Report data visualization method, device, system, equipment and medium

Abstract

The invention provides a visualization method, device, system and equipment for report data and a medium, and the method comprises the steps: obtaining a plurality of pieces of business data, and constructing a corresponding business report by employing each piece of business data and a preset report template; acquiring real-time demand information of a user, determining a plurality of service three-dimensional models based on the real-time demand information, constructing a service digital model by using the plurality of service three-dimensional models, and adding the plurality of service reports to the service digital model to obtain a service display model; and respectively obtaining a static characteristic parameter and a dynamic characteristic parameter from the real-time demand information, rendering the service display model by using the static characteristic parameter to obtain a rendering model, and calling a preset Voyager model to perform visualization processing on the rendering model based on the initial coordinate and the initial angle of the dynamic characteristic parameter. According to the method and the device, the business data in different formats can be unified, so that the situations of visualization errors and data visualization deviation are avoided, and the model is constructed and visualized on the basis of user requirements, so that the display effect is improved.

Description

Technical Field

[0001] The present application relates to the field of data visualization, and in particular to a method, apparatus, system, equipment and medium for visualizing report data. Background Art

[0002] With the development of the digital information age, financial services are gradually transforming towards digitalization. With an increasing number of business services being applied across various platforms, online financial services are becoming increasingly complex, leading to a massive increase in business information and data. Automated and intelligent business processing on online platforms can improve business efficiency.

[0003] After collecting massive amounts of business data, data visualization technology can be used to intuitively represent the disorganized business data, helping users identify business patterns within the massive data and optimize business services. Currently, a common visualization method is to extract business data from different platforms, add different business data to report templates, and then use visualization tools such as tables and charts to visualize the report templates, dynamically displaying the data for technical personnel to analyze and optimize the data information.

[0004] However, the currently commonly used methods have the following technical problems: data definitions and field naming may differ between different systems or platforms. If non-standardized data is used for visualization, the visualization results will have large deviations; and using a single tool for visualization will result in a single display effect, which is difficult to meet users' data visualization needs. Summary of the Invention

[0005] In view of the above problems, the present application is proposed to provide a report data visualization method, apparatus, system, device, and medium that overcomes or at least partially solves the above problems, including: A method for visualizing report data, the method comprising: Acquire multiple business data, and construct corresponding business reports using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; Acquiring real-time demand information of users, and determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model matches one business report; Static feature parameters and dynamic feature parameters are respectively obtained from the real-time demand information, the business display model is rendered using the static feature parameters to obtain a rendering model, and a preset Voyager model is called to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0006] In a possible implementation, calling a preset Voyager model to perform visualization processing on the rendering model based on the starting coordinates and starting angle of the dynamic feature parameters includes: Determining the starting coordinates and starting angles of the dynamic feature parameters, and constructing a visualization trajectory using the starting coordinates and starting angles; The preset Voyager model is called to perform video diffusion on the rendering model based on the visualization trajectory to obtain a model diffusion image, and the model diffusion image is visually displayed.

[0007] In a possible implementation, determining multiple business three-dimensional models based on the real-time demand information includes: Extracting multiple business keywords from the real-time demand information and forming a keyword set; Calculating the cosine similarity between the keyword set and the index combination of each preset model library; Selecting a number of models with values ​​greater than a preset similarity from the plurality of cosine similarities as the models to be determined; First characteristic information of the business report is determined, and one of the models to be determined is determined as a business three-dimensional model based on the first characteristic information, to obtain multiple business three-dimensional models.

[0008] In a possible implementation, determining a plurality of business three-dimensional models based on the real-time demand information further includes: If each of the cosine similarities is less than a preset similarity, determining the second characteristic information of the business report; Calling a preset generative adversarial network to generate a plurality of initial object images according to the object of the second feature information; The physical size parameters of the object in each of the initial object images are determined, and the business three-dimensional model is constructed using the physical size parameters.

[0009] In a possible implementation, the constructing of a business digital model using the plurality of the business three-dimensional models, and adding the plurality of the business reports to the business digital model to obtain a business display model includes: Obtaining a time node of each of the business data, and connecting a plurality of the business three-dimensional models according to a plurality of the time nodes to obtain a business digital model; Obtaining a captured image of the business digital model when displayed on a screen, and determining a plurality of visual areas from the captured image; The spatial coordinates of each visual area in the business digital model are determined, and each business report is added to a corresponding position of the business digital model according to the spatial coordinates to obtain a business display model.

[0010] In a possible implementation, rendering the service presentation model using the static feature parameters to obtain a rendering model includes: extracting background parameters and model parameters from the static feature parameters; Searching for a background image based on the background parameters, fusing the background image with the business presentation model to obtain a fusion model; The fusion model is rendered based on the model parameters to obtain a rendering model.

[0011] A device for visualizing report data, comprising: An acquisition module, configured to acquire a plurality of business data and construct a corresponding business report using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; a construction module for obtaining real-time demand information of users, determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model is matched with a business report; A visualization module is used to obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, use the static feature parameters to render the business display model to obtain a rendering model, and call a preset Voyager model to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0012] In a possible implementation, calling a preset Voyager model to perform visualization processing on the rendering model based on the starting coordinates and starting angle of the dynamic feature parameters includes: Determining the starting coordinates and starting angles of the dynamic feature parameters, and constructing a visualization trajectory using the starting coordinates and starting angles; The preset Voyager model is called to perform video diffusion on the rendering model based on the visualization trajectory to obtain a model diffusion image, and the model diffusion image is visually displayed.

[0013] In a possible implementation, determining multiple business three-dimensional models based on the real-time demand information includes: Extracting multiple business keywords from the real-time demand information and forming a keyword set; Calculating the cosine similarity between the keyword set and the index combination of each preset model library; Selecting a number of models with values ​​greater than a preset similarity from the plurality of cosine similarities as the models to be determined; First characteristic information of the business report is determined, and one of the models to be determined is determined as a business three-dimensional model based on the first characteristic information, to obtain multiple business three-dimensional models.

[0014] In a possible implementation, determining a plurality of business three-dimensional models based on the real-time demand information further includes: If each of the cosine similarities is less than a preset similarity, determining the second characteristic information of the business report; Calling a preset generative adversarial network to generate a plurality of initial object images according to the object of the second feature information; The physical size parameters of the object in each of the initial object images are determined, and the business three-dimensional model is constructed using the physical size parameters.

[0015] In a possible implementation, the constructing of a business digital model using the plurality of the business three-dimensional models, and adding the plurality of the business reports to the business digital model to obtain a business display model includes: Obtaining a time node of each of the business data, and connecting a plurality of the business three-dimensional models according to a plurality of the time nodes to obtain a business digital model; Obtaining a captured image of the business digital model when displayed on a screen, and determining a plurality of visual areas from the captured image; The spatial coordinates of each visual area in the business digital model are determined, and each business report is added to a corresponding position of the business digital model according to the spatial coordinates to obtain a business display model.

[0016] In a possible implementation, rendering the service presentation model using the static feature parameters to obtain a rendering model includes: extracting background parameters and model parameters from the static feature parameters; Searching for a background image based on the background parameters, fusing the background image with the business presentation model to obtain a fusion model; The fusion model is rendered based on the model parameters to obtain a rendering model.

[0017] A report data visualization system, comprising: a data center and multiple business platforms, wherein the data center is suitable for the report data visualization method described above; The data middle platform is connected to multiple business platforms respectively.

[0018] A device includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of visualizing the report data as described above.

[0019] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of visualizing report data as described above.

[0020] This application has the following advantages: In an embodiment of the present application, the present application can obtain multiple business data, use the business data and preset report templates to build corresponding business reports; obtain the user's real-time demand information, build a business digital model based on the user's real-time demand information, and add multiple business reports to the business digital model to obtain a business display model; obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, use the static feature parameters to render the business display model to obtain a rendering model, and call the preset Voyager model to visualize the rendering model based on the dynamic feature parameters. The present application can unify business data of different formats by converting business data into generated reports, thereby avoiding visualization errors caused by inconsistent data and deviations in data visualization. On this basis, building a model based on the user's real-time demand information and controlling the model for visualization can improve the flexibility of visualization, meet the actual needs of users, and improve the display effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for the description of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a flowchart of a method for visualizing report data provided by an embodiment of the present application; Figure 2 This is a structural block diagram of a report data visualization device provided by an embodiment of the present application; Figure 3 This is a structural block diagram of a report data visualization system provided by an embodiment of the present application; Figure 4 It is a structural diagram of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0023] To make the objectives, features, and advantages of this application more readily apparent, the present application is further described below in conjunction with the accompanying drawings and specific embodiments. It is apparent that the embodiments described are only a portion of the embodiments of this application, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments in this application without inventive effort are also within the scope of protection of this application.

[0024] With the development of the digital information age, financial services are gradually transforming towards digitalization. With an increasing number of business services being applied across various platforms, online financial services are becoming increasingly complex, leading to a massive increase in business information and data. Automated and intelligent business processing on online platforms can improve business efficiency.

[0025] After collecting massive amounts of business data, data visualization technology can be used to intuitively represent the disorganized business data, helping users identify business patterns within the massive data and optimize business services. Currently, a common visualization method is to extract business data from different platforms, add different business data to report templates, and then use visualization tools such as tables and charts to visualize the report templates, dynamically displaying the data for technical personnel to analyze and optimize the data information.

[0026] However, the currently commonly used methods have the following technical problems: data definitions and field naming may differ between different systems or platforms. If non-standardized data is used for visualization, the visualization results will have large deviations; and using a single tool for visualization will result in a single display effect, which is difficult to meet users' data visualization needs.

[0027] In order to solve the above problems, the following specific embodiments will be used to introduce and explain in detail a method, device, system, equipment and medium for visualizing report data provided by the embodiments of the present application.

[0028] In order to solve the technical problem that the existing technology uses a single visualization tool to visualize non-uniform data, the visualization effect is poor, and it is difficult to meet the user's data visualization needs, refer to Figure 1 , which shows a flow chart of a method for visualizing report data provided by an embodiment of the present application.

[0029] The method is applied to a data middle platform, which is communicated with different business platforms. Each business platform is used to process different business services, and each business platform corresponds to one or more databases, each database is used to store data of the business services corresponding to the business platform.

[0030] As an example, the report data visualization method may include: S11. Acquire multiple business data, and use each business data and a preset report template to construct a corresponding business report, wherein each business data is business service data of a different business platform.

[0031] In one embodiment, the data center can receive visualization requests from users and, based on the visualization requests, retrieve corresponding business data from different business platforms. For example, if a user needs to visualize vehicle reimbursement business data for the xxth quarter, they can retrieve the accident party data from the responsible party's business platform, retrieve the non-responsible party data from the non-responsible party's business platform, retrieve vehicle data from the damage assessment 4S shop's business platform, and retrieve the claim amount data from the claims settlement business platform.

[0032] Since different business platforms may be developed at different times, with different technical personnel or standards, and different business platforms store data in different formats, they may be external business platforms. Therefore, the formats of multiple business data obtained are different from each other.

[0033] In order to unify the data format, a preset report template can be obtained. Then, the business data of each business platform can be added to the preset report template to obtain the business report corresponding to each business platform.

[0034] In order to adapt to business data in different formats, different business platforms can set different report templates. In one operation mode, business data can be mapped to a report template, so that business data can be added to a preset report template to obtain a business report.

[0035] Because report templates adapt to different business data, the formats of different report templates are also inconsistent. To unify the formats of business reports, in one embodiment, a preset report renderer can be called to render each business report to generate a corresponding style. For example, each business report can be rendered into a web report or an Excel electronic report.

[0036] In another optional embodiment, it is also possible to determine whether each business report is a report in a preset format (e.g., Excel format). If the business report is not in the preset format (e.g., Excel format), the business report is traversed and recognized according to the OCR recognition algorithm to obtain sorted recognition data. The sorted recognition data is then written into a result matrix frame in a preset format based on the row and column vectors to obtain a recognition result matrix. Based on the standard sorting, the recognition result matrix is ​​sorted, adjusted, and converted to obtain a standardized report.

[0037] S12. Obtain the user's real-time demand information, and determine multiple business three-dimensional models based on the real-time demand information, use the multiple business three-dimensional models to build a business digital model, add the multiple business reports to the business digital model, and obtain a business display model, wherein each business three-dimensional model matches one business report.

[0038] After unifying business data across different platforms, real-time user demand information can be obtained. This real-time demand information can include user requirements for displaying business data, including visualization rules, colors, sizes, angles, and methods. This real-time demand information can be used to determine actual user needs, and subsequent visualization processing can be performed based on this real-time demand information to enhance the visualization effect.

[0039] Since business reports typically display various data items, if there are many data items, the amount of content users need to review also increases. However, reviewing each individual data item is not only tedious, but also makes it difficult for users to determine data relationships and characteristics.

[0040] To improve presentation quality, multiple 3D business models can be determined based on real-time demand information. Each 3D business model is matched to a business report. This means that the model corresponding to each business report is found based on real-time demand information. Each business report corresponds to a business platform, and the 3D business model can also be matched to the business platform.

[0041] The business 3D model can be a business icon model, an execution object model, an execution location model, etc. The business 3D model can more intuitively reflect the business services corresponding to its business data, allowing users to identify the relationship between data and business, thereby improving the display effect.

[0042] After finding multiple business three-dimensional models, you can use them to build a business digital model. The entire business digital model can be used to more intuitively display the entire business service. Finally, you can add multiple business reports to the business digital model to obtain a business display model. The business display model can be used to display the entire business service. In addition to viewing the values ​​​​of the report, users can also view their business-related objects through the model, thereby improving the display effect.

[0043] Since business 3D models may be of various styles, including business objects, execution locations, and icons, and different users may need to view similar models, to improve processing efficiency, multiple models can be pre-built. A database can then be constructed using these pre-built models, storing multiple 3D models. In an alternative embodiment, each business platform can have a database that stores the models required by that business platform.

[0044] As an example, determining a plurality of business three-dimensional models based on the real-time demand information may include the following sub-steps: S21. Extract multiple business keywords from the real-time demand information and form a keyword set.

[0045] S22: Calculate the cosine similarity between the keyword set and the index combination of each preset model library.

[0046] S23 , selecting a number of models with values ​​greater than a preset similarity from the plurality of cosine similarities as models to be determined.

[0047] S24. Determine first characteristic information of the business report, and determine one of the models to be determined as a business three-dimensional model based on the first characteristic information, to obtain multiple business three-dimensional models.

[0048] In one embodiment, the real-time demand information may be read and split, and a plurality of business keywords may be extracted from the split words to form a keyword set.

[0049] It should be noted that for each business platform, multiple models can be pre-built, and then the multiple models can be combined into a database to obtain a preset model library, so that each preset model can correspond to a business platform.

[0050] On this basis, in order to distinguish each model in each preset model library, each model can be assigned an index combination, which can be a string of feature vectors. For example, the index corresponding to the business object model is [010101], and the index corresponding to the business icon model is [010001].

[0051] In order to search for the corresponding model in the preset model library corresponding to each business platform, the text characters of the keyword set can be converted into text vectors, and then the cosine similarity is calculated using the text vector and the feature vector of each index of each preset model library, so that multiple cosine similarities corresponding to each preset model library can be calculated.

[0052] In one approach, the Bag of Words (BoW) model can be used to treat the text in the keyword set as an unordered collection of words, count the word frequencies in the keyword text, and then generate vectors based on the word frequencies. Alternatively, a pre-trained language model (such as BERT or GPT) can be used to convert the text in the keyword set into text vectors.

[0053] In one embodiment, the calculation formula of cosine similarity is as follows: ; In the above formula, cosine_similarity(A,B) is the cosine similarity; A is the text vector; B is the feature vector corresponding to the index; dot represents the dot product of the vectors, also known as the inner product, which is the sum of the products of the corresponding elements of the two vectors; ||A|| and ||B|| represent the modulus (or length) of the vector, which can be obtained by calculating the sum of the squares of each vector element and then taking the square root.

[0054] It should be noted that the value of cosine similarity ranges from -1 to 1. When cosine similarity is equal to 1, it means that the two vectors have exactly the same direction in multidimensional space, that is, they are completely similar. When cosine similarity is equal to 0, it means that there is no linear relationship between the two vectors and they are unrelated. When cosine similarity is equal to -1, it means that the two vectors have exactly opposite directions in multidimensional space, that is, they are completely different.

[0055] Next, a number of cosine similarities greater than a preset similarity may be screened from the multiple cosine similarities corresponding to each preset model library, and the models corresponding to the cosine similarities are used as the models to be determined.

[0056] Finally, the first characteristic information of the business report can be determined, and based on the first characteristic information, one of the models to be determined is determined as the business 3D model. Since there are multiple business platforms, each business platform can determine a business 3D model, and finally multiple business 3D models can be obtained.

[0057] The first characteristic information may include the business service device model corresponding to the business platform, the business object corresponding to the business platform, the processing object corresponding to the business platform, the service location corresponding to the business platform, and the like.

[0058] For example, three models to be determined are screened from the preset model library A: the avatar model corresponding to the business platform, the icon model corresponding to the business platform, and the service device model corresponding to the business platform. If the first feature information corresponds to the processing device, the service device model corresponding to the business platform can be used as the business 3D model.

[0059] In one operation mode, the text of the first characteristic information can be read, and the name text of the model to be determined can be determined at the same time. The text of the first characteristic information is matched with the name text of the model to be determined, so as to determine the required model and obtain the business three-dimensional model.

[0060] In an optional embodiment, the model required by the user may not be in the preset model library. Therefore, it is necessary to rebuild a model that meets the user's needs. As an example, determining multiple business three-dimensional models based on the real-time demand information may include the following sub-steps: S25. If each of the cosine similarities is less than a preset similarity, determine the second characteristic information of the business report.

[0061] S26. Call a preset generative adversarial network to generate several initial object images according to the object of the second feature information.

[0062] S27: Determine the physical size parameters of the object in each of the initial object images, and construct a business three-dimensional model using the physical size parameters.

[0063] In one embodiment, it can be determined whether each cosine similarity corresponding to each preset model library is greater than the preset similarity. If each cosine similarity corresponding to the preset model library is less than the preset similarity, it means that none of the models stored in this preset model library meets the user's needs and a new model needs to be rebuilt.

[0064] In order to match user needs, second characteristic information can be extracted from the business report. The second characteristic information is the same as the above-mentioned first characteristic information, and may also include the business service equipment model corresponding to the business platform, the business service personnel corresponding to the business platform, the processing object corresponding to the business platform, the service location corresponding to the business platform, etc.

[0065] Then, a preset generative adversarial network may be called to generate a plurality of initial object images according to the object of the second feature information.

[0066] For example, a generative adversarial network (GAN) may be called to generate an image based on an object (such as an icon or a business service device) of the second feature information to obtain several initial object images.

[0067] Assuming that the business service is vehicle insurance claims, and its second feature information is the target vehicle of the claims business service, a generative adversarial network (GAN) can be called to generate multiple vehicle images to obtain several initial object images.

[0068] After determining the size of the vehicle in each initial object image, the physical size parameters are obtained, and then the 3DGAN generation model is called to generate a three-dimensional model of the vehicle based on the physical size parameters, thereby obtaining a business three-dimensional model.

[0069] For example, if the service is medical insurance claims, and the second feature information is the hospital where the claims service is located, a generative adversarial network (GAN) can be used to generate multiple hospital images to obtain several initial object images. The hospital's dimensions in each initial object image are determined to obtain physical size parameters. A 3D GAN generative model is then used to generate a 3D model of the hospital based on these physical size parameters, ultimately producing a 3D model of the service.

[0070] After generating a new business 3D model, you can also add a corresponding index to it and store it in the preset model library for the next user to use.

[0071] In one of the embodiments, after determining that multiple business three-dimensional models are obtained, a digital twin model can be constructed using the multiple business three-dimensional models to obtain a business digital model. Finally, the business report is added to the business digital model to obtain a business display model for users to view.

[0072] Since the constructed business digital model can only reflect the objects of the business and the order and sequence of business services, in order to integrate various business reports into the model, as an example, the construction of a business digital model using multiple business three-dimensional models and adding multiple business reports to the business digital model to obtain a business display model may include the following sub-steps: S31 , obtaining a time node of each of the business data, and connecting a plurality of the business three-dimensional models according to a plurality of the time nodes to obtain a business digital model.

[0073] S32: Obtain a captured image of the business digital model when it is displayed on the screen, and determine multiple visual areas from the captured image.

[0074] S33. Determine the spatial coordinates of each visual area in the business digital model, and add each business report to a corresponding position in the business digital model according to the spatial coordinates to obtain a business display model.

[0075] In one embodiment, the time node of each business data may be obtained. Specifically, the time stamp of the business data recorded by the business platform may be obtained to obtain the time node of each business data.

[0076] Then, multiple business three-dimensional models are arranged in the order of multiple time nodes to obtain a business digital model.

[0077] After arranging multiple business three-dimensional models, when displaying the business digital model, the business digital model displayed on the screen is empty. In order to integrate various business reports, the business digital model can be displayed on the screen of the data middle platform for users to view the display effect of the business digital model. At the same time, the image of the business digital model when it is displayed can be captured from the screen to obtain a captured image.

[0078] Next, the visual area of ​​the captured image can be determined. This visual area can be the user's viewpoint when viewing the business digital model on the screen. In specific operations, a camera can be set up on the screen of the data center to capture the user's facial image and identify the viewpoint of the eyes in the facial image to determine the visual area of ​​the user viewing the business digital model.

[0079] The visual area may overlap with the model in the business digital model. Optionally, the visual area may also be an area in the captured image where no model is placed, specifically a blank area in the captured image.

[0080] Next, you can obtain the coordinates of any point in the visual area, convert the coordinates of the point into the coordinates of the corresponding coordinate system of the business digital model, and obtain the spatial coordinates of the business digital model. Finally, you can bind the business report to the spatial coordinates, and add the business report to the business digital model through the model plug-in. After rendering the business report, you can then display the business report on the screen of the data middle platform, and integrate the business report with the business digital model to obtain a business display model.

[0081] S13. Obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, render the business display model using the static feature parameters to obtain a rendering model, and call a preset Voyager model to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0082] After integrating business reports with business digital models, static and dynamic feature parameters can be obtained from real-time demand information. Static feature parameters can include the color and size of model visualization, while dynamic feature parameters can include the angle and trajectory of model interaction.

[0083] Static feature parameters can be used to render various models and reports of the business display model, thus obtaining a rendered model. The starting coordinates and starting angle of the dynamic feature parameters can be used to determine the angle and trajectory of the model display. The preset Voyager model is then called to visualize the rendered model based on the starting coordinates and starting angle of the dynamic feature parameters.

[0084] Through the above-mentioned visualization processing method, not only can the business data that need to be displayed be unified, but also the effect of data display can be increased and meet the actual needs of users.

[0085] According to the foregoing description, the business display model is constructed by arranging the corresponding three-dimensional models according to the order of business services. Although the business display model can display the business relationship of each business, the display effect is relatively simple. In order to construct the entire business scenario and improve the display effect, in an optional embodiment, the rendering of the business display model using the static feature parameters to obtain a rendering model may include the following sub-steps: S41. Extracting background parameters and model parameters from the static feature parameters.

[0086] S42: Search for a background image based on the background parameters, and fuse the background image with the service presentation model to obtain a fusion model.

[0087] S43: Rendering the fusion model based on the model parameters to obtain a rendering model.

[0088] Specifically, background parameters and model parameters can be extracted from static feature parameters. Background parameters can be the background parameters of the business scenario that the user needs to build. For example, the user needs to display keywords in the background. Model parameters can be the color and size of the model display.

[0089] Next, a search for a corresponding background image can be performed based on the keywords in the background parameter. This search may yield multiple background images, which can be displayed to the user, allowing them to select one. Once the user's selected background image is determined, the background image can be fused with the business presentation model to create a fused model.

[0090] Specifically, it can be divided into two layers, a top layer and the other as a background layer. The background image is rendered as the background layer, and then the business display model is rendered on the top layer. Then the two layers are fused to obtain a fused model.

[0091] Finally, the fused model can be rendered based on the color and size of the model parameters to obtain a rendered model.

[0092] When displaying a rendered model, if a single static effect is used, the display effect is not good. In order to further improve the display effect, in one embodiment, calling a preset Voyager model to perform visualization processing on the rendered model based on the starting coordinates and starting angle of the dynamic feature parameters may include the following sub-steps: S51 , determining the starting coordinates and starting angle of the dynamic feature parameters, and constructing a visualization trajectory using the starting coordinates and starting angle.

[0093] S52: Calling a preset Voyager model to perform video diffusion on the rendering model based on the visualization trajectory to obtain a model diffusion image, and visually displaying the model diffusion image.

[0094] In one operation mode, the starting coordinates and starting angles of the dynamic feature parameters can be determined, where the starting coordinates are a coordinate point selected by the user in the rendering model after the rendering model is displayed to the user, such as a coordinate of the upper left corner or the upper right corner.

[0095] The starting angle is the heading angle starting from the starting coordinate.

[0096] A model display trajectory can be determined with the starting coordinate as the starting point and the orientation angle of the starting angle to obtain a visual trajectory.

[0097] Finally, the preset Voyager model can be called to perform video diffusion on the rendered model based on the visualization trajectory to obtain the model diffusion image, and the model diffusion image can be visualized.

[0098] In one operation mode, the rendering model can be visually displayed on the screen, and then a screenshot of the rendering model can be captured and input into a preset Voyager model, so that the preset Voyager model can perform video diffusion based on the screenshot of the rendering model, thereby obtaining a model diffusion image.

[0099] The core architecture of the preset Voyager model is the RGB-D diffusion model, which can simultaneously process color and depth information to generate video frames with 3D structure.

[0100] The Voyager model is also preset with a spatiotemporal attention mechanism. Specifically, 4D convolution can be introduced into the Transformer architecture to model spatiotemporal dependencies.

[0101] At the same time, the preset Voyager model is equipped with a camera trajectory controller, which can convert the path parameters input by the user into latent space control signals for video expansion.

[0102] This video generation framework, based on the Voyager model, can generate long-range video sequences with controllable camera trajectories from a single image while maintaining good spatial consistency and visual realism. Its core feature is a diffusion model that integrates RGB and depth information (RGB-D), ensuring that the generated videos naturally contain depth content suitable for 3D reconstruction.

[0103] In this embodiment, the embodiment of the present application provides a method for visualizing report data, and its beneficial effects are: the present application can obtain multiple business data, use the business data and preset report templates to build corresponding business reports; obtain the user's real-time demand information, build a business digital model based on the user's real-time demand information, and add multiple business reports to the business digital model to obtain a business display model; obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, use the static feature parameters to render the business display model to obtain a rendering model, and call the preset Voyager model to visualize the rendering model based on the dynamic feature parameters. The present application can unify business data of different formats by converting business data into generated reports, thereby avoiding visualization errors caused by inconsistent data and deviations in data visualization. On this basis, building a model based on the user's real-time demand information and controlling the model for visualization can improve the flexibility of visualization, meet the actual needs of users, and improve the display effect.

[0104] The present application also provides a visualization device for report data. Figure 2 , shows a structural diagram of a report data visualization device provided by an embodiment of the present application.

[0105] As an example, the report data visualization device may include: An acquisition module 201 is configured to acquire a plurality of business data and construct a corresponding business report using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; A construction module 202 is configured to obtain real-time demand information of users, determine multiple business three-dimensional models based on the real-time demand information, construct a business digital model using the multiple business three-dimensional models, and add multiple business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model is matched with one business report; The visualization module 203 is used to obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, use the static feature parameters to render the business display model to obtain a rendering model, and call the preset Voyager model to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0106] Optionally, calling a preset Voyager model to perform visualization processing on the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters includes: Determining the starting coordinates and starting angles of the dynamic feature parameters, and constructing a visualization trajectory using the starting coordinates and starting angles; The preset Voyager model is called to perform video diffusion on the rendering model based on the visualization trajectory to obtain a model diffusion image, and the model diffusion image is visually displayed.

[0107] Optionally, determining a plurality of business three-dimensional models based on the real-time demand information includes: Extracting multiple business keywords from the real-time demand information and forming a keyword set; Calculating the cosine similarity between the keyword set and the index combination of each preset model library; Selecting a number of models with values ​​greater than a preset similarity from the plurality of cosine similarities as the models to be determined; First characteristic information of the business report is determined, and one of the models to be determined is determined as a business three-dimensional model based on the first characteristic information, to obtain multiple business three-dimensional models.

[0108] Optionally, the determining a plurality of business three-dimensional models based on the real-time demand information further includes: If each of the cosine similarities is less than a preset similarity, determining the second characteristic information of the business report; Calling a preset generative adversarial network to generate a plurality of initial object images according to the object of the second feature information; The physical size parameters of the object in each of the initial object images are determined, and the business three-dimensional model is constructed using the physical size parameters.

[0109] Optionally, the constructing a business digital model using a plurality of the business three-dimensional models, and adding a plurality of the business reports to the business digital model to obtain a business display model includes: Obtaining a time node of each of the business data, and connecting a plurality of the business three-dimensional models according to a plurality of the time nodes to obtain a business digital model; Obtaining a captured image of the business digital model when displayed on a screen, and determining a plurality of visual areas from the captured image; The spatial coordinates of each visual area in the business digital model are determined, and each business report is added to a corresponding position of the business digital model according to the spatial coordinates to obtain a business display model.

[0110] Optionally, rendering the business presentation model using the static feature parameters to obtain a rendering model includes: extracting background parameters and model parameters from the static feature parameters; Searching for a background image based on the background parameters, fusing the background image with the business presentation model to obtain a fusion model; The fusion model is rendered based on the model parameters to obtain a rendering model.

[0111] The present application also provides a visualization system for report data. Figure 3 , shows a structural diagram of a report data visualization system provided by an embodiment of the present application.

[0112] As an example, the report data visualization system may include: a data center and multiple business platforms, wherein the data center is applicable to the report data visualization method as described in the above embodiment; The data middle platform is connected to multiple business platforms respectively.

[0113] Reference Figure 4 , showing a computer device of a report data visualization method of the present application, which may specifically include the following: The computer device 12 is a general-purpose computing device. The components of the computer device 12 may include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0114] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor, or a local bus 18 that utilizes any of a variety of bus 18 architectures. Examples of such architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0115] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0116] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be configured to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 4 Although not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), as well as an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 18 via one or more data media interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42 configured to perform the functions of various embodiments of the present application.

[0117] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in a memory. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules 42, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0118] The computer device 12 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, a camera, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN)), a wide area network (WAN), and / or a public network (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34.

[0119] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the report data visualization method provided in the embodiment of the present application.

[0120] That is, when the processing unit 16 executes the above program, the following is achieved: Acquire multiple business data, and construct corresponding business reports using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; Acquiring real-time demand information of users, and determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model matches one business report; Static feature parameters and dynamic feature parameters are respectively obtained from the real-time demand information, the business display model is rendered using the static feature parameters to obtain a rendering model, and a preset Voyager model is called to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0121] In an embodiment of the present application, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the report data visualization method provided in all embodiments of the present application.

[0122] That is, when the program is executed by the processor: Acquire multiple business data, and construct corresponding business reports using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; Acquiring real-time demand information of users, and determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model matches one business report; Static feature parameters and dynamic feature parameters are respectively obtained from the real-time demand information, the business display model is rendered using the static feature parameters to obtain a rendering model, and a preset Voyager model is called to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

[0123] Any combination of one or more computer-readable media may be employed. A computer-readable medium may be a computer signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program for use by or in connection with an instruction execution system, apparatus, or device.

[0124] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0125] The computer program code for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced.

[0126] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0127] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0128] The above is a detailed introduction to the report data visualization method, system, device and medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for visualizing report data, characterized in that: The method comprises: Acquire multiple business data, and construct corresponding business reports using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; Acquiring real-time demand information of users, and determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model matches one business report; Static feature parameters and dynamic feature parameters are respectively obtained from the real-time demand information, the business display model is rendered using the static feature parameters to obtain a rendering model, and a preset Voyager model is called to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

2. The method for visualizing report data according to claim 1, characterized in that: The calling of the preset Voyager model to perform visualization processing on the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters includes: Determining the starting coordinates and starting angles of the dynamic feature parameters, and constructing a visualization trajectory using the starting coordinates and starting angles; The preset Voyager model is called to perform video diffusion on the rendering model based on the visualization trajectory to obtain a model diffusion image, and the model diffusion image is visually displayed.

3. The method for visualizing report data according to claim 1, wherein: The determining of a plurality of business three-dimensional models based on the real-time demand information includes: Extracting multiple business keywords from the real-time demand information and forming a keyword set; Calculating the cosine similarity between the keyword set and the index combination of each preset model library; Selecting a number of models with values ​​greater than a preset similarity from the plurality of cosine similarities as the models to be determined; First characteristic information of the business report is determined, and one of the models to be determined is determined as a business three-dimensional model based on the first characteristic information, to obtain multiple business three-dimensional models.

4. The method for visualizing report data according to claim 3, characterized in that: The determining of a plurality of business three-dimensional models based on the real-time demand information further includes: If each of the cosine similarities is less than a preset similarity, determining the second characteristic information of the business report; Calling a preset generative adversarial network to generate a plurality of initial object images according to the object of the second feature information; The physical size parameters of the object in each of the initial object images are determined, and the business three-dimensional model is constructed using the physical size parameters.

5. The method for visualizing report data according to claim 1, characterized in that: The method of constructing a business digital model by using the plurality of the business three-dimensional models and adding the plurality of the business reports to the business digital model to obtain a business display model includes: Obtaining a time node of each of the business data, and connecting a plurality of the business three-dimensional models according to a plurality of the time nodes to obtain a business digital model; Obtaining a captured image of the business digital model when displayed on a screen, and determining a plurality of visual areas from the captured image; The spatial coordinates of each visual area in the business digital model are determined, and each business report is added to a corresponding position of the business digital model according to the spatial coordinates to obtain a business display model.

6. The method for visualizing report data according to any one of claims 1 to 5, characterized in that: The step of rendering the business presentation model using the static feature parameters to obtain a rendering model includes: extracting background parameters and model parameters from the static feature parameters; Searching for a background image based on the background parameters, fusing the background image with the business presentation model to obtain a fusion model; The fusion model is rendered based on the model parameters to obtain a rendering model.

7. A visualization device for report data, characterized in that: The device comprises: An acquisition module, configured to acquire a plurality of business data and construct a corresponding business report using each of the business data and a preset report template, wherein each of the business data is business service data of a different business platform; a construction module for obtaining real-time demand information of users, determining a plurality of business three-dimensional models based on the real-time demand information, constructing a business digital model using the plurality of business three-dimensional models, and adding a plurality of business reports to the business digital model to obtain a business display model, wherein each business three-dimensional model is matched with a business report; A visualization module is used to obtain static feature parameters and dynamic feature parameters from the real-time demand information respectively, use the static feature parameters to render the business display model to obtain a rendering model, and call a preset Voyager model to visualize the rendering model based on the starting coordinates and starting angles of the dynamic feature parameters.

8. A report data visualization system, characterized in that: The system includes: a data middle platform and multiple business platforms, wherein the data middle platform is applicable to the report data visualization method according to any one of claims 1 to 6; The data middle platform is connected to multiple business platforms respectively.

9. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the report data visualization method according to any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to enable a computer to execute the report data visualization method according to any one of claims 1 to 6.

Images