A big data-based data visualization analysis method and system

Abstract

The application relates to a big data-based data visualization analysis method and system, which belongs to the technical field of data analysis, and is based on a visualization analysis system. The visualization analysis system comprises a processing terminal and a plurality of feedback terminals. The method comprises the following steps: receiving analysis data fed back by the plurality of feedback terminals in real time, and collecting the analysis data to form an analysis data set, wherein the analysis data carries type identification and collection time; according to a plurality of preset data evaluation parameters, dividing a plurality of analysis data in the analysis data set into excellent analysis data and abnormal analysis data; and according to the divided excellent analysis data and abnormal analysis data, establishing one or more current visualization charts according to the analysis data types.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a data visualization analysis method and system based on big data. Background Technology

[0002] Data analysis refers to the process of analyzing large amounts of collected data using appropriate statistical analysis methods, summarizing and digesting the data in order to maximize its functionality and effectiveness.

[0003] In the era of big data, effective and rapid data analysis is crucial to realizing the value of massive and complex datasets. Data visualization, as an effective method for processing complex information, has become an indispensable tool in intelligent data analysis and mining.

[0004] Data analytics is applied across various fields, including national defense, production, and daily life. For example, the Civil Aviation Administration can use visualization to analyze data such as flight companies, flight numbers, and flight delays to discover the relationship between flight delays and time, thereby further improving flight scheduling and other work methods. Factories can use visualization to analyze the pass rate of products at each stage, product problems, and corresponding maintenance procedures for maintenance personnel, so as to promptly adjust potential problems in the product line and dispatch appropriate maintenance personnel to repair the product line in a timely manner.

[0005] However, due to the large volume of data to be analyzed, it is often difficult to identify problems in a timely manner. This necessitates relying excessively on the personal experience of staff to distinguish anomalies or errors in data analysis, which may affect the final analysis results. Summary of the Invention

[0006] To reduce the impact of data anomalies on analysis results, this application provides a data visualization analysis method and system based on big data.

[0007] Firstly, this application provides a data visualization analysis method based on big data, employing the following technical solution:

[0008] A data visualization analysis method based on big data, the method being based on a visualization analysis system, the visualization analysis system including a processing terminal and multiple feedback terminals, the method comprising:

[0009] The system receives analysis data from multiple feedback terminals in real time and aggregates the analysis data to form an analysis dataset. The analysis data carries a type identifier and the collection time.

[0010] Based on multiple preset data evaluation parameters, the multiple analytical data in the analysis dataset are divided into excellent analytical data and abnormal analytical data.

[0011] Based on the segmented high-quality analysis data and multiple abnormal analysis data, one or more current visualization tables are created according to the data type of analysis.

[0012] Optionally, the method further includes:

[0013] Download the historical analysis dataset from the specified network address. The historical analysis dataset includes multiple anomaly classification data, anomaly factors corresponding to the multiple anomaly classification data, and anomaly solution data.

[0014] Based on the multiple anomaly classification data, the multiple anomaly analysis data collected within the preset detection period are classified.

[0015] Match the categorized target anomaly analysis data with the corresponding target anomaly solution data;

[0016] The system compiles and summarizes multiple target anomaly analysis data, corresponding target anomaly solutions, and target anomaly factors, and creates one or more anomaly visualization charts based on the target anomaly factors.

[0017] Optionally, the visualization system further includes an early warning module, and the processing terminal is pre-set with early warning parameters corresponding to multiple types of analyzed data. The method further includes:

[0018] Compare the specified anomaly analysis data with the corresponding warning parameter area;

[0019] If the specified anomaly analysis data is located within the pre-stored parameter area, an early warning indicator is generated and marked at the position corresponding to the specified anomaly analysis data in the anomaly visualization chart, as well as at the position corresponding to the specified anomaly analysis data in the current visualization chart.

[0020] Optionally, the processing terminal has multiple pre-set account management databases, each including multiple account datasets. Each account dataset includes account information and historical query data. The historical query data includes query data type information and query factor information. The method further includes:

[0021] Generate key type search areas and key question search areas based on the first historical query data corresponding to the first account information;

[0022] Based on the key type search area, multiple current visual tables corresponding to the first account information are filtered out from multiple current visual tables;

[0023] Based on the key issue search area, multiple first abnormal visualization charts corresponding to the first account information are selected from multiple abnormal visualization charts;

[0024] Based on multiple first-time visual charts and multiple first-anomaly visualization charts, a user query analysis chart is created.

[0025] Optionally, the account management database also includes the current task volume, and there is a corresponding relationship between the current task volume and the current anomaly analysis data;

[0026] The processing terminal has multiple preset estimated processing times, and there is a one-to-one mapping relationship between the multiple estimated processing times and multiple abnormal solution data.

[0027] After generating a warning flag when the specified anomaly analysis data is within the pre-stored parameter area, the following steps are also included:

[0028] If multiple second abnormal visualization charts carrying warning signs correspond to multiple second account information, calculate the current task processing time for generating multiple second account information and compare the multiple current task processing times with each other.

[0029] Select the minimum target current task processing time from multiple current task processing times, and generate task assignment information corresponding to the target current task processing time. The task assignment information includes the target account information corresponding to the target current task processing time.

[0030] Optionally, the method further includes:

[0031] Based on real-time user input, search information corresponding to account information, including the type of analyzed data or abnormal factors;

[0032] The query type information and query factors in the historical query data are updated periodically based on the search information.

[0033] Secondly, this application provides a visualization analysis system, which adopts the following technical solution:

[0034] A visualization analysis system includes a processing terminal, a feedback terminal, and an early warning module. The processing terminal includes:

[0035] The receiving module is used to receive analysis data from multiple feedback terminals in real time and summarize the analysis data to form an analysis dataset. The analysis data carries a type identifier and the collection time.

[0036] The partitioning module is used to partition multiple analytical data in the analytical dataset into excellent analytical data and abnormal analytical data based on multiple preset data evaluation parameters.

[0037] The chart creation module is used to create one or more current visual charts based on the data types of the segmented high-quality analysis data and multiple abnormal analysis data.

[0038] Thirdly, this application provides a processing terminal, which adopts the following technical solution:

[0039] A processing terminal includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to perform processing in the data visualization analysis method based on big data as described in the first aspect.

[0040] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0041] A computer-readable storage medium storing at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to perform processing at a processing terminal in the big data-based data visualization analysis method as described in the first aspect.

[0042] In summary, this application includes at least one of the following beneficial technical effects:

[0043] During big data analysis, the processing terminal aggregates and processes multiple analytical data. Further processing terminal classifies the analytical data into excellent analytical data and abnormal analytical data based on data evaluation parameters and the type of analytical data, and creates one or more current visualization charts. This allows staff to adjust their work based on the current visualization charts, reducing their workload and minimizing the impact of data anomalies on the analysis results. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating a data visualization and analysis method based on big data, provided in an embodiment of this application.

[0046] Figure 2 This is a flowchart illustrating a process for generating anomaly visualization charts provided in an embodiment of this application.

[0047] Figure 3 This is a flowchart illustrating the process of creating a user query analysis chart, as provided in an embodiment of this application.

[0048] Figure 4 This is a schematic diagram of a process for matching task assignment information provided in an embodiment of this application.

[0049] Figure 5 This is a system block diagram of a visualization analysis system according to an embodiment of this application.

[0050] Figure 6 This is a structural block diagram of a processing terminal in an embodiment of this application.

[0051] Explanation of reference numerals in the attached diagram: 501, receiving module; 502, segmentation module; 503, chart creation module; 504, information download module; 505, information classification module; 506, matching module; 507, comparison module; 508, deduction module; 509, filtering module; 510, update module. Implementation

[0052] To make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings 1-6.

[0053] This application provides a data visualization analysis method based on big data. The method can be applied to a visualization analysis system, which can consist of a processing terminal, a feedback terminal, and an early warning module. The main execution entity of this method can be the processing terminal in the visualization analysis system, assisted by the early warning module and multiple feedback terminals. This application uses the information interaction between the processing terminal and the feedback terminal in actual factory production as an example for illustration; other situations are similar and will not be described in detail.

[0054] The following will describe the specific implementation methods. Figure 1 The processing flow shown is explained in detail below:

[0055] Step 101: Receive analysis data from multiple feedback terminals in real time, and summarize the analysis data to form an analysis dataset. The analysis data carries type identifiers and collection time.

[0056] In implementation, the processing terminal receives analysis data from multiple feedback terminals in real time, and simultaneously aggregates the multiple analysis data to form an analysis dataset. In this embodiment, the feedback terminal can be a testing device used to inspect various products on a production line, and the processing terminal can be a server set up within the factory. The analysis data can be the status of the product, such as dimensional differences, workmanship efficiency, etc. Due to the influence of its inherent attributes, the analysis data is classified into different types. The analysis data carries a type identifier and acquisition time, for example, the type identifier may be size type or efficiency type.

[0057] Step 102: Based on multiple preset data evaluation parameters, divide the multiple analytical data in the analysis dataset into excellent analytical data and abnormal analytical data.

[0058] In implementation, the processing terminal presets multiple data evaluation parameters, among which there is a one-to-one mapping relationship between the multiple data evaluation parameters and the types of analyzed data. By comparing the analyzed data with the corresponding data evaluation parameters, the analyzed data can be divided into excellent analyzed data and abnormal analyzed data. For example, if the size difference is 0.1, analyzed data with a size difference greater than 0.1 is called abnormal data, and analyzed data with a size difference less than 0.1 is called excellent analyzed data. It should be noted that in the embodiments of this application, the type of analyzed data can be distinguished based on its own carried type identifier.

[0059] Step 103: Based on the multiple high-quality analysis data and multiple abnormal analysis data after division, establish one or more current visual tables according to the analysis data type.

[0060] In practice, the processing terminal will aggregate the analysis data of the same type, and then classify the excellent analysis data and abnormal analysis data into excellent and abnormal labels respectively. After aggregating and processing the analysis data of the same type with labels, it will generate the current visualization chart.

[0061] In this embodiment, the current visualization chart can be a pie chart, a bar chart, or a tabular data chart. Corresponding text annotations can be added to the visualization chart. The processing terminal projects the current visualization chart onto the display screen to enhance the convenience of use.

[0062] It is important to note that in order to ensure the timeliness of the current visualization charts, the current visualization charts should be updated in real time. For example, the analysis data submitted 7 days ago should be cleaned up regularly every day. The time for cleaning up the analysis data can be based on the collection time of the analysis data.

[0063] Staff can analyze product status using one or more current visual charts to improve product yield.

[0064] Optionally, this application may also contain the following: Figure 2 The specific operating procedure for handling this is as follows:

[0065] Step 201: Download the historical analysis dataset from the specified network address. The historical analysis dataset includes multiple anomaly classification data, anomaly factors corresponding to the multiple anomaly classification data, and anomaly solution data.

[0066] In implementation, the processing terminal downloads historical analysis datasets from a designated network address. These historical analysis datasets can be compiled from periodic uploaded analysis data by the processing terminal over a long period of use, pre-defined by the user via the network, or compiled by the manufacturer through uploads and summaries. The historical analysis datasets include multiple anomaly classification data, anomaly factors, and anomaly solution data, with a corresponding relationship between anomaly classification data and anomaly factors, and a corresponding relationship between anomaly factors and anomaly solution data.

[0067] For example, if one type of anomaly data is a difference in product size, the corresponding anomaly factors could be problems with the injection mold or the cutting equipment. The solutions could be adjusting the injection mold core, replacing the injection mold, or adjusting the cutting equipment.

[0068] Step 202: Based on multiple anomaly classification data, classify the multiple anomaly analysis data collected within the preset detection period.

[0069] In implementation, the processing terminal first calculates the data collection time range based on the preset detection period and the current time. Then, within this time range, the terminal categorizes the anomaly data according to the type identifier carried by the anomaly analysis data and the anomaly classification data. The categories of anomaly classification data can be manually set or determined based on the production process. For example, differences in dimensions (length and height) and surface smoothness during product casing manufacturing can also be classified into the same type of anomaly classification data.

[0070] Step 203: Match the categorized target anomaly analysis data with the corresponding target anomaly solution data.

[0071] In implementation, after the anomaly analysis data is categorized at the processing terminal, this anomaly analysis data can be called target anomaly analysis data. The target anomaly analysis data is matched with the corresponding anomaly classification data and the corresponding anomaly solution data. This anomaly solution data can be called target anomaly solution data.

[0072] Step 204: Statistically summarize multiple target anomaly analysis data, corresponding target anomaly solutions, and target anomaly factors, and create one or more anomaly visualization charts based on the target anomaly factors.

[0073] In practice, the processing terminal statistically summarizes multiple target anomaly classification data. The anomaly factors corresponding to the target anomaly analysis data here can be called target anomaly factors.

[0074] Next, the processing terminal divides the target anomaly data into multiple target anomaly categories based on the target anomaly factors, and then creates multiple anomaly visualization charts based on the divided target anomaly factor category data and corresponding anomaly solutions. These anomaly visualization charts can be pie charts, bar charts, tabular data charts, etc. At the same time, by adding existing anomaly solutions, the difficulty of later maintenance by staff is reduced.

[0075] Optionally, the processing terminal has preset warning parameters corresponding to multiple types of analysis data, and the following processing also exists. In this application, the following processing may also exist, and the specific operation process is as follows:

[0076] Compare the specified anomaly analysis data with the corresponding warning parameter area;

[0077] If the specified anomaly analysis data is located within the pre-stored parameter area, an early warning indicator will be generated and marked in the anomaly visualization chart at the position corresponding to the specified anomaly analysis data, as well as in the current visualization chart at the position corresponding to the specified anomaly analysis data.

[0078] In practice, the processing terminal compares a certain anomaly analysis data with the corresponding early warning parameter area. This anomaly analysis data can be referred to as the specified anomaly analysis data.

[0079] When the specified abnormal analysis data falls into the warning parameter area, the processing terminal generates a warning label. Then, the processing terminal marks the warning label at the position corresponding to the specified abnormal analysis data in the abnormal visualization chart, as well as at the position corresponding to the specified abnormal analysis data in the current visualization chart. This allows users to promptly identify abnormal data that requires urgent handling, thereby reducing the impact of a certain abnormal factor on the product during the actual production process.

[0080] Optionally, the processing terminal has multiple pre-set account management databases, each containing multiple account datasets. Each account dataset includes account information and historical query data. The historical query data includes query data type information and query factor information. This application also includes, for example,... Figure 3 The specific operating procedure for handling this is as follows:

[0081] Step 301: Generate a key type search area and a key question search area based on the first historical query data corresponding to the first account information.

[0082] In implementation, any account information is selected as an example. This account information can be referred to as the first account information, and the corresponding historical query data can be referred to as the first historical query data. The processing terminal can use the query data type information and query factor information in the first historical query data to statistically analyze the data type and abnormal factors of the first account information query before the current time. Then, the query data type information generates a key type search area, and the query factor information generates a key question search area.

[0083] Step 302: Based on the key type search area, filter out multiple current visual tables corresponding to the first account information from multiple current visual tables.

[0084] In implementation, the processing terminal filters out multiple identical current visual tables from multiple current visual tables using the key type search area. The current visual table obtained here can be called the first current visual table. At the same time, a correspondence is established between the first current visual table and the first account information.

[0085] Step 303: Based on the key issue search area, select multiple first abnormal visualization charts corresponding to the first account information from multiple abnormal visualization charts.

[0086] In implementation, the processing terminal filters out multiple identical abnormal visual tables from multiple current visual tables from the key issue search area. The abnormal visual table obtained here can be called the first abnormal visual table. At the same time, the correspondence between the first abnormal visual table and the first account information is established.

[0087] Step 304: Based on multiple first-time visual charts and multiple first-anomaly visualization charts, summarize and build user query analysis charts.

[0088] In implementation, multiple first-time visual charts and multiple first-abnormal visual charts are aggregated and processed, and a user query analysis chart is created. This query analysis chart should include the abnormal factors and abnormal solutions corresponding to the multiple first-abnormal visual charts.

[0089] When different staff members log in to their accounts through the processor, they can promptly query and analyze charts based on their own account information, thereby facilitating staff management, accelerating problem handling, and reducing the possibility of oversights.

[0090] Optionally, the account management database also includes the current task volume, and there is a corresponding relationship between the current task volume and the current anomaly analysis data; the processing terminal has multiple preset estimated processing times, and there is a one-to-one mapping relationship between the multiple estimated processing times and multiple anomaly solution data; this application also contains, for example, Figure 4 The specific operating procedure for handling this is as follows:

[0091] Step 401: If there are multiple second abnormal visualization charts carrying warning signs that correspond to multiple second account information, calculate the current task processing time for generating multiple second account information and compare the multiple current task processing times with each other.

[0092] In implementation, a certain anomaly visualization chart may correspond to multiple account information. This anomaly visualization chart can be referred to as the second anomaly visualization chart, and the account information can be referred to as the second account information. The processing terminal first calculates the processing time of the current task volume in the second account information and compares the current task processing times of multiple second account information with each other.

[0093] For example, for the same abnormal factor, namely dimensional abnormality, the second account information, namely the maintenance worker's account, can be used to perform maintenance or repair. At this time, the processing terminal will match the current task volume with the estimated processing time in the maintenance worker account, and add up the multiple estimated processing times to generate the current task volume processing time. Then, the processing terminal will compare the processing times of multiple current tasks.

[0094] Step 402: Select the minimum target current task processing time from multiple current task processing times, and generate task assignment information corresponding to the target current task processing time. The task assignment information includes the target account information corresponding to the target current task processing time.

[0095] In implementation, the processing terminal selects the minimum task processing time from multiple current task processing times. This minimum task processing time can be called the target task processing time. Then, the processing terminal generates task assignment information based on the target task processing time. This task assignment information includes a second anomaly visualization diagram, the corresponding anomaly factors, and the corresponding anomaly solutions.

[0096] Then the processing terminal matches the task assignment information with the second account information corresponding to the target task processing time.

[0097] It should be noted that in this application, the current task volume corresponding to the second account information depends on the task assignment information corresponding to the second account information. When there are multiple second account information with the same current processing time, random assignment will be used.

[0098] Optionally, the following processing also exists in this application, and the specific operation process is as follows:

[0099] Based on real-time user input search information, the search information includes the type of data being analyzed or anomalies;

[0100] The query type information and query factors in historical query data are updated regularly based on search information.

[0101] In practice, the processing terminal periodically updates the query type information and query factors in the historical query data based on the data types and anomalies analyzed by the user in real time within a certain period of time. For example, before searching, the user logs in with their personal account information, and then the processing terminal updates the query type information and query factors in the historical query data based on the search information entered by the user when logging in with that account information within one year from the current time, with the update time being every Sunday.

[0102] This application also discloses a visualization analysis system, such as... Figure 5 As shown, the visualization analysis system includes a processing terminal, a feedback terminal, and an early warning module. The processing terminal includes:

[0103] The receiving module 501 is used to receive analysis data from multiple feedback terminals in real time, and to summarize the analysis data to form an analysis dataset. The analysis data carries a type identifier and the collection time.

[0104] The partitioning module 502 is used to partition multiple analytical data in the analytical dataset into excellent analytical data and abnormal analytical data according to multiple preset data evaluation parameters.

[0105] The chart creation module 503 is used to create one or more current visual charts based on the data types of the segmented high-quality analysis data and multiple abnormal analysis data.

[0106] Optionally, the processing terminal can also be used for:

[0107] The information download module 504 is used to download the historical analysis dataset from the specified network address. The historical analysis dataset includes multiple anomaly classification data, anomaly factors corresponding to the multiple anomaly classification data, and anomaly solution data.

[0108] The information classification module 505 classifies multiple anomaly analysis data collected within a preset detection period based on multiple anomaly classification data.

[0109] Matching module 506 is used to match multiple categorized target anomaly analysis data with corresponding target anomaly solution data;

[0110] The chart creation module 503 is used to statistically summarize multiple target anomaly analysis data, corresponding target anomaly solutions, and target anomaly factors, and to create one or more anomaly visualization charts based on the target anomaly factors.

[0111] Optionally, the processing terminal can also be used for:

[0112] The comparison module 507 is used to compare the specified anomaly analysis data with the corresponding warning parameter area;

[0113] If the specified anomaly analysis data is located within the pre-stored parameter area, an early warning indicator will be generated and marked in the anomaly visualization chart at the position corresponding to the specified anomaly analysis data, as well as in the current visualization chart at the position corresponding to the specified anomaly analysis data.

[0114] Optionally, the processing terminal can also be used for:

[0115] The derivation module 508 is used to generate a key type search area and a key question search area based on the first historical query data corresponding to the first account information.

[0116] The filtering module 509 is used to filter out multiple first current visual tables corresponding to the first account information from multiple current visual tables based on the key type search area;

[0117] The filtering module 509 is used to filter out multiple first abnormal visualization charts corresponding to the first account information from multiple abnormal visualization charts based on the key issue search area;

[0118] The chart creation module 503 is used to create user query analysis charts based on multiple first-time visual charts and multiple first-anomaly visualization charts.

[0119] Optionally, the processing terminal can also be used for:

[0120] If multiple second abnormal visualization charts carrying warning signs correspond to multiple second account information, calculate the current task processing time for generating multiple second account information and compare the multiple current task processing times with each other.

[0121] The filtering module 509 is used to select the minimum target current task processing time from multiple current task processing times and generate task assignment information corresponding to the target current task processing time. The task assignment information includes the target account information corresponding to the target current task processing time.

[0122] Optionally, the processing terminal can also be used for:

[0123] The receiving module 501 is used to receive search information corresponding to account information based on real-time user input. The search information includes the type of analytical data or abnormal factors.

[0124] The update module 510 is used to periodically update the query type information and query factors in historical query data based on search information.

[0125] Figure 6 This is a schematic diagram of the processing terminal provided in the embodiments of this application. The processing terminal can vary significantly due to differences in configuration or performance, and may include one or more central processing units (e.g., one or more processors) and memory, and one or more storage media (e.g., one or more mass storage devices) for storing applications or data. The memory and storage media can be temporary or persistent storage. The program stored in the storage media may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the processing terminal.

[0126] The processing terminal may also include one or more power supplies, one or more wired or wireless network interfaces, one or more input / output interfaces, one or more keyboards, and / or one or more operating systems.

[0127] The processing terminal may include a memory and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by one or more processors. One or more programs include processing for performing the processing terminal in the above-described big data-based data visualization analysis method.

[0128] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory.

[0129] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A data visualization and analysis method based on big data, characterized in that, The method is based on a visualization analysis system, which includes a processing terminal and multiple feedback terminals. The method includes: The system receives analysis data from multiple feedback terminals in real time and aggregates the analysis data to form an analysis dataset. The analysis data carries a type identifier and the collection time. Based on multiple preset data evaluation parameters, the multiple analytical data in the analysis dataset are divided into excellent analytical data and abnormal analytical data. Based on the segmented high-quality analysis data and multiple abnormal analysis data, one or more current visual tables are established according to the data type of analysis. The method further includes: Download the historical analysis dataset from the specified network address. The historical analysis dataset includes multiple anomaly classification data, anomaly factors corresponding to the multiple anomaly classification data, and anomaly solution data. Based on the multiple anomaly classification data, the multiple anomaly analysis data collected within the preset detection period are classified. Match the categorized target anomaly analysis data with the corresponding target anomaly solution data; Statistically summarize multiple target anomaly analysis data, corresponding target anomaly solutions, and target anomaly factors, and create one or more anomaly visualization charts based on target anomaly factors; The visualization analysis system further includes an early warning module, and the processing terminal is pre-set with early warning parameters corresponding to multiple types of analysis data. The method further includes: Compare the specified anomaly analysis data with the corresponding warning parameter area; If the specified abnormal analysis data is located within the pre-stored parameter area, an early warning indicator is generated and marked in the position corresponding to the specified abnormal analysis data in the abnormal visualization chart, as well as in the position corresponding to the specified abnormal analysis data in the current visualization chart. The processing terminal has multiple pre-set account management databases, each including multiple account datasets. Each account dataset includes account information and historical query data. The historical query data includes query data type information and query factor information. The method further includes: Generate key type search areas and key question search areas based on the first historical query data corresponding to the first account information; Based on the key type search area, multiple current visual tables corresponding to the first account information are filtered out from multiple current visual tables; Based on the key issue search area, multiple first abnormal visualization charts corresponding to the first account information are selected from multiple abnormal visualization charts; Based on multiple first-time visible charts and multiple first-anoma visualization charts, a user query analysis chart is compiled and established. The account management database also includes the current task volume, and there is a corresponding relationship between the current task volume and the current anomaly analysis data; The processing terminal has multiple estimated processing times preset, and there is a one-to-one mapping relationship between the multiple estimated processing times and multiple abnormal solution data. After generating a warning flag when the specified anomaly analysis data is within the pre-stored parameter area, the following steps are also included: If multiple second abnormal visualization charts carrying warning signs correspond to multiple second account information, calculate the current task processing time for generating multiple second account information and compare the multiple current task processing times with each other. Select the minimum target current task processing time from multiple current task processing times, and generate task assignment information corresponding to the target current task processing time. The task assignment information includes the target account information corresponding to the target current task processing time. The method further includes: Based on real-time user input, search information corresponding to account information, including the type of analyzed data or abnormal factors; The query type information and query factors in the historical query data are updated periodically based on the search information.

2. A processing terminal, characterized in that, The processing terminal includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to realize the data visualization analysis method based on big data as described in claim 1.

3. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the data visualization analysis method based on big data as described in claim 1.

Images