Visual interpretation generation method and device for data visualization and computer equipment

Abstract

The invention relates to a visual interpretation generation method and device for data visualization and computer equipment. The method comprises the following steps: acquiring enterprise data content and explanation demand information of a user, and identifying data association information of each enterprise data type based on the enterprise data content; based on the data association information of each enterprise data type, generating visual data information corresponding to the enterprise data content through a visual data generation strategy, and extracting data feature information corresponding to the visual data information; and based on the data feature information and the data association information of each enterprise data type, generating visual explanation information corresponding to the enterprise data content through an explanation data generation strategy, and based on the visual explanation information and the explanation demand information of the user, carrying out digital virtual propagation on the enterprise data content through a digital virtual propagation technology. And generating visual interpretation display information corresponding to the enterprise data content. By adopting the method, the user satisfaction and the user experience effect can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data analysis and artificial intelligence, and in particular to a visual explanation generation method and device for data visualization and a computer device. BACKGROUND

[0002] At home and abroad, data visualization research has been quite mature, and its application fields are extensive and in-depth. Many well-known university-level research institutes and the like take big data visualization as an important research topic and have published a large number of widely cited papers. These researches not only promote the development of data visualization theory, but also promote the innovation and application of related technologies. However, the main improvement of data visualization is still in the data display part, and there is no effective information display for the visual explanation part, especially for non-professionals. Even if the data visualization is displayed, it is also difficult to effectively understand the data representation meaning. Therefore, how to improve the visual explanation analysis after data visualization is the current research focus.

[0003] The traditional technical solution is to manually explain the visual data part by voice or directly record the related audio content, and to display the audio and text when the user views. However, manual explanation often has one-sidedness and limitations, and is relatively subjective, which often affects the user's understanding of the visual data content. Moreover, the professional nature and explanation method of manual explanation make the user's understanding have certain deviation, thereby leading to poor universality of the user's understanding effect of the visual explanation part of data visualization, and reducing the user experience effect. SUMMARY

[0004] Therefore, it is necessary to provide a visual explanation generation method and device for data visualization, a computer device, a computer readable storage medium and a computer program product in view of the above technical problems.

[0005] In a first aspect, the present application provides a visual explanation generation method for data visualization, comprising: obtaining enterprise data content and user explanation requirement information, and identifying data correlation information of each enterprise data type based on the enterprise data content; generating visual data information corresponding to the enterprise data content through a visual data generation strategy based on the data correlation information of each enterprise data type, and extracting data feature information corresponding to the visual data information; Based on the data feature information and the data correlation information of each enterprise data type, the visualized interpretation information corresponding to the enterprise data content is generated through an interpretation data generation strategy, and based on the visualized interpretation information and the interpretation requirement information of the user, the visualized interpretation display information corresponding to the enterprise data content is generated through a digital virtual propagation technology.

[0006] Optionally, the data correlation information of each enterprise data type is identified based on the enterprise data content, including: The enterprise data content is split into sub-data content of each enterprise data type, and data distribution information of each enterprise data type is generated based on the sub-data content of each enterprise data type; Based on the data distribution information of each enterprise data type, data change correlation information between the data content of each enterprise data type and the data content of other enterprise data types is identified, and single data change correlation information between the data content of each enterprise data type and the data content of other enterprise data types is taken as explicit correlation information of each enterprise data type; In the database, each associated enterprise data type corresponding to each enterprise data type is queried, and for each enterprise data type, joint data change correlation information between the enterprise data type and each associated enterprise data type is identified based on the data distribution information of the enterprise data type and the data distribution information of each associated enterprise data type through a data correlation analysis network; The joint data change correlation information between the enterprise data type and each associated enterprise data type is taken as implicit correlation information of each enterprise data type, and the explicit correlation information of each enterprise data type and the implicit correlation information of each enterprise data type are taken as the data correlation information of each enterprise data type.

[0007] Optionally, the visualized data information corresponding to the enterprise data content is generated based on the data correlation information of each enterprise data type through a visualized data generation strategy, including: Each visualized data generation tool is acquired, and each visualized data information of each enterprise data type is constructed through each visualized data generation tool based on the sub-data content of each enterprise data type; Based on the single data change correlation information between the data content of each enterprise data type and the data content of other enterprise data types, first visualized change correlation information between each visualized data information of each enterprise data type and each visualized data information of other enterprise data types is constructed; constructing second visual change association information of the visual data information of each enterprise data type and the visual data information of each associated enterprise data type corresponding to each enterprise data type based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type; The visual data information of each enterprise data type, the first visual change association information of the visual data information of each enterprise data type and the visual data information of other enterprise data types, and the second visual change association information of the visual data information of each enterprise data type and the visual data information of each associated enterprise data type corresponding to each enterprise data type are taken as the visual data information corresponding to the enterprise data content.

[0008] Optionally, the extracting the data feature information corresponding to the visual data information comprises: Based on each visual data information, each first visual change association information, and each second visual change association information, each visual data feature and each visual change association feature are identified through an image feature recognition network; Each visual data feature and each visual change association feature are taken as the data feature information corresponding to the visual data information.

[0009] Optionally, the generating the visual interpretation information corresponding to the enterprise data content based on the data feature information and the data association information of each enterprise data type through an interpretation data generation strategy comprises: Based on each visual data feature and each visual change association feature, feature interpretation information corresponding to the data feature information is identified through an image feature analysis network in the interpretation data generation strategy; Based on the explicit association information of each enterprise data type and the implicit association information of each enterprise data type, data association interpretation information between each enterprise data type is identified through an association semantic recognition network in the interpretation data generation strategy; The feature interpretation information corresponding to the data feature information and the data association interpretation information between each enterprise data type are taken as the visual interpretation information corresponding to the enterprise data content.

[0010] Optionally, the generating the visual interpretation display information corresponding to the enterprise data content based on the visual interpretation information and the interpretation demand information of the user through a digital virtual propagation technology comprises: Based on the interpretation demand information of the user, demand interpretation keywords and demand interpretation key semantics of the user are extracted through a keyword extraction network. Based on the demand explanation keyword and the demand explanation semantic, target visual explanation content is screened in the visual explanation information, and target explanation text corresponding to the user is generated through an explanation text generation network; Through digital virtual propagation technology, the target explanation text is converted into display content, and visual explanation display information corresponding to the enterprise data content is obtained.

[0011] In a second aspect, the present application also provides a visual explanation generation device for data visualization, comprising: An acquisition module is configured to acquire enterprise data content and explanation demand information of a user, and identify data correlation information of each enterprise data type based on the enterprise data content; An extraction module is configured to generate visual data information corresponding to the enterprise data content through a visual data generation strategy based on the data correlation information of each enterprise data type, and extract data feature information corresponding to the visual data information; A generation module is configured to generate visual explanation information corresponding to the enterprise data content through an explanation data generation strategy based on the data feature information and the data correlation information of each enterprise data type, and generate visual explanation display information corresponding to the enterprise data content through digital virtual propagation technology based on the visual explanation information and the explanation demand information of the user.

[0012] Optionally, the acquisition module is specifically configured to: Split the enterprise data content into sub-data content of each enterprise data type, and generate data distribution information of each enterprise data type based on the sub-data content of each enterprise data type; Identify data change correlation information between data content of each enterprise data type and data content of other enterprise data types based on the data distribution information of each enterprise data type, and take single data change correlation information between data content of each enterprise data type and data content of other enterprise data types as explicit correlation information of each enterprise data type; Query each associated enterprise data type corresponding to each enterprise data type in a database, and identify joint data change correlation information between the enterprise data type and each associated enterprise data type through a data correlation analysis network based on the data distribution information of the enterprise data type and the data distribution information of each associated enterprise data type for each enterprise data type; The joint data change association information between the enterprise data type and each associated enterprise data type is associated as implicit association information of each enterprise data type, and the explicit association information of each enterprise data type and the implicit association information of each enterprise data type are taken as data association information of each enterprise data type.

[0013] Optionally, the extraction module is specifically configured to: Each visualization data generation tool is acquired, and each visualization data information of each enterprise data type is constructed through each visualization data generation tool based on the sub-data content of each enterprise data type; The first visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each other enterprise data type is constructed based on the single data change association information between the data content of each enterprise data type and the data content of each other enterprise data type; The second visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type is constructed based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type; Each visualization data information of each enterprise data type, the first visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each other enterprise data type, and the second visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type are taken as the visualization data information corresponding to the enterprise data content.

[0014] Optionally, the extraction module is specifically configured to: Each visualization data feature and each visualization change association feature is identified through an image feature recognition network based on each visualization data information, each first visualization change association information, and each second visualization change association information; Each visualization data feature and each visualization change association feature is taken as data feature information corresponding to the visualization data information.

[0015] Optionally, the generation module is specifically configured to: The feature explanation information corresponding to the data feature information is identified through an image feature analysis network in an explanation data generation strategy based on each visualization data feature and each visualization change association feature. Based on the explicit association information of each enterprise data type and the implicit association information of each enterprise data type, data association explanation information between the enterprise data types is identified by an association semantic recognition network in the explanation data generation strategy. The feature explanation information corresponding to the data feature information and the data association explanation information between the enterprise data types are taken as the visual explanation information corresponding to the enterprise data content.

[0016] Optionally, the generation module is specifically configured to: Based on the user's explanation requirement information, the requirement explanation keywords and the requirement explanation key semantics of the user are extracted by a keyword extraction network. Based on the requirement explanation keywords and the requirement explanation key semantics, target visual explanation content is filtered in the visual explanation information, and the target explanation text corresponding to the user is generated by an explanation text generation network. The target explanation text is converted into display content by digital virtual propagation technology to obtain visual explanation display information corresponding to the enterprise data content.

[0017] In a third aspect, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the steps of the method in any one of the first aspect are implemented.

[0018] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the method in any one of the first aspect are implemented.

[0019] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the steps of the method in any one of the first aspect are implemented.

[0020] The visualization explanation generation method, device and computer equipment of the above data visualization, by acquiring enterprise data content and user explanation requirement information, and based on the enterprise data content, identifying the data correlation information of each enterprise data type; based on the data correlation information of each enterprise data type, generating the visualization data information corresponding to the enterprise data content through a visualization data generation strategy, and extracting the data feature information corresponding to the visualization data information; based on the data feature information and the data correlation information of each enterprise data type, generating the visualization explanation information corresponding to the enterprise data content through an explanation data generation strategy, and based on the visualization explanation information and the user's explanation requirement information, generating the visualization explanation display information corresponding to the enterprise data content through digital virtual propagation technology. The scheme first identifies the data correlation of each enterprise data type corresponding to the enterprise data content, thereby generating the visualization data information corresponding to the enterprise data content. Compared with the traditional visualization data information, the visualization data information generated by the scheme not only visually displays the data content of each enterprise data type, but also effectively displays the correlation information between each enterprise data type in the enterprise data content, enabling the user to more intuitively and comprehensively understand the correlation between each enterprise data type, improving the visualization display comprehensiveness and display effect of the enterprise data content. Secondly, the scheme generates visualization explanation content and builds visualization explanation display information based on the above technical scheme, thereby effectively avoiding the user's intuitive understanding deviation of the enterprise data and the data understanding error problem, and the visualization explanation display information can comprehensively explain the generated visualization data content, which can not only visually display the data content, but also display and explain the data content, improving the user's understanding level, thereby effectively improving the universal user understanding effect of the visualization explanation part of the data visualization, and improving the user satisfaction and user experience effect. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the embodiment or related art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0022] Figure 1 A flowchart of a visualization explanation generation method of data visualization in an embodiment; Figure 2 A flowchart of a visualization explanation generation example of data visualization in an embodiment; Figure 3A structural block diagram of a device for generating a visual explanation of data visualization in an embodiment; Figure 4 An internal structural diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0023] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0024] The method for generating a visual explanation of data visualization provided by the embodiments of the present application can be applied to an intelligent control system for generating a visual explanation of data visualization. The system can be applied to a terminal, which can be, but is not limited to, various personal computers, notebook computers, medium-sized computers, etc. The terminal first performs data correlation identification on each enterprise data type corresponding to the enterprise data content, thereby generating visual data information corresponding to the enterprise data content. Compared with traditional visual data information, the visual data information generated by the present application not only visually displays the data content of each enterprise data type, but also effectively displays the correlation information between each enterprise data type in the enterprise data content, so that the user can more intuitively and comprehensively understand the correlation between each enterprise data type, thereby improving the comprehensiveness and display effect of the visual display of the enterprise data content. In addition, the present application generates visual explanation content and constructs visual explanation display information based on the above technical solution, thereby effectively avoiding the problem of deviation of the user's intuitive understanding of the enterprise data and the error of the data understanding, and the visual explanation display information can be comprehensively explained in combination with the generated visual data content, which can not only visually display the data content, but also display and explain the data content, thereby improving the understanding degree of the user, thereby effectively improving the universal user understanding effect of the visual explanation part of the data visualization, and comprehensively improving the user satisfaction and user experience effect.

[0025] In an exemplary embodiment, as shown in Figure 1 A method for generating a visual explanation of data visualization is provided. The method is applied to a terminal as an example and includes the following steps S101 to S103. Wherein: Step S101, obtaining enterprise data content and user explanation requirement information, and identifying data correlation information of each enterprise data type based on the enterprise data content.

[0026] In this embodiment, the terminal collects enterprise data content which needs to be visualized and displayed, and in response to a user's information uploading operation, acquires voice / text content which the user needs to be visualized and explained. Then, the terminal identifies data correlation information of each enterprise data type based on the enterprise data content. The enterprise data content includes but is not limited to business intelligence (BI), financial analysis, market analysis, operation analysis, health care, government and public service, etc. Each enterprise data type can also be divided according to different time points and different data types, such as last month's financial data type, last month's marketing data type, this month's operation data type, etc. The data correlation information includes but is not limited to enterprise data type, joint data change correlation information between each associated enterprise data type; data content of each enterprise data type, single data change correlation information between the data content of other enterprise data types. The joint data change correlation information is the influence degree of the change of each enterprise data type on the data change of the enterprise data type which has correlation information with the enterprise data type, and the single data change correlation information is the change relationship formula between the data change of two enterprise data types and other information. The specific identification process will be described in detail later.

[0027] In step S102, based on the data correlation information of each enterprise data type, the visualized data generation strategy is used to generate visualized data information corresponding to the enterprise data content, and extract data feature information corresponding to the visualized data information.

[0028] In this embodiment, the terminal generates visual data information corresponding to the enterprise data content based on the data association information of each enterprise data type and through a visual data generation strategy, and extracts data feature information corresponding to the visual data information. The visual data information includes but is not limited to visual data information of each enterprise data type, first visual change association information of visual data information of each enterprise data type and visual data information of each other enterprise data type, and second visual change association information of visual data information of each enterprise data type and visual data information of each associated enterprise data type corresponding to each enterprise data type. The first visual change association information is visual association display information of data content change association between two enterprise data types, for example, a data change amount of A enterprise data type causes a data change amount of B enterprise data type, and the change amounts can be displayed through images, charts and the like. The second visual change association information is visual association display information of the influence degree between data change amounts of other enterprise data types associated with the enterprise data type caused by the data change amount of one enterprise data type, for example, the data change amount of A enterprise data type causes the data change amount degree of B, C and D enterprise data types. It should be explained that the first visual change association information is used to visually display the change association information between two enterprise data types with direct change association, for example, the data change amount of financial data type and the data change amount of marketing data type. The second visual change association information is used to visually display the influence degree of a certain enterprise data type on other enterprise data types. That is, the data change amount of a single enterprise data type is affected by the enterprise data change of multiple enterprise data types. The specific identification process will be described in detail later.

[0029] In step S103, based on the data feature information and the data association information of each enterprise data type, the visual interpretation information corresponding to the enterprise data content is generated through an interpretation data generation strategy, and based on the visual interpretation information and the interpretation demand information of the user, the visual interpretation display information corresponding to the enterprise data content is generated through a digital virtual propagation technology.

[0030] In this embodiment, the terminal generates visual interpretation information corresponding to the enterprise data content based on the data feature information and the data correlation information of each enterprise data type by interpreting the data generation strategy, and generates visual interpretation display information corresponding to the enterprise data content based on the visual interpretation information and the interpretation demand information of the user by using digital virtual propagation technology. The interpretation data generation strategy includes a keyword extraction network and an interpretation text generation network. Both of these neural networks are artificial neural networks constructed based on a large language model of natural language processing technology. The digital virtual propagation technology can be AI (Artificial Intelligence) digital virtual human technology, that is, the visual interpretation display information generated by the present scheme is the display information for interpreting and introducing the visual data content to the user by the digital virtual human.

[0031] Based on the above scheme, first, the data correlation of each enterprise data type corresponding to the enterprise data content is identified, thereby generating visual data information corresponding to the enterprise data content. Compared with traditional visual data information, the visual data information generated by the present scheme not only visually displays the data content of each enterprise data type, but also effectively displays the correlation information between each enterprise data type in the enterprise data content, so that the user can more intuitively and comprehensively understand the correlation between each enterprise data type, and the visual display comprehensiveness and display effect of the enterprise data content are improved. Secondly, based on the above technical scheme, the present scheme generates visual interpretation content and constructs visual interpretation display information, thereby effectively avoiding the problem of deviation of the user's intuitive understanding of the enterprise data and data understanding error, and the visual interpretation display information can be combined with the generated visual data content for comprehensive interpretation, which can not only visually display the data content, but also display and interpret the data content, thereby improving the user's understanding degree, effectively improving the universal user understanding effect of the visual interpretation part of the data visualization, and comprehensively improving the user satisfaction and user experience effect.

[0032] Optionally, based on the enterprise data content, data association information of each enterprise data type is identified, including: splitting the enterprise data content into sub-data content of each enterprise data type, and generating data distribution information of each enterprise data type based on the sub-data content of each enterprise data type; based on the data distribution information of each enterprise data type, identifying data change association information between the data content of each enterprise data type and the data content of other enterprise data types, and taking single data change association information between the data content of each enterprise data type and the data content of other enterprise data types as explicit association information of each enterprise data type; in the database, querying each associated enterprise data type corresponding to each enterprise data type, and based on the data distribution information of each enterprise data type and the data distribution information of each associated enterprise data type, identifying joint data change association information between each enterprise data type and each associated enterprise data type through a data association analysis network; taking the joint data change association information between each enterprise data type and each associated enterprise data type as implicit association information of each enterprise data type, and taking the explicit association information of each enterprise data type and the implicit association information of each enterprise data type as the data association information of each enterprise data type.

[0033] In this embodiment, the terminal splits the enterprise data content into sub-data content of each enterprise data type, and generates data distribution information of each enterprise data type based on the sub-data content of each enterprise data type; wherein the enterprise data distribution information is data distribution information obtained by distributing and arranging each sub-data content in time sequence.

[0034] The terminal identifies data change association information between the data content of each enterprise data type and the data content of other enterprise data types based on the data distribution information of each enterprise data type, and takes single data change association information between the data content of each enterprise data type and the data content of other enterprise data types as explicit association information of each enterprise data type. Wherein the single data change association information is direct change association between two enterprise data types, or the change influence degree of two enterprise data types is 100%.

[0035] In the database, the terminal queries each enterprise data type corresponding to each associated enterprise data type, and for each enterprise data type, based on the data distribution information of the enterprise data type and the data distribution information of each associated enterprise data type, through a data association analysis network, the joint data change association information between the enterprise data type and each associated enterprise data type is identified. Wherein, the data association analysis network is an analysis neural network for identifying the change influence degree of each enterprise data type on the associated enterprise data type, and the analysis neural network is a convolutional neural network based on a self-attention mechanism, which is used to identify the percentage of the change influence degree of different enterprise data types.

[0036] The terminal takes the joint data change association information between the enterprise data type and each associated enterprise data type as the implicit association information of each enterprise data type, and takes the explicit association information of each enterprise data type and the implicit association information of each enterprise data type as the data association information of each enterprise data type.

[0037] Based on the above scheme, by splitting the association information between the enterprise data types into direct and full association information and partial association information, the comprehensive identification of the data association information of each enterprise data type is improved.

[0038] Optionally, based on the data association information of each enterprise data type, the visual data information corresponding to the enterprise data content is generated through a visual data generation strategy, including: obtaining each visual data generation tool, and based on the sub-data content of each enterprise data type, constructing each visual data information of each enterprise data type through each visual data generation tool; based on the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types, constructing the first visual change association information between the visual data information of each enterprise data type and the visual data information of other enterprise data types; based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type, constructing the second visual change association information between the visual data information of each enterprise data type and the visual data information of each associated enterprise data type corresponding to each enterprise data type; taking each visual data information of each enterprise data type, the first visual change association information between the visual data information of each enterprise data type and the visual data information of other enterprise data types, and the second visual change association information between the visual data information of each enterprise data type and the visual data information of each associated enterprise data type corresponding to each enterprise data type, as the visual data information corresponding to the enterprise data content.

[0039] In this embodiment, the terminal obtains each visualization data generation tool, and based on the sub-data content of each enterprise data type, constructs each visualization data information of each enterprise data type through each visualization data generation tool. The visualization data generation tool is to generate different visualization chart types, such as line chart, column chart, pie chart, map, radar chart, etc. After the visualization data information is generated, image adjustment can be performed on the visualization data information through a graphics rendering technology to ensure the high definition and smoothness of the chart and three-dimensional model.

[0040] Then, the terminal constructs the first visualization change correlation information of each visualization data information of each enterprise data type and each visualization data information of each other enterprise data type based on the single data change correlation information between the data content of each enterprise data type and the data content of each other enterprise data type. The visualization change correlation information is the visualization display content corresponding to the change amount of the visualization data information of the other enterprise data type when the visualization data information of each enterprise data type changes.

[0041] Then, the terminal constructs the second visualization change correlation information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type based on the joint data change correlation information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type.

[0042] Finally, the terminal constructs the visualization data information corresponding to the enterprise data content as each visualization data information of each enterprise data type, the first visualization change correlation information of each visualization data information of each enterprise data type and each visualization data information of each other enterprise data type, and the second visualization change correlation information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type.

[0043] Based on the above scheme, the visualization data information is generated by combining the visualization tool, and then the visualization change correlation information is generated, which improves the comprehensiveness of the generation of the visualization data information corresponding to the enterprise data content, and effectively enables the user to obtain a more stereoscopic interactive experience effect.

[0044] Optionally, the data feature information corresponding to the visualization data information includes: identifying each visualization data feature and each visualization change correlation feature through an image feature recognition network based on each visualization data information, each first visualization change correlation information, and each second visualization change correlation information; and taking each visualization data feature and each visualization change correlation feature as the data feature information corresponding to the visualization data information.

[0045] In this embodiment, the terminal identifies the visual data features and the visual change correlation features based on the visual data information, the first visual change correlation information, and the second visual change correlation information through an image feature recognition network. The image feature recognition network can be constructed based on a convolutional neural network of deep learning.

[0046] Then, the terminal takes the visual data features and the visual change correlation features as the data feature information corresponding to the visual data information.

[0047] Based on the above scheme, the data feature information corresponding to the visual data information is effectively identified by feature extraction on the visual change correlation information, thereby improving the comprehensiveness of feature extraction on the visual data information.

[0048] Optionally, based on the data feature information and the data correlation information of each enterprise data type, the visual explanation information corresponding to the enterprise data content is generated through an explanation data generation strategy, including: based on the visual data features and the visual change correlation features, the feature explanation information corresponding to the data feature information is identified through an image feature analysis network in the explanation data generation strategy; based on the explicit correlation information of each enterprise data type and the implicit correlation information of each enterprise data type, the data correlation explanation information between each enterprise data type is identified through a correlation semantic recognition network in the explanation data generation strategy; and the feature explanation information corresponding to the data feature information and the data correlation explanation information between each enterprise data type are taken as the visual explanation information corresponding to the enterprise data content.

[0049] In this embodiment, the terminal identifies the visual data features and the visual change correlation features based on the visual data information, the first visual change correlation information, and the second visual change correlation information through an image feature recognition network. The image feature recognition network can be constructed based on a convolutional neural network of deep learning.

[0050] Then, the terminal identifies the visual data features and the visual change correlation features based on the visual data information, the first visual change correlation information, and the second visual change correlation information through an image feature recognition network. The image feature recognition network can be constructed based on a convolutional neural network of deep learning.

[0051] Finally, the terminal takes the data feature information corresponding to the feature explanation information and the data correlation explanation information between each enterprise data type as the visual explanation information corresponding to the enterprise data content.

[0052] Based on the above scheme, the comprehensiveness of the explanation text generation of enterprise data content is improved by generating explanation text for visual content and data association information.

[0053] Optionally, based on the visual explanation information and the user's explanation requirement information, the visual explanation display information corresponding to the enterprise data content is generated through digital virtual propagation technology, including: based on the user's explanation requirement information, the demand explanation keywords and the demand explanation key semantics of the user are extracted through a keyword extraction network; based on the demand explanation keywords and the demand explanation key semantics, the target visual explanation content is filtered in the visual explanation information, and the target explanation text corresponding to the user is generated through an explanation text generation network; the target explanation text is converted into display content through digital virtual propagation technology to obtain the visual explanation display information corresponding to the enterprise data content.

[0054] In this embodiment, the terminal extracts the demand explanation keywords and the demand explanation key semantics of the user based on the user's explanation requirement information through a keyword extraction network. The keyword extraction network is a convolutional neural network based on natural language processing technology.

[0055] The terminal filters the target visual explanation content in the visual explanation information based on the demand explanation keywords and the demand explanation key semantics, and generates the target explanation text corresponding to the user through an explanation text generation network. The filtering method is to filter the visual explanation content that is semantically similar to the demand explanation key semantics or contains the demand explanation keywords.

[0056] Finally, the terminal converts the target explanation text into display content through digital virtual propagation technology to obtain the visual explanation display information corresponding to the enterprise data content.

[0057] Based on the above scheme, the visual explanation display information for different users can be customized and generated by adapting the visual explanation content to the user's explanation requirement information, thereby improving the comprehensiveness and accuracy of the visual explanation.

[0058] The application also provides a visual explanation generation example of data visualization, as shown in Figure 2 The specific processing process includes the following steps: Step S201, obtaining enterprise data content and user's explanation requirement information.

[0059] Step S202, splitting the enterprise data content into sub-data content of each enterprise data type, and generating data distribution information of each enterprise data type based on the sub-data content of each enterprise data type.

[0060] Step S203, based on the data distribution information of each enterprise data type, identifying the data content of each enterprise data type, the data change association information between the data content of each enterprise data type and the data content of other enterprise data types, and taking the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types as the explicit association information of each enterprise data type.

[0061] Step S204, in the database, querying each associated enterprise data type corresponding to each enterprise data type, and for each enterprise data type, based on the data distribution information of the enterprise data type and the data distribution information of each associated enterprise data type, identifying the joint data change association information between the enterprise data type and each associated enterprise data type through data association analysis network.

[0062] Step S205, taking the joint data change association information between the enterprise data type and each associated enterprise data type as the implicit association information of each enterprise data type, and taking the explicit association information of each enterprise data type and the implicit association information of each enterprise data type as the data association information of each enterprise data type.

[0063] Step S206, obtaining each visualization data generation tool, and based on the sub-data content of each enterprise data type, constructing each visualization data information of each enterprise data type through each visualization data generation tool.

[0064] Step S207, based on the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types, constructing the first visualization change association information of each visualization data information of each enterprise data type and each visualization data information of other enterprise data types.

[0065] Step S208, based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type, constructing the second visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type.

[0066] Step S209, taking each visualization data information of each enterprise data type, the first visualization change association information of each visualization data information of each enterprise data type and each visualization data information of other enterprise data types, and the second visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type as the visualization data information corresponding to the enterprise data content.

[0067] At step S210, based on the visual data information, the first visual change correlation information, and the second visual change correlation information, the visual data features and the visual change correlation features are identified through the image feature recognition network.

[0068] At step S211, the visual data features and the visual change correlation features are taken as the data feature information corresponding to the visual data information.

[0069] At step S212, based on the visual data features and the visual change correlation features, the feature explanation information corresponding to the data feature information is identified through the image feature analysis network in the explanation data generation strategy.

[0070] At step S213, based on the explicit correlation information of the enterprise data types and the implicit correlation information of the enterprise data types, the data correlation explanation information between the enterprise data types is identified through the correlation semantic recognition network in the explanation data generation strategy.

[0071] At step S214, the feature explanation information corresponding to the data feature information and the data correlation explanation information between the enterprise data types are taken as the visual explanation information corresponding to the enterprise data content.

[0072] At step S215, based on the explanation requirement information of the user, the requirement explanation keywords and the requirement explanation key semantics of the user are extracted through the keyword extraction network.

[0073] At step S216, based on the requirement explanation keywords and the requirement explanation key semantics, the target visual explanation content is filtered from the visual explanation information, and the target explanation text corresponding to the user is generated through the explanation text generation network.

[0074] At step S217, the target explanation text is converted into the display content through the digital virtual propagation technology, and the visual explanation display information corresponding to the enterprise data content is obtained.

[0075] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0076] Based on the same inventive concept, the embodiments of the present application also provide a data visualization visual explanation generation device for implementing the data visualization visual explanation generation method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more data visualization visual explanation generation device embodiments provided below can refer to the limitations of the data visualization visual explanation generation method described above, which will not be repeated here.

[0077] In one exemplary embodiment, as shown in Figure 3 A data visualization visual explanation generation device is provided, comprising: an acquisition module 310, an extraction module 320 and a generation module 330, wherein: The acquisition module 310 is configured to acquire enterprise data content and user explanation requirement information, and identify data correlation information of each enterprise data type based on the enterprise data content; The extraction module 320 is configured to generate visual data information corresponding to the enterprise data content by a visual data generation strategy based on the data correlation information of each enterprise data type, and extract data feature information corresponding to the visual data information; The generation module 330 is configured to generate visual explanation information corresponding to the enterprise data content by an explanation data generation strategy based on the data feature information and the data correlation information of each enterprise data type, and generate visual explanation display information corresponding to the enterprise data content by a digital virtual propagation technology based on the visual explanation information and the user's explanation requirement information.

[0078] Optionally, the acquisition module 310 is specifically configured to: split the enterprise data content into sub-data content of each enterprise data type, and generate data distribution information of each enterprise data type based on the sub-data content of each enterprise data type; identify data change correlation information between the data content of each enterprise data type and the data content of other enterprise data types based on the data distribution information of each enterprise data type, and take single data change correlation information between the data content of each enterprise data type and the data content of other enterprise data types as explicit correlation information of each enterprise data type; In the database, query each enterprise data type corresponding to each associated enterprise data type, and for each enterprise data type, based on the data distribution information of the enterprise data type and the data distribution information of each associated enterprise data type, through the data association analysis network, identify the joint data change association information between the enterprise data type and each associated enterprise data type. The joint data change association information between the enterprise data type and each associated enterprise data type is taken as the implicit association information of each enterprise data type, and the explicit association information of each enterprise data type and the implicit association information of each enterprise data type are taken as the data association information of each enterprise data type.

[0079] Optionally, the extraction module 320 is specifically used for: Obtain each visualization data generation tool, and based on the sub-data content of each enterprise data type, construct each visualization data information of each enterprise data type through each visualization data generation tool; Based on the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types, construct the first visualization change association information between each visualization data information of each enterprise data type and each visualization data information of other enterprise data types; Based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type, construct the second visualization change association information between each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type; Take each visualization data information of each enterprise data type, the first visualization change association information between each visualization data information of each enterprise data type and each visualization data information of other enterprise data types, and the second visualization change association information between each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type, as the visualization data information corresponding to the enterprise data content.

[0080] Optionally, the extraction module 320 is specifically used for: Based on each visualization data information, each first visualization change association information, and each second visualization change association information, identify each visualization data feature and each visualization change association feature through an image feature recognition network; Take each visualization data feature and each visualization change association feature as the data feature information corresponding to the visualization data information.

[0081] Optionally, the generating module 330 is specifically used for: Based on each of the visualization data features and each of the visualization change-related features, the feature explanation information corresponding to the data feature information is identified by an image feature analysis network in the explanation data generation strategy. Based on the explicit association information of each of the enterprise data types and the implicit association information of each of the enterprise data types, the data association explanation information between each of the enterprise data types is identified by an association semantic recognition network in the explanation data generation strategy. The feature explanation information corresponding to the data feature information and the data association explanation information between each of the enterprise data types are taken as the visualization explanation information corresponding to the enterprise data content.

[0082] Optionally, the generating module 330 is specifically used for: Based on the explanation requirement information of the user, the requirement explanation keywords and the requirement explanation key semantics of the user are extracted by a keyword extraction network. Based on the requirement explanation keywords and the requirement explanation key semantics, the target visualization explanation content is filtered in the visualization explanation information, and the target explanation text corresponding to the user is generated by an explanation text generation network. The target explanation text is converted into display content by digital virtual propagation technology to obtain the visualization explanation display information corresponding to the enterprise data content.

[0083] Each of the modules in the above visualization explanation generation device for data visualization can be realized by software, hardware and combinations thereof, in whole or in part. Each of the above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each of the above modules.

[0084] In one exemplary embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in Figure 4As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with the external terminal in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize a data visualization visual interpretation generation method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0085] Those skilled in the art can understand that, Figure 4 The skilled in the art can understand that,

[0086] In one exemplary embodiment, a computer device is provided, comprising a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps of the data visualization visual interpretation generation method.

[0087] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to realize the steps of the data visualization visual interpretation generation method.

[0088] In one embodiment, a computer program product is provided, comprising a computer program, and the computer program is executed by the processor to realize the steps of the data visualization visual interpretation generation method.

[0089] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0090] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0091] The technical features of the above embodiments can be combined in any way. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0092] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A method for generating a visual explanation of data visualization, characterized in that: The method comprises: Acquire enterprise data content and user interpretation requirement information, and identify data association information of each enterprise data type based on the enterprise data content; Based on the data association information of each of the enterprise data types, generating visual data information corresponding to the enterprise data content through a visual data generation strategy, and extracting data feature information corresponding to the visual data information; Based on the data feature information and the data association information of each type of enterprise data, the visual interpretation information corresponding to the enterprise data content is generated through the interpretation data generation strategy, and based on the visual interpretation information and the user's interpretation demand information, the visual interpretation display information corresponding to the enterprise data content is generated through digital virtual communication technology.

2. The method according to claim 1, characterized in that The identifying, based on the enterprise data content, data association information of each enterprise data type includes: Splitting the enterprise data content into sub-data content of each enterprise data type, and generating data distribution information of each enterprise data type based on the sub-data content of each enterprise data type; Based on the data distribution information of each of the enterprise data types, identifying the data content of each enterprise data type and the data change association information between the data content of each enterprise data type and the data content of other enterprise data types, and using the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types as the explicit association information of each of the enterprise data types; Inquiring in a database about each associated enterprise data type corresponding to each enterprise data type, and for each enterprise data type, identifying, through a data association analysis network, joint data change association information between the enterprise data type and each associated enterprise data type based on data distribution information of the enterprise data type and data distribution information of each associated enterprise data type; The enterprise data type and the joint data change association information between each of the related enterprise data types are used as implicit association information of each of the enterprise data types, and the explicit association information of each of the enterprise data types and the implicit association information of each of the enterprise data types are used as data association information of each of the enterprise data types.

3. The method according to claim 2, characterized in that The generating of visual data information corresponding to the enterprise data content by using a visual data generation strategy based on the data association information of each enterprise data type includes: Obtaining each visualization data generation tool, and constructing each visualization data information of each enterprise data type through each visualization data generation tool based on the sub-data content of each enterprise data type; Based on the data content of each enterprise data type and the single data change association information between the data content of each enterprise data type and the data content of other enterprise data types, construct first visualization change association information of each visualization data information of each enterprise data type and each visualization data information of other enterprise data types; Based on the joint data change association information between each enterprise data type and each associated enterprise data type corresponding to each enterprise data type, construct second visualization change association information of each visualization data information of each enterprise data type and each visualization data information of each associated enterprise data type corresponding to each enterprise data type; The visual data information of each enterprise data type, the first visual change association information of each enterprise data type and the visual data information of other enterprise data types, and the second visual change association information of each enterprise data type and the visual data information of each associated enterprise data type corresponding to each enterprise data type are used as the visual data information corresponding to the enterprise data content.

4. The method according to claim 3, characterized in that The extracting data feature information corresponding to the visual data information includes: Based on each of the visualization data information, each of the first visualization change association information, and each of the second visualization change association information, identifying each of the visualization data features and each of the visualization change association features through an image feature recognition network; Each of the visualization data features and each of the visualization change associated features is used as data feature information corresponding to the visualization data information.

5. The method according to claim 4, characterized in that The generating of visual interpretation information corresponding to the enterprise data content by interpreting the data generation strategy based on the data feature information and the data association information of each enterprise data type includes: Based on each of the visualization data features and each of the visualization change association features, identifying feature interpretation information corresponding to the data feature information through an image feature analysis network in an interpretation data generation strategy; Based on the explicit association information of each enterprise data type and the implicit association information of each enterprise data type, identifying data association interpretation information between each enterprise data type through the association semantic recognition network in the interpretation data generation strategy; The feature explanation information corresponding to the data feature information and the data association explanation information between the enterprise data types are used as the visual explanation information corresponding to the enterprise data content.

6. The method according to claim 5, characterized in that The generating of visual interpretation display information corresponding to the enterprise data content based on the visual interpretation information and the user's interpretation demand information by using digital virtual communication technology includes: Based on the user's interpretation demand information, extracting the user's demand interpretation keywords and the user's demand interpretation key semantics through a keyword extraction network; Based on the demand explanation keywords and demand explanation key semantics, target visual explanation content is screened in the visual explanation information, and a target explanation text corresponding to the user is generated through an explanation text generation network; Through digital virtual communication technology, the target explanation text is converted into display content to obtain visual explanation display information corresponding to the enterprise data content.

7. A visual explanation generating device for data visualization, characterized in that: The device comprises: An acquisition module, configured to acquire enterprise data content and user interpretation requirement information, and identify data association information of each enterprise data type based on the enterprise data content; An extraction module, configured to generate visual data information corresponding to the enterprise data content based on the data association information of each enterprise data type and through a visual data generation strategy, and extract data feature information corresponding to the visual data information; A generation module is used to generate visual interpretation information corresponding to the enterprise data content based on the data feature information and the data association information of each type of enterprise data by interpreting the data generation strategy, and to generate visual interpretation display information corresponding to the enterprise data content based on the visual interpretation information and the user's interpretation demand information by digital virtual communication technology.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images