Multi-channel annular access method and system for meteorological observation data

Abstract

The embodiment of the invention discloses a multichannel annular access method and system for meteorological observation data, and belongs to the technical field of meteorological data processing. According to the embodiment of the invention, the annular buffer structure is adopted to manage meteorological observation data, and compared with a traditional linear stack, the annular buffer has obvious advantages. The linear stack is low in efficiency when the data volume is large, and the annular buffer supports multiple independent data streams to share a storage space, so that continuous writing and cyclic coverage are realized, for example, different sensor data streams can be stored orderly. Read-write pointers circularly move to ensure continuous access of data, the parallel access capability is improved in speed and efficiency, and the multi-task concurrence requirement of meteorological services is met. And an overflow and underflow detection mechanism and a capacity management strategy guarantee data integrity and system stability, and prevent problems of data loss or system crash and the like. Attribute knowledge mining and related mapping are beneficial to accurate management of data, management is carried out according to data characteristics, decision accuracy and efficiency are improved, and data management and operation of a meteorological service system are optimized.

Description

Technical Field

[0001] The embodiment of the present invention belongs to the technical field of meteorological data processing, and specifically relates to a multi-channel ring access method and system for meteorological observation data. Background Art

[0002] In the development of meteorological business systems, equipment operation control and data management have always been core issues. The traditional linear stack access method can meet the basic needs of meteorological business systems when the amount of data is small and there are specific requirements for the order in the early days. For example, in terms of simple device control instruction storage and sequential execution, the last-in-first-out principle of the linear stack can ensure that the instructions are executed by the device in a specific order, and when the amount of data is limited, its efficiency in managing data is acceptable.

[0003] However, with the continuous development of meteorological observation technology, meteorological business systems are facing new challenges. On the one hand, the increase in meteorological observation equipment and the improvement in observation accuracy have led to a sharp increase in the amount of data. In this case, the limitations of linear stacks gradually become apparent. Since the insertion and deletion of data elements in linear stacks are all performed at the top of the stack, as the amount of data increases, the efficiency of data storage and reading will be greatly reduced. For example, when a large amount of meteorological observation data (such as long time series data from multiple meteorological stations) needs to be stored and processed, the operation of the linear stack will become very slow, resulting in system response delays and affecting the normal development of meteorological business.

[0004] On the other hand, the lack of flexibility of the linear stack becomes a serious problem in meteorological business systems under unstable networks and complex multi-threaded scenarios. When the network is unstable, data transmission may be interrupted or delayed, and it is difficult for the linear stack to effectively handle this situation, which may lead to data loss or disordered command execution order. In multi-threaded scenarios, such as when performing meteorological data collection, equipment control, data query and other operations at the same time, the linear stack cannot meet the concurrent access requirements of multiple threads to data, which limits the overall performance of the system.

[0005] In addition, the linear stack lacks effective capacity management and data integrity protection mechanisms in data management. As the amount of data increases, the linear stack will occupy more bandwidth, which not only affects the efficiency of data transmission, but may also cause problems in the operation of the business system. Moreover, since there is no special overflow and underflow detection mechanism, when the amount of data exceeds the stack capacity or the data reading is abnormal, it is easy to cause data loss or system errors, and it is impossible to ensure the integrity of the data in the meteorological business system and the stability of the system. Summary of the invention

[0006] The embodiments of the present invention provide a multi-channel ring access method and system for meteorological observation data, which can solve or partially solve the technical problems involved in the above-mentioned background technology.

[0007] An embodiment of the present invention provides a multi-channel ring access method for meteorological observation data, which is applied to a meteorological observation data access system. The method includes: taking multiple meteorological observation data streams in a target database as initial meteorological observation data streams, performing a timing marking operation based on a ring buffer structure on the initial meteorological observation data streams to obtain multiple timing marking observation information, each of the timing marking observation information includes multiple target meteorological observation data; performing attribute knowledge mining on the multiple target meteorological observation data to obtain meteorological observation attribute knowledge encodings of the multiple target meteorological observation data; taking the multiple timing marking observation information as data access marking information, performing read-write state mapping on the meteorological observation attribute knowledge encodings of the multiple target meteorological observation data in the data access marking information to obtain a read-write state description vector of the data access marking information; determining an access management suggestion vector of the initial meteorological observation data stream using the read-write state description vectors of the multiple timing marking observation information; performing read-write state mapping on the access management suggestion vectors of the multiple meteorological observation data streams in the target database to obtain a global read-write state label of the target database, and the global read-write state label of the target database is used to determine the data access strategy of the target database.

[0008] An embodiment of the present invention provides a meteorological observation data access system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the above method.

[0009] An embodiment of the present invention provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the above method are implemented.

[0010] The embodiment of the present invention adopts a ring buffer structure to manage meteorological observation data. Compared with the traditional linear stack, the ring buffer has obvious advantages. The linear stack is inefficient when the amount of data is large, while the ring buffer supports multiple independent data streams to share storage space, realizing continuous writing and circular overwriting, such as different sensor data streams can be stored in order. Its read and write pointers move cyclically to ensure continuous data access, and the parallel access capability improves speed and efficiency, meeting the multi-task concurrency requirements of meteorological services. Overflow and underflow detection mechanisms and capacity management strategies ensure data integrity and system stability, and prevent problems such as data loss or system crashes. Attribute knowledge mining and related mapping help to accurately manage data, manage according to data characteristics, improve decision-making accuracy and efficiency, and optimize data management and operation of meteorological business systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1The present invention provides a flowchart of a multi-channel ring access method for meteorological observation data.

[0012] Figure 2 A schematic diagram of the structure of a meteorological observation data access system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0013] Figure 1 A multi-channel ring access method for meteorological observation data is shown, which is applied to a meteorological observation data access system. The method includes the following steps 110 to 150.

[0014] Step 110: Use multiple meteorological observation data streams in the target database as initial meteorological observation data streams, perform timing marking operations based on a ring buffer structure on the initial meteorological observation data streams to obtain multiple timing marked observation information, each of which includes multiple target meteorological observation data.

[0015] In an optional embodiment, the step of determining the multiple meteorological observation data streams includes: extracting data from original meteorological observation reports to obtain the multiple meteorological observation data streams.

[0016] Step 120: performing attribute knowledge mining on the plurality of target meteorological observation data respectively to obtain meteorological observation attribute knowledge coding of the plurality of target meteorological observation data.

[0017] Step 130: Use the multiple time-series mark observation information as data access mark information respectively, perform read-write state mapping on the meteorological observation attribute knowledge encoding of the multiple target meteorological observation data in the data access mark information, and obtain the read-write state description vector of the data access mark information.

[0018] Step 140: Determine the access management suggestion vector of the initial meteorological observation data stream by using the read and write state description vectors of the plurality of time-series-tagged observation information.

[0019] Step 150: Perform read-write status mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain a global read-write status label of the target database, which is used to determine the data access strategy of the target database.

[0020] Meteorological observation data is of great significance in many fields such as meteorological research and weather forecasting, and effective access to the data is crucial. The meteorological observation data access system involved in the embodiment of the present invention implements efficient data access through steps 110 to 150.

[0021] First, in step 110, the meteorological observation data access system operates on multiple meteorological observation data streams in the target database. These meteorological observation data streams are the basic data sources for the entire system processing. The meteorological observation data streams in the embodiment of the present invention may come from a variety of ways. In an optional embodiment, they are obtained by extracting data from the original meteorological observation report. For example, the original meteorological observation report may contain observation records of various meteorological elements such as temperature, humidity, air pressure, wind speed, wind direction, etc. at different time points. After data extraction, the observation data of different types or different observation sites are separated into multiple meteorological observation data streams. Then, these meteorological observation data streams are used as initial meteorological observation data streams, and the ring buffer structure is used to perform operations based on time series marking to obtain multiple time series marking observation information. This ring buffer structure is a core structure of the embodiment of the present invention, and it has unique advantages. For example, each time series marking observation information covers 100 target meteorological observation data, and these target meteorological observation data are meteorological observation results under a specific time series. Through the time series marking operation, the position of each data in the entire meteorological observation time series can be clearly defined, which provides a reference basis in the time dimension for subsequent data processing.

[0022] Next, entering step 120, the system will perform attribute knowledge mining on the multiple target meteorological observation data obtained previously. Meteorological observation data has rich attribute information. For example, temperature data may have seasonal attributes, regional attributes, etc., and humidity data may have associated attributes with precipitation probability, etc. Through attribute knowledge mining, a meteorological observation attribute knowledge code is generated for each target meteorological observation data. This encoding process is similar to attaching a label with a specific meaning to each data, making the data richer and easier to understand. For example, for high temperature data in a specific area in summer, its meteorological observation attribute knowledge code may contain information such as the climate characteristics of the area in summer, the association between high temperature and other meteorological elements, etc.

[0023] In the subsequent step 130, the system uses multiple timing mark observation information as data access mark information, and performs read-write state mapping for the meteorological observation attribute knowledge encoding of multiple target meteorological observation data. The read-write state mapping in the embodiment of the present invention is an operation that associates the attribute knowledge of data with read-write operations. Through this mapping, a read-write state description vector of the data access mark information is obtained. For example, if the meteorological observation attribute knowledge encoding of a target meteorological observation data indicates that the data is frequently updated in the near future and is of great significance to weather forecasts, then in the read-write state mapping, it may be marked as a high-frequency read-write state, and this state will have a corresponding representation in the read-write state description vector. The read-write state description vector can be understood as a comprehensive description of each timing mark observation information in terms of read-write operations, which covers the information on the read-write state of all target meteorological observation data therein.

[0024] At step 140, the system uses the read-write state description vectors of multiple time-series tagged observation information to determine the access management recommendation vector of the initial meteorological observation data stream. Since each time-series tagged observation information has its own read-write state description vector, these vectors combined can reflect the overall read-write demand characteristics of the initial meteorological observation data stream. For example, if the read-write state description vectors of multiple time-series tagged observation information all show that a certain type of meteorological observation data (such as wind speed data in a specific area) has a very high read-write frequency within a certain time period, then in the access management recommendation vector of the initial meteorological observation data stream, it will be recommended to perform special access management on this type of data, such as allocating more cache space or using more efficient read-write algorithms.

[0025] Finally, in step 150, the system performs read-write status mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database, thereby obtaining a global read-write status label of the target database. The global read-write status label is a comprehensive identifier of the entire target database in terms of data access. It can reflect the read-write requirements of different meteorological observation data streams in the entire target database. For example, if there are multiple meteorological observation data streams in the target database from different meteorological observation sites, some of which have data that is frequently updated and is of key significance to meteorological analysis, and other sites have data that is relatively stable and has a low read-write frequency, then this difference will be reflected in the global read-write status label. The importance of the global read-write status label lies in that it can be used to determine the data access strategy of the target database. According to the label, an access strategy suitable for the entire target database can be formulated, for example, a faster storage medium or a more optimized reading algorithm can be used for data with a high read-write frequency, and a more economical storage method can be used for data with a low read-write frequency.

[0026] In the whole process, the ring buffer structure plays a vital role. It supports multiple independent meteorological observation data streams to share storage space in the same buffer, realizing continuous writing and cyclic overwriting of data. For example, the total capacity of the ring buffer is 1000 data units. When the meteorological observation data stream continuously generates new data, the new data can be written into the buffer in sequence. When the buffer is full, the new data will cyclically overwrite the earliest data, just like a ring-shaped circular storage structure. This structure ensures continuous access to data through the cyclic movement of the read and write pointers, and supports parallel access. For example, when performing read and write status mapping of data access tag information, multiple timing tag observation information can be operated at the same time, greatly improving the data access speed and efficiency.

[0027] At the same time, the embodiment of the present invention also has an overflow and underflow detection mechanism and a capacity management strategy for multi-channel data streams. In the access process of meteorological observation data, since meteorological observation is carried out continuously, the amount of data may continue to increase. If it is not controlled, an overflow may occur. For example, when the ring buffer receives a large amount of meteorological observation data in a short period of time, exceeding the capacity of the buffer, the overflow detection mechanism will be triggered, and the system will take corresponding measures, such as temporarily stopping the writing of some unimportant data streams or compressing and storing the data. The underflow situation may occur when the data reading speed is too fast and the writing speed cannot keep up. The underflow detection mechanism will also detect and take measures, such as prompting the data source to speed up the data generation speed or adjust the reading strategy. The capacity management strategy of multi-channel data streams is to reasonably allocate the capacity of the ring buffer according to factors such as the importance, read and write frequency, etc. of different meteorological observation data streams. For example, for those meteorological observation data streams that are important to weather forecasts and have high read and write frequencies, a larger buffer capacity can be allocated to ensure the integrity of the data and the stability of the system.

[0028] The meteorological observation data access system involved in the embodiment of the present invention is applicable to a variety of scenarios, such as real-time systems, streaming media processing, and sensor networks. In real-time systems, it can process continuously updated meteorological observation data in a timely manner to provide fast and accurate data support for weather forecasts; in streaming media processing scenarios, it can efficiently process the continuous flow of meteorological observation data to ensure orderly access to data; in sensor network scenarios, it can flexibly respond to meteorological observation data streams generated by different sensors, and can flexibly expand the number of channels according to the characteristics and requirements of the sensors, thereby improving the system processing capabilities. In summary, the meteorological observation data access system achieves efficient, stable, and intelligent access management of meteorological observation data through a series of closely connected operating steps and effective mechanisms.

[0029] In some examples, examples of meteorological observation attribute knowledge encoding, read-write status description vectors, access management suggestion vectors, and global read-write status labels are as follows.

[0030] 1. Knowledge Coding of Meteorological Observation Attributes Meteorological observation data contains a variety of meteorological elements. Different elements have different attribute characteristics, which can be encoded by numerical feature vectors.

[0031] For example, for temperature observation data, a feature vector encoding meteorological observation attribute knowledge is [1, 0.8, 0.2, 0.5, 0.3].

[0032] The first element "1" indicates the observation type to which the temperature data belongs. For example, "1" here represents ground temperature observation (if there are multiple observation types, different values ​​can be used to distinguish them, such as 0 represents high-altitude temperature observation, etc.).

[0033] The second element "0.8" indicates the degree of correlation between the temperature data and the season. The higher the value, the stronger the correlation. Here, 0.8 indicates that the temperature data is in a relatively typical temperature range in the current season, which may be close to the average temperature of the season or within a common fluctuation range.

[0034] The third element "0.2" indicates the correlation between the temperature data and the altitude. A lower value indicates that the temperature is relatively less affected by the altitude (if it is a temperature observation in a mountainous area, the value may be higher).

[0035] The fourth element "0.5" represents the relationship between the temperature data and the surrounding geographical environment (such as oceans, forests, etc.). Here, 0.5 means that there is a certain correlation. For example, the observation point is located on land close to the ocean, and the ocean has a certain regulating effect on the temperature.

[0036] The fifth element "0.3" represents the fluctuation of the temperature data in the historical data of the same period. 0.3 represents a relatively small fluctuation, which may suggest that the current meteorological system is relatively stable or that the climate in the region has a certain stability.

[0037] For humidity observation data, the characteristic vector encoding the meteorological observation attribute knowledge may be [0, 0.6, 0.3, 0.7, 0.4], where "0" represents the humidity observation type (distinguished from the temperature observation type), "0.6" represents the correlation between humidity and season, "0.3" represents the correlation with altitude, "0.7" represents the relationship with the surrounding geographical environment (for example, the humidity may be higher in forest areas, and 0.7 in the embodiment of the present invention represents a stronger correlation), and "0.4" represents the fluctuation in historical data of the same period.

[0038] 2. Read and write status description vector Take the time-series tagged observation information containing three meteorological elements, temperature, humidity, and air pressure, as an example, for example, its read-write state description vector is [0.6, 0.4, 0.8].

[0039] The first element "0.6" corresponds to the read and write status of the temperature data. 0.6 indicates that the read and write frequency of temperature data is relatively high, probably because temperature data is a key element in meteorological analysis and forecasting, and is often read to analyze weather trends, and new temperature observation data also needs to be written in a timely manner.

[0040] The second element "0.4" corresponds to the read and write status of humidity data. Compared with temperature data, the read and write frequency of humidity data is slightly lower. This may be because in the current meteorological analysis process, the influence of humidity data on the results is slightly lower than that of temperature data, or the update frequency of humidity data itself is relatively low.

[0041] The third element "0.8" corresponds to the read and write status of the air pressure data. 0.8 in the embodiment of the present invention indicates that the read and write frequency of the air pressure data is relatively high, because the air pressure change is very important for the analysis of the meteorological system, and the air pressure data is often read and written, whether it is short-term weather changes or long-term climate research.

[0042] 3. Access Management Recommendation Vector For example, for an initial meteorological observation data stream (containing multiple meteorological elements), the access management recommendation vector is [0.3, 0.5, 0.2, 0.4].

[0043] The first element "0.3" is related to the priority of data storage. 0.3 indicates a relatively low storage priority, which may mean that some data in the data stream (such as some auxiliary meteorological observation data that has little impact on the overall meteorological analysis) can be appropriately delayed in storage or use a lower-performance storage medium when storage resources are tight.

[0044] The second element "0.5" is related to the optimization strategy for data reading. 0.5 means that a certain degree of reading optimization is required, for example, a cache mechanism can be used to increase the reading speed, because some data in the data stream may have certain delays or efficiency issues when reading, and optimization is needed to meet the real-time requirements of meteorological analysis.

[0045] The third element "0.2" indicates the redundant storage strategy of the data. 0.2 indicates a low redundant storage requirement, that is, there is no need to perform a large amount of redundant storage on the data in the data stream, because the data may be relatively easy to obtain or regenerate, or its importance is not enough to support high redundant storage.

[0046] The fourth element "0.4" indicates the data security storage level. 0.4 means that certain security storage measures are required, such as data verification and encryption, to ensure data integrity and security, but the highest level of security storage measures (such as advanced encryption and multiple backups, etc.) are not required.

[0047] 4. Global read and write status tags For multiple meteorological observation data streams in the target database, the feature vector of the global read-write status label may be [0.5, 0.4, 0.6, 0.3].

[0048] The first element "0.5" represents the overall read and write frequency of meteorological observation data in the entire database. 0.5 means that the read and write frequency is at a medium level, which may be because the database contains meteorological observation data streams with different read and write frequencies, which together form such a medium overall read and write frequency.

[0049] The second element "0.4" indicates the timeliness requirement of the data. 0.4 means that the data in the database as a whole has certain timeliness requirements, but not very strict real-time requirements. For example, some meteorological observation data streams may be updated at the hourly level, rather than the minute-level or second-level, so the overall timeliness requirement is at a medium level.

[0050] The third element "0.6" indicates the data integrity requirement. 0.6 indicates a higher data integrity requirement, because the accuracy of meteorological observation data is crucial to meteorological analysis and forecasting. Even if the reading and writing frequency of some data is not very high, any data loss or damage may affect the final meteorological analysis results, so there is a higher requirement for data integrity overall.

[0051] The fourth element "0.3" indicates the concurrent access requirement of the data. 0.3 indicates a low concurrent access requirement, which means that in most cases, the number of users or applications accessing the database at the same time is relatively small, and highly concurrent read and write operation design is not required, but a certain degree of concurrent processing capability still needs to be considered to cope with occasional concurrent access situations.

[0052] In an example embodiment, the method described in step 130 of using the multiple timing mark observation information as data access mark information, performing read-write state mapping on the meteorological observation attribute knowledge encodings of the multiple target meteorological observation data in the data access mark information, and obtaining the read-write state description vector of the data access mark information includes: using the multiple timing mark observation information as data access mark information, performing read-write state mapping on the meteorological observation attribute knowledge encodings of the multiple target meteorological observation data in the data access mark information to obtain a first read-write state mapping feature, the first read-write state mapping feature including multiple first read-write state mapping clusters; determining the read-write state description vector of the data access mark information based on the read-write state description vectors of the multiple first read-write state mapping clusters.

[0053] On the basis of this example embodiment, the access management suggestion vectors of the multiple meteorological observation data streams in the target database described in step 150 are mapped to read and write states to obtain a global read and write state label of the target database, including: mapping the access management suggestion vectors of the multiple meteorological observation data streams in the target database to read and write states to obtain a second read and write state mapping feature, the second read and write state mapping feature including multiple second read and write state mapping clusters; determining the global read and write state label of the target database based on the read and write state description vectors of the multiple second read and write state mapping clusters.

[0054] In the meteorological observation data access system, the core invention point involves the specific operation methods in step 130 and step 150.

[0055] For step 130, firstly, multiple time-series mark observation information are used as data access mark information, and the meteorological observation attribute knowledge encoding of multiple target meteorological observation data is mapped to a read-write state to obtain a first read-write state mapping feature. The first read-write state mapping feature includes multiple first read-write state mapping clusters. For example, there are three time-series mark observation information, each of which includes five target meteorological observation data, and its meteorological observation attribute knowledge encoding is represented in the form of a feature vector. For the first target meteorological observation data in the first time-series mark observation information, its meteorological observation attribute knowledge encoding feature vector is [0.2, 0.5, 0.3, 0.1, 0.4]. After the read-write state mapping, it may be divided into a first read-write state mapping cluster, which may have specific read-write attributes, such as high-frequency writing, low-frequency reading, etc. For example, other data in the cluster also have similar read-write attribute associations, and may have commonalities in the source of the data, the relationship between the data and other meteorological elements, etc., which leads to their similarity in read-write status. For different target meteorological observation data in each time-series mark observation information, read-write state mapping is performed in this way to form multiple first read-write state mapping subgroups.

[0056] Then, the read-write state description vector of the data access mark information is determined based on the read-write state description vectors of these multiple first read-write state mapping clusters. The read-write state description vectors of these clusters can be regarded as a comprehensive description of the read-write state of the data within the cluster. For example, a first read-write state mapping cluster contains three target meteorological observation data, and their meteorological observation attribute knowledge encoding forms the read-write state description vector of the cluster after the read-write state mapping. For example, the read-write state description vector of the cluster is [0.6, 0.3, 0.4], where the first value 0.6 represents the write frequency weight of the data in the cluster as a whole, 0.3 represents the read frequency weight, and 0.4 represents the importance weight of the data in the entire meteorological observation data stream (this weight is related to the role of the data in meteorological analysis, for example, the data that has a greater impact on the accuracy of meteorological forecasts has a higher weight). By comprehensively processing the read-write state description vectors of each cluster, such as weighted averaging or combining according to specific rules, the read-write state description vector of the data access mark information is finally determined.

[0057] For step 150, firstly, read-write state mapping is performed on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain a second read-write state mapping feature, and the second read-write state mapping feature includes multiple second read-write state mapping clusters. For example, there are four meteorological observation data streams in the target database, and each meteorological observation data stream obtains its own access management suggestion vector after the previous operation. For example, the feature vector of the access management suggestion vector of the first meteorological observation data stream is [0.3, 0.5, 0.2, 0.4]. After read-write state mapping, it may be divided into a second read-write state mapping cluster. The access management suggestion vectors of other meteorological observation data streams in the cluster may have similar read-write state mapping features, such as commonalities in data storage strategies, read optimization requirements, etc. Such read-write state mapping is performed on the access management suggestion vector of each meteorological observation data stream to form multiple second read-write state mapping clusters.

[0058] Then, the global read-write status label of the target database is determined based on the read-write status description vectors of multiple second read-write status mapping subclusters. Each second read-write status mapping subclusters has its own read-write status description vector, which reflects the overall read-write status characteristics of the meteorological observation data stream within the subclusters. For example, the read-write status description vector of a second read-write status mapping subclusters is [0.5, 0.4, 0.6, 0.3], where 0.5 represents the overall read-write frequency of the meteorological observation data stream within the subclusters, 0.4 represents the timeliness requirement of the data, 0.6 represents the integrity requirement of the data, and 0.3 represents the concurrent access requirement of the data. The global read-write status label of the target database is finally determined by comprehensively processing the read-write status description vectors of each second read-write status mapping subclusters, such as summing or taking the maximum or minimum value according to certain weights. The feature vector of the global read-write status label can accurately reflect the overall characteristics of the entire target database in terms of data access. For example, it may be [0.4, 0.3, 0.5, 0.2], which respectively represent the overall read-write frequency, timeliness requirements, integrity requirements and concurrent access requirements of the entire database.

[0059] With this design, firstly, by mapping the read-write status of the meteorological observation attribute knowledge encoding, the read-write status can be determined more accurately according to the data's own characteristics, avoiding the problem of ignoring the inherent differences of the data through unified processing. For example, in the process of determining the read-write status description vector, the read-write characteristics of the data cluster are taken into account, so that data of different properties can be processed appropriately. Secondly, in the determination of the global read-write status label, comprehensive processing based on the read-write status description vectors of multiple clusters can fully reflect the read-write status requirements of the entire database. This helps to formulate a more reasonable data access strategy. For example, more system resources can be allocated for optimized processing for data with high read-write frequency, and data protection measures can be strengthened for data with high integrity requirements. Furthermore, this cluster-based processing method improves the scalability of the system. When a new meteorological observation data stream is added or the data characteristics change, the division and mapping rules of the cluster can be adjusted relatively easily without large-scale reconstruction of the entire system. In short, this technical solution improves the efficiency, accuracy and adaptability of the meteorological observation data access system, and provides reliable technical support for the effective management and utilization of meteorological data.

[0060] Under the further design ideas for step 130 and step 150, the determination of the read-write state description vector of the data access tag information based on the read-write state description vectors of the multiple first read-write state mapping subgroups includes: fusing the vector elements of the key state mapping members of the multiple first read-write state mapping subgroups to determine the read-write state description vector of the data access tag information. The determination of the global read-write state label of the target database based on the read-write state description vectors of the multiple second read-write state mapping subgroups includes: fusing the vector elements of the key state mapping members of the multiple second read-write state mapping subgroups to determine the global read-write state label of the target database.

[0061] Each second read-write state mapping feature includes local mapping features corresponding to multiple different second feature dimensions, each local mapping feature includes multiple second read-write state mapping clusters; the second feature dimension is used to indicate the number of second read-write state mapping clusters in the corresponding second read-write state mapping feature. And the read-write state description vector of each first feature dimension of the target database includes multiple local read-write state vectors of the first feature dimension of the target database corresponding to multiple second feature dimensions.

[0062] In the meteorological observation data access system, the above technical solution further elaborates how to determine the read-write status description vector and the global read-write status label based on the vector elements of the key status mapping members of the cluster.

[0063] The key to the process of determining the read-write state description vector of the data access tag information based on the read-write state description vectors of multiple first read-write state mapping groups in step 130 is to fuse the vector elements of the key state mapping members of multiple first read-write state mapping groups. Take the actual situation of access to a certain meteorological observation data as an example, for example, there are four first read-write state mapping groups, and the vector elements of the key state mapping members of each group have different numerical representations. For example, the vector elements of the key state mapping members of the first group are [0.3, 0.5, 0.2], where 0.3 may represent the set weight related to data writing, 0.5 represents the read-related weight, and 0.2 represents the set importance weight of the data in the current group; the vector elements of the second group are [0.4, 0.3, 0.3]; the third group is [0.2, 0.6, 0.2]; the fourth group is [0.5, 0.2, 0.3]. When fusing these vector elements, a specific fusion rule may be adopted, such as weighted averaging according to the proportion of the amount of data in each group. If the first cluster contains 20% of the total data volume, the second cluster contains 30%, the third cluster contains 25%, and the fourth cluster contains 25%, then the first element of the fused read-write state description vector is calculated as: (0.3×0.2+0.4×0.3+0.2×0.25+0.5×0.25), and the second and third elements are calculated in the same way. The read-write state description vector of the data access tag information determined in this way can comprehensively reflect the key read-write state characteristics of each cluster, thereby more accurately describing the read-write state of the entire data access tag information.

[0064] For the process of determining the global read-write state label of the target database based on the read-write state description vectors of multiple second read-write state mapping clusters in step 150, the vector elements of the key state mapping members of multiple second read-write state mapping clusters are also fused. For example, there are three second read-write state mapping features in the target database, and each second read-write state mapping feature has a different second feature dimension, which means that there are different numbers of second read-write state mapping clusters. For example, the first second read-write state mapping feature has two second read-write state mapping clusters, and the vector elements of its key state mapping members are [0.4, 0.3, 0.3] and [0.5, 0.2, 0.3] respectively; the second second read-write state mapping feature has three clusters, and the vector elements are [0.3, 0.4, 0.3], [0.4, 0.3, 0.3] and [0.3, 0.3, 0.4] respectively; the third second read-write state mapping feature has two clusters, and the vector elements are [0.2, 0.5, 0.3] and [0.3, 0.4, 0.3]. For each second read-write state mapping feature, firstly, the vector elements of the key state mapping members of the cluster are fused according to the set weight of the cluster (such as the importance weight of the meteorological observation data stream within the cluster), and the intermediate result vector of each second read-write state mapping feature is obtained. Then, according to the overall weight of the three second read-write state mapping features in the target database (for example, determined according to the importance of different meteorological observation types), the three intermediate result vectors are fused again, and finally the global read-write state label of the target database is determined.

[0065] In this way, firstly, by fusing the vector elements of the key state mapping members of the cluster, whether in determining the read-write state description vector of the data access tag information or determining the global read-write state label of the target database, the key information within the cluster can be fully utilized to avoid information loss and misjudgment. For example, after the fusion of vector elements of different clusters, the read-write state characteristics of the data under different hierarchical structures can be accurately reflected. Secondly, when dealing with clusters with multiple feature dimensions, fusion according to certain rules can make the determination of the global read-write state label and the read-write state description vector more scientific and reasonable. This helps the system to formulate data access strategies that are more in line with actual needs based on these accurate state labels and vectors, improve the accuracy, efficiency and adaptability of the meteorological observation data access system, and ensure the effective management and utilization of meteorological data.

[0066] On the basis of the above-mentioned example embodiments, the method of using the multiple timing mark observation information as data access mark information, performing read-write state mapping on the meteorological observation attribute knowledge encoding of the multiple target meteorological observation data in the data access mark information, and obtaining a first read-write state mapping feature includes: using the multiple timing mark observation information as data access mark information, based on multiple different first feature dimensions, performing read-write state mapping on the meteorological observation attribute knowledge encoding of the multiple target meteorological observation data in the data access mark information, and obtaining first read-write state mapping features corresponding to multiple first feature dimensions, wherein the first feature dimension is used to indicate the number of first read-write state mapping clusters in the corresponding first read-write state mapping feature; the read-write state description vector of the data access mark information includes the read-write state description vectors corresponding to the multiple first feature dimensions of the data access mark information.

[0067] The method of utilizing the read / write state description vectors of the multiple timing mark observation information to determine the access management recommendation vector of the initial meteorological observation data stream in step 140 includes: fusing the read / write state description vectors corresponding to the same first characteristic dimension in the read / write state description vectors of the multiple timing mark observation information to obtain the access management recommendation vectors of the initial meteorological observation data stream corresponding to multiple first characteristic dimensions respectively.

[0068] The further refined embodiment of step 150 performs read-write state mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain a second read-write state mapping feature, including: performing read-write state mapping on the access management suggestion vectors corresponding to the same first feature dimension among the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain second read-write state mapping features corresponding to multiple first feature dimensions respectively; the global read-write state label of the target database includes the read-write state description vectors corresponding to the multiple first feature dimensions of the target database respectively.

[0069] The process of using multiple time-series mark observation information as data access mark information and performing read-write state mapping on the meteorological observation attribute knowledge encoding of the target meteorological observation data to obtain the first read-write state mapping feature is based on multiple different first feature dimensions. For example, there are three different first feature dimensions, namely 3, 4, and 5. When the first feature dimension is 3, when performing read-write state mapping on the meteorological observation attribute knowledge encoding of the target meteorological observation data in the data access mark information, a first read-write state mapping feature corresponding to the first feature dimension will be obtained. The number of first read-write state mapping clusters contained in this feature is 3. For example, in this mapping process, for a certain target meteorological observation data, its meteorological observation attribute knowledge encoding is represented by the feature vector [0.3, 0.5, 0.2], which is divided into a first read-write state mapping cluster after mapping, and the overall read-write state of the cluster is associated with the encoding feature of the data. Similarly, for the cases where the first feature dimension is 4 and 5, mapping will be performed according to the respective rules to obtain the corresponding first read-write state mapping features, and the number of first read-write state mapping clusters in each feature is 4 and 5 respectively. In addition, the read-write state description vector of the data access mark information contains multiple read-write state description vectors corresponding to the first feature dimensions, which means that the read-write state descriptions under different first feature dimensions are independent of each other and together constitute the overall read-write state description.

[0070] Next, in step 140, when the access management recommendation vector of the initial meteorological observation data stream is determined using the read-write state description vectors of multiple time-series mark observation information, the read-write state description vectors corresponding to the same first characteristic dimension in the read-write state description vectors of the multiple time-series mark observation information are fused. For example, for the three first characteristic dimensions mentioned above, the read-write state description vectors under each first characteristic dimension are fused. For example, when the first characteristic dimension is 3, there are three time-series mark observation information, and their read-write state description vectors under the first characteristic dimension are [0.4, 0.3, 0.3], [0.3, 0.4, 0.3] and [0.3, 0.3, 0.4] respectively. During the fusion process, the fusion weight may be determined based on factors such as the importance of each element of the vector or the amount of data. If a simple addition and averaging method with equal weights is used, the first element of the fused access management recommendation vector is (0.4+0.3+0.3) / 3, and the second and third elements are calculated similarly. In this way, the access management suggestion vector of the initial meteorological observation data stream under the first characteristic dimension is obtained. The same operation is performed for other first characteristic dimensions, and finally the access management suggestion vectors of the initial meteorological observation data stream corresponding to multiple first characteristic dimensions are obtained.

[0071] In a further refined embodiment of step 150, the process of performing read-write state mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain the second read-write state mapping feature is as follows. For the access management suggestion vectors of multiple meteorological observation data streams in the target database, first perform read-write state mapping on the access management suggestion vectors corresponding to the same first feature dimension. For example, there are four meteorological observation data streams. When the first feature dimension is 3, the access management suggestion vectors of these four meteorological observation data streams under the first feature dimension are [0.3, 0.5, 0.2], [0.4, 0.3, 0.3], [0.2, 0.6, 0.2] and [0.5, 0.2, 0.3] respectively. Through a specific read-write state mapping rule, the second read-write state mapping feature corresponding to the first feature dimension is obtained. The mapping operation is also performed in the same manner for other first feature dimensions, thereby obtaining second read-write state mapping features corresponding to multiple first feature dimensions respectively. Furthermore, the global read / write status tag of the target database includes read / write status description vectors corresponding to multiple first characteristic dimensions of the target database, which enables the global read / write status tag to fully reflect the read / write status of the target database under different first characteristic dimensions.

[0072] It can be seen that by performing operations such as read-write state mapping based on different first characteristic dimensions, the processing of meteorological observation data can be made more detailed and accurate. For example, when determining the first read-write state mapping feature, different first characteristic dimensions can correspond to different meteorological observation data characteristics or data grouping methods, so as to better mine the read-write state characteristics of the data. In terms of fusion operations, whether it is the fusion of the read-write state description vector of the time-series mark observation information to obtain the access management suggestion vector, or the read-write state mapping of the access management suggestion vector of the meteorological observation data stream, it can integrate the information of multiple related vectors to avoid one-sidedness. This helps to accurately determine the access management strategy of the data, improve the accuracy and reliability of the meteorological observation data access system, and can better adapt to the complexity and diversity of meteorological observation data, providing solid technical support for the effective management and utilization of meteorological data.

[0073] In an optional design idea, based on steps 110 to 150, the method further includes: (1) performing feature matching on the global read-write status tag of the target database based on a strategy vector coordinate system to obtain a read-write execution strategy vector of the target database; and (2) processing the read-write execution strategy vector of the target database to obtain a data access strategy of the target database.

[0074] In the meteorological observation data access system, based on the previous step 110150, there are further optional design ideas. First, the global read-write status label of the target database is feature matched based on the strategy vector coordinate system to obtain the read-write execution strategy vector of the target database. The global read-write status label of the target database exists in the form of a feature vector, which contains comprehensive information about the data access of the entire target database. For example, the feature vector of the global read-write status label is [0.4, 0.3, 0.5, 0.2], where 0.4 may represent the overall read-write frequency of the entire database, 0.3 represents the timeliness requirement of the data, 0.5 represents the integrity requirement of the data, and 0.2 represents the concurrent access requirement of the data.

[0075] The strategy vector coordinate system is a reference system built to determine the read-write execution strategy vector. In this coordinate system, different coordinate axes represent different factors related to data access strategies, such as read-write frequency, timeliness, integrity, concurrent access, etc. For the feature vector [0.4, 0.3, 0.5, 0.2] of the global read-write status label, when performing feature matching in the strategy vector coordinate system, the read-write execution strategy vector will be determined according to the meaning represented by each coordinate axis and the pre-set matching rules. For example, in the strategy vector coordinate system, for the read-write frequency coordinate axis, if the value is between 00.3, it represents a low-frequency read-write strategy, between 0.30.7, it represents a medium-frequency read-write strategy, and between 0.71, it represents a high-frequency read-write strategy, then the read-write frequency of 0.4 corresponds to the medium-frequency read-write strategy. Timeliness, integrity, and concurrent access requirements are also matched according to their respective matching rules. For example, in terms of timeliness, 0.3 corresponds to a general timeliness strategy, integrity 0.5 corresponds to a high-integrity strategy, and concurrent access requirements 0.2 correspond to a low-concurrency access strategy. By combining these matching results, the read-write execution strategy vector of the target database is obtained. This vector reflects the specific execution strategy determined in the strategy vector coordinate system according to the global read-write status label. For example, the read-write execution strategy vector may be expressed as [medium-frequency read-write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy].

[0076] Next, the read and write execution strategy vector of the target database is processed to obtain the data access strategy of the target database. For the read and write execution strategy vectors obtained above [medium-frequency read and write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy], corresponding processing is performed according to different strategies to determine the data access strategy. Under the medium-frequency read and write strategy, a moderately optimized read and write algorithm may be adopted, which does not require extremely high speed optimization like the high-frequency read and write strategy, nor can it be treated more leniently like the low-frequency read and write strategy. For the general timeliness strategy, the data update and storage cycle can be set according to the regular time interval, and there is no need for particularly frequent or loose time arrangements. The high integrity strategy requires strict data verification, backup and other measures in the data access process to ensure the accuracy and integrity of the data. For example, data verification is performed after each data is written, and data is backed up to multiple storage locations regularly. The low concurrent access strategy means that there is no need to make too much preparation for a large number of concurrent accesses in the allocation of system resources, such as the need to configure too many concurrent access channels or complex concurrent control mechanisms. By processing each strategy in the read-write execution strategy vector, the data access strategy of the target database is finally determined. The data access strategy is a comprehensive and integrated solution that covers specific operating methods in many aspects such as data read-write frequency, timeliness, integrity and concurrent access.

[0077] Therefore, by obtaining the read-write execution strategy vector through feature matching based on the strategy vector coordinate system, the complex information contained in the global read-write status tag can be converted into a specific execution strategy in a targeted and regularized manner. For example, by converting numerical features into actual strategy descriptions through clear matching rules, ambiguity and uncertainty are avoided. Then, by processing the read-write execution strategy vector to obtain the data access strategy, all aspects of data access can be fully considered, making the data access strategy more scientific and reasonable. This step-by-step derivation process from the global read-write status tag to the read-write execution strategy vector and then to the data access strategy improves the accuracy, reliability and adaptability of the meteorological observation data access system, ensures that the meteorological observation data can be effectively managed and operated according to its own characteristics and needs during the access process, and guarantees the quality and availability of meteorological data.

[0078] In a preferred technical solution, the processing of the read-write execution strategy vector of the target database to obtain the data access strategy of the target database includes: based on the data access demand indicated by the channel capacity control vector, the read-write execution strategy vector of the target database is processed by a feedforward neural network based on conditional probability to determine the data access strategy of the target database.

[0079] In the technical solution of the meteorological observation data access system, a method based on the data access demand indicated by the channel capacity control vector and a feedforward neural network based on conditional probability is adopted for the process of processing the read and write execution strategy vector of the target database into the data access strategy of the target database.

[0080] The read / write execution strategy vector of the target database contains various strategy information about database read / write operations. For example, the read / write execution strategy vector may be expressed as [medium frequency read / write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy]. Each strategy element in the embodiment of the present invention reflects the specific requirements or attributes of the target database in terms of data access.

[0081] The channel capacity control vector indicates the data access demand from another perspective. It may contain various information related to the data channel capacity, such as the data flow limit of each channel, the data storage capacity limit, etc. For example, the channel capacity control vector is [0.6, 0.4, 0.3], where 0.6 may represent the capacity utilization limit of a main data channel, 0.4 represents the capacity limit of another related channel, and 0.3 represents the additional capacity limit under specific conditions or the capacity limit of the backup channel. This vector provides constraints and demand information on channel capacity for determining data access strategies.

[0082] The feedforward neural network based on conditional probability plays a key role in this process. The feedforward neural network is a neural network structure with an input layer, a hidden layer, and an output layer. In this scenario, the input layer receives the read-write execution strategy vector and the channel capacity control vector of the target database. For example, the read-write execution strategy vector [medium frequency read-write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy] and the channel capacity control vector [0.6, 0.4, 0.3] are used as input. The neurons in the network are connected by weights, which are determined during the training process and are related to the conditional probability.

[0083] The conditional probability here is reflected as the probability of adopting the set data access strategy under different read-write execution strategies and channel capacity conditions. For example, under the capacity constraints represented by the medium-frequency read-write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy, and channel capacity control vector, there is a certain probability for the set data storage method (such as using the set storage medium, storage format, etc.). This probability is obtained by analyzing and learning the access conditions of a large amount of meteorological observation data.

[0084] In the hidden layer of the network, neurons process the input information. They transform and combine the input vector information according to predetermined weights and activation functions. In this process, different neurons may focus on the relationship between different strategies and capacity information, thereby mining the features hidden behind this information. For example, some neurons may focus on the relationship between high integrity strategies and channel capacity constraints to determine how to ensure data integrity while meeting channel capacity requirements in this case.

[0085] Finally, the data access strategy of the target database is obtained at the output layer. The data access strategy is a result obtained by processing the read-write execution strategy vector and the channel capacity control vector based on conditional probability through a feedforward neural network. For example, the generated data access strategy may include using a specific storage medium (such as a high-speed hard disk to meet certain speed requirements under the medium-frequency read-write strategy), setting a specific data update cycle (determined according to the general timeliness strategy), using a strict data verification and backup mechanism (determined by the high integrity strategy), and configuring an appropriate amount of concurrent access processing capabilities (based on the low concurrent access strategy), while also meeting the channel capacity restrictions indicated by the channel capacity control vector, such as reasonably allocating the storage of data in different channels to avoid exceeding the channel capacity.

[0086] In this way, by introducing the channel capacity control vector, the channel capacity limitation in the data access process can be fully considered, avoiding problems such as data storage failure or performance degradation caused by ignoring capacity issues. The use of feedforward neural networks based on conditional probability makes the determination of data access strategies more scientific and accurate. It can use a large amount of historical data and empirical knowledge to reflect the complex relationship between different factors through conditional probability, thereby providing a more reliable basis for data access strategies. This method, which comprehensively considers multiple factors and uses advanced neural network technology, improves the adaptability, reliability and efficiency of the meteorological observation data access system, ensures that appropriate data access strategies can be formulated under different read-write execution strategies and channel capacity requirements, and ensures the effective management and utilization of meteorological observation data.

[0087] In an alternative preferred technical idea, the data access demand indicated by the channel capacity control vector is based on the data access demand, and the read and write execution strategy vector of the target database is processed by a feedforward neural network based on conditional probability to determine the data access strategy of the target database, including: combining the read and write execution strategy vector of the target database and the overflow detection mechanism execution vector of the target database by a feedforward neural network based on conditional probability to obtain a multi-channel access interaction vector of the target database; based on the data access demand indicated by the channel capacity control vector, the multi-channel access interaction vector of the target database is processed to determine the data access strategy of the target database.

[0088] In the technical solution of the meteorological observation data access system, for the key link of determining the data access strategy of the target database, there is a more detailed operation process under an alternative optimal technical idea.

[0089] Firstly, it involves combining the read-write execution strategy vector of the target database and the overflow detection mechanism execution vector of the target database through a feedforward neural network based on conditional probability to obtain a multi-channel access interaction vector of the target database.

[0090] The read-write execution strategy vector of the target database contains important information related to the database read-write operations. For example, the read-write execution strategy vector may be [medium-frequency read-write strategy, looser timeliness strategy, high integrity strategy, low concurrent access strategy]. The "medium-frequency read-write strategy" in the embodiment of the present invention indicates that the read-write frequency of the data is at a medium level, which means that the frequency of read-write operations within a certain time range is neither very high nor very low; the "relaxed timeliness strategy" indicates that the data does not have particularly strict requirements on timeliness, and may allow updates or reading within a relatively long time interval; the "high integrity strategy" reflects that the integrity of the data is of vital importance, and multiple measures need to be taken during the data access process to ensure that the data is not damaged or lost; the "low concurrent access strategy" reflects that the system does not need to deal with a large number of concurrent read-write requests, and does not need to over-consider high concurrency in resource allocation and architecture design.

[0091] The overflow detection mechanism execution vector of the target database is also an important component. For example, the overflow detection mechanism execution vector is [0.3, 0.6, 0.1], where 0.3 may represent the overflow detection sensitivity in a specific channel or data block. The lower the value, the lower the sensitivity, and the strict processing mechanism may not be triggered immediately for a small amount of data overflow; 0.6 means that the overflow detection sensitivity in another situation (such as a specific type of data or a specific storage area) is relatively high, which means that once the amount of data approaches or may exceed the set capacity limit, the overflow detection mechanism will be triggered quickly and corresponding measures will be taken; 0.1 means that the overflow detection sensitivity in other special situations (such as spare channels or temporary storage areas) is very low, which may be because these areas have a certain degree of flexibility in accommodating the amount of data or the temporary nature of the data in these areas makes a small amount of overflow not have serious consequences.

[0092] The feedforward neural network based on conditional probability plays a core role in this combination process. The feedforward neural network consists of an input layer, a hidden layer, and an output layer. In this scenario, the input layer receives the read-write execution strategy vector and the overflow detection mechanism execution vector. The neurons in the neural network are connected by weights, which are related to the conditional probability. The conditional probability reflects the probability of various combinations under different read-write execution strategies and overflow detection mechanism execution states. For example, under the combination of medium-frequency read-write strategy and overflow detection sensitivity of 0.3, there is a specific probability that this combination is likely to occur in the actual data access process. This probability is obtained by analyzing and learning the access conditions of a large amount of meteorological observation data.

[0093] In the hidden layer of the neural network, neurons process the input vector information. Neurons in the hidden layer transform and combine the read-write execution strategy vector and the overflow detection mechanism execution vector according to predetermined weights and activation functions. For example, some neurons may focus on the relationship between a high integrity policy and a higher overflow detection sensitivity (such as 0.6), because a high integrity policy may require a stricter overflow detection mechanism to ensure that data is not lost or damaged due to overflow under any circumstances. Different neurons will explore the potential relationship between different policy elements and overflow detection mechanism elements, thereby integrating this information.

[0094] Through the processing of the feedforward neural network, the multi-channel access interaction vector of the target database is obtained at the output layer. The multi-channel access interaction vector integrates the information of the read-write execution strategy vector and the overflow detection mechanism execution vector. It reflects the interaction relationship and requirements of data access between various channels under the consideration of the read-write strategy and overflow detection mechanism. For example, the multi-channel access interaction vector may be expressed as [channel 1 interaction relationship, channel 2 interaction relationship, channel 3 interaction relationship], where the interaction relationship of each channel may contain comprehensive information such as read-write frequency, integrity requirements, overflow detection sensitivity, etc.

[0095] Next, based on the data access demand indicated by the channel capacity regulation vector, the multi-channel access interaction vector of the target database is processed to determine the data access strategy of the target database.

[0096] The channel capacity control vector contains key information about the data channel capacity. For example, the channel capacity control vector is [0.5, 0.4, 0.3], where 0.5 may represent the upper limit of the capacity utilization of the main data channel, that is, the channel can only use up to 50% of its capacity during data access to ensure the stable operation of the system and efficient data transmission; 0.4 represents the capacity limit of another auxiliary channel, which may be mainly used to store some less frequently accessed data or as a data cache area; 0.3 represents the capacity limit of a spare channel or a specific functional channel (such as a channel dedicated to data verification or temporary data storage).

[0097] When processing multi-channel access interaction vectors, the constraints brought by the channel capacity control vector need to be fully considered. For example, if a channel interaction relationship in the multi-channel access interaction vector indicates that the channel requires a higher read and write frequency (such as the high-frequency read and write requirements in the channel 1 interaction relationship), but the capacity utilization limit of the channel in the channel capacity control vector is 0.5, then when determining the data access strategy, it is necessary to adjust the read and write operation mode of the channel. Data compression technology may be used to reduce the amount of data read and written each time, or the read and write time interval may be adjusted to avoid exceeding the channel capacity. For channels with higher integrity requirements (such as the high integrity requirements reflected by the channel 2 interaction relationship in the multi-channel access interaction vector), if the capacity limit of the channel in the channel capacity control vector is 0.4, it may be necessary to prioritize the allocation of more system resources for data verification and backup to ensure data integrity while meeting the capacity limit. For channels that are sensitive to overflow detection mechanisms (such as the channel 3 interaction relationship in the multi-channel access interaction vector shows high overflow detection sensitivity), if the capacity limit of the channel in the channel capacity control vector is 0.3, then when approaching the capacity limit, the overflow detection and processing mechanism needs to be more strictly executed, and data migration or cleanup operations may be performed in advance.

[0098] Through such a process, the data access strategy of the target database is finally determined. This data access strategy is a comprehensive solution that covers the read and write frequency, integrity requirements, overflow detection mechanism, and channel capacity limit of each channel. For example, the data access strategy may include: for channel 1, medium-frequency read and write operations are used, data is updated once an hour, appropriate data compression technology is used, and capacity warning is issued when the capacity utilization rate reaches 40%; for channel 2, it is set to low-frequency read and write operations, data verification is performed once a day, and a double backup mechanism is used to ensure data integrity when the channel capacity utilization rate does not exceed 30%; for channel 3, according to its high overflow detection sensitivity and low capacity limit, it is used as a temporary data storage channel, only temporary data generated in the last hour is stored, and the oldest data is automatically cleaned up when the capacity utilization rate reaches 20%.

[0099] Based on the above-mentioned preferred technical ideas, firstly, by combining the read-write execution strategy vector and the overflow detection mechanism execution vector into a multi-channel access interaction vector, it is possible to comprehensively consider the read-write operation, integrity requirements, overflow detection and other factors and their interrelationships in the data access process. This comprehensive consideration avoids the data access problem caused by focusing only on a single factor. For example, the coordinated consideration between the high integrity strategy and the high overflow detection sensitivity can ensure that when data integrity is critical, timely detection and avoidance of data damage or loss that may be caused by overflow. Secondly, based on the channel capacity control vector, the multi-channel access interaction vector is processed to determine the data access strategy, which can fully consider the limitation of channel capacity. This makes the data access strategy more in line with the actual system architecture and hardware conditions, avoiding performance degradation, data loss and other problems caused by the mismatch between data access requirements and channel capacity. For example, adjusting the read-write frequency and data processing method according to the capacity limitations of different channels can maximize the use of channel capacity and improve the overall efficiency of the system while ensuring normal data access. Finally, the entire technical solution combines and processes vectors through a feedforward neural network based on conditional probability, which utilizes the learning and processing capabilities of neural networks for complex relationships. The conditional probability obtained by learning from a large amount of data can more accurately reflect the intrinsic connection between different factors, thereby providing a more scientific and reasonable basis for determining data access strategies, improving the accuracy, reliability and adaptability of meteorological observation data access systems, and ensuring the effective management and utilization of meteorological observation data.

[0100] Based on the above-mentioned preferred technical ideas, the feature matching of the global read-write status label of the target database based on the strategy vector coordinate system is performed to obtain the read-write execution strategy vector of the target database, including: performing feature matching of the global read-write status label of the target database based on the strategy vector coordinate system through a deep learning network to obtain the read-write execution strategy vector of the target database.

[0101] The method further includes: debugging the deep learning network based on debugging examples including meteorological observation debugging vectors, overflow detection mechanism debugging vectors, channel capacity regulation training vectors and data access labeling strategies.

[0102] It can be understood that the deep learning network is used to perform feature matching on the meteorological observation debugging vector based on the strategy vector coordinate system to obtain the read-write debugging strategy vector. The feedforward neural network based on conditional probability is used to combine the read-write debugging strategy vector and the overflow detection mechanism debugging vector to obtain a multi-channel access debugging vector; based on the data access requirements indicated by the channel capacity regulation training vector, the multi-channel access debugging vector is processed to determine the data access debugging strategy, and the network weight of the deep learning network is optimized according to the data access debugging strategy and the data access annotation strategy.

[0103] In the technical solution framework of the meteorological observation data access system, the deep learning network is used to perform feature matching based on the strategy vector coordinate system for the global read and write status labels of the target database to obtain the read and write execution strategy vector.

[0104] The global read-write status label of the target database exists in the form of a specific feature vector, which contains comprehensive information about the overall read-write status of the target database. For example, the feature vector of the global read-write status label is [0.4, 0.3, 0.5, 0.2], where 0.4 may represent the read-write frequency weight of the database as a whole, 0.3 represents the timeliness weight of the data, 0.5 represents the integrity weight of the data, and 0.2 represents the concurrent access weight of the data. The strategy vector coordinate system is a reference system built for feature matching. Different coordinate axes represent various factors related to data access strategies, such as read-write frequency, timeliness, integrity, concurrent access, etc. In this process, the deep learning network matches the features of the global read-write status label in the strategy vector coordinate system based on its complex structure and algorithm. Through the calculation and processing of multiple hidden layers and neurons in the deep learning network, each element in the global read-write status label is associated and matched with each factor in the strategy vector coordinate system, and finally the read-write execution strategy vector of the target database is obtained. The read-write execution strategy vector reflects the specific execution strategy determined according to the matching result of the global read-write status label in the strategy vector coordinate system. For example, the read-write execution strategy vector may be expressed as [medium frequency read-write strategy, general timeliness strategy, high integrity strategy, low concurrent access strategy].

[0105] On this basis, the method also includes a process of debugging the deep learning network. The debugging process is based on a variety of debugging examples, including meteorological observation debugging vectors, overflow detection mechanism debugging vectors, channel capacity regulation training vectors, and data access annotation strategies.

[0106] The meteorological observation debugging vector is a vector related to meteorological observation data, which contains relevant information about meteorological observation data used to debug the deep learning network. For example, the meteorological observation debugging vector is [0.3, 0.5, 0.2], where 0.3 may represent the weight related to the set meteorological observation data type, 0.5 represents the weight of the set characteristics of the data (such as the stability or volatility of the data), and 0.2 represents the weight related to the data source or acquisition device. The deep learning network first performs feature matching on the meteorological observation debugging vector based on the strategy vector coordinate system to obtain the read-write debugging strategy vector. This process is similar to feature matching on the global read-write status label of the target database. The information in the meteorological observation debugging vector is matched with the factors in the strategy vector coordinate system through the deep learning network to obtain the read-write debugging strategy vector. For example, the read-write debugging strategy vector may be expressed as [low-frequency read-write strategy, relaxed timeliness strategy, medium integrity strategy, low concurrent access strategy].

[0107] The overflow detection mechanism debugging vector is also an important part of the debugging process. For example, the overflow detection mechanism debugging vector is [0.2, 0.6, 0.2], where 0.2 represents the initial value of the overflow detection sensitivity in a specific channel or data block, 0.6 represents a relatively high value of the overflow detection sensitivity in another case (such as a specific type of data or a specific storage area), and 0.2 represents the value of the overflow detection sensitivity in other special cases (such as spare channels or temporary storage areas). The feedforward neural network based on conditional probability plays a role in this process. It combines the previously obtained read-write debugging strategy vector and the overflow detection mechanism debugging vector to obtain a multi-channel access debugging vector. The neurons in the feedforward neural network are connected by weights, which are related to the conditional probabilities. The conditional probability reflects the probability of various combinations under different read-write debugging strategies and overflow detection mechanism debugging states. For example, under the combination of low-frequency read-write strategy and overflow detection sensitivity of 0.6, there is a specific probability that represents the possibility of this combination in the actual data access process. The input vector is processed through the hidden layer of the feedforward neural network to explore the potential relationship between the read-write debugging strategy vector and the overflow detection mechanism debugging vector, and finally a multi-channel access debugging vector is obtained at the output layer. For example, the multi-channel access debugging vector may be expressed as [channel 1 debugging relationship, channel 2 debugging relationship, channel 3 debugging relationship], where the debugging relationship of each channel contains comprehensive information such as read-write frequency, integrity requirements, overflow detection sensitivity, etc.

[0108] The channel capacity control training vector contains key information for training about the data channel capacity. For example, the channel capacity control training vector is [0.4, 0.3, 0.3], where 0.4 may represent the training value of the upper limit of the capacity utilization of the main data channel, 0.3 represents the training value of the capacity limit of another auxiliary channel, and 0.3 represents the training value of the capacity limit of a spare channel or a specific functional channel (such as a channel dedicated to data verification or temporary data storage). Based on the data access requirements indicated by the channel capacity control training vector, the multi-channel access debugging vector is processed to determine the data access debugging strategy. During the processing, the constraints brought by the channel capacity control training vector need to be fully considered. For example, if a channel debugging relationship in the multi-channel access debugging vector indicates that the channel requires a higher read and write frequency (such as the high-frequency read and write requirements in the channel 1 debugging relationship), but the capacity utilization upper limit of the channel in the channel capacity control training vector is 0.4, then when determining the data access debugging strategy, it is necessary to adjust the read and write operation mode of the channel, and data compression technology may be used to reduce the amount of data read and written each time, or adjust the time interval of reading and writing to avoid exceeding the channel capacity. For channels with high integrity requirements (such as the channel 2 debugging relationship in the multi-channel access debugging vector that reflects high integrity requirements), if the capacity limit of the channel in the channel capacity control training vector is 0.3, it may be necessary to prioritize the allocation of more system resources for data verification and backup to ensure data integrity while meeting the capacity limit. For channels that are sensitive to overflow detection mechanisms (such as the channel 3 debugging relationship in the multi-channel access debugging vector that shows high overflow detection sensitivity), if the capacity limit of the channel in the channel capacity control training vector is 0.3, then when approaching the capacity limit, the overflow detection and handling mechanism needs to be more strictly enforced, and data migration or cleanup operations may be performed in advance.

[0109] The data access annotation strategy is a pre-set standard used to measure the correctness of the data access debugging strategy. The network weights of the deep learning network are optimized based on the data access debugging strategy and the data access annotation strategy. In this process, the weights in the deep learning network are adjusted by comparing the differences between the data access debugging strategy and the data access annotation strategy. If there is a large difference between the data access debugging strategy and the data access annotation strategy, it means that the current weights of the deep learning network may not be appropriate and need to be adjusted. For example, if the read and write frequencies in the data access debugging strategy differ greatly from the read and write frequencies in the data access annotation strategy, the deep learning network will adjust the neuron connection weights related to the read and write frequencies so that results closer to the data access annotation strategy can be obtained in subsequent processing. By continuously debugging with debugging examples, the deep learning network can continuously optimize its network weights, thereby improving the accuracy of feature matching based on the strategy vector coordinate system for the global read and write status labels of the target database, and thus obtaining a more reasonable read and write execution strategy vector.

[0110] It can be seen that, firstly, the read-write execution strategy vector is obtained by feature matching based on the strategy vector coordinate system through the deep learning network, which utilizes the powerful feature learning and pattern matching capabilities of the deep learning network. It can accurately mine the relationship between the factors in the strategy vector coordinate system from the complex information of the global read-write status label, so as to obtain a read-write execution strategy vector that is more in line with actual needs. For example, the deep learning network can accurately match the appropriate read-write execution strategy according to the integrity weight and timeliness weight in the global read-write status label, avoiding the limitations that may exist in manually set rules. Secondly, debugging the deep learning network based on debugging examples including meteorological observation debugging vectors, overflow detection mechanism debugging vectors, channel capacity regulation training vectors and data access annotation strategies can enable the deep learning network to continuously optimize its network weights. This helps to improve the accuracy and reliability of the entire data access system. For example, by comparing the data access debugging strategy and the data access annotation strategy to adjust the network weight, it can ensure that the deep learning network can obtain more accurate results under different data situations and requirements. Furthermore, the interactive operations between the various vectors involved in the debugging process, such as the combination of the read-write debugging strategy vector and the overflow detection mechanism debugging vector based on the conditional probability feedforward neural network, and the processing of the multi-channel access debugging vector based on the channel capacity regulation training vector, fully consider various factors in the data access process, such as the overflow detection mechanism, channel capacity, etc. This comprehensive consideration of multiple factors can make the data access strategy more complete and reasonable, improve the adaptability and effectiveness of the meteorological observation data access system, and ensure the efficient management and accurate use of meteorological observation data.

[0111] In one technical idea, step 110 describes taking the multiple meteorological observation data streams in the target database as initial meteorological observation data streams respectively, performing timing marking operations based on a ring buffer structure on the initial meteorological observation data streams to obtain multiple timing marked observation information, including: taking the multiple meteorological observation data streams in the target database as initial meteorological observation data streams respectively, performing grouping marking based on timing nodes on the initial meteorological observation data streams to obtain meteorological observation marked groups; dividing the meteorological observation marked groups into multiple timing marked observation information according to observation priority.

[0112] In the technical solution of the meteorological observation data access system, the operation of step 110 is the starting part of the entire data processing flow, which includes the timing marking operation of the initial meteorological observation data stream based on the ring buffer structure.

[0113] First, multiple meteorological observation data streams in the target database are respectively used as initial meteorological observation data streams, and grouping and marking them based on time series nodes to obtain meteorological observation marking groups. The meteorological observation data stream contains rich meteorological observation data, which have certain regularities and characteristics in the time series. For example, a meteorological observation data stream may contain observation data of meteorological elements such as temperature, humidity, and air pressure in a certain area for many consecutive years. Time series nodes can be set according to a certain time interval, such as in hours, and the observation data per hour is used as a time series node. By grouping and marking these initial meteorological observation data streams according to time series nodes, meteorological observation marking groups can be obtained. For example, a meteorological observation marking group contains meteorological observation data with hours as time series nodes in a certain day, and these data cover the meteorological element information at different times of the day.

[0114] Then, the meteorological observation mark group is divided into multiple time-series mark observation information according to the observation priority. The observation priority is determined according to the importance of meteorological elements in meteorological analysis, forecasting and other applications. For example, in weather forecasting, air pressure data may have a higher observation priority because changes in air pressure play a key role in indicating the evolution of the weather system; while some auxiliary meteorological elements, such as local wind speed changes in certain specific locations (when the impact on the overall weather conditions is relatively small), may have a lower observation priority. For meteorological observation mark groups containing multiple meteorological elements, they are divided according to the observation priority. For example, the data feature vector in a meteorological observation mark group is [0.6, 0.3, 0.1], where 0.6 represents the weight related to air pressure data (reflecting its relative importance in the group), 0.3 represents the weight related to temperature data, and 0.1 represents the weight related to local wind speed data. According to such a weight relationship, the meteorological observation mark group can be divided into multiple time-series mark observation information. For example, the part closely related to the air pressure data is used as a time-series marked observation information with a higher priority. Since the air pressure data has a higher weight, this part of information may be paid attention to and processed first in the subsequent meteorological analysis; while the part related to the local wind speed data is used as a time-series marked observation information with a relatively low priority.

[0115] This method of obtaining time-series marked observation information by dividing meteorological observation mark groups according to observation priority is of great significance in the entire meteorological observation data access system. It enables subsequent data processing to perform targeted operations according to the importance of different data. For example, in terms of data storage, higher-quality storage resources, such as high-speed storage media or larger storage space, can be allocated to high-priority time-series marked observation information to ensure the rapid storage and reliable preservation of these key data; while for low-priority time-series marked observation information, a relatively economical storage method can be adopted. In the process of data reading and analysis, high-priority time-series marked observation information can also be paid attention to and processed first, improving the efficiency of meteorological analysis and forecasting. At the same time, this operation method based on the ring buffer structure lays the foundation for the continuous writing, cyclic overwriting and efficient management of multi-channel data of subsequent data. For example, the ring buffer structure can realize multiple independent meteorological observation data streams sharing storage space in the same buffer. When processing multiple time-series marked observation information, it can ensure continuous access to data through reasonable read and write pointer movement, and support parallel access, thereby greatly improving data access speed and efficiency.

[0116] In addition, the data division method in this technical solution is conducive to the classification management and orderly processing of data. Different management strategies can be adopted for time-series tagged observation information of different priorities. For example, high-priority time-series tagged observation information may require more frequent integrity checks and backups to prevent data loss or damage from causing serious impact on meteorological analysis; while low-priority time-series tagged observation information can appropriately reduce the inspection frequency to reduce the consumption of system resources. In the data processing process, different time-series tagged observation information can also be processed in order of priority, making the entire data processing process more orderly and efficient.

[0117] Based on the above technical scheme, firstly, the intrinsic value difference of meteorological observation data can be better reflected by grouping and marking based on time series nodes and dividing according to observation priority. For example, by dividing priorities according to the importance of meteorological elements in meteorological analysis, key data can be focused on and processed, which improves the pertinence and effectiveness of meteorological observation data processing. Secondly, in terms of data storage and management, allocating resources according to priority can improve resource utilization efficiency. For example, providing high-quality storage resources for high-priority data can not only ensure the security and availability of important data, but also optimize the allocation of storage resources as a whole. Furthermore, this division method is conducive to improving the efficiency and accuracy of data processing. In the process of meteorological analysis, data can be processed in order of priority, and key data can be processed first, reducing unnecessary calculations and processing processes, so as to obtain accurate meteorological analysis results more quickly. At the same time, it provides an orderly and efficient data management mode for the entire meteorological observation data access system, ensuring the effective use and long-term management of meteorological observation data.

[0118] In an independent embodiment, the step 120 of performing attribute knowledge mining on the plurality of target meteorological observation data to obtain meteorological observation attribute knowledge encodings of the plurality of target meteorological observation data includes: (1) Inputting each target meteorological observation data into the spatiotemporal feature mining layer in the MetNet model, obtaining a first spatiotemporal attribute vector and a second spatiotemporal attribute vector of each target meteorological observation data generated by the spatiotemporal feature mining layer, wherein the spatiotemporal feature mining layer includes a plurality of residual cores connected to each other, the first spatiotemporal attribute vector is a spatiotemporal attribute vector generated by a non-final residual core among the plurality of residual cores connected to each other, and the second spatiotemporal attribute vector is a spatiotemporal attribute vector generated by a final residual core among the plurality of residual cores connected to each other; (2) inputting the second spatiotemporal attribute vector into a recursive layer in the MetNet model to obtain a linear feature of the target observation attribute generated by the recursive layer; (3) Inputting the first spatiotemporal attribute vector, the second spatiotemporal attribute vector and the third spatiotemporal attribute vector as well as the linear feature of the target observation attribute into the fully connected layer in the MetNet model, and obtaining the meteorological observation attribute knowledge encoding of each target meteorological observation data generated by the fully connected layer, wherein the third spatiotemporal attribute vector is a spatiotemporal attribute vector generated by the residual kernel in the recursive layer according to the augmented attribute knowledge encoding, and the augmented attribute knowledge encoding is obtained by feature augmentation of the second spatiotemporal attribute vector.

[0119] In the meteorological observation data access system, the attribute knowledge mining operation of step 120 is of key significance for understanding and processing meteorological observation data.

[0120] First, each target meteorological observation data is input into the spatiotemporal feature mining layer in the MetNet model. The MetNet model is a model specifically used to process meteorological data, and its spatiotemporal feature mining layer contains multiple residual cores that are connected to each other. These residual cores play an important role in mining the spatiotemporal features of the target meteorological observation data. For example, when a target meteorological observation data is input, multiple residual cores gradually process the data in the spatiotemporal feature mining layer. Among them, the non-final residual core will generate a first spatiotemporal attribute vector. For example, the first spatiotemporal attribute vector obtained after a target meteorological observation data is processed by a non-final residual core is [0.3, 0.5, 0.2]. The numerical values ​​in the embodiment of the present invention can represent different spatiotemporal feature weights, such as 0.3 may represent the feature weight in a specific spatial area, 0.5 represents the feature weight in a certain time period, and 0.2 represents the association weight with other related meteorological elements in time and space. The final residual kernel will generate a second spatiotemporal attribute vector. For example, the second spatiotemporal attribute vector corresponding to the target meteorological observation data is [0.4, 0.4, 0.2]. Similarly, each value also reflects a specific spatiotemporal feature.

[0121] Next, the second spatiotemporal attribute vector is input into the recursive layer in the MetNet model. Based on its own structure and algorithm, the recursive layer processes the input second spatiotemporal attribute vector to generate the linear feature of the target observation attribute. For example, the linear feature of the target observation attribute may be expressed as [0.6, 0.3, 0.1], where 0.6 may represent the linear feature weight related to the long-term change trend of meteorological elements, 0.3 represents the linear feature weight related to short-term fluctuations, and 0.1 represents the linear feature weight related to other interference factors.

[0122] Then, the first spatiotemporal attribute vector, the second spatiotemporal attribute vector, the third spatiotemporal attribute vector and the linear features of the target observation attributes are input into the fully connected layer in the MetNet model. The third spatiotemporal attribute vector in the embodiment of the present invention is a spatiotemporal attribute vector generated by the residual kernel in the recursive layer according to the augmented attribute knowledge coding, and the augmented attribute knowledge coding is obtained by feature augmentation of the second spatiotemporal attribute vector. For example, the augmented third spatiotemporal attribute vector is [0.5, 0.3, 0.2]. The fully connected layer integrates the vector information of these inputs, and generates the meteorological observation attribute knowledge coding of each target meteorological observation data through its complex neuronal connections and calculations. The coding comprehensively reflects the various feature information of the target meteorological observation data, and is obtained on the basis of comprehensively considering the residual kernel outputs of different levels of the spatiotemporal feature mining layer, the linear features of the recursive layer and the augmented spatiotemporal attribute vector.

[0123] The consistency of this technical solution lies in that it starts from the spatiotemporal feature mining layer and gradually digs deeper into the features of the target meteorological observation data. First, the spatiotemporal attributes of different levels are distinguished through multiple residual kernels, then the linear features are extracted using the recursive layer, and finally all relevant information is integrated in the fully connected layer to obtain a complete meteorological observation attribute knowledge encoding. This method makes full use of the functional characteristics of each layer of the MetNet model, so that the meteorological observation attribute knowledge encoding can accurately reflect the essential characteristics of the target meteorological observation data.

[0124] With this design, the spatiotemporal characteristics of the target meteorological observation data can be deeply analyzed by first using the spatiotemporal feature mining layer of the MetNet model and mining the spatiotemporal attribute vectors through multiple residual kernels. Different levels of residual kernels output different spatiotemporal attribute vectors. This hierarchical processing helps to fully capture the characteristics of the data at different spatiotemporal scales and avoid the limitations of single-scale analysis. Secondly, the linear features of the target observation attributes generated by the recursive layer add information about the changing trends of meteorological elements to the meteorological observation attribute knowledge encoding. This helps to better understand the dynamic change laws of meteorological elements in subsequent data processing and analysis. Furthermore, the fully connected layer generates meteorological observation attribute knowledge encoding by integrating multiple vector information, so that the encoding contains rich and comprehensive information. This helps to improve the accuracy and effectiveness of meteorological observation data in subsequent processing. For example, in applications such as data classification, association analysis, and meteorological forecasting, more comprehensive and accurate attribute knowledge encoding can provide a more reliable basis for these operations, thereby improving the performance of the entire meteorological observation data access system.

[0125] In summary, the embodiment of the present invention adopts a ring buffer structure to manage meteorological observation data, which has great advantages over the traditional linear stack method. When the traditional linear stack accesses commands and data, due to its last-in-first-out principle and the data operations are concentrated on the top of the stack, when faced with a large amount of meteorological observation data stream, the problem of low efficiency will arise. The ring buffer structure of the embodiment of the present invention can support multiple independent data streams to share storage space in the same buffer, and realize continuous writing and cyclic overwriting of data. For example, in meteorological observation, data streams from different sensors (such as temperature sensors, humidity sensors, wind speed sensors, etc.) can be stored in order in the ring buffer at the same time, avoiding the rapid performance degradation caused by the increase of data volume like a linear stack.

[0126] The circular movement of the read and write pointers ensures continuous access to data, which is crucial in meteorological business systems. Meteorological observation is a continuous process, and data is continuously generated. The read and write pointer mechanism of the ring buffer ensures that the data can be stored and read in a timely and continuous manner, without blocking or delaying the linear stack when the amount of data is large. In addition, the ring buffer supports parallel access, which greatly improves the speed and efficiency of data access. In the meteorological business system, there may be multiple tasks (such as real-time meteorological data monitoring, historical data query, equipment control instruction transmission, etc.) that need to access data at the same time. The parallel access capability of the ring buffer enables these tasks to be efficiently executed concurrently, greatly improving the operating efficiency of the entire system.

[0127] The overflow and underflow detection mechanism and the capacity management strategy of multi-channel data streams provided by the embodiments of the present invention provide a strong guarantee for the data integrity and system stability of the meteorological business system. In the process of continuous generation of meteorological observation data, if there is no effective overflow detection mechanism, when the amount of data exceeds the storage capacity, it may cause data loss or system crash, and the overflow detection mechanism of the ring buffer can detect and handle this situation in time. Similarly, the underflow detection mechanism can prevent abnormal situations that occur when the data reading speed is too fast or the data generation is insufficient. The capacity management strategy of multi-channel data streams can reasonably allocate storage space according to the needs of different data streams to ensure that the data of each channel can be properly processed. This is particularly important in the environment of multi-source data fusion such as the meteorological business system, avoiding the operation of the entire system being affected by the excessive or small amount of data in a certain channel.

[0128] Attribute knowledge mining is performed on meteorological observation data to generate meteorological observation attribute knowledge encoding, and then a series of read-write state mappings are performed based on this to obtain relevant vectors and labels, which helps to manage meteorological observation data more accurately. Meteorological observation data has rich connotations, and different data have different importance and functions in meteorological analysis, forecasting, and equipment control. Through attribute knowledge mining, the characteristics of each target meteorological observation data can be deeply understood, and then targeted management can be carried out according to these characteristics during data access. For example, for data that plays a key role in meteorological forecasting, a higher priority can be given in the read-write state mapping, so that it can be reflected in the data access management suggestion vector and the global read-write state label, so as to formulate a more optimized data access strategy and improve the decision-making accuracy and efficiency of the meteorological business system.

[0129] Further, Figure 2 Schematic diagram of a meteorological observation data access system 200 provided in an embodiment of the present invention. Figure 2 The meteorological observation data access system 200 shown includes a processor 210. The processor 210 can call and run a computer program from a memory to implement the method in the embodiment of the present invention.

[0130] Alternatively, if Figure 2 As shown, the meteorological observation data access system 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method in the embodiment of the present invention. The memory 230 may be a separate device independent of the processor 210, or may be integrated in the processor 210. Optionally, as Figure 2 As shown, the meteorological observation data access system 200 may also include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. Optionally, the meteorological observation data access system 200 may implement the corresponding processes corresponding to the storage engine or the components in the storage engine (such as a processing module) or the device deployed with the storage engine in each method of the embodiment of the present invention. For the sake of brevity, it will not be repeated here. It should be understood that the processor of the embodiment of the present invention may be an integrated circuit chip with signal processing capabilities. It can be understood that the memory in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. It should be noted that the memory of the system and method described herein is intended to include, but is not limited to, a memory of a suitable type.

[0131] Based on the above, a readable storage medium is provided, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the above method are implemented.

[0132] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the embodiments of the present invention are not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the embodiments of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose of the embodiments of the present invention and the scope of protection of the embodiments of the present invention, all of which are within the protection of the embodiments of the present invention.

Claims

1. A multi-channel ring access method for meteorological observation data, characterized in that: The method is applied to a meteorological observation data access system, and the method comprises: Taking multiple meteorological observation data streams in the target database as initial meteorological observation data streams respectively, performing a timing marking operation based on a ring buffer structure on the initial meteorological observation data streams to obtain multiple timing marked observation information, each of which includes multiple target meteorological observation data; Performing attribute knowledge mining on the multiple target meteorological observation data to obtain meteorological observation attribute knowledge codes of the multiple target meteorological observation data; The plurality of time series mark observation information are respectively used as data access mark information, and the meteorological observation attribute knowledge encoding of the plurality of target meteorological observation data in the data access mark information is mapped to a read-write state to obtain a read-write state description vector of the data access mark information; Determine the access management suggestion vector of the initial meteorological observation data stream by using the read and write state description vectors of the plurality of time-series-tagged observation information; The access management suggestion vectors of multiple meteorological observation data streams in the target database are mapped to read and write states to obtain a global read and write state label of the target database, which is used to determine the data access strategy of the target database.

2. The method according to claim 1, characterized in that The method of using the multiple time series mark observation information as data access mark information, performing read-write state mapping on the meteorological observation attribute knowledge encoding of multiple target meteorological observation data in the data access mark information, and obtaining the read-write state description vector of the data access mark information includes: using the multiple time series mark observation information as data access mark information, performing read-write state mapping on the meteorological observation attribute knowledge encoding of multiple target meteorological observation data in the data access mark information, and obtaining a first read-write state mapping feature, wherein the first read-write state mapping feature includes a plurality of first read-write state mapping subgroups; determining the read-write state description vector of the data access mark information based on the read-write state description vectors of the plurality of first read-write state mapping subgroups; The method of performing read-write status mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain a global read-write status label of the target database includes: performing read-write status mapping on the access management suggestion vectors of multiple meteorological observation data streams in the target database to obtain a second read-write status mapping feature, wherein the second read-write status mapping feature includes multiple second read-write status mapping clusters; and determining the global read-write status label of the target database based on the read-write status description vectors of the multiple second read-write status mapping clusters.

3. The method according to claim 2, characterized in that The determining the read / write state description vector of the data access tag information based on the read / write state description vectors of the plurality of first read / write state mapping subgroups comprises: fusing vector elements of key state mapping members of the plurality of first read / write state mapping subgroups to determine the read / write state description vector of the data access tag information; Determining the global read-write status label of the target database based on the read-write status description vectors of the multiple second read-write status mapping subgroups includes: fusing vector elements of key status mapping members of the multiple second read-write status mapping subgroups to determine the global read-write status label of the target database.

4. The method according to claim 2, characterized in that The method of using the plurality of time series mark observation information as data access mark information respectively, and performing read-write state mapping on the meteorological observation attribute knowledge encoding of the plurality of target meteorological observation data in the data access mark information to obtain a first read-write state mapping feature includes: The multiple time-series mark observation information are respectively used as data access mark information, and based on multiple different first feature dimensions, the meteorological observation attribute knowledge encodings of multiple target meteorological observation data in the data access mark information are mapped to read and write states, so as to obtain first read and write state mapping features respectively corresponding to the multiple first feature dimensions, wherein the first feature dimension is used to indicate the number of first read and write state mapping subgroups in the corresponding first read and write state mapping features; the read and write state description vector of the data access mark information includes the read and write state description vectors respectively corresponding to the multiple first feature dimensions of the data access mark information; The method of using the read / write state description vectors of the plurality of timing mark observation information to determine the access management suggestion vector of the initial meteorological observation data stream comprises: fusing the read / write state description vectors corresponding to the same first characteristic dimension in the read / write state description vectors of the plurality of timing mark observation information to obtain the access management suggestion vectors of the initial meteorological observation data stream corresponding to the plurality of first characteristic dimensions respectively; The access management suggestion vectors of the multiple meteorological observation data streams in the target database are mapped to read and write states to obtain a second read and write state mapping feature, including: among the access management suggestion vectors of the multiple meteorological observation data streams in the target database, access management suggestion vectors corresponding to the same first feature dimension are mapped to read and write states to obtain second read and write state mapping features corresponding to multiple first feature dimensions respectively; the global read and write state label of the target database includes the read and write state description vectors corresponding to the multiple first feature dimensions of the target database respectively.

5. The method according to claim 3, characterized in that Each second read-write state mapping feature includes local mapping features corresponding to multiple different second feature dimensions, and each local mapping feature includes multiple second read-write state mapping clusters; the second feature dimension is used to indicate the number of second read-write state mapping clusters in the corresponding second read-write state mapping feature; the read-write state description vector of each first feature dimension of the target database includes multiple local read-write state vectors of the first feature dimension of the target database corresponding to multiple second feature dimensions.

6. The method according to any one of claims 1 to 5, characterized in that: The method further comprises: Performing feature matching based on a strategy vector coordinate system on the global read / write status tag of the target database to obtain a read / write execution strategy vector of the target database; The read and write execution strategy vector of the target database is processed to obtain a data access strategy of the target database.

7. The method according to claim 6, characterized in that The processing of the read / write execution strategy vector of the target database to obtain the data access strategy of the target database includes: based on the data access demand indicated by the channel capacity control vector, processing the read / write execution strategy vector of the target database through a feedforward neural network based on conditional probability to determine the data access strategy of the target database; The data access demand indicated by the channel capacity control vector is based on the data access demand indicated by the channel capacity control vector, and the read / write execution strategy vector of the target database is processed by a feed-forward neural network based on conditional probability to determine the data access strategy of the target database, including: combining the read / write execution strategy vector of the target database and the overflow detection mechanism execution vector of the target database by a feed-forward neural network based on conditional probability to obtain a multi-channel access interaction vector of the target database; based on the data access demand indicated by the channel capacity control vector, the multi-channel access interaction vector of the target database is processed to determine the data access strategy of the target database; The performing feature matching based on the strategy vector coordinate system on the global read-write status tag of the target database to obtain the read-write execution strategy vector of the target database includes: performing feature matching based on the strategy vector coordinate system on the global read-write status tag of the target database through a deep learning network to obtain the read-write execution strategy vector of the target database; The method further includes: debugging the deep learning network based on debugging examples including meteorological observation debugging vectors, overflow detection mechanism debugging vectors, channel capacity regulation training vectors, and data access annotation strategies; Among them, the deep learning network is used to perform feature matching on the meteorological observation debugging vector based on the strategy vector coordinate system to obtain the read-write debugging strategy vector; the feedforward neural network based on conditional probability is used to combine the read-write debugging strategy vector and the overflow detection mechanism debugging vector to obtain a multi-channel access debugging vector; based on the data access demand indicated by the channel capacity regulation training vector, the multi-channel access debugging vector is processed to determine the data access debugging strategy, and the network weights of the deep learning network are optimized according to the data access debugging strategy and the data access labeling strategy.

8. The method according to any one of claims 1 to 5, characterized in that: The method of using the multiple meteorological observation data streams in the target database as initial meteorological observation data streams respectively and performing a timing marking operation based on a ring buffer structure on the initial meteorological observation data streams to obtain multiple timing marked observation information includes: Taking multiple meteorological observation data streams in the target database as initial meteorological observation data streams respectively, and performing group marking based on time series nodes on the initial meteorological observation data streams to obtain meteorological observation marking groups; The meteorological observation mark group is divided into a plurality of time-series mark observation information according to the observation priority.

9. The method according to any one of claims 1 to 5, characterized in that: The method further includes: extracting data from the original meteorological observation report to obtain the multiple meteorological observation data streams.

10. A meteorological observation data access system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.

Images