset ratio;

[0025] The training data set, the validation data set, and the test data set are imported into the semantic analysis model for cyclic training until the semantic analysis accuracy reaches a preset accuracy.

[0026] In this solution, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic and static data, and a graph is constructed based on the extracted data to form a city knowledge graph. Specifically,

[0027] Acquiring the dynamic data and static data;

[0028] Integrating the dynamic data with the static data to form city monitoring data;

[0029] Converting the city monitoring data into text data format to obtain text big data;

[0030] The text big data is segmented by a word segmentation method based on HMM, the segmented text big data is imported into a semantic analysis model for semantic analysis, and data extraction based on relationships, entities, and attributes is performed according to semantic relationships to obtain relationship data, entity data, and attribute data;

[0031] Semantic relationship analysis is performed based on the relationship data, entity data, and attribute data, and a city knowledge graph is constructed based on the graph structure.

[0032] In this solution, within a preset time period, model data is acquired in real time, and data classification and data integrity calculation and analysis based on the city knowledge graph are performed on the model data to obtain data integrity and data rationality, specifically:

[0033] Obtain model data in real time within a preset time period;

[0034] The model data includes city dynamic data and city static data;

[0035] Convert the model data into text data format and perform word segmentation processing to obtain real-time text data;

[0036] Importing the real-time text data into a semantic analysis model to perform relationship, entity, and attribute analysis, and obtaining entity, relationship, and attribute data of the real-time text data;

[0037] Importing the entities, relationships, and attribute data of the real-time text data into the city knowledge graph, performing retrieval and analysis based on the entity data, and obtaining the completeness of the entity data and the corresponding missing entity data;

[0038] Based on the relationship between real-time text data, the relationship between attribute data and urban knowledge graph, and the attribute data, comparative analysis is performed and data rationality verification is performed to obtain data rationality and abnormal data areas.

[0039] In this solution, the data adjustment solution is generated based on the data integrity and data rationality, specifically:

[0040] Obtain information on city mission analysis needs;

[0041] Convert urban task analysis demand information into text data and import it into the semantic analysis model for semantic analysis to obtain task demand data reports;

[0042] The task demand data report includes the demand data type and demand data priority information corresponding to the city task analysis demand information;

[0043] According to the task requirement data report, completeness and corresponding missing entity data, data rationality and abnormal data area, a regulation analysis of missing data and abnormal data is performed on each entity data in the model data, and a priority analysis of the requirement data is performed in combination with the task requirement data report to obtain a regulation plan for missing data and abnormal data.

[0044] A second aspect of the present invention further provides a data rationality verification system based on semantic integrity, the system comprising: a memory and a processor, wherein the memory includes a data rationality verification program based on semantic integrity, and when the data rationality verification program based on semantic integrity is executed by the processor, the following steps are implemented:

[0045] Build a city simulation model based on digital twins;

[0046] Obtaining dynamic data and static data in the model;

[0047] Based on the CNN semantic analysis algorithm, the dynamic data and static data are extracted based on relationships, entities, and attributes, and a graph is constructed based on the extracted data to form a city knowledge graph;

[0048] Within a preset time period, the model data is acquired in real time, and the model data is subjected to data classification and data integrity calculation and analysis based on the city knowledge graph to obtain data integrity and data rationality;

[0049] A data adjustment plan is generated based on the data integrity and data rationality.

[0050] In this solution, the construction of a city simulation model based on digital twins is specifically as follows:

[0051] Obtain the target city's area, outline, transportation roads, and infrastructure information;

[0052] Perform visual modeling based on the city information to form a city model;

[0053] Conduct digital twin-based traffic simulation analysis based on city information and build a digital twin-based traffic model;

[0054] The city model and the traffic model are integrated to form a city simulation model based on visualization and digital twins.

[0055] The third aspect of the present invention also provides a computer-readable storage medium, which includes a data rationality verification program based on semantic integrity. When the data rationality verification program based on semantic integrity is executed by a processor, the steps of the data rationality verification method based on semantic integrity as described in any one of the above items are implemented.

[0056] The present invention discloses a data rationality verification method, system and storage medium based on semantic integrity, which constructs a city simulation model based on digital twins; obtains dynamic data and static data in the model; extracts data based on relationships, entities and attributes of the dynamic data and static data based on the CNN semantic analysis algorithm, builds a graph based on the extracted data to form a city knowledge graph; obtains model data in real time within a preset time period, performs data classification and data integrity calculation analysis on the model data based on the city knowledge graph, and obtains data integrity and data rationality; generates a data adjustment plan based on the data integrity and data rationality. The present invention can make full use of the semantic information in the model, verify data consistency and integrity, and improve the accuracy and stability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flowchart of a method for verifying data rationality based on semantic integrity according to the present invention is shown;

[0058] Figure 2 Shows a flow chart of constructing a city simulation model according to the present invention;

[0059] Figure 3 The flowchart of constructing the semantic analysis model of the present invention is shown;

[0060] Figure 4 A block diagram of a data rationality verification system based on semantic integrity of the present invention is shown. DETAILED DESCRIPTION

[0061] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0063] Figure 1 A flow chart of a method for verifying data rationality based on semantic integrity according to the present invention is shown.

[0064] like Figure 1 As shown, the first aspect of the present invention provides a data rationality verification method based on semantic integrity, comprising:

[0065] S102, building a city simulation model based on digital twins;

[0066] S104, obtaining dynamic data and static data in the model;

[0067] S106, extracting data based on relationships, entities, and attributes from the dynamic data and static data based on a CNN semantic analysis algorithm, and constructing a graph based on the extracted data to form a city knowledge graph;

[0068] S108, within a preset time period, acquiring model data in real time, performing data classification and data integrity calculation and analysis on the model data based on the city knowledge graph, and obtaining data integrity and data rationality;

[0069] S110: Generate a data adjustment plan based on the data integrity and data rationality.

[0070] Figure 2 The flowchart of building the city simulation model of the present invention is shown.

[0071] According to an embodiment of the present invention, the construction of a city simulation model based on digital twins is specifically as follows:

[0072] S202, obtaining the area, outline, transportation roads, and infrastructure information of the target city;

[0073] S204, performing visual modeling based on the city information to form a city model;

[0074] S206, performing traffic simulation analysis based on the digital twin according to the city information, and constructing a traffic model based on the digital twin;

[0075] S208: Fusing the city model with the traffic model to form a city simulation model based on visualization and digital twins.

[0076] It should be noted that the city model is specifically used for data visualization of the target city. The model includes a map model, and the traffic model is specifically used for data processing and analysis. The two complement each other to realize the model functions of visualization and digital twins.

[0077] According to an embodiment of the present invention, the obtaining of dynamic data and static data in the model is specifically as follows:

[0078] Obtain urban dynamic data through monitoring devices in the target city;

[0079] Based on the urban simulation model, obtain urban static data;

[0080] The urban static data includes the scale, shape, and location information of urban roads, urban tunnels, and urban platforms;

[0081] The dynamic data includes traffic flow, pedestrian flow, vehicle type statistics, pedestrian flow distribution, and vehicle distribution information on various roads in the city.

[0082] It should be noted that the urban platforms are various transportation hubs within the city, such as train stations and high-speed rail stations. The pedestrian and vehicle flow data can reflect the city's traffic conditions. The dynamic data is collected from various urban roads, including urban roads, urban tunnels, and roads on urban platforms. The monitoring devices include video surveillance and pedestrian and vehicle flow monitoring equipment distributed throughout the city.

[0083] Figure 3 The flowchart of constructing the semantic analysis model of the present invention is shown.

[0084] According to an embodiment of the present invention, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic data and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, which includes:

[0085] S302, constructing a semantic analysis model based on the CNN algorithm;

[0086] S304, obtaining historically collected city data from the system database;

[0087] S306, dividing the historically collected city data into a training data set, a validation data set, and a test data set according to a preset ratio;

[0088] S308: Import the training data set, the validation data set, and the test data set into the semantic analysis model for cyclic training until the semantic analysis accuracy reaches a preset accuracy.

[0089] It should be noted that the historically collected urban data is standardized and includes both dynamic and static data, which is used to train semantic models. Among semantic analysis algorithms, CNN is a self-learning and highly intelligent model algorithm that enables accurate semantic analysis and knowledge extraction from text.

[0090] According to an embodiment of the present invention, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic data and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, specifically:

[0091] Acquiring the dynamic data and static data;

[0092] Integrating the dynamic data with the static data to form city monitoring data;

[0093] Converting the city monitoring data into text data format to obtain text big data;

[0094] The text big data is segmented by a word segmentation method based on HMM, the segmented text big data is imported into a semantic analysis model for semantic analysis, and data extraction based on relationships, entities, and attributes is performed according to semantic relationships to obtain relationship data, entity data, and attribute data;

[0095] Semantic relationship analysis is performed based on the relationship data, entity data, and attribute data, and a city knowledge graph is constructed based on the graph structure.

[0096] It should be noted that entities are the core data in the city knowledge graph, and there are certain relationships between entities, which can be analyzed and displayed through the knowledge graph. In addition, the city knowledge graph can be used to verify and analyze data in real time. By importing real-time data into the knowledge graph, the rationality and integrity of the data can be analyzed.

[0097] According to an embodiment of the present invention, within a preset time period, model data is acquired in real time, and data classification and data integrity calculation and analysis based on the city knowledge graph are performed on the model data to obtain data integrity and data rationality, specifically:

[0098] Obtain model data in real time within a preset time period;

[0099] The model data includes city dynamic data and city static data;

[0100] Convert the model data into text data format and perform word segmentation processing to obtain real-time text data;

[0101] Importing the real-time text data into a semantic analysis model to perform relationship, entity, and attribute analysis, and obtaining entity, relationship, and attribute data of the real-time text data;

[0102] Importing the entities, relationships, and attribute data of the real-time text data into the city knowledge graph, performing retrieval and analysis based on the entity data, and obtaining the completeness of the entity data and the corresponding missing entity data;

[0103] Based on the relationship between real-time text data, the relationship between attribute data and urban knowledge graph, and the attribute data, comparative analysis is performed and data rationality verification is performed to obtain data rationality and abnormal data areas.

[0104] It should be noted that the word segmentation process is generally based on the HMM word segmentation method. The entity data-based retrieval and analysis is specifically performed by comparing and searching the entity data of the real-time text data with the entity data in the knowledge graph, and calculating the completeness of the missing entity data. If there is missing entity data, the completeness is less than 100%. For example, in the knowledge graph, there are multiple entities, namely total platform flow, platform passenger flow, and platform vehicle flow. In the knowledge graph, total platform flow is first-level data, and platform passenger flow and platform vehicle flow are second-level data. The first-level data and second-level data are data inclusion relationships. When the entity data of the real-time text data only has the total platform flow and platform passenger flow entities, it means that the corresponding second-level entity "platform vehicle flow" data is missing. In addition, the second-level data may also have the next level of data depending on the actual situation. For example, in the platform vehicle flow, there is also third-level entity data corresponding to vehicle type, vehicle number, etc. The abnormal data area is the data area between two entity data with unreasonable data relationships. This area is the data address mapping area in the real-time text data. The abnormal data area can be used to find out which data relationships have abnormalities. For example, in a real-time data collection, the city's traffic flow data, vehicle type data, vehicle quantity data, and vehicle distribution data are collected. In the knowledge graph, traffic flow data is included in vehicle type data, vehicle quantity data, and vehicle distribution data, and has a certain data relationship. However, in actual data collection, due to the diversity and complexity of the data, the final data relationship may be different (not conforming to the relationship model in the knowledge graph). Directly importing real-time data with abnormal relationships into the city simulation model for simulation analysis will produce abnormal data results. Therefore, the present invention can further quickly retrieve abnormal data relationships by constructing a city knowledge graph and using it for data verification of relationships and attributes, thereby analyzing the rationality of the data and making data adjustments or re-collection.

[0105] In real-time urban data collection, there may be problems with the data processing sequence or the data conversion process, or there may be data anomalies or loss. The present invention can achieve rapid data verification through precise analysis of the knowledge graph, further improve the verification efficiency of real-time data, reduce data errors and anomalies, improve the efficiency of urban model data analysis and improve the robustness of the program.

[0106] According to an embodiment of the present invention, generating a data adjustment plan based on the data integrity and data rationality is specifically:

[0107] Obtain information on city mission analysis needs;

[0108] Convert urban task analysis demand information into text data and import it into the semantic analysis model for semantic analysis to obtain task demand data reports;

[0109] The task demand data report includes the demand data type and demand data priority information corresponding to the city task analysis demand information;

[0110] According to the task requirement data report, completeness and corresponding missing entity data, data rationality and abnormal data area, a regulation analysis of missing data and abnormal data is performed on each entity data in the model data, and a priority analysis of the requirement data is performed in combination with the task requirement data report to obtain a regulation plan for missing data and abnormal data.

[0111] It should be noted that the city task analysis requirements are acquired in real time and generally include tasks such as vehicle flow analysis, pedestrian flow analysis, and vehicle traffic load analysis. These are specifically set by the user. Different task analysis requirements correspond to different data requirements and different data priorities. The priority reflects the importance of a certain data to the city task analysis requirements. The missing data and abnormal data generally overlap with the required data. This overlapping data is the data object that is focused on regulation, and the data can be prioritized for regulation and analysis based on the priority. The regulation scheme can achieve data consistency regulation.

[0112] The construction of the city knowledge graph further includes:

[0113] Acquiring the dynamic data and static data;

[0114] Calculate the data volume difference between dynamic data and static data;

[0115] Based on the semantic analysis model, entity data is extracted from dynamic data and static data respectively to obtain static entity data and dynamic entity data;

[0116] Through the urban simulation model, the data correlation between static entity data and dynamic entity data in task demand analysis is analyzed;

[0117] If the data volume difference is greater than a first preset value and the data relevance is greater than a second preset value, knowledge graphs are constructed based on the dynamic data and the static data respectively to form two corresponding knowledge graph structures;

[0118] The two knowledge graph structures are integrated to form a city knowledge graph.

[0119] It should be noted that the dynamic data and static data are the urban dynamic data and urban static data in the present invention. The data correlation refers to the joint use of static data and dynamic data during the normal task requirement analysis and data processing of the urban simulation model. The higher the data correlation, the higher the correlation analysis required for static data and dynamic data to meet the task requirements. The lower the data correlation, the relatively independent dynamic data and static data in the model analysis, and the correlation requirements are not high. It is worth mentioning that when conducting urban task analysis, it is often necessary to jointly analyze dynamic data and static data to meet the analysis requirements. The first and second preset values ​​are set by the user.

[0120] In the present invention, by analyzing the correlation between dynamic data and static data (data volume difference and data association), it is determined whether it is necessary to perform separate graph analysis on dynamic data and static data, and two knowledge graphs are obtained in the knowledge graph, corresponding to static data and dynamic data. When performing real-time model data analysis subsequently, data verification analysis can be performed separately in the corresponding two knowledge graphs for real-time static data and dynamic data, thereby improving the verification accuracy of model data and reducing the verification time cost. Although the complexity of the knowledge graph is increased to a certain extent, it can effectively improve the accuracy of model analysis in complex urban model analysis.

[0121] In addition, for simpler urban models, unified semantic analysis and knowledge graph construction can be performed by integrating or fusing dynamic data with static data.

[0122] Figure 4 A block diagram of a data rationality verification system based on semantic integrity of the present invention is shown.

[0123] A second aspect of the present invention further provides a data rationality verification system 4 based on semantic integrity, the system comprising: a memory 41 and a processor 42, wherein the memory comprises a data rationality verification program based on semantic integrity, and when the data rationality verification program based on semantic integrity is executed by the processor, the following steps are implemented:

[0124] Build a city simulation model based on digital twins;

[0125] Obtaining dynamic data and static data in the model;

[0126] Based on the CNN semantic analysis algorithm, the dynamic data and static data are extracted based on relationships, entities, and attributes, and a graph is constructed based on the extracted data to form a city knowledge graph;

[0127] Within a preset time period, the model data is acquired in real time, and the model data is subjected to data classification and data integrity calculation and analysis based on the city knowledge graph to obtain data integrity and data rationality;

[0128] A data adjustment plan is generated based on the data integrity and data rationality.

[0129] According to an embodiment of the present invention, the construction of a city simulation model based on digital twins is specifically as follows:

[0130] Obtain the target city's area, outline, transportation roads, and infrastructure information;

[0131] Perform visual modeling based on the city information to form a city model;

[0132] Conduct digital twin-based traffic simulation analysis based on city information and build a digital twin-based traffic model;

[0133] The city model and the traffic model are integrated to form a city simulation model based on visualization and digital twins.

[0134] It should be noted that the city model is specifically used for data visualization of the target city. The model includes a map model, and the traffic model is specifically used for data processing and analysis. The two complement each other to realize the model functions of visualization and digital twins.

[0135] According to an embodiment of the present invention, the obtaining of dynamic data and static data in the model is specifically as follows:

[0136] Obtain urban dynamic data through monitoring devices in the target city;

[0137] Based on the urban simulation model, obtain urban static data;

[0138] The urban static data includes the scale, shape, and location information of urban roads, urban tunnels, and urban platforms;

[0139] The dynamic data includes traffic flow, pedestrian flow, vehicle type statistics, pedestrian flow distribution, and vehicle distribution information on various roads in the city.

[0140] It should be noted that the urban platforms are various transportation hubs within the city, such as train stations and high-speed rail stations. The pedestrian and vehicle flow data can reflect the city's traffic conditions. The dynamic data is collected from various urban roads, including urban roads, urban tunnels, and roads on urban platforms. The monitoring devices include video surveillance and pedestrian and vehicle flow monitoring equipment distributed throughout the city.

[0141] According to an embodiment of the present invention, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic data and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, which includes:

[0142] Build a semantic analysis model based on CNN algorithm;

[0143] Obtain historically collected city data from the system database;

[0144] Dividing the historically collected city data into a training data set, a validation data set, and a test data set according to a preset ratio;

[0145] The training data set, the validation data set, and the test data set are imported into the semantic analysis model for cyclic training until the semantic analysis accuracy reaches a preset accuracy.

[0146] It should be noted that the historically collected urban data is standardized and includes both dynamic and static data, which is used to train semantic models. Among semantic analysis algorithms, CNN is a self-learning and highly intelligent model algorithm that enables accurate semantic analysis and knowledge extraction from text.

[0147] According to an embodiment of the present invention, the CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic data and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, specifically:

[0148] Acquiring the dynamic data and static data;

[0149] Integrating the dynamic data with the static data to form city monitoring data;

[0150] Converting the city monitoring data into text data format to obtain text big data;

[0151] The text big data is segmented by a word segmentation method based on HMM, the segmented text big data is imported into a semantic analysis model for semantic analysis, and data extraction based on relationships, entities, and attributes is performed according to semantic relationships to obtain relationship data, entity data, and attribute data;

[0152] Semantic relationship analysis is performed based on the relationship data, entity data, and attribute data, and a city knowledge graph is constructed based on the graph structure.

[0153] It should be noted that entities are the core data in the city knowledge graph, and there are certain relationships between entities, which can be analyzed and displayed through the knowledge graph. In addition, the city knowledge graph can be used to verify and analyze data in real time. By importing real-time data into the knowledge graph, the rationality and integrity of the data can be analyzed.

[0154] According to an embodiment of the present invention, within a preset time period, model data is acquired in real time, and data classification and data integrity calculation and analysis based on the city knowledge graph are performed on the model data to obtain data integrity and data rationality, specifically:

[0155] Obtain model data in real time within a preset time period;

[0156] The model data includes city dynamic data and city static data;

[0157] Convert the model data into text data format and perform word segmentation processing to obtain real-time text data;

[0158] Importing the real-time text data into a semantic analysis model to perform relationship, entity, and attribute analysis, and obtaining entity, relationship, and attribute data of the real-time text data;

[0159] Importing the entities, relationships, and attribute data of the real-time text data into the city knowledge graph, performing retrieval and analysis based on the entity data, and obtaining the completeness of the entity data and the corresponding missing entity data;

[0160] Based on the relationship between real-time text data, the relationship between attribute data and urban knowledge graph, and the attribute data, comparative analysis is performed and data rationality verification is performed to obtain data rationality and abnormal data areas.

[0161] It should be noted that the word segmentation process is generally based on the HMM word segmentation method. The entity data-based retrieval and analysis is specifically performed by comparing and searching the entity data of the real-time text data with the entity data in the knowledge graph, and calculating the completeness of the missing entity data. If there is missing entity data, the completeness is less than 100%. For example, in the knowledge graph, there are multiple entities, namely total platform flow, platform passenger flow, and platform vehicle flow. In the knowledge graph, total platform flow is first-level data, and platform passenger flow and platform vehicle flow are second-level data. The first-level data and second-level data are data inclusion relationships. When the entity data of the real-time text data only has the total platform flow and platform passenger flow entities, it means that the corresponding second-level entity "platform vehicle flow" data is missing. In addition, the second-level data may also have the next level of data depending on the actual situation. For example, in the platform vehicle flow, there is also third-level entity data corresponding to vehicle type, vehicle number, etc. The abnormal data area is the data area between two entity data with unreasonable data relationships. This area is the data address mapping area in the real-time text data. The abnormal data area can be used to find out which data relationships have abnormalities. For example, in a real-time data collection, the city's traffic flow data, vehicle type data, vehicle quantity data, and vehicle distribution data are collected. In the knowledge graph, traffic flow data is included in vehicle type data, vehicle quantity data, and vehicle distribution data, and has a certain data relationship. However, in actual data collection, due to the diversity and complexity of the data, the final data relationship may be different (not conforming to the relationship model in the knowledge graph). Directly importing real-time data with abnormal relationships into the city simulation model for simulation analysis will produce abnormal data results. Therefore, the present invention can further quickly retrieve abnormal data relationships by constructing a city knowledge graph and using it for data verification of relationships and attributes, thereby analyzing the rationality of the data and making data adjustments or re-collection.

[0162] In real-time urban data collection, there may be problems with the data processing sequence or the data conversion process, or there may be data anomalies or loss. The present invention can achieve rapid data verification through precise analysis of the knowledge graph, further improve the verification efficiency of real-time data, reduce data errors and anomalies, improve the efficiency of urban model data analysis and improve the robustness of the program.

[0163] According to an embodiment of the present invention, generating a data adjustment plan based on the data integrity and data rationality is specifically:

[0164] Obtain information on city mission analysis needs;

[0165] Convert urban task analysis demand information into text data and import it into the semantic analysis model for semantic analysis to obtain task demand data reports;

[0166] The task demand data report includes the demand data type and demand data priority information corresponding to the city task analysis demand information;

[0167] According to the task requirement data report, completeness and corresponding missing entity data, data rationality and abnormal data area, a regulation analysis of missing data and abnormal data is performed on each entity data in the model data, and a priority analysis of the requirement data is performed in combination with the task requirement data report to obtain a regulation plan for missing data and abnormal data.

[0168] It should be noted that the city task analysis requirements are acquired in real time and generally include tasks such as vehicle flow analysis, pedestrian flow analysis, and vehicle traffic load analysis. These are specifically set by the user. Different task analysis requirements correspond to different data requirements and different data priorities. The priority reflects the importance of a certain data to the city task analysis requirements. The missing data and abnormal data generally overlap with the required data. This overlapping data is the data object that is focused on regulation, and the data can be prioritized for regulation and analysis based on the priority. The regulation scheme can achieve data consistency regulation.

[0169] The construction of the city knowledge graph further includes:

[0170] Acquiring the dynamic data and static data;

[0171] Calculate the data volume difference between dynamic data and static data;

[0172] Based on the semantic analysis model, entity data is extracted from dynamic data and static data respectively to obtain static entity data and dynamic entity data;

[0173] Through the urban simulation model, the data correlation between static entity data and dynamic entity data in task demand analysis is analyzed;

[0174] If the data volume difference is greater than a first preset value and the data relevance is greater than a second preset value, knowledge graphs are constructed based on the dynamic data and the static data respectively to form two corresponding knowledge graph structures;

[0175] The two knowledge graph structures are integrated to form a city knowledge graph.

[0176] It should be noted that the dynamic data and static data are the urban dynamic data and urban static data in the present invention. The data correlation refers to the joint use of static data and dynamic data during the normal task requirement analysis and data processing of the urban simulation model. The higher the data correlation, the higher the correlation analysis required for static data and dynamic data to meet the task requirements. The lower the data correlation, the relatively independent dynamic data and static data in the model analysis, and the correlation requirements are not high. It is worth mentioning that when conducting urban task analysis, it is often necessary to jointly analyze dynamic data and static data to meet the analysis requirements. The first and second preset values ​​are set by the user.

[0177] In the present invention, by analyzing the correlation between dynamic data and static data (data volume difference and data association), it is determined whether it is necessary to perform separate graph analysis on dynamic data and static data, and two knowledge graphs are obtained in the knowledge graph, corresponding to static data and dynamic data. When performing real-time model data analysis subsequently, data verification analysis can be performed separately in the corresponding two knowledge graphs for real-time static data and dynamic data, thereby improving the verification accuracy of model data and reducing the verification time cost. Although the complexity of the knowledge graph is increased to a certain extent, it can effectively improve the accuracy of model analysis in complex urban model analysis.

[0178] In addition, for simpler urban models, unified semantic analysis and knowledge graph construction can be performed by integrating or fusing dynamic data with static data.

[0179] The third aspect of the present invention also provides a computer-readable storage medium, which includes a data rationality verification program based on semantic integrity. When the data rationality verification program based on semantic integrity is executed by a processor, the steps of the data rationality verification method based on semantic integrity as described in any one of the above items are implemented.

[0180] The present invention discloses a data rationality verification method, system and storage medium based on semantic integrity, which constructs a city simulation model based on digital twins; obtains dynamic data and static data in the model; extracts data based on relationships, entities and attributes of the dynamic data and static data based on the CNN semantic analysis algorithm, builds a graph based on the extracted data to form a city knowledge graph; obtains model data in real time within a preset time period, performs data classification and data integrity calculation analysis on the model data based on the city knowledge graph, and obtains data integrity and data rationality; generates a data adjustment plan based on the data integrity and data rationality. The present invention can make full use of the semantic information in the model, verify data consistency and integrity, and improve the accuracy and stability of the model.

[0181] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0182] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0183] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0184] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0185] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0186] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A data rationality verification method based on semantic integrity, characterized in that: include: Build a city simulation model based on digital twins, specifically by obtaining the target city’s area, outline, transportation roads, and infrastructure information; Perform visual modeling based on the city information to form a city model; Conduct digital twin-based traffic simulation analysis based on city information and build a digital twin-based traffic model; Fusing the city model with the traffic model to form a city simulation model based on visualization and digital twins; Obtaining dynamic data and static data in the model; Based on the CNN semantic analysis algorithm, the dynamic data and static data are extracted based on relationships, entities, and attributes, and a graph is constructed based on the extracted data to form a city knowledge graph; Within a preset time period, the model data is acquired in real time, and the model data is subjected to data classification and data integrity calculation and analysis based on the city knowledge graph to obtain data integrity and data rationality; generating a data adjustment plan based on the data integrity and data rationality; The acquisition of dynamic data and static data in the model is specifically as follows: Obtain urban dynamic data through monitoring devices in the target city; Based on the urban simulation model, obtain urban static data; The urban static data includes the scale, shape, and location information of urban roads, urban tunnels, and urban platforms; The dynamic data includes traffic flow, pedestrian flow, vehicle type statistics, pedestrian flow distribution, and vehicle distribution information on various roads in the city; The CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, which previously includes: Build a semantic analysis model based on CNN algorithm; Obtain historically collected city data from the system database; Dividing the historically collected city data into a training data set, a validation data set, and a test data set according to a preset ratio; Importing the training data set, the validation data set, and the test data set into the semantic analysis model for cyclic training until the semantic analysis accuracy reaches a preset accuracy; The CNN semantic analysis algorithm is used to extract data based on relationships, entities, and attributes from the dynamic and static data, and a graph is constructed based on the extracted data to form a city knowledge graph, specifically: Acquiring the dynamic data and static data; Integrating the dynamic data with the static data to form city monitoring data; Converting the city monitoring data into text data format to obtain text big data; The text big data is segmented by a word segmentation method based on HMM, the segmented text big data is imported into a semantic analysis model for semantic analysis, and data extraction based on relationships, entities, and attributes is performed according to semantic relationships to obtain relationship data, entity data, and attribute data; Performing semantic relationship analysis based on the relationship data, entity data, and attribute data and constructing a city knowledge graph based on a graph structure; The model data is acquired in real time within a preset time period, and the model data is subjected to data classification and data integrity calculation and analysis based on the city knowledge graph to obtain data integrity and data rationality, specifically: Obtain model data in real time within a preset time period; The model data includes city dynamic data and city static data; Convert the model data into text data format and perform word segmentation processing to obtain real-time text data; Importing the real-time text data into a semantic analysis model to perform relationship, entity, and attribute analysis, and obtaining entity, relationship, and attribute data of the real-time text data; Importing the entities, relationships, and attribute data of the real-time text data into the city knowledge graph, performing retrieval and analysis based on the entity data, and obtaining the completeness of the entity data and the corresponding missing entity data; Based on the relationship between real-time text data, the relationship between attribute data and urban knowledge graph, and attribute data, comparative analysis and data rationality verification are performed to obtain data rationality and abnormal data areas; The data adjustment plan generated based on the data integrity and data rationality is specifically: Obtain information on city mission analysis needs; Convert urban task analysis demand information into text data and import it into the semantic analysis model for semantic analysis to obtain task demand data reports; The task demand data report includes the demand data type and demand data priority information corresponding to the city task analysis demand information; Based on the task requirement data report, completeness and corresponding missing entity data, data rationality and abnormal data areas, a missing data and abnormal data control analysis is performed on each entity data in the model data, and a priority analysis of the demand data is performed in combination with the task requirement data report to obtain a control plan for missing data and abnormal data; The construction of the city knowledge graph further includes: Acquiring the dynamic data and static data; Calculate the data volume difference between dynamic data and static data; Based on the semantic analysis model, entity data is extracted from dynamic data and static data respectively to obtain static entity data and dynamic entity data; Through the urban simulation model, the data correlation between static entity data and dynamic entity data in task demand analysis is analyzed; If the data volume difference is greater than a first preset value and the data relevance is greater than a second preset value, knowledge graphs are constructed based on the dynamic data and the static data respectively to form two corresponding knowledge graph structures; The two knowledge graph structures are integrated to form a city knowledge graph.

2. A data rationality verification system based on semantic integrity, characterized by: The system includes: a memory and a processor, wherein the memory includes a data rationality verification program based on semantic integrity, and when the data rationality verification program based on semantic integrity is executed by the processor, the steps of the data rationality verification method based on semantic integrity as described in claim 1 are implemented.

3. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a data rationality verification program based on semantic integrity. When the data rationality verification program based on semantic integrity is executed by a processor, the steps of the data rationality verification method based on semantic integrity as described in any one of claim 1 are implemented.

Images