A data processing method and device for data visualization processing

Abstract

The application discloses a data processing method and device for data visualization processing, and the method comprises the following steps: obtaining to-be-processed user data information based on user interaction; the to-be-processed user data information comprises terminal user data information input by a user on a smart terminal; performing data optimization processing on the to-be-processed user data information to obtain target optimization data information; the target optimization data information comprises target category optimization data information; the target category optimization data information comprises target category data value information; performing classification processing on the target optimization data information to obtain target data analysis result information; the target data analysis result information comprises target classification analysis result information; and the target classification analysis result information comprises at least one target category analysis result information.

Description

Technical Field

[0001] This invention relates to the fields of visualization technology and industrial big data processing, and in particular to a data processing method and apparatus for data visualization processing. Background Technology

[0002] In today's digital age, the generation and accumulation of production data in the industrial sector are rapid, requiring enterprises and factories across various industries to efficiently process and analyze massive amounts of data to extract value. Data visualization technology has emerged to address this need, presenting data in an intuitive way to help users quickly understand the data and make decisions. However, current industrial data visualization and fault analysis technologies have some shortcomings:

[0003] Data acquisition stage: Industrial data comes from diverse sources and has complex formats. When acquiring data from multiple sources such as databases, files and networks, problems such as format incompatibility and encoding chaos are often encountered, resulting in low acquisition efficiency and data errors. When acquiring data from various sensors, the data acquisition time and industrial scenarios are not statistically analyzed, making it difficult to achieve effective data registration.

[0004] Data preprocessing stage: Data quality varies greatly, with issues such as missing data, duplication, and errors. Traditional preprocessing methods struggle to automatically adapt to different data characteristics, leading to a cumbersome and error-prone process, especially when dealing with large-scale datasets, where efficiency and accuracy are difficult to balance.

[0005] Data analysis and processing: With the increasing volume and complexity of industrial data, traditional industrial fault detection and analysis methods and visualization methods struggle to quickly extract valuable information. For example, in high-dimensional data visualization analysis, the dimensionality reduction effect is poor, affecting the accuracy of subsequent industrial fault analysis. In industrial data processing, how to achieve effective fault prediction and analysis of industrial production scenarios based on multi-dimensional industrial data is a crucial problem that needs to be solved.

[0006] Data visualization presentation: User needs are becoming increasingly diverse, with higher requirements for visualization effects. Existing technologies struggle to meet their personalized needs for presentation formats and interactive functions, such as the lack of convenient ways to flexibly adjust visualization configuration parameters, which limits user experience and in-depth data exploration.

[0007] Therefore, a data processing method and apparatus for data visualization are provided to improve the efficiency of data analysis and processing, enrich the diversity and interactivity of visualization, and meet the complex needs of current data visualization and industrial production fault analysis. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide a data processing method and apparatus for data visualization processing that can improve the efficiency of data analysis and processing, enrich the diversity and interactivity of visualization display, and meet the complex needs of current data visualization processing and industrial production fault analysis and processing.

[0009] To address the aforementioned technical problems, a first aspect of the present invention discloses a data processing method for data visualization processing, the method comprising:

[0010] Acquire user data information to be processed based on user interaction; the user data information to be processed includes several terminal user data information input by the user on the smart terminal;

[0011] The user data information to be processed is subjected to data optimization processing to obtain target optimized data information; the target optimized data information includes several target category optimized data information; the target category optimized data information includes several target category data value information;

[0012] The target optimization data information is categorized and analyzed to obtain target data analysis results; the target data analysis results are used to characterize the fault assessment value of the production equipment corresponding to the target category of the target vector data information.

[0013] The step of optimizing the user data information to obtain the target optimized data information includes:

[0014] The user data information to be processed is subjected to data transformation processing to obtain the first user data information;

[0015] Based on the first user data information, the target optimization data information is determined.

[0016] The step of determining the target optimization data information based on the first user data information includes:

[0017] The first user data information is cleaned to obtain the first processed data information;

[0018] The first processed data information is processed to obtain the target optimized data information.

[0019] The step of processing the first processed data information to obtain target optimized data information includes:

[0020] The first processed data information is subjected to generalized data processing to obtain the second processed data information;

[0021] The second processed data information is decomposed to obtain the third processed data information;

[0022] The third processed data information is smoothed to obtain the fourth processed data information;

[0023] The fourth processed data information is linearly mapped to obtain the target optimized data information.

[0024] The process of classifying and analyzing the target optimization data information to obtain target data analysis results includes:

[0025] The target category data value information in the target optimization data information is vectorized to obtain target vector data information; the target vector data information includes several target category vector data information; the target category vector data information includes several vectorized data value information.

[0026] Based on the target vector data information, the target data analysis results are determined.

[0027] The determination of target data analysis results based on the target vector data information includes:

[0028] The vectorized data value information is a sequence of working status acquisition information used to represent the target category; the working status acquisition information sequence may be the working voltage, working temperature, power, working noise, etc. of various target categories of production equipment in the factory; one vectorized data value information corresponds to a sequence of acquisition information of a type of working parameters; working parameters include working voltage, working temperature, power, and working noise;

[0029] Obtain a set of standard working status values ​​corresponding to each target category; the set of standard working status values ​​includes several standard working status values;

[0030] For each vectorized data value included in the target category vector data information, subtract the corresponding standard working state value to obtain the difference sequence;

[0031] By using each difference sequence as a column vector, a difference matrix is ​​constructed.

[0032] The difference matrix is ​​decomposed into eigenvalues ​​to obtain an eigenvalue sequence; each eigenvalue in the eigenvalue sequence corresponds to a row vector of the difference matrix.

[0033] Based on the eigenvalue sequence, the cumulative eigenvalues ​​corresponding to each row vector of the difference matrix are obtained by performing integration on each row vector.

[0034] Perform the RVMD transformation on each column vector of the difference matrix to obtain the corresponding transformation vector;

[0035] By using each transformation vector as a column vector, a transformation difference matrix is ​​constructed.

[0036] The transformation difference matrix and the difference matrix are fused together to obtain the fusion matrix;

[0037] The trace and rank of the fusion matrix are calculated.

[0038] Fault assessment calculations are performed on the cumulative feature value, trace value, and rank value to obtain target data analysis results; the larger the fault assessment value, the greater the probability of a fault occurring in the production equipment of the target category corresponding to the target vector data information;

[0039] The expression for the integration operation is:

[0040]

[0041] Where z is the eigenvalue corresponding to the row vector, x is the integration variable, and y i Let θ be the i-th element of the row vector, and θ be the cumulative eigenvalue.

[0042] The expression for the fault assessment calculation is as follows:

[0043]

[0044] Where, θ i Let D be the cumulative eigenvalue corresponding to the i-th row vector. i ( ) is the i-th order Weiber function, M is the number of row vectors, Rg is the target data analysis result information, and α and β are the trace and rank of the fusion matrix, respectively;

[0045] The expression for calculating the fusion matrix is:

[0046]

[0047] Where YU is the fusion matrix, A is the difference matrix, and B is the transformation difference matrix;

[0048] The RVMD transform is a reduced-order variational mode decomposition transform.

[0049] The determination of target data analysis results based on the target vector data information includes:

[0050] The target vector data information is coarsely classified to obtain first classified user data information; the first classified user data information includes several first classified data value information; the first classified data value information includes at least one first vectorized data information.

[0051] The first category of user data information is filtered to obtain the second category of user data information.

[0052] The second category of user data is further refined to obtain the target data analysis results.

[0053] The coarse classification processing of the target vector data information to obtain the first classified user data information includes:

[0054] For any of the target category vector data information in the target vector data information, a vectorized data value information is randomly selected from the target category vector data information as the vectorized data information to be processed;

[0055] Determine whether the vectorized data information to be processed is the first vectorized data value information selected from the target category vector data information to obtain the order judgment result;

[0056] When the order judgment result is yes, a basic classification data value information is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0057] Remove the vectorized data value information corresponding to the vectorized data information to be processed from the target category vector data information;

[0058] Trigger the execution of randomly selecting a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0059] When the order judgment result is negative, the classification calculation model is used to calculate the vectorized data information to be processed and the basic vectorized data information in all the basic classification data value information to obtain at least one classification value.

[0060] The classification calculation model is as follows:

[0061] GLZ = ||DYXL - DEXL||;

[0062] In the formula, GLZ represents the classification value; DYXL represents the vectorized data information to be processed; and DEXL represents the basic vectorized data information.

[0063] Determine whether there exists a classification value less than or equal to the first classification threshold among the classification values, and obtain the first comparison judgment result;

[0064] When the first comparison judgment result is yes, the vectorized data information to be processed is used as a second vectorized data information in the basic classification data value information corresponding to the classification value that is less than or equal to the first classification threshold.

[0065] When the first comparison judgment result is negative, it is determined whether there is a classification value less than or equal to the second classification threshold among the classification values, and the second comparison judgment result is obtained.

[0066] When the second comparison judgment result is negative, the process of randomly selecting a vectorized data value from the target category vector data information as the vectorized data information to be processed is triggered.

[0067] When the second comparison judgment result is yes, a basic classification data value information is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0068] Determine whether the vectorized data value information corresponding to the vectorized data information to be processed is the last vectorized data value information in the target category vector data information, and obtain the third comparison judgment result;

[0069] When the third comparison judgment result is negative, the vectorized data value information corresponding to the vectorized data information to be processed is removed from the target category vector data information;

[0070] Trigger the execution of randomly selecting a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0071] When the third comparison judgment result is yes, the first classification data value information corresponding to the target category vector data information is determined based on all the basic classification data value information.

[0072] A second aspect of this invention discloses a data processing apparatus for data visualization processing, the apparatus comprising:

[0073] The acquisition module is used to acquire user data information to be processed based on user interaction; the user data information to be processed includes several terminal user data information input by the user on the smart terminal;

[0074] The first processing module is used to perform data optimization processing on the user data information to be processed to obtain target optimized data information; the target optimized data information includes several target category optimized data information; the target category optimized data information includes several target category data value information;

[0075] The second processing module is used to classify and analyze the target optimization data information to obtain target data analysis result information; the target data analysis result information is used to characterize the fault assessment value of the production equipment of the target category corresponding to the target vector data information.

[0076] A third aspect of the present invention discloses another data processing apparatus for data visualization processing, the apparatus comprising:

[0077] Memory containing executable program code;

[0078] A processor coupled to memory;

[0079] The processor calls executable program code stored in memory to execute some or all of the steps in the data processing method for data visualization disclosed in the first aspect of the present invention.

[0080] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the data processing method for data visualization processing disclosed in the first aspect of the present invention.

[0081] The beneficial effects of this invention include:

[0082] The data processing method of this invention performs a series of optimization processes on user data information to be processed. It can standardize data collected from multiple sources (such as databases, files, networks, and various sensors) at the source, effectively solving problems such as format incompatibility and encoding chaos. It avoids data registration problems caused by inconsistencies in data collection time and industrial scenarios, making the collected data more standardized and accurate, thereby significantly improving the efficiency of the data collection process and reducing the possibility of data errors.

[0083] To address the issues of inconsistent data quality, including missing, duplicate, and erroneous data, this invention employs a multi-step process in data optimization. This process first involves data transformation, followed by data cleaning, data category checking, generalized data processing, data decomposition, smoothing, and linear mapping. This allows for automatic adaptation to different data characteristics and targeted optimization for data in various situations, making the preprocessing more scientific and efficient. Even when processing large-scale data, it balances efficiency and accuracy, effectively improving the performance of the data preprocessing stage.

[0084] When classifying and analyzing target optimization data, a series of complex and scientific analytical methods are employed, including vectorization, comparison with standard working state values ​​to construct a difference matrix, and subsequent eigenvalue decomposition, integral operation, RVMD transformation, and fusion matrix calculation. These methods can better extract key information from massive and complex industrial data. In particular, for the processing of high-dimensional data, it can achieve better dimensionality reduction results compared with traditional methods, thereby greatly improving the accuracy of industrial fault analysis and providing strong support for effective fault prediction and analysis in industrial production scenarios based on multi-dimensional industrial data. Attached Figure Description

[0085] 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.

[0086] Figure 1 This is a schematic diagram of a data processing system for data visualization provided in an embodiment of the present invention;

[0087] Figure 2 This is a flowchart illustrating a data processing method for data visualization disclosed in an embodiment of the present invention;

[0088] Figure 3 This is a schematic diagram of the structure of a data processing device for data visualization processing disclosed in an embodiment of the present invention;

[0089] Figure 4 This is a schematic diagram of another data processing device for data visualization processing disclosed in an embodiment of the present invention. Detailed Implementation

[0090] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0091] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0092] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0093] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0094] It should be noted that since the method in this application embodiment is executed in a computer device, the processing objects of each computer device exist in the form of data or information, such as time, which is essentially time information. It is understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the computer device can process them. Specific details will not be elaborated here.

[0095] It should be noted that the artificial intelligence-related technologies that may be involved in this application will be briefly described. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. Artificial intelligence is the study of the design principles and implementation methods of various intelligent machines, enabling machines to have the functions of perception, reasoning, and decision-making.

[0096] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0097] Computer vision (CV) is the science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing and measuring targets, and then performs image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0098] Monomodal information refers to data of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information refers to data that includes at least two types of monomodal information. Furthermore, multimodal information is suitable for complex tasks that require the integration of multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can usually be achieved in these tasks.

[0099] Large models refer to artificial neural network models with a very large number of parameters. In the field of artificial intelligence, large models typically refer to models with hundreds of millions to trillions of parameters. These models usually need to be trained on large-scale datasets and require a significant amount of computing resources for optimization and tuning. Large models are commonly used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is a type of AI that can create new content and ideas, including dialogues, stories, images, videos, and music. In this embodiment, the large model can be a large-scale pre-trained model such as the ChatGPT series, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Tongwen Qianyi model, MiniMax model, Xinghuo model, Llama model, 360GPT model, Qwen model, Baichuan model, Yunque model, vivoLM model, deepseek, Tencent Yuanbao, and Wenxin Yiyan, etc., and this embodiment does not limit the scope of the large model.

[0100] This application provides a data processing method, apparatus, computer device, and computer-readable storage medium for data visualization processing, which will be described in detail below.

[0101] Please see Figure 1 , Figure 1This is a schematic diagram of a data processing system for data visualization provided in an embodiment of this application. The data processing system for data visualization may include a computer device 100, which integrates a data processing unit for data visualization, such as... Figure 1 Computer equipment in the country.

[0102] In this embodiment of the application, the computer device 100 is mainly used to acquire user data information to be processed based on interaction with the user; the user data information to be processed includes several terminal user data information input by the user on the smart terminal;

[0103] The user data information to be processed is subjected to data optimization processing to obtain target optimized data information; the target optimized data information includes several target category optimized data information; the target category optimized data information includes several target category data value information;

[0104] The target optimization data information is categorized and analyzed to obtain target data analysis results information; the target data analysis results information includes several target classification analysis results information; the target classification analysis results information includes at least one target category analysis results information; the target category analysis results information includes at least one target classification data value information; the target classification data value information corresponds to the target category data value information.

[0105] It can improve the efficiency of data analysis and processing, enrich the diversity and interactivity of visualization, and meet the complex needs of current data visualization processing.

[0106] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0107] It is understood that the computer device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and may also be one of a mobile phone, tablet computer, laptop computer, etc.

[0108] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the data processing system for data visualization may also include one or more other services, which are not limited here.

[0109] In addition, such as Figure 1 As shown, the data processing system for data visualization may also include a memory 200 for storing data, such as image data, location information, etc.

[0110] It should be noted that, Figure 1 The schematic diagram of the data processing system for data visualization shown is merely an example. The data processing system and scenario for data visualization described in this application are for the purpose of more clearly illustrating the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of data processing systems for data visualization and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0111] This invention discloses a data processing method and apparatus for data visualization, which helps to improve the efficiency of data analysis and processing, enrich the diversity and interactivity of visualization, and meet the complex needs of current data visualization processing. These will be described in detail below.

[0112] Example 1

[0113] Please see Figure 2 , Figure 2 This is a flowchart illustrating a data processing method for data visualization disclosed in an embodiment of the present invention. Figure 2 The data processing method described for data visualization is applied in a management system, such as a local server or cloud server for management, and this embodiment of the invention is not limited thereto. Figure 2 As shown, the data processing method for data visualization may include the following operations:

[0114] 101. Obtain user data information to be processed based on user interaction.

[0115] In this embodiment of the invention, the user data information to be processed includes several terminal user data information input by the user on the smart terminal.

[0116] 102. Perform data optimization processing on the user data to be processed to obtain the target optimized data.

[0117] In this embodiment of the invention, the target optimization data information includes several target category optimization data information; the target category optimization data information includes several target category data value information.

[0118] 103. Classify and process the target optimization data information to obtain the target data analysis results.

[0119] In this embodiment of the invention, the target data analysis result information includes several target classification analysis result information; the target classification analysis result information includes at least one target category analysis result information; the target category analysis result information includes at least one target classification data value information; and the target classification data value information corresponds to the target category data value information.

[0120] It should be noted that the aforementioned smart terminal can be a PC or a mobile device, and this embodiment of the invention does not limit it. Furthermore, the aforementioned terminal user data information represents information input by the user regarding data management, such as user unit, data volume, user name, etc., and this embodiment of the invention does not limit it.

[0121] It should be noted that the above target data analysis results are used for appropriate mapping based on the characteristics of the data and charts. For example, line chart data is time series data, so time needs to be mapped to the x-axis and data to the y-axis; bar chart data is categorical data, so categories need to be mapped to the x-axis and data to the y-axis; pie chart data is percentage data, so categories need to be mapped to the x-axis and percentages to the y-axis, and so on.

[0122] It should be noted that after classifying and processing the target optimization data information to obtain the target data analysis results, this application can also display the target data analysis results on a display screen and update the data periodically via Ajax. This embodiment of the invention is not limited in scope, and allows for real-time monitoring and tracking of data trends and patterns. Furthermore, the animation effects provided by Echarts can be used to enhance the visualization of the data and the user experience.

[0123] The step of determining the target optimization data information based on the first user data information includes:

[0124] The first user data information is cleaned to obtain the first processed data information;

[0125] The first processed data information is processed to obtain the target optimized data information.

[0126] The data category check involves determining the data category of each data point in the first processed data information and whether it matches a preset data category. Data that does not match is deleted from the first processed data information to obtain the target optimized data information.

[0127] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0128] In an optional embodiment, the above-described data optimization processing of the user data information to be processed to obtain target optimized data information includes:

[0129] The user data information to be processed is transformed to obtain the first user data information;

[0130] Based on the first user data, the target optimization data is determined.

[0131] In this optional embodiment, as an optional implementation, the above-described data transformation processing of the user data information to be processed to obtain the first user data information includes:

[0132] The format of the terminal user data information in the user data information to be processed is converted to obtain user data information in several formats;

[0133] All formatted user data information is concatenated and combined from front to back according to the serial number of the smart terminal to obtain the first user data information.

[0134] It should be noted that the above-mentioned format conversion of the terminal user data information in the user data information to be processed is to convert the data into standard data in JSON format in order to unify the data presentation format of various smart terminals and facilitate subsequent data analysis and display. This embodiment of the invention does not limit the scope of the invention.

[0135] It should be noted that each of the aforementioned smart terminals corresponds to a serial number. Furthermore, concatenating all formatted user data information from front to back according to the smart terminal serial numbers involves piecing together all the data into a data matrix to form a standard data structure representation, which is beneficial for improving the efficiency of user data analysis. This embodiment of the invention does not impose limitations on this. The data matrix can be:

[0136] Terminal serial number User unit Username Data A Data B 1 Unit 1 Name 1 A1 B1 2 Unit 2 Name 2 A2 B2 3 Unit 3 Name 3 A3 B3

[0137] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0138] In another optional embodiment, target optimization data information is determined based on the first user data information, including:

[0139] The first user data information is cleaned to obtain the first processed data information;

[0140] The first batch of processed data is subjected to data category checks to obtain the target optimized data.

[0141] It should be noted that the above-mentioned data cleaning process for the first user data information mainly aims to remove problematic data in the user data, such as cleaning missing values ​​(filling, deleting, etc.) and correcting logical errors, thereby ensuring the consistency of user data in all dimensions and thus ensuring the quality of user data, so as to improve the analysis quality and efficiency of user data. This embodiment of the invention does not limit this.

[0142] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0143] In another optional embodiment, the first processed data information is generalized to obtain target optimized data information, including:

[0144] The first processed data information is subjected to generalized data processing to obtain the second processed data information;

[0145] The second processed data information is decomposed and processed to obtain the third processed data information;

[0146] The third-processed data information is smoothed to obtain the fourth-processed data information;

[0147] The fourth processing data information is linearly mapped to obtain the target optimized data information.

[0148] It should be noted that the above-mentioned generalized data processing of the first processed data information uses a number to replace the user unit. For example, unit A is generalized using the number DW001, and the user name is obfuscated. For example, user Zhang AA is replaced with Zhang San, thereby ensuring the user's anonymity. This embodiment of the invention does not limit this.

[0149] It should be noted that the aforementioned third-processing data information includes several third-sub-processing data information, which is not limited in this embodiment of the invention. Furthermore, the third-sub-processing data information includes identity information and decomposed data information, which is not limited in this embodiment of the invention. Furthermore, the aforementioned decomposed data information can be expressed in the form shown in Table 1:

[0150] Table 1

[0151] Identity information 1 Identity information 2 Decompose data information 3 Decompose data information 4 Decompose data information 5 Decompose data information 1 Decompose data information 2 Decompose data information 3 Decompose data information 4 Decompose data information 5

[0152] In this optional embodiment, as an optional implementation, the above-described decomposition of the second processed data information to obtain the third processed data information includes:

[0153] Non-data information is extracted from the second-processed data to obtain several identity identification information.

[0154] Assign an identity identifier to each data information of the same type, and arrange them in order according to the terminal serial number to obtain several third-sub-processed data information.

[0155] It should be noted that the aforementioned identity information represents non-data value information in the data, such as terminal serial number, user unit, user name, etc., and this embodiment of the invention does not limit it.

[0156] It should be noted that the above-mentioned assignment of an identity identifier to data of the same type in sequence and the orderly arrangement according to the terminal serial number refers to the sequential assignment of the corresponding identity identifier to the data in the same column of the data matrix, and then sorting and distributing it according to the terminal serial number in the identity identifier into the form of Table 1. This embodiment of the invention does not limit this.

[0157] It should be noted that the above-mentioned smoothing of the third-processed data information is to smooth the decomposed data information in the third-processed data information using linear regression, so that the collected user data regression is closer to reality, thereby removing noise in the data and improving the quality of user data. This embodiment of the invention does not limit the scope of the invention.

[0158] It should be noted that the above-mentioned linear mapping processing of the fourth-processed data information is a normalization process for the decomposed data information after smoothing, in order to further eliminate excessive relative numerical differences between data and improve the reliability and accuracy of data analysis. This embodiment of the invention does not limit this.

[0159] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0160] In another optional embodiment, the target optimization data information is classified and analyzed to obtain target data analysis results information, including:

[0161] The target category data value information in the target optimization data information is vectorized to obtain target vector data information; the target vector data information includes several target category vector data information; the target category vector data information includes several vectorized data value information.

[0162] Based on the target vector data information, the target data analysis results are determined.

[0163] The determination of target data analysis results based on the target vector data information includes:

[0164] The vectorized data value information is a sequence of working status acquisition information used to represent the target category; the working status acquisition information sequence may be the working voltage, working temperature, power, working noise, etc. of various target categories of production equipment in the factory; one vectorized data value information corresponds to a sequence of acquisition information of a type of working parameters; working parameters include working voltage, working temperature, power, and working noise;

[0165] Obtain a set of standard working status values ​​corresponding to each target category; the set of standard working status values ​​includes several standard working status values;

[0166] For each vectorized data value included in the target category vector data information, subtract the corresponding standard working state value to obtain the difference sequence;

[0167] By using each difference sequence as a column vector, a difference matrix is ​​constructed.

[0168] The difference matrix is ​​decomposed into eigenvalues ​​to obtain an eigenvalue sequence; each eigenvalue in the eigenvalue sequence corresponds to a row vector of the difference matrix.

[0169] Based on the eigenvalue sequence, the cumulative eigenvalues ​​corresponding to each row vector of the difference matrix are obtained by performing integration on each row vector.

[0170] Perform the RVMD transformation on each column vector of the difference matrix to obtain the corresponding transformation vector;

[0171] By using each transformation vector as a column vector, a transformation difference matrix is ​​constructed.

[0172] The transformation difference matrix and the difference matrix are fused together to obtain the fusion matrix;

[0173] The trace and rank of the fusion matrix are calculated.

[0174] Fault assessment calculations are performed on the cumulative feature value, trace value, and rank value to obtain target data analysis results; the larger the fault assessment value, the greater the probability of a fault occurring in the production equipment of the target category corresponding to the target vector data information;

[0175] The expression for the integration operation is:

[0176]

[0177] Where z is the eigenvalue corresponding to the row vector, x is the integration variable, and y i Let θ be the i-th element of the row vector, and θ be the cumulative eigenvalue.

[0178] The expression for the integral operation integrates multiple key elements, including cumulative eigenvalues, the trace and rank of the fusion matrix, and the Weber function. Through specific mathematical relationships, it performs calculations to achieve the scientific calculation of the target data analysis results (i.e., fault assessment values). It fully considers the equipment status characteristics reflected by the data at different processing stages, organically combining the key data obtained from each stage. This avoids the one-sidedness of single-indicator evaluation, enabling the final fault assessment value to more objectively, comprehensively, and accurately reflect the probability of faults in the target category of production equipment. It provides a reliable quantitative basis for timely and accurate assessment of equipment fault risks in industrial production, helping enterprises to rationally arrange equipment maintenance plans, optimize production processes, and reduce production losses caused by equipment failures.

[0179] The expression for the fault assessment calculation is as follows:

[0180]

[0181] Where, θ i Let D be the cumulative eigenvalue corresponding to the i-th row vector. i ( ) is the i-th order Weiber function, M is the number of row vectors, Rg is the target data analysis result information, and α and β are the trace and rank of the fusion matrix, respectively;

[0182] This expression integrates key elements such as cumulative eigenvalues, the trace and rank of the fusion matrix, and the Weiber function. Through specific mathematical relationships, it performs calculations to achieve the scientific calculation of the target data analysis results (i.e., fault assessment values). It fully considers the equipment status characteristics reflected by the data at different processing stages, organically combining the key data obtained from each stage. This avoids the one-sidedness of single-indicator evaluation, enabling the final fault assessment value to more objectively, comprehensively, and accurately reflect the probability of failure in the target category of production equipment. It provides a reliable quantitative basis for timely and accurate assessment of equipment failure risks in industrial production, helping enterprises to rationally arrange equipment maintenance plans, optimize production processes, and reduce production losses caused by equipment failures.

[0183] The expression for calculating the fusion matrix is:

[0184]

[0185] Where YU is the fusion matrix, A is the difference matrix, and B is the transformation difference matrix;

[0186] This fusion matrix calculation expression cleverly utilizes the difference matrix A and the transformed difference matrix B to effectively integrate the information from two important matrices obtained through different processing steps, generating a fusion matrix YU. The fusion matrix comprehensively reflects the correlation and differences between the original data and the data after complex transformations. It provides a crucial data carrier for subsequent calculations of its trace and rank values, and its participation in fault assessment calculations. This makes the entire data analysis process more coherent and systematic in extracting data value, contributing to improving the scientific rigor and accuracy of industrial production fault analysis. It also makes data-driven equipment fault judgments more closely aligned with actual production conditions, assisting enterprises in better understanding equipment operating status and ensuring the stable and efficient operation of production activities.

[0187] The RVMD transform is a reduced-order variational mode decomposition transform.

[0188] It should be noted that the above-mentioned vectorization processing of the target category data value information in the target optimization data information is performed using a vectorization model, such as the BERT model, large model, etc., and this embodiment of the invention does not limit it.

[0189] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0190] In an optional embodiment, the above-mentioned determination of target data analysis result information based on target vector data information includes:

[0191] The target vector data information is coarsely classified to obtain the first category user data information; the first category user data information includes several first category data value information; the first category data value information includes at least one first vectorized data information.

[0192] The first category of user data is filtered to obtain the second category of user data.

[0193] The second-classified user data information is further refined to obtain the target data analysis results. In this optional implementation, as one possible method, the above-mentioned filtering of the first-classified user data information to obtain the second-classified user data information includes:

[0194] For any first-classified data value in the first-classified user data information, determine whether the number of first-vectorized data information in the first-classified data value information is greater than or equal to M, and obtain the quantity judgment result;

[0195] When the quantity judgment result is yes, the first category data value information is removed from the first category user data information;

[0196] When the quantity judgment result is negative, the analysis and judgment process of the first category data value information ends;

[0197] The first vectorized data information of the first categorized user data information after analysis and judgment is randomly arranged to obtain the second categorized user data information.

[0198] It should be noted that M is a positive integer not less than 5, such as 6, but this embodiment of the invention does not limit it.

[0199] It should be noted that removing the first category data value information less than M from the first category user data information is to ensure the sufficiency of user sample data, so as to characterize the user data of this category as representative, rather than abnormal or niche data, thereby improving the efficiency and accuracy of data analysis that characterizes data features. This embodiment of the invention does not limit this.

[0200] It should be noted that the above-mentioned random arrangement and distribution of all first vectorized data information in the first category of user data information after analysis and judgment is to randomly divide the vectorized data information after coarse classification and deletion of niche data again, returning to the initial distribution state of the data, so as not to be affected by the classification of coarse classification during fine classification, thereby improving the independence of data analysis of fine classification. This embodiment of the invention does not limit this.

[0201] It should be noted that the above-mentioned fine classification processing of the second category of user data information can be implemented based on the K-means clustering algorithm, and this embodiment of the invention does not limit it.

[0202] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0203] In another optional embodiment, the target vector data information is coarsely classified to obtain first-classified user data information, including:

[0204] For any target category vector data in the target vector data information, a vectorized data value is randomly selected from that target category vector data information as the vectorized data information to be processed;

[0205] Determine whether the vectorized data information to be processed is the first vectorized data value information selected from the target category vector data information to obtain the order judgment result;

[0206] When the sequential judgment result is yes, a basic classification data value is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0207] Remove the vectorized data value information corresponding to the vectorized data information to be processed from the target category vector data information;

[0208] The execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0209] When the sequential judgment result is negative, the classification calculation model is used to obtain at least one classification value from the vectorized data information to be processed and the basic vectorized data information in all basic classification data value information.

[0210] The classification calculation model is as follows:

[0211] GLZ = ||DYXL - DEXL||;

[0212] In the formula, GLZ represents the classification value; DYXL represents the vectorized data information to be processed; DEXL represents the basic vectorized data information;

[0213] Determine whether there are any classification values ​​less than or equal to the first classification threshold among the classification values, and accept the result of the first comparison judgment;

[0214] When the first comparison judgment result is yes, the vectorized data information to be processed is used as a second vectorized data information in the basic classification data value information corresponding to the classification value that is less than or equal to the first classification threshold.

[0215] If the result of the first comparison judgment is negative, determine whether there is a classification value in the classification value that is less than or equal to the second classification threshold, and accept the result of the second comparison judgment.

[0216] When the result of the second comparison is negative, the execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0217] When the result of the second comparison judgment is yes, a basic classification data value information is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0218] Determine whether the vectorized data value information corresponding to the vectorized data information to be processed is the last vectorized data value information in the target category vector data information, and obtain the third comparison judgment result;

[0219] When the result of the third comparison is negative, the vectorized data value information corresponding to the vectorized data information to be processed will be removed from the target category vector data information.

[0220] The execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0221] When the third comparison judgment result is yes, the first classification data value information corresponding to the target category vector data information is determined based on all the basic classification data value information.

[0222] It should be noted that the first classification data information corresponding to the target category vector data information determined above based on all the basic classification data value information is the first vectorized data information in the basic classification data value information, which is the basic vectorized data information and the second vectorized data information in the basic classification data value information. This embodiment of the invention does not limit this.

[0223] It should be noted that the first and second classification thresholds mentioned above can be set by the user or obtained by the large model based on historical threshold data analysis; this embodiment of the invention does not impose any limitations. Furthermore, the first classification threshold is less than the second classification threshold. Further, the first classification threshold is a data value between [0.1, 0.3], such as 0.2, and the second classification threshold is a value between [0.5, 0.8], such as 0.5; this embodiment of the invention does not impose any limitations. Furthermore, by analyzing the magnitude of the first classification threshold, classification values ​​with the same characteristics can be identified. When the classification value is between the two thresholds, it indicates that the classification values ​​are related but cannot be classified together. Thus, it can be defined as a basic classification data value. However, if it exceeds the second classification threshold, it indicates that they are not related to each other, but it cannot be determined that there is no data of the same category. Therefore, it is necessary to return to the target category vector data information to select vectorized data value information. The vectorized data information to be processed that exceeds the second classification threshold is not classified temporarily. It will be reclassified after the new basic classification data value information is determined to improve the accuracy of classification. This embodiment of the invention does not limit the scope of the invention.

[0224] It should be noted that the above-mentioned basic vectorized data information and other vectorized data values ​​with similar characteristics are used as the second vectorized data information. The analysis and judgment are based on a single classification value, and the classification accuracy is relatively general. Therefore, it can only be used as a coarse classification, serving as a reference for subsequent small sample classification data to filter out user data information of small categories, and providing higher quality user data for subsequent fine classification, thereby improving the accuracy of data analysis. This embodiment of the invention does not limit this.

[0225] It is evident that implementing the data processing method for data visualization described in the embodiments of the present invention is beneficial to improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0226] Through the advantages demonstrated in each of the above-mentioned stages, the system can help enterprises and factories in various fields to process and analyze large amounts of industrial production data more efficiently, uncover the value contained therein, and assess and predict the failure status of production equipment in a timely and accurate manner. This provides a reliable basis for decision-making, equipment maintenance, and production process optimization in industrial production, ultimately improving the efficiency and quality of the entire industrial production and enhancing the competitiveness of enterprises in the digital age.

[0227] Example 2

[0228] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a data processing device for data visualization processing disclosed in an embodiment of the present invention. Figure 3The described apparatus can be applied in management systems, such as local servers or cloud servers for management, and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the device may include:

[0229] The acquisition module 201 is used to acquire user data information to be processed based on user interaction; the user data information to be processed includes several terminal user data information input by the user on the smart terminal;

[0230] The first processing module 202 is used to perform data optimization processing on the user data information to be processed to obtain target optimized data information; the target optimized data information includes several target category optimized data information; the target category optimized data information includes several target category data value information;

[0231] The second processing module 203 is used to classify and analyze the target optimization data information to obtain target data analysis result information; the target data analysis result information is used to characterize the fault assessment value of the production equipment of the target category corresponding to the target vector data information.

[0232] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0233] In another alternative embodiment, such as Figure 3 As shown, data optimization processing is performed on the user data to be processed to obtain the target optimized data information, including:

[0234] The user data information to be processed is transformed to obtain the first user data information;

[0235] Based on the first user data, the target optimization data is determined.

[0236] The data conversion process can be a data format conversion;

[0237] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0238] In yet another alternative embodiment, such as Figure 3 As shown, based on the first user data information, the target optimization data information is determined, including:

[0239] The first user data information is cleaned to obtain the first processed data information;

[0240] The first batch of processed data is subjected to data category checks to obtain the target optimized data.

[0241] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0242] In yet another alternative embodiment, such as Figure 3 As shown, the first processed data information is generalized to obtain the target optimized data information, including:

[0243] The first processed data information is subjected to generalized data processing to obtain the second processed data information;

[0244] The second processed data information is decomposed and processed to obtain the third processed data information;

[0245] The third-processed data information is smoothed to obtain the fourth-processed data information;

[0246] The fourth processing data information is linearly mapped to obtain the target optimized data information.

[0247] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0248] In yet another alternative embodiment, such as Figure 3 As shown, the target optimization data information is categorized and processed to obtain the target data analysis results, including:

[0249] The target category data value information in the target optimization data information is vectorized to obtain target vector data information; the target vector data information includes several target category vector data information; the target category vector data information includes several vectorized data value information.

[0250] Based on the target vector data information, the target data analysis results are determined.

[0251] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0252] In yet another alternative embodiment, such as Figure 3As shown, based on the target vector data information, the target data analysis results are determined, including:

[0253] The target vector data information is coarsely classified to obtain the first category user data information; the first category user data information includes several first category data value information; the first category data value information includes at least one first vectorized data information.

[0254] The first category of user data is filtered to obtain the second category of user data.

[0255] The second category of user data is further refined to obtain the target data analysis results.

[0256] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0257] In yet another alternative embodiment, such as Figure 3 As shown, the target vector data information is subjected to coarse classification processing to obtain the first classified user data information, including:

[0258] For any target category vector data in the target vector data information, a vectorized data value is randomly selected from that target category vector data information as the vectorized data information to be processed;

[0259] Determine whether the vectorized data information to be processed is the first vectorized data value information selected from the target category vector data information to obtain the order judgment result;

[0260] When the sequential judgment result is yes, a basic classification data value is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0261] Remove the vectorized data value information corresponding to the vectorized data information to be processed from the target category vector data information;

[0262] The execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0263] When the sequential judgment result is negative, the classification calculation model is used to obtain at least one classification value from the vectorized data information to be processed and the basic vectorized data information in all basic classification data value information.

[0264] The classification calculation model is as follows:

[0265] GLZ = ||DYXL - DEXL||;

[0266] In the formula, GLZ represents the classification value; DYXL represents the vectorized data information to be processed; DEXL represents the basic vectorized data information;

[0267] Determine whether there are any classification values ​​less than or equal to the first classification threshold among the classification values, and accept the result of the first comparison judgment;

[0268] When the first comparison judgment result is yes, the vectorized data information to be processed is used as a second vectorized data information in the basic classification data value information corresponding to the classification value that is less than or equal to the first classification threshold.

[0269] If the result of the first comparison judgment is negative, determine whether there is a classification value in the classification value that is less than or equal to the second classification threshold, and accept the result of the second comparison judgment.

[0270] When the result of the second comparison is negative, the execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0271] When the result of the second comparison judgment is yes, a basic classification data value information is generated, and the vectorized data information to be processed is used as the basic vectorized data information in the basic classification data information;

[0272] Determine whether the vectorized data value information corresponding to the vectorized data information to be processed is the last vectorized data value information in the target category vector data information, and obtain the third comparison judgment result;

[0273] When the result of the third comparison is negative, the vectorized data value information corresponding to the vectorized data information to be processed will be removed from the target category vector data information.

[0274] The execution is triggered to randomly select a vectorized data value from the target category vector data information as the vectorized data information to be processed;

[0275] When the third comparison judgment result is yes, the first classification data value information corresponding to the target category vector data information is determined based on all the basic classification data value information.

[0276] It is evident that implementation Figure 3 The data processing device described is beneficial for improving the efficiency of data analysis and processing, enriching the diversity and interactivity of visualization, and meeting the complex needs of current data visualization processing.

[0277] Example 3

[0278] Please see Figure 4 , Figure 4This is a schematic diagram of the structure of another data processing device for data visualization processing disclosed in an embodiment of the present invention. Figure 4 The described apparatus can be applied in management systems, such as local servers or cloud servers for management, and the embodiments of the present invention are not limited thereto. Figure 4 As shown, the device may include:

[0279] Memory 301 storing executable program code;

[0280] Processor 302 coupled to memory 301;

[0281] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the data processing method for data visualization processing described in Embodiment 1.

[0282] Example 4

[0283] This invention discloses a computer-readable storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to perform the steps in the data processing method for data visualization processing described in Embodiment 1.

[0284] Example 5

[0285] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the data processing method for data visualization processing described in Embodiment 1.

[0286] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0287] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0288] Finally, it should be noted that the data processing method and apparatus for data visualization disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method for data visualization processing, characterized by, The method comprises: obtaining to-be-processed user data information obtained based on user interaction; the to-be-processed user data information comprises terminal user data information input by a user on an intelligent terminal; performing data optimization processing on the to-be-processed user data information to obtain target optimization data information; the target optimization data information comprises target category optimization data information; the target category optimization data information comprises target category data value information; performing classified analysis processing on the target optimization data information to obtain target data analysis result information; the target data analysis result information is used to represent a fault evaluation value of a production device of a target category corresponding to target vector data information; the classified analysis processing on the target optimization data information to obtain target data analysis result information comprises: performing vectorization processing on the target category data value information in the target optimization data information to obtain target vector data information; the target vector data information comprises target category vector data information; the target category vector data information comprises vectorized data value information; based on the target vector data information, determining target data analysis result information comprises: the vectorized data value information is used to represent a working state collection information sequence of a target category; obtaining a standard working state value set corresponding to each target category; the standard working state value set comprises standard working state values; subtracting each vectorized data value information included in the target category vector data information from a corresponding standard working state value to obtain a difference sequence; using each difference sequence as a column vector to construct a difference matrix; performing eigenvalue decomposition on the difference matrix to obtain an eigenvalue sequence; each eigenvalue of the eigenvalue sequence corresponds to a row vector of the difference matrix; based on the eigenvalue sequence, performing integral operation on each row vector of the difference matrix to obtain a cumulative eigenvalue corresponding to the row vector; performing RVMD transformation on each column vector of the difference matrix to obtain a corresponding transformed vector; using each transformed vector as a column vector to construct a transformed difference matrix; performing fusion matrix calculation on the transformed difference matrix and the difference matrix to obtain a fusion matrix; calculating a trace value and a rank value of the fusion matrix; performing fault evaluation calculation on the cumulative eigenvalue, the trace value, and the rank value to obtain target data analysis result information.

2. The data processing method for data visualization processing according to claim 1, wherein, the data optimization processing on the to-be-processed user data information to obtain target optimization data information comprises: performing data conversion processing on the to-be-processed user data information to obtain first user data information; based on the first user data information, determining target optimization data information.

3. The data processing method for data visualization processing according to claim 2, characterized in that, the determination of target optimization data information based on the first user data information comprises: performing data cleaning processing on the first user data information to obtain first processing data information; performing data processing on the first processing data information to obtain target optimization data information.

4. The data processing method for data visualization processing according to claim 3, characterized in that, the data processing on the first processing data information to obtain target optimization data information comprises: Generalizing data processing is performed on the first processing data information to obtain second processing data information; Disassembling processing is performed on the second processing data information to obtain third processing data information; Smoothing processing is performed on the third processing data information to obtain fourth processing data information; Linear mapping processing is performed on the fourth processing data information to obtain target optimization data information.

5. The data processing method for data visualization processing according to claim 1, wherein, Based on the target vector data information, target data analysis result information is determined, including: Coarse classification processing is performed on the target vector data information to obtain first classified user data information; the first classified user data information includes a plurality of first classified data value information; the first classified data value information includes at least one first vectorized data information; Filtering processing is performed on the first classified user data information to obtain second classified user data information; Fine classification processing is performed on the second classified user data information to obtain target data analysis result information.

6. The data processing method for data visualization processing according to claim 5, characterized in that, The coarse classification processing on the target vector data information to obtain the first classified user data information includes: For any target category vector data information in the target vector data information, a vectorized data value information in the target category vector data information is randomly selected as a to-be-processed vectorized data information; It is judged whether the to-be-processed vectorized data information is the first vectorized data value information selected from the target category vector data information to obtain a sequence judgment result; When the sequence judgment result is yes, a basic classified data value information is generated, and the to-be-processed vectorized data information is taken as a basic vectorized data information in the basic classified data value information; The vectorized data value information corresponding to the to-be-processed vectorized data information is excluded from the target category vector data information; Triggering execution of the random selection of a vectorized data value information from the target category vector data information as a to-be-processed vectorized data information; When the sequence judgment result is no, a classification calculation model is used to calculate the to-be-processed vectorized data information and the basic vectorized data information in all the basic classified data value information to obtain at least one classified value; The classification calculation model is: ； In the formula, GLZ represents the classified value, DYXL represents the to-be-processed vectorized data information, and DEXL represents the basic vectorized data information; It is judged whether there is a classified value less than or equal to a first classification threshold value in the classified value to obtain a first comparison judgment result; When the first comparison judgment result is yes, the to-be-processed vectorized data information is taken as a second vectorized data information corresponding to the basic classified data value information less than or equal to the first classification threshold value; When the first comparison judgment result is no, it is judged whether there is a classified value less than or equal to a second classification threshold value in the classified value to obtain a second comparison judgment result; When the second comparison judgment result is no, the random selection of a vectorized data value information from the target category vector data information as a to-be-processed vectorized data information is triggered to be executed. When the second comparison judgment result is yes, a basic classification data value information is generated, and the to-be-processed vectorization data information is taken as a basic vectorization data information in the basic classification data value information; A third comparison judgment result is obtained by judging whether the vectorization data value information corresponding to the to-be-processed vectorization data information is the last vectorization data value information in the target category vector data information; When the third comparison judgment result is no, the vectorization data value information corresponding to the to-be-processed vectorization data information is excluded from the target category vector data information; A trigger is triggered to execute the random selection of one of the vectorization data value information from the target category vector data information as the to-be-processed vectorization data information; When the third comparison judgment result is yes, a first classification data value information corresponding to the target category vector data information is determined based on all the basic classification data value information.

7. A data processing apparatus for data visualization processing, characterized by, The device for executing the data processing method for data visualization processing according to any one of claims 1-6, comprising: an acquisition module configured to acquire to-be-processed user data information obtained based on user interaction; the to-be-processed user data information includes terminal user data information input by a user on a smart terminal; a first processing module configured to perform data optimization processing on the to-be-processed user data information to obtain target optimization data information; the target optimization data information includes target category optimization data information; the target category optimization data information includes target category data value information; a second processing module configured to perform classification analysis processing on the target optimization data information to obtain target data analysis result information; the target data analysis result information is used to represent a fault evaluation value of a production device of a target category corresponding to target vector data information.

8. A data processing apparatus for data visualization processing, characterized by, The device comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the data processing method for data visualization processing according to any one of claims 1-6.

Images