High-definition rendering method and system for liquid circulation processing configuration
By adopting B/S architecture and deep learning models in liquid processing systems, the challenges of existing systems in rendering efficiency, resource consumption, accessibility, scalability and real-time performance are solved, and high-definition rendering effect of efficient, real-time and scalable liquid cycle processing configuration is achieved.
Patent Information
- Application Number
- CN202411836547.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-03-04
AI Technical Summary
Existing liquid processing systems have many challenges in rendering efficiency, resource consumption, accessibility, scalability and real-time, especially in large-scale or complex scenarios, which are difficult to meet the needs of real-time monitoring and rapid decision-making.
Adopting a browser/server (B/S) architecture, data processing and image rendering tasks are transferred to cloud servers, cloud-based high-performance GPUs are used to simulate and render liquid fluid dynamics, and high-definition rendering is achieved in combination with WebGL technology. At the same time, deep learning models are introduced to predict user operations and areas of concern, and the allocation of rendering resources is optimized.
It greatly improves rendering efficiency, reduces dependence on client hardware, improves system accessibility and scalability, achieves higher real-time and lower hardware burden, and can run smoothly on low-performance devices.
Smart Images
Figure CN119559311A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of 3D rendering technology, and more specifically to a high-definition rendering method and system for a liquid circulation processing configuration. Background Art
[0002] With the development of industrial automation and data analysis technology, liquid handling systems are increasingly dependent on efficient monitoring and management technologies. In many fields, such as chemical industry, biotechnology, environmental protection, etc., the dynamic monitoring of liquid handling needs to be not only accurate, but also intuitively presented through visualization. However, existing liquid handling and monitoring systems face multiple technical challenges and limitations.
[0003] Common problems in liquid handling systems include: Low rendering efficiency: Traditional liquid handling systems often rely on heavy client software for calculations in graphics rendering. This approach usually requires powerful local computing resources (such as high-end GPUs and CPUs) to perform fluid dynamics calculations and 3D rendering, especially in large-scale or complex scenes, the computing burden will increase significantly. Due to low rendering efficiency, the system response time is prolonged, and it is impossible to quickly visualize feedback on real-time data, which in turn affects the decision-making speed of operators.
[0004] High resource consumption: Liquid handling systems, especially those that require high-precision real-time rendering, often consume a lot of computing resources. High-end graphics cards, large memory, and high-performance processors are necessary for these systems to operate normally. However, this also greatly increases the deployment and operation costs of the system and limits the scalability of the system. In addition, for resource-constrained environments (such as remote monitoring or low-performance equipment), running such systems will face many difficulties and cannot meet the needs of real-time monitoring.
[0005] Poor accessibility: Many existing liquid handling systems need to run in a specific software environment, often requiring users to install complex software locally and relying on specific operating systems and hardware devices. This approach limits the accessibility of the system, especially in scenarios that require remote operation or multi-location collaboration, where users face inconvenient access. At the same time, when accessed across platforms (such as on different operating systems or mobile devices), the system's portability is poor, limiting its scope of application.
[0006] Scalability issues: As industrial processes become more complex and data volumes increase, liquid handling systems must handle more and more data and computing tasks. Traditional systems often require major adjustments to the underlying architecture during expansion, such as increasing the number of servers, improving hardware specifications, or redesigning the software architecture. This expansion method not only increases the complexity and maintenance costs of the system, but may also lead to a decrease in the stability and reliability of the system during expansion.
[0007] Insufficient real-time performance: In application scenarios that require rapid response, such as environmental monitoring and chemical reaction control, existing liquid handling systems often have difficulty providing sufficient real-time performance. Due to insufficient rendering and calculation speeds, the system cannot display dynamic changes in the liquid handling process in a timely manner, making it difficult for operators to make quick and accurate decisions based on real-time data. This lack of real-time performance is particularly prominent in some high-demand industrial process controls.
[0008] In addition, the current high-definition rendering system of the liquid circulation processing configuration has not introduced artificial intelligence technology and cannot intelligently control and schedule the resources of the cloud server. Summary of the invention
[0009] In this embodiment, a high-definition rendering method, system, electronic device and storage medium of a liquid circulation processing configuration are provided to solve the problems in the related art of low system rendering efficiency and inability to intelligently schedule cloud server performance according to user habits to pre-render liquid and improve system efficiency and fluency.
[0010] In a first aspect, an embodiment of the present invention provides a high-definition rendering system of a liquid circulation processing configuration, wherein the high-definition rendering system of the liquid circulation processing configuration comprises: The high-definition rendering system of the liquid circulation processing configuration includes a client and a cloud server, wherein the client is used to obtain the user's eye movement data and send a request to the cloud server; The cloud server comprises: API Gateway, which is used to obtain eye movement data and requests from clients, distribute the requests and eye movement data to corresponding service modules, and then return the processing results to the client; A fluid dynamics calculation module performs fluid dynamics simulation on the liquid according to the request information to obtain fluid dynamics calculation results; The image rendering module is used to receive the fluid dynamics calculation results, convert them into 3D images according to the fluid dynamics calculation results, and transmit the 3D images back to the client through the API gateway. The client displays the dynamic changes of the liquid in real time in WebGL mode.
[0011] In an optional embodiment, it also includes a data management module, which is used for storing and managing system data, and the system data includes user data, operation records, liquid processing parameters, and rendering data.
[0012] In an optional embodiment, it also includes a resource allocation module, which is configured in the cloud server. The resource allocation module is configured with a pre-trained first prediction model, which is used to predict the user's future operations and schedule the performance of the cloud server according to the prediction results.
[0013] In an optional embodiment, the pre-trained first prediction model construction includes: Acquire historical operation data of the user through the client, wherein the historical operation data includes liquid processing parameter adjustment data, adjustment frequency and sequence; A deep learning model is trained based on historical operation data to obtain a first prediction model; The first prediction model is used to predict the user's future operations and the computing performance allocation of the cloud server is scheduled according to the prediction results.
[0014] In an optional embodiment, the client includes an eye tracking module, and the eye tracking module uses an eye tracking device or a software tool with integrated eye tracking function; The eye tracking module is used to obtain the user's eye movement data, and the eye movement data includes visual focus and dwell time.
[0015] In an optional embodiment, the resource allocation module is further configured with a pre-trained second prediction model, which is used to predict user behavior based on eye movement data obtained by the eye tracking module of the client, so as to pre-render the user focus area based on the predicted user behavior.
[0016] In an optional embodiment, pre-rendering the user focus area according to the predicted user behavior includes: According to the user's visual focus, the liquid area in the user's field of view is rendered first, and the rendering details of the area outside the user's field of view or the background area are reduced.
[0017] Compared with the prior art, the high-definition rendering system of the liquid circulation processing configuration of the present invention has the following beneficial effects: The predictive model can predict future computing needs and the user's focus areas based on the user's operating behavior. For example, if the system predicts that the user is about to adjust the temperature of the liquid, the system can prepare relevant rendering resources or fluid simulation data in advance to reduce computing delays. At the same time, the user's focus area can be obtained based on information such as the user's visual focus to achieve early rendering.
[0018] The client sends HTTP / HTTPS requests to the cloud server, which processes the client's requests to achieve cloud rendering, greatly improving rendering efficiency. This solution uses high-performance cloud GPUs to simulate and render liquid fluid dynamics, and combined with WebGL technology, it can present high-definition rendering effects on the client with lower hardware burden. In addition, by introducing deep learning models, the system can learn fluid behavior patterns from historical data and predict future fluid states, thereby reducing reliance on real-time solutions to complex physical equations and optimizing the allocation of rendering resources.
[0019] In a second aspect, an embodiment of the present invention provides a high-definition rendering method of a liquid circulation treatment configuration, based on the high-definition rendering system of the liquid circulation treatment configuration described in the first aspect, comprising the following steps: The eye tracking module configured on the client side obtains the user's eye movement data and sends the eye movement data and user request to the cloud server through the client side; Receive eye movement data and user requests through the API gateway in the cloud server; Predicting the user's future operations and areas of interest using the first prediction model and the second prediction model configured in the resource allocation module; The fluid dynamics calculation module performs calculations based on the predicted future user operations and areas of interest, and converts the fluid dynamics calculation results into 3D images. The 3D images are transmitted back to the client through the API gateway, and the client displays the dynamic changes of the liquid in real time in WebGL.
[0020] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor, a communication interface, a memory and a bus, wherein the processor, the communication interface and the memory communicate with each other through the bus, and the processor can call logical instructions in the memory to execute the steps of the method provided in the second aspect.
[0021] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the high-definition rendering method of the liquid circulation treatment configuration as described in the second aspect.
[0022] Compared with the prior art, the beneficial effects of the high-definition rendering method, electronic device and storage medium of the liquid circulation treatment configuration of the present invention are the same as those of the high-definition rendering system of the liquid circulation treatment configuration described in the first aspect, so they are not repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 It is a principle block diagram of a high-definition rendering system of a liquid circulation processing configuration in an embodiment of the present invention; Figure 2 It is a flow chart of a high-definition rendering method of a liquid circulation processing configuration in an embodiment of the present invention; Figure 3 1 is a structural block diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0025] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.
[0026] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with general skills in the technical field to which this application belongs. The words "one", "a", "the", "these" and the like in this application do not indicate a quantitative limitation, and they may be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone. Generally, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0027] At present, liquid handling systems still mainly rely on the client-server (C / S) architecture. The client is responsible for handling most of the computing and rendering tasks, while the server is responsible for data transmission and some computing. Although this architecture can meet basic liquid handling needs to a certain extent, it still has a large bottleneck when facing complex fluid dynamics simulations and real-time rendering. With the increasing demand for liquid handling systems in the industrial and scientific research fields, especially the application needs in large-scale and complex scenarios, the traditional C / S architecture has gradually exposed its limitations.
[0028] In recent years, some emerging technologies have brought new opportunities to solve the above problems of liquid handling systems, especially the combination of WebGL and cloud computing. WebGL is a browser-based 3D graphics rendering technology that can fully utilize the graphics processing capabilities of the client GPU and has cross-platform features, allowing users to perform complex 3D rendering through browsers on various devices. At the same time, the development of cloud computing has also provided new solutions for the scalability and resource management of liquid handling systems. By transferring data processing and rendering tasks to the cloud, the system can make full use of the powerful computing power of the cloud server and dynamically adjust resource allocation according to demand, thereby greatly improving the scalability and real-time performance of the system.
[0029] In an embodiment of the present invention, a high-definition rendering system of a liquid circulation processing configuration is provided. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of a predetermined function. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware or a combination of software and hardware is also possible and conceivable.
[0030] like Figure 1 As shown, Figure 1 It is a principle block diagram of a high-definition rendering system of a liquid circulation processing configuration in the present invention, and the high-definition rendering system of the liquid circulation processing configuration includes a client and a cloud server, and the client is used to obtain the user's eye movement data and send a request to the cloud server; It should be noted that this system adopts a browser / server (B / S) architecture, which transfers most of the data processing and image rendering tasks to the cloud server, and the client accesses the system through a standard Web browser. This architecture has the following advantages: Centralized management and processing in the cloud: All data processing, calculation and rendering tasks are completed by the cloud server, and the client is only responsible for receiving the rendering results and displaying them. This method reduces the dependence on client hardware, allowing the system to run smoothly on low-performance devices.
[0031] Cross-platform compatibility: The client accesses the system through a standard Web browser, without the need to install dedicated software, and the operating system and hardware platform are no longer obstacles to operation. Users can access the system using desktops, laptops, tablets, and even smartphones, greatly improving the accessibility of the system.
[0032] Simplified maintenance and upgrades: The B / S architecture allows system maintenance and upgrades to be concentrated on the cloud server. Users do not need to frequently update client software, reducing system maintenance costs.
[0033] Further, the client includes an eye tracking module, and the eye tracking module adopts an eye tracking device or a software tool integrating an eye tracking function; The eye tracking module is used to obtain the user's eye movement data, and the eye movement data includes visual focus and dwell time.
[0034] The eye tracking module is used to track the user's eye movements or predict the gaze. The results are sent to the cloud server, and the cloud server predicts the user's focus area and optimizes the user's focus area in a targeted manner.
[0035] The client sends HTTP / HTTPS requests to the cloud server, which processes the client's requests to achieve cloud rendering, greatly improving rendering efficiency. This solution uses high-performance cloud GPUs to simulate and render liquid fluid dynamics, combined with WebGL technology, to present high-definition rendering effects on the client with a lower hardware burden.
[0036] Furthermore, the cloud server includes: API Gateway, which is used to obtain eye movement data and requests from clients, distribute the requests and eye movement data to corresponding service modules, and then return the processing results to the client; Specifically, the API gateway is responsible for processing HTTP / HTTPS requests from the client, distributing the requests to the corresponding service modules (the service modules include fluid dynamics calculation module, image rendering module, data management module and resource allocation module), and returning the processing results to the client.
[0037] The fluid dynamics calculation module performs fluid dynamics simulation on the liquid according to the request information to obtain the fluid dynamics calculation results; the fluid dynamics calculation module is responsible for the fluid dynamics simulation of the liquid and calculates the velocity field, pressure field and density field of the liquid based on the Navier-Stokes equation.
[0038] The image rendering module is used to receive the fluid dynamics calculation results, convert them into 3D images according to the fluid dynamics calculation results, and transmit the 3D images back to the client through the API gateway. The client displays the dynamic changes of the liquid in real time in WebGL mode. The image rendering module receives the fluid dynamics calculation results and converts them into high-definition 3D images.
[0039] Through the operation of the above modules, the system can collect and input data, and then perform data calculation and processing. By generating rendering data, the cloud server transmits the processed rendering results and liquid status to the client, and the client displays the dynamic changes of the liquid in real time in WebGL mode.
[0040] Furthermore, the system also includes a data management module, which is used for storing and managing system data, and the system data includes user data, operation records, liquid processing parameters, and rendering data.
[0041] Furthermore, it also includes a resource allocation module, which is configured in the cloud server. The resource allocation module is configured with a pre-trained first prediction model, which is used to predict the user's future operations and schedule the performance of the cloud server according to the prediction results.
[0042] In the liquid rendering system, by introducing a deep learning model, the system can learn the behavior patterns of the fluid from historical data and predict the future state of the fluid, thereby reducing the reliance on real-time solutions of complex physical equations and optimizing the allocation of rendering resources.
[0043] Neural network fluid simulation uses deep learning models to replace traditional numerical solution processes to accelerate fluid dynamics simulation. Fluid dynamics simulation usually relies on solving complex partial differential equations (such as the Navier-Stokes equations), and solving these equations requires a lot of computing resources, especially in real-time scenarios. By training neural networks, the system can learn and predict the flow trajectory, velocity field, and pressure field of the fluid, thereby reducing the reliance on real-time solution of the Navier-Stokes equations and greatly improving the calculation speed.
[0044] AI-based rendering optimization uses machine learning technology to optimize the allocation of rendering resources, enabling the system to intelligently predict the user's visual focus, prioritize rendering areas of concern to the user, and simplify unimportant areas. This can significantly reduce the amount of rendering calculations and improve rendering efficiency, especially in complex scenes and high-resolution rendering.
[0045] Specifically, the construction of the pre-trained first prediction model includes: Obtain historical operation data of the user through the client operation, wherein the historical operation data includes liquid processing parameter adjustment data, adjustment frequency and sequence; first, a large amount of fluid dynamics data is obtained to train the neural network model. In addition to the user's historical operation data, these data can also be generated through traditional fluid simulation software, including physical phenomena such as fluid flow, mixing, diffusion under different conditions, and data types include velocity field, pressure field, density field, etc.
[0046] A deep learning model is trained based on historical operation data to obtain a first prediction model; The first prediction model is used to predict the user's future operations and the computing performance allocation of the cloud server is scheduled according to the prediction results.
[0047] Specifically, the deep learning model can use convolutional neural network (CNN) or recurrent neural network (RNN) or long short-term memory network (LSTM). The convolutional neural network (CNN) can capture the spatial characteristics of fluid motion, and the convolution layer can process the local characteristics of the fluid, such as fluctuations, vortices and other dynamic phenomena. Recurrent neural network (RNN) or long short-term memory network (LSTM): RNN or LSTM can capture the time series characteristics of the fluid and is suitable for processing the dynamic behavior of the fluid that changes over time, such as flow rate changes, mixing processes, etc.
[0048] Furthermore, the deep learning model is trained using the collected fluid dynamics data. The training process uses supervised learning methods to adjust the network weights through real data from existing fluid simulations (for example, through traditional Navier-Stokes equations simulations), so that the model can accurately predict future fluid states.
[0049] In actual operation, the trained neural network can receive the current state of the fluid (such as velocity, pressure, etc.) and predict the future state of the fluid. The prediction speed of the first prediction model is significantly higher than that of traditional numerical solution methods, enabling faster fluid simulation while maintaining sufficient accuracy.
[0050] It should be noted that the resource allocation module is also configured with a pre-trained second prediction model, which is used to predict user behavior based on eye movement data obtained by the eye tracking module of the client, so as to pre-render the user focus area according to the predicted user behavior.
[0051] Pre-rendering user focus areas based on predicted user behavior, including: According to the user's visual focus, the liquid area in the user's field of view is rendered first, and the rendering details of the area outside the user's field of view or the background area are reduced.
[0052] The training process of the second prediction model is similar to that of the first prediction model. The difference is that the second prediction model uses pre-collected historical eye movement data as training data, uses the historical eye movement data to train a deep learning model, and uses the trained deep learning model as the second prediction model to predict the user's attention area.
[0053] Specifically, the user's area of interest is obtained through the second prediction model, and according to the user's visual focus, the system will give priority to rendering the liquid area in the user's field of view. The rendering of this area will remain in high definition, including detailed reflection, refraction, lighting, and fluid details. For areas outside the user's field of view or unimportant background areas, the system will reduce the rendering resolution or simplify the rendering process. By reducing the rendering details in these areas, the system is able to save a lot of computing resources. The AI model can predict the user's possible next operation and focus based on the user's interaction history, prepare rendering data for related areas in advance, and further reduce latency. The model will dynamically adjust the allocation of rendering resources based on information such as the user's operation frequency and the time the line of sight stays.
[0054] AI-based rendering optimization uses machine learning technology to optimize the allocation of rendering resources, enabling the system to intelligently predict the user's visual focus, prioritize rendering areas of concern to the user, and simplify unimportant areas. This can significantly reduce the amount of rendering calculations and improve rendering efficiency, especially in complex scenes and high-resolution rendering.
[0055] Exemplarily, the application scenarios of the present invention are as follows: In chemical production, the flow and mixing process of liquids are very important. Through the system of the present invention, users can monitor and analyze the flow of liquids in real time on the cloud server. The system can render the flow of liquids in the pipeline in real time and adjust the flow direction and flow rate of the liquid according to the user's operation. The cloud server is equipped with a high-performance GPU, and the client is an ordinary laptop computer, which is operated using a browser that supports WebGL.
[0056] Specifically, the user accesses the system through a browser, selects the liquid processing pipeline to be monitored, and starts to monitor the liquid flow in real time while obtaining the user's visual focus. After receiving the request, the system performs fluid dynamics calculations and renders the liquid flow image in real time based on the predicted results or visual focus and user habits and cloud server scheduling performance. Users can control the flow rate and direction of the liquid by adjusting parameters through the interface. The system achieves a millisecond-level response, and users can adjust the liquid flow in real time and achieve high-definition rendering with low hardware configuration.
[0057] In addition, in the field of environmental monitoring, the flow of water bodies such as rivers and lakes and the diffusion of pollutants need to be monitored in real time. The system of the present invention can simulate the flow of water bodies and the diffusion of pollutants, and render the results in real time through the cloud.
[0058] The cloud server is equipped with a GPU, and the client is a mobile device (such as a tablet), which is operated using a browser that supports WebGL. Users access the system through mobile devices, select the water area to be monitored, and obtain the user's visual focus. After receiving the request, the system schedules the performance of the cloud server based on the predicted results or visual focus and user habits. After receiving the request, the system performs fluid dynamics calculations and renders the flow of water and the diffusion of pollutants in real time. Users can view the diffusion path and speed of pollutants through the interface.
[0059] The prediction model of the present invention can predict future computing needs and the user's attention area based on the user's operating behavior. For example, if the system predicts that the user is about to adjust the temperature of the liquid, the system can prepare relevant rendering resources or fluid simulation data in advance, thereby reducing computing delays. At the same time, the user's attention area can be obtained based on information such as the user's visual focus to achieve early rendering.
[0060] In an embodiment of the present invention, a high-definition rendering method of a liquid circulation processing configuration is also provided. Figure 2 is a flow chart of a high-definition rendering method of a liquid circulation processing configuration of the present invention, such as Figure 2 As shown, the process includes the following steps: S11, obtaining user eye movement data through an eye movement tracking module configured on the client and sending the eye movement data and user request to the cloud server through the client; S12, receiving eye movement data and user requests through the API gateway in the cloud server; S13, predicting the user's future operations and areas of interest using the first prediction model and the second prediction model configured in the resource allocation module; S14, the fluid dynamics calculation module performs calculations based on the predicted future user operations and focus areas, and converts the fluid dynamics calculation results into 3D images; the 3D images are transmitted back to the client through the API gateway, and the client displays the dynamic changes of the liquid in real time in WebGL mode.
[0061] In this method, the prediction model can predict future computing needs and the user's focus area based on the user's operating behavior. For example, if the system predicts that the user is about to adjust the temperature of the liquid, the system can prepare relevant rendering resources or fluid simulation data in advance to reduce computing delays. At the same time, the user's focus area can be obtained based on information such as the user's visual focus to achieve early rendering.
[0062] The client sends HTTP / HTTPS requests to the cloud server, which processes the client's requests to achieve cloud rendering, greatly improving rendering efficiency. This solution uses high-performance cloud GPUs to simulate and render liquid fluid dynamics, and combined with WebGL technology, it can present high-definition rendering effects on the client with lower hardware burden. In addition, in this method, by introducing deep learning models, the system can learn the behavior patterns of fluids from historical data and predict future fluid states, thereby reducing reliance on real-time solutions to complex physical equations and optimizing the allocation of rendering resources.
[0063] Figure 3 A structural block diagram of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the following method: The eye tracking module configured on the client side obtains the user's eye movement data and sends the eye movement data and user request to the cloud server through the client side; Receive eye movement data and user requests through the API gateway in the cloud server; Predicting the user's future operations and areas of interest using the first prediction model and the second prediction model configured in the resource allocation module; The fluid dynamics calculation module performs calculations based on the predicted future user operations and areas of interest, and converts the fluid dynamics calculation results into 3D images. The 3D images are transmitted back to the client through the API gateway, and the client displays the dynamic changes of the liquid in real time in WebGL.
[0064] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0065] An embodiment of the present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including: The eye tracking module configured on the client side obtains the user's eye movement data and sends the eye movement data and user request to the cloud server through the client side; Receive eye movement data and user requests through the API gateway in the cloud server; Predicting the user's future operations and areas of interest using the first prediction model and the second prediction model configured in the resource allocation module; The fluid dynamics calculation module performs calculations based on the predicted future user operations and areas of interest, and converts the fluid dynamics calculation results into 3D images. The 3D images are transmitted back to the client through the API gateway, and the client displays the dynamic changes of the liquid in real time in WebGL.
[0066] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.
[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A high-definition rendering system for a liquid circulation processing configuration, characterized in that: The high-definition rendering system of the liquid circulation processing configuration includes a client and a cloud server, wherein the client is used to obtain the user's eye movement data and send a request to the cloud server; The cloud server comprises: API Gateway, which is used to obtain eye movement data and requests from clients, distribute the requests and eye movement data to corresponding service modules, and then return the processing results to the client; A fluid dynamics calculation module performs fluid dynamics simulation on the liquid according to the request information to obtain fluid dynamics calculation results; The image rendering module is used to receive the fluid dynamics calculation results, convert them into 3D images according to the fluid dynamics calculation results, and transmit the 3D images back to the client through the API gateway. The client displays the dynamic changes of the liquid in real time in WebGL mode.
2. The high-definition rendering system of the liquid circulation processing configuration according to claim 1 is characterized in that: It also includes a data management module, which is used for storing and managing system data. The system data includes user data, operation records, liquid processing parameters, and rendering data.
3. The high-definition rendering system of the liquid circulation processing configuration according to claim 1 is characterized in that: It also includes a resource allocation module, which is configured in the cloud server. The resource allocation module is configured with a pre-trained first prediction model, which is used to predict the user's future operations and schedule the performance of the cloud server according to the prediction results.
4. The high-definition rendering system of the liquid circulation processing configuration according to claim 3 is characterized in that: The pre-trained first prediction model construction includes: Acquire historical operation data of the user through the client, wherein the historical operation data includes liquid processing parameter adjustment data, adjustment frequency and sequence; A deep learning model is trained based on historical operation data to obtain a first prediction model; The first prediction model is used to predict the user's future operations and the computing performance allocation of the cloud server is scheduled according to the prediction results.
5. The high-definition rendering system of the liquid circulation processing configuration according to claim 3 is characterized in that: The client includes an eye tracking module, and the eye tracking module uses an eye tracking device or a software tool with integrated eye tracking function; The eye tracking module is used to obtain the user's eye movement data, and the eye movement data includes visual focus and dwell time.
6. The high-definition rendering system of the liquid circulation processing configuration according to claim 5, characterized in that: The resource allocation module is also configured with a pre-trained second prediction model, which is used to predict user behavior based on eye movement data obtained by the eye movement tracking module of the client, so as to pre-render the user's attention area based on the predicted user behavior.
7. The high-definition rendering system of the liquid circulation treatment configuration according to claim 6, characterized in that: Pre-rendering user focus areas based on predicted user behavior, including: According to the user's visual focus, the liquid area in the user's field of view is rendered first, and the rendering details of the area outside the user's field of view or the background area are reduced.
8. A high-definition rendering method for a liquid circulation treatment configuration, characterized in that: A high-definition rendering system based on the liquid circulation processing configuration according to any one of claims 1 to 7, comprising: The eye tracking module configured on the client side obtains the user's eye movement data and sends the eye movement data and user request to the cloud server through the client side; Receive eye movement data and user requests through the API gateway in the cloud server; Predicting the user's future operations and areas of interest using the first prediction model and the second prediction model configured in the resource allocation module; The fluid dynamics calculation module performs calculations based on the predicted future user operations and areas of interest, and converts the fluid dynamics calculation results into 3D images. The 3D images are transmitted back to the client through the API gateway, and the client displays the dynamic changes of the liquid in real time in WebGL.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the high-definition rendering method of the liquid circulation processing configuration as claimed in claim 8 is implemented.
10. A non-transitory 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 high-definition rendering method of the liquid circulation treatment configuration as claimed in claim 8 are implemented.