An AI-based data visualization processing system and method

Abstract

The present invention discloses an AI-based data visualization processing system and method, including a data acquisition module, a cache processing module, a data multi-level classification module, a cloud storage module, a data extraction module, a version decoder, a data processing module, and a visualization management interface. The visualization management interface is implemented based on AI recognition technology and visually displays the transformed data. The present invention classifies power grid operation and maintenance data by version and multi-node and stores them using cloud storage technology, improving data storage performance. The version decoder uniformly decodes data of different versions, enabling the visualization management interface to be compatible with various versions of data. Meanwhile, the visualization management interface based on AI recognition technology can achieve rapid data extraction and visualization management, which is convenient and fast.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment, and particularly to an AI-based data visualization processing system and method. Background Art

[0002] With the continuous deepening of the energy transformation, the power regulation system has entered a new era. The scale of the UHV AC / DC hybrid power grid has expanded rapidly, the new energy with high penetration rate has developed rapidly, and the proportion of new loads such as distributed power sources and energy storage has increased rapidly. Upgrading the traditional power grid regulation system characterized by extensive interconnection, intelligent interaction, flexible flexibility, safety and controllability is forming a new generation of power grid regulation system. The new generation of power grid regulation system and operation and maintenance data have put forward new requirements for regulation technology and data processing capabilities.

[0003] There are various data in power grid operation and maintenance, showing the characteristics of multi-source and heterogeneous. It is necessary to use big data technology for processing. After the big data is processed, there will be problems whether the data visualization tool supports these data, and whether it supports the differences between different versions. At the same time, many current visualizations only stay at the level of graphics and charts, and do not extend to the data level. Therefore, the present invention proposes an AI-based data visualization processing system and method to solve the problems existing in the prior art. Summary of the Invention

[0004] In view of the above problems, the purpose of the present invention is to propose an AI-based data visualization processing system and method. The AI-based data visualization processing system and method classify and store the power grid operation and maintenance data by version and multi-node, and use cloud storage technology for storage, which improves the data storage performance. The version decoder is used to uniformly decode the data of different versions, so that the visualization management interface is compatible with the data of multiple versions. At the same time, the visualization management interface based on AI recognition technology can realize the rapid extraction and visualization management of data, which is convenient and fast.

[0005] To achieve the object of the present invention, the present invention is realized through the following technical solutions: An AI-based data visualization processing system includes a data acquisition module, a cache processing module, a data multi-level classification module, a cloud storage module, a data extraction module, a version decoder, a data processing module, and a visualization management interface. The data acquisition module is used to acquire multi-source heterogeneous data existing in power grid operation and maintenance. The cache processing module is used to perform cache processing on the acquired data. The data multi-level classification module classifies the cached data. The cloud storage module stores the classified data in blocks. The data extraction module is used to extract the data to be displayed from the cloud storage module. The version decoder is used to perform unified decoding processing on data of multiple different versions. The data processing module converts the decoded data according to visualization requirements. The visualization management interface is implemented based on AI recognition technology and visually displays the converted data.

[0006] A further improvement lies in that: The cache processing module includes a version recognition module. The version recognition module is used to identify the version classification of the acquired multi-source heterogeneous data and classify and import the data of the same version into the data multi-level classification module for multi-level classification and then into the cloud storage module for storage.

[0007] A further improvement lies in that: The data multi-level classification module includes a first-level classification node, a second-level classification node, and a third-level classification node. The data processed by the first-level classification node flows into the second-level classification node after preprocessing. The second-level classification node performs a large-scale classification according to the types of data and then flows into the third-level classification node. The third-level classification node performs branch storage according to the correlation degree of each piece of data.

[0008] A further improvement lies in that: The data processing module processes the extracted data according to visualization requirements and visually displays the processed data. The visualization requirements include the graphics of the data, the charts of the data, and the intuitive comparison of the data.

[0009] A further improvement lies in that: The visualization management interface includes a user login system, a demand data input system, and a visualization display system. The demand data input system is data-interconnected with the data extraction module. The demand data input system is used to input the data information to be queried. The demand data input system also includes AI speech recognition, AI image and text recognition, and text input recognition.

[0010] A processing method for an AI-based data visualization processing system includes the following steps:

[0011] Step 1: Use the data acquisition module to acquire multi-source heterogeneous data in power grid operation and maintenance. After acquisition, import the data into the cache processing module to classify the data according to the recognized version;

[0012] Step 2: Import the data processed by the cache processing module into the data multi-level classification module, and then neatly classify the data according to the three classification nodes of the data multi-level classification module;

[0013] Step 3: Import the data classified by the data multi-level classification module into the cloud storage module. The cloud storage module creates multiple groups of storage blocks according to the category and data size, and the storage blocks perform addition and deletion of data;

[0014] Step 4: Input the data information that needs to be visually managed on the visual management interface based on AI speech recognition, AI image and text recognition, and text input recognition, and then the data extraction module extracts the data from the corresponding storage blocks of the cloud storage module according to the data information;

[0015] Step 5: Import the extracted data into the version decoder to decode the data version, and process the decoded data according to the visual requirements through the data processing module. Finally, visually manage and display the processed data.

[0016] Further improvement lies in: When importing the updated data of the data information in Step 3, the storage block identifies the updated information, deletes the original data, and then stores the updated data information; When the data in a certain block exceeds the block storage capacity, the storage block divides and merges the storage capacities of other storage blocks into the over-capacity storage block to increase the storage capacity.

[0017] The beneficial effects of the present invention are as follows: The present invention classifies the power grid operation and maintenance data by version and multi-node and stores them using cloud storage technology, which improves the data storage performance. The version decoder uniformly decodes data of different versions, so that the visual management interface is compatible with data of multiple versions, avoiding abnormal data visualization processing caused by version differences. At the same time, the visual management interface based on AI recognition technology can achieve rapid extraction and visual management of data, which is convenient and fast. Brief Description of the Drawings

[0018] Figure 1 It is the system architecture diagram of Embodiment 1 of the present invention.

[0019] Figure 2 It is the system architecture diagram of Embodiment 2 of the present invention. Detailed Embodiment

[0020] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation to the protection scope of the present invention.

[0021] Embodiment 1

[0022] According toFigure 1 As shown in the figure, this embodiment provides an AI-based data visualization processing system, including a data acquisition module, a cache processing module, a data multi-level classification module, a cloud storage module, a data extraction module, a version decoder, a data processing module, and a visualization management interface. The data acquisition module is used to acquire multi-source heterogeneous data existing in power grid operation and maintenance. The cache processing module is used to perform cache processing on the acquired data. The data multi-level classification module classifies the cached data. The cloud storage module stores the classified data in blocks. By classifying the power grid operation and maintenance data by version and multi-node and using cloud storage technology for storage, the data storage performance is increased. The data extraction module is used to extract the data to be displayed from the cloud storage module. The version decoder is used to perform unified decoding processing on data of multiple different versions. The version decoder performs unified decoding on data of different versions, so that the visualization management interface is compatible with data of multiple versions, avoiding abnormal data visualization processing caused by version differences. The data processing module converts the decoded data according to visualization requirements. The visualization management interface is implemented based on AI recognition technology and visually displays the converted data.

[0023] The cache processing module includes a version recognition module. The version recognition module is used to identify the version classification of the acquired multi-source heterogeneous data and classify and import data of the same version into the data multi-level classification module for multi-level classification and then import it into the cloud storage module for storage.

[0024] The data multi-level classification module includes a first-level classification node, a second-level classification node, and a third-level classification node. The data processed by the first-level classification node flows into the second-level classification node after preprocessing. The second-level classification node performs a large-scale classification according to the type of data and then flows into the third-level classification node. The third-level classification node performs branch storage according to the correlation degree of each piece of data. Multi-node classification enables multi-source heterogeneous data to be stored in partitions, facilitating data extraction by the system, increasing the speed of visualization processing, and reducing the operating load of the system.

[0025] The data processing module processes the extracted data according to visualization requirements and visually displays the processed data. The visualization requirements include the graphics of the data, the charts of the data, and the intuitive comparison of the data.

[0026] The visualization management interface includes a user login system, a required data input system, and a visualization display system. The required data input system is interconnected with the data extraction module. The required data input system is used to input the data information to be queried. The required data input system also includes AI voice recognition, AI image and text recognition, and text input recognition. The visualization management interface based on AI recognition technology can achieve fast data extraction and visualization management, which is convenient and fast.

[0027] A processing method for an AI-based data visualization processing system, comprising the following steps:

[0028] Step 1: Use a data acquisition module to collect multi-source heterogeneous data in power grid operation and maintenance. After collection, import the data into a cache processing module to classify the data according to the identified version;

[0029] Step 2: Import the data processed by the cache processing module into a data multi-level classification module, and then neatly classify the data according to the three classification nodes of the data multi-level classification module;

[0030] Step 3: Import the data classified by the data multi-level classification module into a cloud storage module. The cloud storage module creates multiple groups of storage blocks according to the category and data size, and the storage blocks perform data addition and deletion. When importing data with updated information, the storage blocks identify the updated information, delete the original data, and then store the updated data information;

[0031] When the data in a certain block exceeds the block storage capacity, the storage block divides and merges the storage capacities of other storage blocks into the over-capacity storage block to increase the storage capacity;

[0032] Step 4: Based on AI speech recognition, AI image and text recognition, and text input recognition, input the data information that needs to be visually managed on the visual management interface, and then the data extraction module extracts the data from the corresponding storage block of the cloud storage module according to the data information;

[0033] Step 5: Import the extracted data into a version decoder to decode the data version, and process the decoded data according to the visualization requirements through a data processing module. Finally, visually manage and display the processed data.

[0034] Embodiment 2

[0035] According to Figure 2As shown in the figure, this embodiment provides an AI-based data visualization processing system, including a data acquisition module, a cache processing module, a data multi-level classification module, a cloud storage module, a data extraction module, a version decoder, a data processing module, and a visualization management interface. The data acquisition module is used to acquire multi-source heterogeneous data existing in power grid operation and maintenance. The cache processing module is used to perform cache processing on the acquired data. The data multi-level classification module classifies the cached data. The cloud storage module stores the classified data in blocks. By classifying the power grid operation and maintenance data by version and multi-node and using cloud storage technology for storage, the data storage performance is increased. The data extraction module is used to extract the data to be displayed from the cloud storage module. The version decoder is used to perform unified decoding processing on data of multiple different versions. The version decoder performs unified decoding on data of different versions, so that the visualization management interface is compatible with data of multiple versions, avoiding abnormal data visualization processing caused by version differences. The data processing module converts the decoded data according to visualization requirements. The visualization management interface is implemented based on AI recognition technology and visually displays the converted data.

[0036] The cache processing module includes a version recognition module. The version recognition module is used to identify the version classification of the acquired multi-source heterogeneous data and classify and import the data of the same version into the data multi-level classification module for multi-level classification and then import it into the cloud storage module for storage.

[0037] The data multi-level classification module includes a first-level classification node, a second-level classification node, and a third-level classification node. The data processed by the first-level classification node and the cache processing module flows into the second-level classification node after preprocessing. The second-level classification node performs a large-scale classification according to the type of data and then flows into the third-level classification node. The third-level classification node performs branch storage according to the correlation degree of each piece of data. Multi-node classification enables multi-source heterogeneous data to be stored in partitions, facilitating data extraction by the system, increasing the speed of visualization processing, and reducing the operating load of the system.

[0038] The data processing module processes the extracted data according to visualization requirements and visually displays the processed data. The visualization requirements include the graphics of the data, the charts of the data, and the intuitive comparison of the data.

[0039] The visualization management interface includes a user logging into the system, a demand data input system, and a visualization display system. The demand data input system is interconnected with the data extraction module. The demand data input system is used to input the data information to be queried. The demand data input system also includes AI voice recognition, AI image and text recognition, and text input recognition. The visualization management interface based on AI recognition technology can achieve rapid data extraction and visualization management, which is convenient and fast.

[0040] The visual management interface also includes a remote linkage module, which is used for the linkage visual management of data on multiple touch displays, and the multiple touch displays can be independently operated. The remote linkage module is implemented based on the multi-screen linkage technology.

[0041] A processing method for an AI-based data visualization processing system includes the following steps:

[0042] Step 1: Use the data acquisition module to collect multi-source heterogeneous data in power grid operation and maintenance. After collection, import the data into the cache processing module to classify the data according to the identified version.

[0043] Step 2: Import the data processed by the cache processing module into the data multi-level classification module, and then neatly classify the data according to the three classification nodes of the data multi-level classification module.

[0044] Step 3: Import the data classified by the data multi-level classification module into the cloud storage module. The cloud storage module establishes multiple groups of storage blocks according to the category and data size, and the storage blocks perform data addition and deletion. When updating data information is imported, the storage blocks identify the updated information, delete the original data, and then store the updated data information.

[0045] When the data in a certain block exceeds the block storage capacity, the storage block divides and merges the storage capacities of other storage blocks into the over-capacity storage block to increase the storage capacity.

[0046] Step 4: Based on AI speech recognition, AI image and text recognition, and text input recognition, input the data information that needs to be visually managed in the visual management interface, and then the data extraction module extracts the data from the corresponding storage block of the cloud storage module according to the data information.

[0047] Step 5: Import the extracted data into the version decoder to decode the data version, and process the decoded data according to the visualization requirements through the data processing module. Finally, realize the linkage visual management display of the processed data based on the multi-screen linkage technology.

[0048] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An AI-based data visualization processing system, characterized in that: It includes a data acquisition module, a cache processing module, a data multi-level classification module, a cloud storage module, a data extraction module, a version decoder, a data processing module, and a visualization management interface. The data acquisition module is used to acquire multi-source heterogeneous data existing in power grid operation and maintenance. The cache processing module is used to perform cache processing on the acquired data. The data multi-level classification module classifies the cached data. The cloud storage module stores the classified data in blocks. The data extraction module is used to extract the data to be displayed from the cloud storage module. The version decoder is used to perform unified decoding processing on data of multiple different versions. The data processing module converts the decoded data according to visualization requirements. The visualization management interface is implemented based on AI recognition technology and visually displays the converted data; Among them, the cache processing module includes a version recognition module. The version recognition module is used to identify the version classification of the acquired multi-source heterogeneous data, and classify and import the data of the same version into the data multi-level classification module for multi-level classification and then into the cloud storage module for storage; Among them, the data multi-level classification module includes a first-level classification node, a second-level classification node, and a third-level classification node. The data processed by the first-level classification node and the cache processing module flows into the second-level classification node after preprocessing. The second-level classification node performs a large-scale classification according to the types of data and then flows into the third-level classification node. The third-level classification node performs branch storage according to the correlation degree of each piece of data.

2. The data visualization processing system based on AI according to claim 1, characterized in that: The data processing module processes the extracted data according to visualization requirements and visually displays the processed data. The visualization requirements include the graphics of the data, the charts of the data, and the intuitive comparison of the data.

3. An AI-based data visualization processing system according to claim 1, characterized in that: The visualization management interface includes a user login system, a demand data input system, and a visualization display system. The demand data input system is data-interconnected with the data extraction module. The demand data input system is used to input the data information to be queried. The demand data input system also includes AI speech recognition, AI image and text recognition, and text input recognition.

4. The processing method of an AI-based data visualization processing system according to claim 1, characterized in that It includes the following steps: Step 1: Use the data acquisition module to acquire multi-source heterogeneous data in power grid operation and maintenance. After acquisition, import the data into the cache processing module to classify the data according to the identified version; Step 2: Import the data processed by the cache processing module into the data multi-level classification module, and then neatly classify the data according to the three classification nodes of the data multi-level classification module; Step 3: Import the data classified by the data multi-level classification module into the cloud storage module. The cloud storage module establishes multiple groups of storage blocks according to the category and data size, and the storage blocks perform addition and deletion of data; Step 4: Based on AI speech recognition, AI image and text recognition, and text input recognition, input the data information that needs to be visually managed in the visualization management interface. Then, the data extraction module extracts the data from the corresponding storage block of the cloud storage module according to the data information; Step 5: Import the extracted data into the version decoder to decode the data version, process the decoded data according to the visualization requirements through the data processing module, and finally perform visual management and display on the processed data; Among them, the cache processing module includes a version recognition module, which is used to identify the version classification of the collected multi-source heterogeneous data, and classify and import the data of the same version into the data multi-level classification module for multi-level classification and then into the cloud storage module for storage; Among them, the data multi-level classification module includes a first-level classification node, a second-level classification node, and a third-level classification node. The data processed by the first-level classification node cache processing module flows into the second-level classification node after preprocessing. The second-level classification node performs a large-scale classification according to the types of data and then flows into the third-level classification node. The third-level classification node performs branch storage according to the correlation degree of each piece of data.

5. The processing method of an AI-based data visualization processing system according to claim 4, characterized in that: When importing the updated data of the data information in Step 3, the storage block identifies the updated information, deletes the original data, and then stores the updated data information; when the data in a certain block exceeds the block storage capacity, the storage block divides and merges the storage capacity of other storage blocks into the over-storage block to increase the storage capacity.

Images