A method for constructing a standardized database for tunnel structure monitoring and detection data

Abstract

The present invention relates to the field of data processing, and in particular to a method for constructing a standardized database for tunnel structure monitoring and detection data. The method comprises: obtaining multi-source monitoring and detection data from a tunnel monitoring system; performing hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; selecting multiple groups of the detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of the spatiotemporal index, the inverted index, and the multi-level index; according to the index hierarchical identifier, the multiple groups of the detection data are hierarchically stored to obtain a target database corresponding to the tunnel monitoring system. The method can realize efficient data management of the tunnel monitoring system, optimize storage costs and data access speed, and also improve the query performance, processing efficiency and scalability of the system.

Description

Technical Field

[0001] The invention relates to the field of data processing, and in particular to a method for constructing a standardized database for tunnel structure monitoring and detection data. Background Art

[0002] The construction of the detection database faces many technical challenges, especially in data collection and integration, data standardization, and data storage and management. In related technologies, the amount of data generated by tunnel detection is huge and diverse. How to design an efficient storage architecture to manage these big data and optimize the performance of the database is one of the core challenges of data management.

[0003] In the related technologies, taking the tunnel monitoring scenario as an example, the tunnel monitoring system is usually composed of a large number of sensors and devices, including accelerometers, strain gauges, displacement sensors, temperature and humidity sensors, etc. These devices continuously generate data, especially in the case of high-frequency collection, the amount of data generated every day may reach TB level.

[0004] In addition, tunnel detection involves a variety of sensors and devices, and the data formats and structures they generate are different. For example, the data formats and structures generated by different sensors vary, including time series data, image data, video data, text records, etc. The effective integration and management of these heterogeneous data has become a major challenge. How to effectively integrate these heterogeneous data has become an important technical challenge.

[0005] It is urgent to propose a completely new technical solution to solve at least one of the above technical problems. Summary of the invention

[0006] In view of the technical problems existing in the prior art, the present invention provides a method for constructing a standardized database for tunnel structure monitoring and detection data, which is used to integrate a large amount of heterogeneous data generated in the tunnel structure detection process, realize efficient management of these heterogeneous big data, and optimize the performance of the standardized database for tunnel structure detection data.

[0007] In a first aspect, an embodiment of the present application provides a method for constructing a standardized database of tunnel structure monitoring and detection data, the method comprising:

[0008] Acquire multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data;

[0009] Performing hot-cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot-cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system;

[0010] Selecting multiple groups of detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of detection data; the index hierarchical identifiers are obtained by mixing at least two of a spatiotemporal index, an inverted index, and a multi-level index;

[0011] According to the index hierarchical identifier, multiple groups of detection data are stored in layers to obtain a target database corresponding to the tunnel monitoring system.

[0012] In a second aspect, an embodiment of the present application provides a system for constructing a standardized database for tunnel structure detection data, using any of the methods for constructing a standardized database for tunnel structure detection data described above, the system includes the following units, wherein:

[0013] A collection unit is configured to obtain multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data;

[0014] A separation unit is configured to perform hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system;

[0015] An allocation unit is configured to select multiple groups of the detection data and allocate index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of a spatiotemporal index, an inverted index, and a multi-level index;

[0016] The storage unit is configured to store the multiple groups of detection data in layers according to the index layer identifier to obtain a target database corresponding to the tunnel monitoring system.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0018] at least one processor, memory, and input-output unit;

[0019] The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the method for constructing a standardized database for tunnel structure detection data of the first aspect.

[0020] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes the method for constructing a standardized database of tunnel structure detection data according to the first aspect.

[0021] The beneficial effects of the present invention are: providing a method for constructing a standardized database for tunnel structure monitoring and detection data. In the technical solution, multi-source monitoring and detection data are obtained from the tunnel monitoring system; the multi-source monitoring and detection data are subjected to cold and hot separation processing to obtain detection data; the cold and hot separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; multiple groups of the detection data are selected, and index hierarchical identifiers corresponding to the multiple groups of the detection data are assigned; the index hierarchical identifier is obtained by mixing at least two of the spatiotemporal index, the inverted index, and the multi-level index; according to the index hierarchical identifier, the multiple groups of the detection data are hierarchically stored to obtain the target database corresponding to the tunnel monitoring system. In the technical solution, the hot and cold data separation, index hierarchical identifier and hierarchical storage technology are adopted to realize efficient data management of the tunnel monitoring system. The technical solution not only helps to optimize storage costs and data access speed, but also helps to improve the query performance, processing efficiency and scalability of the system. At the same time, the technical solution enhances data management and security, and supports more complex intelligent analysis tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a method for constructing a standardized database for tunnel structure monitoring and detection data according to an embodiment of the present application;

[0023] Figure 2 It is a structural schematic diagram of a tunnel structure detection data standardization database construction system according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0025] Figure 4 It is a structural schematic diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0027] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0028] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0029] The construction of the detection database faces many technical challenges, especially in data collection and integration, data standardization, and data storage and management. In related technologies, the amount of data generated by tunnel detection is huge and diverse. How to design an efficient storage architecture to manage these big data and optimize the performance of the database is one of the core challenges of data management.

[0030] In the related technologies, taking the tunnel monitoring scenario as an example, the tunnel monitoring system is usually composed of a large number of sensors and devices, including accelerometers, strain gauges, displacement sensors, temperature and humidity sensors, etc. These devices continuously generate data, especially in the case of high-frequency collection, the amount of data generated every day may reach TB level.

[0031] In addition, tunnel detection involves a variety of sensors and devices, and the data formats and structures they generate are different. For example, the data formats and structures generated by different sensors vary, including time series data, image data, video data, text records, etc. The effective integration and management of these heterogeneous data has become a major challenge. How to effectively integrate these heterogeneous data has become an important technical challenge.

[0032] It is urgent to propose a completely new technical solution to solve at least one of the above technical problems.

[0033] The embodiment of the present application provides a method for constructing a standardized database of tunnel structure monitoring and detection data. In this technical solution, multi-source monitoring and detection data are obtained from a tunnel monitoring system; the multi-source monitoring and detection data are subjected to cold and hot separation processing to obtain detection data; the cold and hot separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; multiple groups of the detection data are selected, and index hierarchical identifiers corresponding to the multiple groups of the detection data are assigned; the index hierarchical identifier is obtained by mixing at least two of the spatiotemporal index, inverted index, and multi-level index; according to the index hierarchical identifier, the multiple groups of the detection data are hierarchically stored to obtain the target database corresponding to the tunnel monitoring system.

[0034] In the embodiments of the present application, the separation of hot and cold data, index hierarchical identification and hierarchical storage technology can be used to achieve efficient data management of the tunnel monitoring system. The embodiments of the present application not only help to optimize storage costs and data access speed, but also help to improve the query performance, processing efficiency and scalability of the system. At the same time, the embodiments of the present application enhance the management and security of data and support more complex intelligent analysis tasks.

[0035] Specifically, by dividing data into "hot data" and "cold data" and storing them on high-performance storage media (such as SSD) and low-cost storage media (such as HDD) respectively, storage costs can be significantly reduced. Hot data is usually data that needs to be accessed frequently, such as real-time monitoring data, while cold data is historical data or archived data. This separation strategy can optimize storage costs without sacrificing access speed. Hierarchical storage of data according to its access frequency and type can improve data access speed. Real-time data is stored in an in-memory database (such as Redis) to ensure fast reading and writing; processed data is stored in a relational database to facilitate complex queries and analysis; and raw data is stored in a distributed file system (such as HDFS), which is suitable for large-scale data processing. This hierarchical storage can effectively improve the system's response speed and data processing efficiency. Data related to a specific time and space can be efficiently located. For example, the R-tree index technology can quickly find monitoring data at a specific location and time point, which is crucial for real-time monitoring and problem location of tunnel structures. It is suitable for fast retrieval of text data. For example, the search and analysis of fault logs can greatly improve retrieval efficiency through inverted index technology. Hierarchical indexing of data can further improve query performance and adapt to different data access modes and query requirements. By storing different levels of data in different types of storage systems (such as SSD, HDD, in-memory database, etc.), the use of storage resources can be optimized while ensuring data access speed. This strategy enables the system to respond quickly when processing real-time data and remain efficient when performing large-scale data analysis. It enables the system to scale horizontally based on data volume and processing requirements. New storage nodes can be added flexibly to adapt to the growing amount of data and processing requirements. Through a reasonable hierarchical storage architecture, the system load can be balanced and the overall scalability of the system can be improved.

[0036] By building multi-layer indexes, data can be managed and retrieved more accurately, improving data availability and security. The optimization of index structure helps to quickly discover and deal with potential problems and reduce system response time. It enhances the flexibility of data management and enables the system to better cope with dynamic changes in data and complex management needs.

[0037] Improved data processing capabilities can support more complex analytical tasks, such as trend forecasting and anomaly detection using machine learning algorithms. Efficient management and processing of real-time and historical data provides a solid data foundation for intelligent analysis.

[0038] The tunnel structure detection data standardization database construction scheme provided by the embodiment of the present application can also be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a special device (such as a special terminal device with a tunnel structure detection data standardization database construction system). The chip introduced in the above embodiment can also be carried in these electronic devices. Alternatively, these electronic devices can also be installed with a service program for executing the tunnel structure detection data standardization database construction scheme.

[0039] Figure 1 A schematic diagram of a process for constructing a standardized database for tunnel structure monitoring and detection data provided by an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0040] 101, obtain multi-source monitoring and detection data from the tunnel monitoring system;

[0041] 102, performing cold and hot separation processing on the multi-source monitoring and detection data to obtain detection data;

[0042] 103, selecting multiple groups of detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of detection data;

[0043] 104. According to the index hierarchical identifier, the plurality of groups of detection data are stored in a hierarchical manner to obtain a target database corresponding to the tunnel monitoring system.

[0044] In an embodiment of the present application, the tunnel monitoring system is deployed with a variety of sensors, and the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data. It is worth noting that the tunnel monitoring system is equipped with a variety of sensors, which are responsible for collecting different types of detection data. The configuration of these sensors covers a variety of monitoring needs, such as temperature sensors for monitoring temperature changes in the tunnel, vibration sensors for detecting vibration conditions of the tunnel structure, humidity sensors for measuring ambient humidity, and pressure sensors for monitoring pressure changes inside the tunnel. The data collected by these sensors form multi-source monitoring and detection data, covering all aspects of the tunnel structure, ensuring comprehensive monitoring and real-time tracking of the tunnel status. This integration of multi-source data can provide detailed information support for the safe operation of the tunnel, help to promptly discover potential problems, and provide a scientific basis for maintenance decisions.

[0045] In the embodiment of the present application, the hot and cold separation process is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system. That is, the hot and cold data separation process is closely related to the importance of the tunnel structure at each deployment position in the tunnel monitoring system. This means that the data management strategy will be customized according to the importance and monitoring needs of the tunnel structure at each location. For example, more frequent monitoring and data collection are carried out on important structures (such as tunnel entrances and station intersections) to ensure real-time and accuracy. These data are regarded as "hot data" and need to be able to be quickly accessed on high-performance storage media. Relatively speaking, for secondary structures or places with fewer potential problems, the frequency and importance of data updates can be appropriately reduced, and these data can be defined as "cold data" and stored on storage devices with lower costs but equally reliable. This targeted data hierarchical processing strategy can ensure the timeliness and decision-making quality of key data, while also reducing the overall data storage cost.

[0046] As an optional embodiment, in step 102, the multi-source monitoring and detection data are subjected to cold and hot separation processing to obtain detection data, which can be implemented as follows:

[0047] Determine the deployment location corresponding to each multi-source monitoring and detection data;

[0048] According to the attribute information corresponding to each deployment position, the tunnel monitoring system is restored in virtual structure to obtain the importance degree of the tunnel structure corresponding to each deployment position;

[0049] According to the importance of the tunnel structure corresponding to each deployment position, each multi-source monitoring and detection data is separated into cold and hot streams to obtain the detection data.

[0050] Exemplarily, the above steps implement hot and cold separation processing of multi-source monitoring and detection data to obtain detection data. First, determine the specific deployment location corresponding to the multi-source monitoring and detection data collected by each sensor. Then, based on the attribute information of these deployment locations, the tunnel monitoring system is restored to a virtual structure, and then the importance of the tunnel structure at each deployment location is evaluated. Specifically, this involves analyzing the importance of the structure of each location to the overall safety and operation of the tunnel. On this basis, the collected multi-source monitoring and detection data are processed by hot and cold diversion according to the importance of the tunnel structure at each deployment location. Locations with high importance will be classified as "hot data" because their data have a greater impact on tunnel safety and operation, requiring fast access and frequent updates; while data at locations with lower importance are classified as "cold data" and can be stored and accessed at a lower frequency. This hot and cold diversion processing method effectively optimizes data storage resources and ensures timely monitoring and processing of key data.

[0051] Further optionally, in the above steps, based on the attribute information corresponding to each deployment position, the tunnel monitoring system is restored by virtual structure to obtain the importance degree of the tunnel structure corresponding to each deployment position, which can be implemented as follows:

[0052] Creating an initial virtual space model corresponding to the tunnel monitoring system;

[0053] According to the attribute information corresponding to each deployment position, the deployment position of each sensor is marked in the initial virtual space model, and the detection behavior of each sensor in the respective deployment position is simulated;

[0054] Obtaining structural attribute information of the tunnel;

[0055] Based on the structural attribute information and the detection behavior, the importance of the tunnel structure corresponding to each deployment position is predicted.

[0056] For example, first, create an initial virtual space model corresponding to the tunnel monitoring system, which reflects the overall structure and layout of the tunnel. Then, based on the actual deployment location of the sensors, mark the location of each sensor in the virtual space model, simulate their detection behavior in their respective locations, and predict the various data they may capture. Next, obtain the structural attribute information of the tunnel, such as the tunnel's supporting structure, material strength, and service life. This information, combined with the simulated detection behavior, is used to evaluate and predict the importance of the tunnel structure corresponding to each deployment location, thereby providing a basis for hot and cold diversion processing.

[0057] Further optionally, in the above steps, based on the structural attribute information and the detection behavior, predicting the importance of the tunnel structure corresponding to each deployment position can be implemented as follows:

[0058] The structural strength information in the structural attribute information and the detection behavior are input into the prediction scoring model, and the importance degree of the tunnel structure corresponding to each deployment position is output through the prediction scoring model.

[0059] Exemplarily, the prediction scoring model is expressed as:

[0060] Where P(i) represents the predicted evaluation value of the importance of the tunnel structure corresponding to the i-th sensor node, q i represents the structural strength information of the deployment location of the i-th sensor node, S i is the historical score performance value of the same detection behavior of the i-th sensor node under the same structure, α i is the optional structural attribute information corresponding to the deployment location of the i-th sensor node, β iis the structural correlation coefficient between the deployment location of the i-th sensor node and the surrounding structure.

[0061] The purpose of the above formula is to comprehensively consider the structural strength of the sensor location, historical data performance, specific structural properties, and the correlation of surrounding structures, so as to accurately predict the importance of the tunnel structure at each deployment location. This method can ensure a more comprehensive and scientific assessment of importance, help optimize data management strategies, and improve the overall effectiveness of the monitoring system.

[0062] In an embodiment of the present application, the index hierarchical identification is obtained by mixing at least two of the spatiotemporal index, the inverted index, and the multi-level index. This hybrid indexing method combines the advantages of different types of indexes and provides more efficient data retrieval and management capabilities. The spatiotemporal index is used to process the time and space information of the data, so that the data can be quickly retrieved according to time and location; the inverted index optimizes the query for keywords, and is particularly suitable for fast matching of text data; the multi-level index further speeds up the data search speed through the hierarchical structure. By combining the characteristics of these indexing methods, the system can achieve more accurate and rapid data access in a complex data environment, improving overall performance and response speed.

[0063] As an optional embodiment, selecting multiple groups of detection data in 103 and assigning index hierarchical identifiers corresponding to the multiple groups of detection data may be implemented as follows:

[0064] The detection data are similarly calculated according to a preset grouping evaluation dimension; clustering processing is performed based on the similarity between each data in the detection data to obtain multiple groups of the detection data; the multiple groups of the detection data are input into an adaptive allocation model, and index hierarchical identifiers corresponding to the multiple groups of the detection data are output.

[0065] In step 103, first, the detection data is subjected to similarity calculation of the preset grouping evaluation dimension. This process includes performing similarity analysis on each group of data to determine which data are similar in characteristics and can be classified into the same group. Next, based on the results of the similarity calculation, the detection data is clustered to generate multiple groups of data, and the data in each group has a high degree of similarity in characteristics. Subsequently, these clustered data groups are input into an adaptive allocation model, which automatically assigns corresponding index hierarchical identifiers based on the characteristics and similarities of the data.

[0066] The core of this method is to divide the data into multiple groups with similar characteristics through similarity calculation and clustering, and then use the adaptive allocation model to assign appropriate index identifiers to each group of data. This hierarchical identification method not only optimizes the management and retrieval efficiency of data, but also ensures that the data index is more targeted and flexible, thereby improving the performance of the system when processing complex data.

[0067] Further, assuming that the adaptive allocation model includes at least the following structures: an identification layer, an adaptive parsing layer, and an allocation layer; based on the above structure, in the above steps, multiple groups of the detection data are input into the adaptive allocation model, and the index hierarchical identifiers corresponding to the multiple groups of the detection data are output, which can be implemented as follows:

[0068] identifying, by the recognition layer, archived feature information in a plurality of groups of the detection data;

[0069] Adaptively parsing the plurality of detection data sets based on the archive feature information through an adaptive parsing layer to obtain archive feature labels corresponding to the plurality of detection data sets;

[0070] By allocating layers, corresponding index hierarchical identifiers are configured for the plurality of groups of detection data according to the archiving feature tags.

[0071] In the above steps, multiple groups of detection data are input into the model, and the index hierarchical identification of each group of data is output, which can be achieved through the following process: First, the recognition layer identifies the archival feature information in the multiple groups of detection data. This layer is responsible for extracting and identifying the key features in the data for subsequent processing. Next, the adaptive parsing layer adaptively parses the data based on the identified archival feature information, thereby generating corresponding archival feature labels for each group of data. These labels are used to describe the specific characteristics and categories of the data. Finally, in the allocation layer, according to the generated archival feature labels, appropriate index hierarchical identification is configured for each group of data, thereby realizing hierarchical management and efficient retrieval of data.

[0072] Through this method, the adaptive allocation model can automatically allocate and optimize index identifiers according to the characteristic information of the data, improve the flexibility and efficiency of data management, and ensure fast retrieval and accurate positioning of data. The adaptive allocation model extracts the archival characteristic information of the data through the recognition layer, so as to accurately grasp the core characteristics of each group of data. The recognition of this characteristic information ensures that the basic data for subsequent processing is accurate and meaningful. The adaptive parsing layer further analyzes these features and generates corresponding archival characteristic tags, so that each group of data can obtain a unique and clear identifier. This processing method can efficiently manage and organize data and improve the efficiency of data management. By assigning data to appropriate index hierarchical identifiers, the allocation layer can configure the appropriate index structure according to the characteristic tags of the data. This configuration of index hierarchical identifiers optimizes the data retrieval path, so that relevant data can be quickly located when querying, thereby significantly improving the data retrieval speed and response time. The adaptive parsing layer labels the data with features, ensuring that the classification and identification of the data are based on the actual data features. This precise identification can reduce errors and deviations in data processing, improve the accuracy and reliability of data analysis, and make the data more effective in subsequent applications. The design of the adaptive allocation model allows the system to dynamically adjust according to changes in data features. As data characteristics change, the model can update index hierarchical identifiers in real time to adapt to new data distribution and characteristics. This flexibility ensures that the system can continue to adapt to the changing data environment and maintain efficient operating performance. By configuring multi-level index identifiers for data, more complex query requirements can be supported. For example, multi-dimensional queries or analyses can be performed based on different characteristics of the data, which is very important for processing complex data sets and application scenarios.

[0073] In summary, inputting multiple sets of detection data into the adaptive allocation model and outputting the corresponding index hierarchical identifiers can significantly improve the efficiency, accuracy and flexibility of data management and retrieval, while also supporting more complex data analysis requirements. This method has important application value in big data processing and intelligent systems.

[0074] Further optionally, in the above steps, adaptively parsing the multiple groups of detection data based on the archive feature information to obtain the archive feature labels corresponding to the multiple groups of detection data can be implemented as follows:

[0075] Based on the archiving feature information, at least two retrieval types that match each group of the detection data are selected; and retrieval type labels corresponding to the at least two retrieval types are used as archiving feature labels that match each group of the detection data.

[0076] In the above steps, based on the archive feature information, multiple groups of detection data are adaptively parsed to obtain the archive feature labels corresponding to each group of data, which can be achieved in the following way: First, the system selects at least two matching retrieval types for each group of detection data based on the extracted archive feature information. These retrieval types can be selected according to data characteristics and usage scenarios, such as content-based retrieval, time-based retrieval, etc. Then, the retrieval type labels corresponding to these retrieval types are assigned as archive feature labels for each group of detection data. This method not only improves the identifiability of the data through rich data labeling, but also facilitates subsequent retrieval and analysis, so that users can find relevant data more quickly during data management and query, thereby improving overall query efficiency and accuracy.

[0077] In an embodiment of the present application, the shorter the retrieval delay obtained after any retrieval type is applied to the detection data, the higher the matching degree between any retrieval type and the detection data; the retrieval delay is predicted based on the archived feature information of any retrieval type.

[0078] In the embodiment of the present application, the selection of the search type is based on a specific principle, that is, it is assumed that the shorter the search delay obtained by the application of various search types for the detection data, the higher the matching degree between the search type and the detection data. Such a selection mechanism helps to ensure that the selected search type can process the detection data more effectively, thereby improving the overall efficiency of data processing.

[0079] The process of predicting retrieval delay needs to be based on archived feature information, which contains details about the data processing task, such as data quantity, data type, data structure, etc. When using archived feature information for prediction, a pre-trained model or algorithm is usually required for estimation. Through historical data statistics, machine learning and other technical means, these models can predict the possible retrieval delay under different retrieval types based on the relationship between different retrieval types and archived features.

[0080] For example, in some typical cases, for some large data sets, if you choose a content-based search type, it may take a long time to index and search, because these types of searches may require in-depth analysis of the content. In contrast, if the data can be effectively divided into time periods or the data format is relatively standard and easy to process, then a time-based search type may have a shorter search delay, because this type of search may only require filtering on the time dimension without involving detailed processing of the content.

[0081] Finally, based on the prediction results of retrieval delay, the adaptive allocation model selects corresponding retrieval type labels as archiving feature labels for multiple groups of detection data, and uses these labels for index layer allocation to ensure maximum efficiency of data processing.

[0082] In the embodiment of the present application, at least two search types are at least two of a spatiotemporal search type, a reverse search type, and a multi-level search type. The following is a brief introduction and application examples of these search types:

[0083] The spatiotemporal retrieval type is mainly used to process the time and space dimensions of data. This retrieval method is usually suitable for information retrieval tasks that need to consider time and geographic location. In tunnel management systems, this type of retrieval can be used to track and analyze the status and events of tunnels. For example, the tunnel is equipped with sensors to record the temperature, humidity and other environmental data in the tunnel in real time. Based on this, using the spatiotemporal retrieval type, you can quickly find environmental data for a specific section (such as "the 5th kilometer of Tunnel No. 1") within a specific time period (such as "August 1 to August 15, 2024"). For example, you can find the temperature changes at the 5th kilometer during this period to evaluate whether the tunnel's ventilation system is working properly.

[0084] The inverted index type is used to build an inverted index from keywords to data items. This type of search is widely used in the field of text data and information retrieval. Keywords can be used to quickly find data containing the keyword. In a tunnel management system, inverted indexing can help quickly locate data records containing specific information. For example, suppose a tunnel management system records all maintenance logs and inspection reports. Through the inverted index, all reports containing the keywords "crack repair" or "leakage inspection" can be quickly found. You can enter "crack repair" to retrieve all documents and records related to tunnel crack repair, so as to quickly obtain the required historical maintenance information.

[0085] The multi-level search type searches based on different levels of data structure. This method is suitable for complex data structures that require multi-level classification and filtering. In tunnel management systems, this search method can be used to classify data at different levels for more detailed filtering. For example, suppose the maintenance records of a tunnel are organized in different levels, such as the following levels:

[0086] First level: the line where the tunnel is located (such as "Line 1", "Line 2")

[0087] Second level: specific sections (such as "the northern section of Line 1", "the southern section of Line 1")

[0088] Third level: Maintenance type (such as "structural inspection", "environmental monitoring")

[0089] The user can first select "Line 1", then select "Southern Section" within the line, and then select the "Environmental Monitoring" type. Finally, the environmental monitoring records for the southern section of the line are retrieved. This multi-level search method helps to efficiently find specific data in a complex management system.

[0090] Exemplarily, assume that in a comprehensive tunnel management system, spatiotemporal retrieval type and reverse retrieval type are used to optimize data access. In spatiotemporal retrieval, it can be used to find environmental data or maintenance records within a certain period of time to help engineers analyze the operating status of the tunnel. In reverse retrieval, it can be used to quickly locate relevant logs and reports based on specific keywords (such as "safety inspection") for rapid review and decision-making. Combining these two retrieval types, efficient data processing and analysis can be achieved in the maintenance and management of the tunnel, improving the overall operating efficiency and maintenance response speed of the system.

[0091] In step 104, multiple groups of detection data are stored in layers according to the index layer identification, and finally the target database of the tunnel monitoring system is obtained. This processing method stores the data in layers according to the index layer identification, so that data at different levels are stored in different types of storage media (such as SSD, HDD, memory database, etc.). This layered storage strategy ensures that hot data (high-frequency access data) can be accessed quickly, while cold data (low-frequency access data) can be stored in a more economical way, thereby improving the overall data access efficiency. Data is stored in layers according to its access frequency and importance, avoiding the waste of resources of high-performance storage media. Hot data is stored on high-performance media, ensuring efficient data reading and writing speed, while cold data is stored in low-cost media, reducing storage overhead. This optimization strategy effectively balances storage performance and cost.

[0092] By mixing the index hierarchical identifiers generated by technologies such as spatiotemporal indexing, inverted indexing, and multi-level indexing, relevant data can be quickly located during querying. Spatiotemporal indexing helps to find data by time and space conditions, inverted indexing improves text retrieval capabilities, and multi-level indexing optimizes the hierarchy and efficiency of data retrieval. The combined application of these indexing technologies significantly improves query performance and reduces retrieval time. Through hierarchical storage, data can be flexibly managed according to its life cycle and access requirements. For example, real-time monitoring data can be stored in an efficient in-memory database, while historical data can be archived in a distributed file system. This flexible management method supports dynamic adjustment and optimization of data. The application of hierarchical storage and index hierarchical identifiers not only improves the access speed of data, but also enhances support for complex data analysis tasks. The system can quickly analyze real-time data and conduct in-depth mining of historical data, support machine learning and intelligent analysis, and provide more comprehensive insights and predictions.

[0093] In addition, the tiered storage architecture can further optionally support horizontal expansion of the system. As the amount of data increases, nodes can be added in different storage layers to cope with the growing data storage and processing needs. This scalability ensures that the system can still operate efficiently when the data grows.

[0094] Optionally, tiered storage can also be combined with security policies for data protection. Sensitive data can be encrypted and stored in a high-security storage layer, while ordinary data is stored in a standard storage layer. This tiered storage solution can improve data security and privacy protection.

[0095] In summary, the embodiment of the present application stores multiple groups of detection data in layers through index hierarchical identification, which not only optimizes data access speed and storage cost, but also improves query performance, system flexibility and data management capabilities. In addition, this technical solution supports complex data analysis tasks and improves the scalability and data security of the system.

[0096] In an embodiment of the present application, in a tunnel monitoring system, after obtaining multi-source monitoring and detection data, the data can be divided into detection data through hot and cold data separation processing. This hot and cold separation processing method is associated with the importance of the tunnel structure at each monitoring location. Then, multiple groups of detection data are selected and assigned corresponding index hierarchical identifiers, which are generated by a mixture of at least two index types (such as spatiotemporal index, inverted index, multi-level index). According to these index hierarchical identifiers, the data is stored in layers, and finally a target database is constructed. In an embodiment of the present application, efficient data management is achieved through hot and cold data separation, index hierarchical identification and hierarchical storage technology. It not only optimizes storage costs and data access speed, but also improves the query performance, processing efficiency and scalability of the system. In addition, the solution enhances data management and security, and supports more complex intelligent analysis tasks.

[0097] In another embodiment of the present application, a system for constructing a standardized database of tunnel structure detection data is provided. Figure 2 The tunnel structure detection data standardization database construction system comprises the following units:

[0098] A collection unit is configured to obtain multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data;

[0099] A separation unit is configured to perform hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system;

[0100] An allocation unit is configured to select multiple groups of the detection data and allocate index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of a spatiotemporal index, an inverted index, and a multi-level index;

[0101] The storage unit is configured to store the multiple groups of detection data in layers according to the index layer identifier to obtain a target database corresponding to the tunnel monitoring system.

[0102] Further optionally, the separation unit performs hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data, and is configured as follows:

[0103] Determine the deployment location corresponding to each multi-source monitoring and detection data;

[0104] According to the attribute information corresponding to each deployment position, the tunnel monitoring system is restored in virtual structure to obtain the importance degree of the tunnel structure corresponding to each deployment position;

[0105] According to the importance of the tunnel structure corresponding to each deployment position, each multi-source monitoring and detection data is separated into cold and hot streams to obtain the detection data.

[0106] Further optionally, the separation unit performs virtual structural restoration on the tunnel monitoring system according to the attribute information corresponding to each deployment position to obtain the importance degree of the tunnel structure corresponding to each deployment position, and is configured as follows:

[0107] Creating an initial virtual space model corresponding to the tunnel monitoring system;

[0108] According to the attribute information corresponding to each deployment position, the deployment position of each sensor is marked in the initial virtual space model, and the detection behavior of each sensor in the respective deployment position is simulated;

[0109] Obtaining structural attribute information of the tunnel;

[0110] Based on the structural attribute information and the detection behavior, the importance of the tunnel structure corresponding to each deployment position is predicted.

[0111] Further optionally, the separation unit predicts the importance of the tunnel structure corresponding to each deployment position based on the structural attribute information and the detection behavior, and is configured to:

[0112] The structural strength information in the structural attribute information and the detection behavior are input into the prediction scoring model, and the importance of the tunnel structure corresponding to each deployment position is output through the prediction scoring model; wherein the prediction scoring model is expressed as:

[0113] Where P(i) represents the predicted evaluation value of the importance of the tunnel structure corresponding to the i-th sensor node, q i represents the structural strength information of the deployment location of the i-th sensor node, S i is the historical score performance value of the same detection behavior of the i-th sensor node under the same structure, α i is the optional structural attribute information corresponding to the deployment location of the i-th sensor node, β i is the structural correlation coefficient between the deployment location of the i-th sensor node and the surrounding structure.

[0114] Further optionally, the allocating unit selects multiple groups of the detection data and allocates index hierarchical identifiers corresponding to the multiple groups of the detection data, and is configured to:

[0115] Performing similarity calculation on the detection data according to preset grouping evaluation dimensions;

[0116] Performing clustering processing based on the similarity between each data in the detection data to obtain multiple groups of the detection data;

[0117] The multiple groups of detection data are input into an adaptive allocation model, and index hierarchical identifiers corresponding to the multiple groups of detection data are output.

[0118] Further optionally, the adaptive allocation model comprises at least the following structures: a recognition layer, an adaptive parsing layer, and an allocation layer;

[0119] The construction unit inputs the plurality of groups of detection data into the adaptive allocation model and outputs index hierarchical identifiers corresponding to the plurality of groups of detection data, and is configured as follows:

[0120] identifying, by the recognition layer, archived feature information in a plurality of groups of the detection data;

[0121] Adaptively parsing the plurality of detection data sets based on the archive feature information through an adaptive parsing layer to obtain archive feature labels corresponding to the plurality of detection data sets;

[0122] By allocating layers, corresponding index hierarchical identifiers are configured for the plurality of groups of detection data according to the archiving feature tags.

[0123] Further optionally, the allocation unit adaptively analyzes the multiple groups of detection data based on the archiving feature information to obtain the archiving feature labels corresponding to the multiple groups of detection data, and is configured as follows:

[0124] Based on the archived feature information, at least two retrieval types matching each group of the detection data are selected; wherein the shorter the retrieval delay obtained after any retrieval type is applied to the detection data, the higher the matching degree between the any retrieval type and the detection data; the retrieval delay is predicted based on the archived feature information of any retrieval type;

[0125] Using retrieval type labels corresponding to at least two retrieval types as archiving feature labels matched by each group of detection data;

[0126] Among them, at least two search types are at least two of a spatiotemporal search type, a reverse index search type, and a multi-level search type.

[0127] The system can implement various steps in the above method embodiment, which will not be expanded here.

[0128] In the embodiment of the present application, a large amount of heterogeneous data generated during the tunnel structure detection process is integrated to achieve efficient management of these heterogeneous big data and optimize the performance of the standardized database for tunnel structure detection data.

[0129] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 5102, and a computer program 511 stored in the memory 510 and executable on the processor 5102. When the processor 5102 executes the computer program 511, the following steps are implemented: obtaining multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, and the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data; performing hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; selecting multiple groups of the detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of the spatiotemporal index, the inverted index, and the multi-level index; according to the index hierarchical identifier, the multiple groups of the detection data are hierarchically stored to obtain the target database corresponding to the tunnel monitoring system.

[0130] See also Figure 4 , Figure 4A schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. This embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored, and when the computer program 611 is executed by a processor, the following steps are implemented: obtaining multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, and the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data; performing hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; selecting multiple groups of the detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of the spatiotemporal index, the inverted index, and the multi-level index; according to the index hierarchical identifier, the multiple groups of the detection data are hierarchically stored to obtain the target database corresponding to the tunnel monitoring system.

[0131] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0134] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0135] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0136] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0137] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for constructing a standardized database for tunnel structure monitoring and detection data, characterized in that: The method comprises: Acquire multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, the multiple sensors respectively collect different types of monitoring and detection data, and the different types of monitoring and detection data constitute the multi-source monitoring and detection data; Performing hot-cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot-cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; Selecting multiple groups of detection data, and assigning index hierarchical identifiers corresponding to the multiple groups of detection data; the index hierarchical identifiers are obtained by mixing at least two of a spatiotemporal index, an inverted index, and a multi-level index; According to the index hierarchical identifier, the plurality of groups of detection data are hierarchically stored to obtain a target database corresponding to the tunnel monitoring system; The selecting of the plurality of groups of detection data and assigning index hierarchical identifiers corresponding to the plurality of groups of detection data includes: Performing similarity calculation on the detection data according to preset grouping evaluation dimensions; Performing clustering processing based on the similarity between each data in the detection data to obtain multiple groups of the detection data; Inputting the plurality of groups of detection data into an adaptive allocation model, and outputting index hierarchical identifiers corresponding to the plurality of groups of detection data; The adaptive allocation model at least includes the following structures: a recognition layer, an adaptive analysis layer, and an allocation layer; The step of inputting the plurality of groups of detection data into an adaptive allocation model and outputting index hierarchical identifiers corresponding to the plurality of groups of detection data includes: identifying, by the recognition layer, archived feature information in a plurality of groups of the detection data; Adaptively parsing the plurality of detection data sets based on the archive feature information through an adaptive parsing layer to obtain archive feature labels corresponding to the plurality of detection data sets; By allocating layers, corresponding index hierarchical identifiers are configured for the plurality of groups of detection data according to the archiving feature tags.

2. The method for constructing a standardized database of tunnel structure detection data according to claim 1, characterized in that: The step of performing hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data includes: Determine the deployment location corresponding to each multi-source monitoring and detection data; According to the attribute information corresponding to each deployment position, the tunnel monitoring system is restored in virtual structure to obtain the importance degree of the tunnel structure corresponding to each deployment position; According to the importance of the tunnel structure corresponding to each deployment position, each multi-source monitoring and detection data is separated into cold and hot streams to obtain the detection data.

3. The method for constructing a standardized database of tunnel structure detection data according to claim 2, characterized in that: The virtual structure restoration of the tunnel monitoring system is performed according to the attribute information corresponding to each deployment position to obtain the importance degree of the tunnel structure corresponding to each deployment position, including: Creating an initial virtual space model corresponding to the tunnel monitoring system; According to the attribute information corresponding to each deployment position, the deployment position of each sensor is marked in the initial virtual space model, and the detection behavior of each sensor in the respective deployment position is simulated; Obtaining structural attribute information of the tunnel; Based on the structural attribute information and the detection behavior, the importance of the tunnel structure corresponding to each deployment position is predicted.

4. The method for constructing a standardized database of tunnel structure detection data according to claim 3 is characterized in that: The predicting the importance of the tunnel structure corresponding to each deployment position based on the structural attribute information and the detection behavior includes: The structural strength information in the structural attribute information and the detection behavior are input into the prediction scoring model, and the importance of the tunnel structure corresponding to each deployment position is output through the prediction scoring model; wherein the prediction scoring model is expressed as: ; in, P ( i ) indicates the i The predicted evaluation value of the tunnel structure importance corresponding to the sensor node, q i Indicates i The structural strength information of the deployment location of each sensor node, S i For the i The historical score performance value of the same detection behavior of sensor nodes under the same structure, α i For the i The optional structural attribute information corresponding to the deployment location of each sensor node, β i For the i The structural correlation coefficient between the deployment location of each sensor node and the surrounding structure.

5. The method for constructing a standardized database of tunnel structure detection data according to claim 1, characterized in that: The adaptively parsing the plurality of detection data based on the archiving feature information to obtain the archiving feature labels corresponding to the plurality of detection data respectively includes: Based on the archived feature information, at least two retrieval types matching each group of the detection data are selected; wherein the shorter the retrieval delay obtained after any retrieval type is applied to the detection data, the higher the matching degree between the any retrieval type and the detection data; the retrieval delay is predicted based on the archived feature information of any retrieval type; Using retrieval type labels corresponding to at least two retrieval types as archiving feature labels matched by each group of detection data; Among them, at least two search types are at least two of a spatiotemporal search type, a reverse index search type, and a multi-level search type.

6. A system for constructing a standardized database for tunnel structure detection data, using the method for constructing a standardized database for tunnel structure detection data according to any one of claims 1 to 5, characterized in that: The system comprises the following units, wherein: A collection unit is configured to obtain multi-source monitoring and detection data from a tunnel monitoring system; the tunnel monitoring system is deployed with a variety of sensors, the multiple sensors respectively collect different types of detection data, and the different types of detection data constitute the multi-source monitoring and detection data; A separation unit is configured to perform hot and cold separation processing on the multi-source monitoring and detection data to obtain detection data; the hot and cold separation processing is related to the importance of the tunnel structure corresponding to each deployment position in the tunnel monitoring system; An allocation unit is configured to select multiple groups of the detection data and allocate index hierarchical identifiers corresponding to the multiple groups of the detection data; the index hierarchical identifier is obtained by mixing at least two of a spatiotemporal index, an inverted index, and a multi-level index; A storage unit configured to store the plurality of detection data in layers according to the index layer identifier to obtain a target database corresponding to the tunnel monitoring system; The selecting of the plurality of groups of detection data and assigning index hierarchical identifiers corresponding to the plurality of groups of detection data includes: Performing similarity calculation on the detection data according to preset grouping evaluation dimensions; Performing clustering processing based on the similarity between each data in the detection data to obtain multiple groups of the detection data; Inputting the plurality of groups of detection data into an adaptive allocation model, and outputting index hierarchical identifiers corresponding to the plurality of groups of detection data; The adaptive allocation model at least includes the following structures: a recognition layer, an adaptive analysis layer, and an allocation layer; The step of inputting the plurality of groups of detection data into an adaptive allocation model and outputting index hierarchical identifiers corresponding to the plurality of groups of detection data includes: identifying, by the recognition layer, archived feature information in a plurality of groups of the detection data; Adaptively parsing the plurality of detection data sets based on the archive feature information through an adaptive parsing layer to obtain archive feature labels corresponding to the plurality of detection data sets; By allocating layers, corresponding index hierarchical identifiers are configured for the plurality of groups of detection data according to the archiving feature tags.

7. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the method for constructing a standardized database for tunnel structure detection data as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the method for constructing a standardized database for tunnel structure detection data as described in any one of claims 1 to 5.

Images