CN115373761A - AI-based dynamic loading method for scene resources in real-time cloud rendering - Google Patents
AI-based dynamic loading method for scene resources in real-time cloud rendering Download PDFInfo
- Publication number
- CN115373761A CN115373761A CN202211146246.0A CN202211146246A CN115373761A CN 115373761 A CN115373761 A CN 115373761A CN 202211146246 A CN202211146246 A CN 202211146246A CN 115373761 A CN115373761 A CN 115373761A
- Authority
- CN
- China
- Prior art keywords
- resources
- scene
- cloud rendering
- data
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44521—Dynamic linking or loading; Link editing at or after load time, e.g. Java class loading
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method for dynamically loading scene resources in real-time cloud rendering based on AI, which relates to the technical field of cloud rendering and comprises the following steps: s1, constructing an open cloud rendering knowledge system, generating different scenes, iteratively generating field knowledge and application rules, and generating corresponding scene resources, wherein the method has the beneficial effects that: the invention provides a method for dynamically loading scene resources in real-time cloud rendering based on AI (artificial intelligence) by establishing an open cloud rendering knowledge system by using a body and iteratively generating field knowledge and application rules, on the basis that the scene is taken as a key point, on the aspect of continuous learning of the field knowledge, a composite apprentice model is adopted, on the aspect of accurately mastering the actual situation of the scene, improved grayish optimization is adopted, on the aspect of dynamically and efficiently putting the scene resources, a dynamic weighting service level decision is adopted, so that the method for dynamically loading the scene resources in real-time cloud rendering based on AI is provided, the rendered scene can be automatically identified, the scene resources are dynamically loaded, the rendering is accelerated, the memory pressure is reduced, and the intelligent management is realized.
Description
Technical Field
The invention relates to the technical field of cloud rendering, in particular to a scene resource dynamic loading method in real-time cloud rendering based on AI.
Background
In the cloud era of everything, internet Service Providers (ISPs) and Cloud Service Providers (CSPs) tend to merge, and with the continuous and deep application of cloud network convergence, multi-cloud interconnection becomes a main development trend. Under a cloudy environment, the integrated service of various Cloud Service Providers (CSPs) can realize dynamic adjustment of service resources, reasonable distribution of computing resources and customized service intercommunication, has the characteristics of dynamic property and elasticity, and brings flexible, automatic and intelligent cloudy service to users.
The real-time cloud rendering is a real-time cloud service based on cloud computing. Under a multi-cloud environment, application scenes of users in different industries are different, and rendering requirements are also different, so that in real-time cloud rendering, a system platform can meet the complex rendering requirements of cross-industry users by loading different scene resources. However, scene resources are various and occupy a certain storage space, and if loading is performed at one time, a series of problems such as large system cache, slow rendering speed and the like are caused.
Therefore, a scene resource dynamic loading method in real-time cloud rendering based on AI is provided.
Disclosure of Invention
The invention aims to provide a scene resource dynamic loading method in real-time cloud rendering based on AI (artificial intelligence) so as to solve a series of problems that various scene resources are provided, a certain storage space is required to be occupied, and if the scene resources are loaded at one time, a system cache is large, the rendering speed is low and the like.
In order to achieve the purpose, the invention provides the following technical scheme: a scene resource dynamic loading method in real-time cloud rendering based on AI comprises the following steps:
s1, constructing an open cloud rendering knowledge system, generating different scenes, iteratively generating domain knowledge and application rules, and generating corresponding scene resources;
s2, adopting a composite apprentice model mode, and according to the maturity characteristics of the scene resources, combining inheritance of the existing scene resources to carry out innovation so as to ensure continuous learning through domain knowledge;
s3, adopting an improved wolf optimization algorithm to enhance the loading performance of resources in batches on the premise of accurately mastering the actual situation of a scene;
and S4, processing dynamic high-efficiency release scene resources by adopting a dynamic weighting service level decision mode, and performing real-time rendering dynamic loading.
Preferably, the scenes in step S1 are classified into movie and television animations, game development, industrial design, and architectural design scenes according to industry types, and there are corresponding different places and similar places for domain knowledge according to different scene resources and industries.
Preferably, the scene resources in step S1 include a core ontology, a high-level ontology, and a domain ontology;
the core body of the scene resource comprises a movie scene resource, a game scene resource and a building design scene resource;
the high-level body of the scene resources comprises model library resources, material library resources and database resources;
the field ontology of the scene resources comprises a scene model and a three-dimensional model; lighting, graphics, camera resources; version data and behavior log resources.
Preferably, the composite apprenticeship model in step S2 includes the following contents:
the multivariate learning mode comprises diversification of the business main body, namely source data and knowledge data of other fields;
the multi-direction learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning;
and (4) a multi-level learning mode comprising an important, skilled and understood form of the business teaching degree.
Preferably, the improved grayish wolf optimization algorithm in the step S3 includes the following steps:
layering optimization, namely layering the processed cloud resources according to the rendering service requirements to form a layered network and realize distribution operation;
and (4) grading optimization, namely classifying and grading the scene resources according to complexity and customer requirements, and taking the service orientation as a key point, so that the loading performance of the batch resources is enhanced, and the utilization rate of the resources is improved.
Preferably, the dynamic weighting service level decision manner in step S4 includes the following specific contents:
the dynamic processing is carried out, the types and the quantity of resources required by the execution of tasks are accurately predicted according to the actual user requirements, the resource utilization rate can be improved, and the cost is reduced;
and performing differentiation processing, namely selecting a resource allocation mode according to the service weight, wherein the resource allocation mode comprises static, dynamic, static/dynamic mixing and user self-service, and monitoring the service quality parameters.
Preferably, the monitoring service quality parameters include availability, reliability, response time, throughput and security performance.
Preferably, the model library resource comprises a three-dimensional model, a scene model and a task model;
the material library resources comprise agent data, camera data, geometric data, graphic data and light data;
the database resources include version data, behavior logs, and user data.
Preferably, the hierarchical network comprises a central controller, a gateway and heterogeneous devices;
the central controller is used for controlling route allocation and resource selection of the grey wolf optimization algorithm;
the gateway is used for receiving data sent by the cluster nodes and the receiving point nodes;
the heterogeneous device is used for receiving a plurality of server resources, processing the sudden flow change condition in the server resources and sending standby data to the central controller.
Preferably, the open cloud rendering knowledge system in the step S1 is based on the inside of a cloud rendering platform, a control terminal is installed outside the cloud rendering platform, and the cloud rendering platform is in communication connection with the control terminal.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for dynamically loading scene resources in real-time cloud rendering based on AI (artificial intelligence) by establishing an open cloud rendering knowledge system by using a body and iteratively generating field knowledge and application rules, on the basis that the scene is taken as a key point, on the aspect of continuous learning of the field knowledge, a composite apprentice model is adopted, on the aspect of accurately mastering the actual situation of the scene, improved grayish optimization is adopted, on the aspect of dynamically and efficiently putting the scene resources, a dynamic weighting service level decision is adopted, so that the method for dynamically loading the scene resources in real-time cloud rendering based on AI is provided, the rendered scene can be automatically identified, the scene resources are dynamically loaded, the rendering is accelerated, the memory pressure is reduced, and the intelligent management is realized.
Drawings
Fig. 1 is a schematic overall step flow diagram of a method for dynamically loading scene resources in AI-based real-time cloud rendering according to an embodiment of the present invention;
fig. 2 is a high-level ontology topology diagram of scene resources of the method for dynamically loading scene resources in AI-based real-time cloud rendering according to the embodiment of the present invention;
fig. 3 is a hierarchical network topology diagram of a scene resource dynamic loading method in AI-based real-time cloud rendering according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, fig. 2 and fig. 3, the present invention provides a technical solution:
a scene resource dynamic loading method in real-time cloud rendering based on AI comprises the following steps:
s1, constructing an open cloud rendering knowledge system, generating different scenes, iteratively generating domain knowledge and application rules, and generating corresponding scene resources; the scenes in the step S1 are divided into scenes of movie and television animation, game development, industrial design and building design according to industry types, and corresponding different places and similar places exist in domain knowledge according to different scene resources and industries; the scene resources in the step S1 comprise a core body, a high-level body and a field body; the scene resource core body comprises a film scene resource, a game scene resource and a building design scene resource; the high-level body of the scene resources comprises model library resources, material library resources and database resources; the field ontology of the scene resources comprises a scene model and a three-dimensional model; lighting, graphics, camera resources; version data and behavior log resources; the model library resources comprise a three-dimensional model, a scene model and a task model; the material library resources comprise agent data, camera data, geometric data, graphic data and light data; the database resources comprise version data, behavior logs and user data;
s2, adopting a composite apprentice model mode, and according to the maturity characteristics of the scene resources, combining inheritance of the existing scene resources to carry out innovation so as to ensure continuous learning through domain knowledge; the composite apprenticeship model in the step S2 includes the following contents: the multivariate learning mode comprises diversification of the business main body, namely source data and knowledge data of other fields; the multi-direction learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning; a multi-level learning mode comprising an important, skilled and understood mode of the business teaching degree;
s3, adopting an improved wolf optimization algorithm to enhance the loading performance of resources in batches on the premise of accurately mastering the actual situation of a scene; the improved grey wolf optimization algorithm in the step S3 comprises the following steps: layering optimization, namely layering the processed cloud resources according to the rendering service requirements to form a layered network and realize distribution operation; grading optimization, namely classifying and grading scene resources according to complexity and customer requirements, and taking service orientation as a key point to enhance the loading performance of batch resources and improve the utilization rate of the resources; the hierarchical network comprises a central controller, a gateway and heterogeneous equipment; the central controller is used for controlling the route allocation and the resource selection of the gray wolf optimization algorithm; the gateway is used for receiving data sent by the cluster nodes and the receiving point nodes; the heterogeneous equipment is used for receiving a plurality of server resources, processing the sudden flow change condition in the server resources and sending standby data to the central controller;
s4, processing the dynamically and efficiently delivered scene resources by adopting a dynamic weighting service level decision mode, and performing real-time rendering dynamic loading, wherein the dynamic weighting service level decision mode in the step S4 comprises the following specific contents: the dynamic processing is carried out, the types and the quantity of resources required by the execution of tasks are accurately predicted according to the actual user requirements, the resource utilization rate can be improved, and the cost is reduced; and performing differentiated processing, namely selecting a resource allocation mode according to the service weight, wherein the resource allocation mode comprises static, dynamic, static/dynamic mixing and user self-service, and monitoring service quality parameters, and the monitoring service quality parameters comprise availability, reliability, response time, throughput and safety performance.
Further, the open cloud rendering knowledge system in the step S1 is based on the inside of a cloud rendering platform, a control terminal is installed outside the cloud rendering platform, and the cloud rendering platform is in communication connection with the control terminal.
Example 1
When the method for dynamically loading scene resources in real-time cloud rendering based on AI is applied to the field of game development:
s1, constructing an open cloud game development rendering knowledge system, generating a game development design scene, iteratively generating field knowledge and application rules, and generating corresponding scene resources; the game development scene resources comprise game scene resources, building design scene resources, model library resources, material library resources, database resources, scene models and three-dimensional models;
s2, adopting a composite apprentice model mode, and according to the maturity characteristics of game development and design scene resources, innovating by combining inheritance of the existing scene resources to ensure continuous learning through domain knowledge; the multi-element learning mode comprises diversification of the main business body, namely game development and design scene resource data and knowledge data of other fields; the multi-directional learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning; a multi-level learning mode comprising an important, skilled and understood mode of the business teaching degree;
s3, adopting an improved wolf optimization algorithm to enhance the loading performance of resources in batches on the premise of accurately mastering the actual situation of a game development design scene; layering optimization, namely layering the processed data according to the rendering service requirement to form a layered network and realize distribution operation; grading optimization, namely classifying and grading the cloud resource scene resources according to complexity and customer requirements, and taking service orientation as a key point to enhance the loading performance of the resources in batches and improve the utilization rate of the resources;
s4, a dynamic weighting service level decision-making mode is adopted to process dynamic and high-efficiency release of scene resources, dynamic processing is carried out, the types and the number of resources required by executing game development and design tasks are accurately predicted according to the requirements of game development workers, the resource utilization rate can be improved, and the cost is reduced; and performing differentiation processing, namely selecting a resource allocation mode according to the service weight, wherein the resource allocation mode comprises static, dynamic, static/dynamic mixing and user self-service, monitoring service quality parameters, and performing game development data and scene real-time rendering dynamic loading.
Example 2
When the method for dynamically loading scene resources in real-time cloud rendering based on AI is applied to the field of movie and animation:
s1, constructing an open cloud movie and television cartoon rendering knowledge system, generating movie and television cartoon scenes, iteratively generating domain knowledge and application rules, and generating corresponding scene resources; the movie and animation scene resources comprise building design scenes, movie and animation scene resources, game scene resources, building design scene resources, model library resources, material library resources, database resources, scene models and three-dimensional models;
s2, adopting a composite apprentice model mode, and according to the maturity characteristics of movie and television cartoon scene resources, innovating by combining inheritance of the existing scene resources, and ensuring continuous learning through domain knowledge; the multi-element learning mode comprises diversification of the main business body, namely movie and animation source data and knowledge data of other fields; the multi-direction learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning; a multi-level learning mode comprising an important, skilled and understood mode of the business teaching degree;
s3, adopting an improved grey wolf optimization algorithm to enhance the loading performance of resources in batches on the premise of accurately mastering the actual situation of the movie and television cartoon scene; layering optimization, namely layering the processed cloud resources according to the rendering service requirements to form a layered network and realize distribution operation; grading optimization, namely classifying and grading the scene resources according to complexity and customer requirements, and taking service orientation as a key point to enhance the loading performance of the batch resources and improve the utilization rate of the resources;
s4, a dynamic weighting service level decision-making mode is adopted, dynamic and efficient scene resource releasing is processed, dynamic processing is carried out, the type and the number of resources required for executing the animation development task are accurately predicted according to the requirements of animation development workers, the resource utilization rate can be improved, and the cost is reduced; and performing differentiation processing, namely selecting a resource allocation mode according to the service weight, wherein the resource allocation mode comprises static, dynamic, static/dynamic mixing and user self-service, monitoring service quality parameters, the monitoring service quality parameters comprise availability, reliability, response time, throughput and safety performance, and performing animation development data and scene real-time rendering dynamic loading.
The working principle of the invention is as follows: when the method is used, an open cloud rendering knowledge system is constructed, different scenes are generated, domain knowledge and application rules are generated in an iterative mode, and corresponding scene resources are generated; the scenes in the step S1 are divided into scenes of movie and television animation, game development, industrial design and building design according to industry types, and corresponding different places and similar places exist in domain knowledge according to different scene resources and industries; the scene resources in the step S1 comprise a core body, a high-level body and a field body; the core body of the scene resource comprises a movie scene resource, a game scene resource and a building design scene resource; the high-level body of the scene resources comprises model library resources, material library resources and database resources; the field ontology of the scene resources comprises a scene model and a three-dimensional model; lighting, graphics, camera resources; version data and behavior log resources; the model library resources comprise a three-dimensional model, a scene model and a task model; the material library resources comprise agent data, camera data, geometric data, graphic data and light data; the database resources comprise version data, behavior logs and user data; a composite apprentice model mode is adopted, innovation is carried out according to the maturity characteristics of scene resources and the inheritance of the existing scene resources, and continuous learning through domain knowledge is ensured; the composite apprenticeship model in the step S2 includes the following contents: the multivariate learning mode comprises diversification of the business main body, namely source data and knowledge data of other fields; the multi-direction learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning; a multi-level learning mode comprising an important, skilled and understood mode of the business teaching degree; the loading performance of resources is enhanced in batch on the premise of accurately grasping the actual situation of a scene by adopting an improved wolf optimization algorithm; the improved grey wolf optimization algorithm in the step S3 comprises the following steps: layering optimization, namely layering the processed cloud resources according to the requirements of rendering services to form a layering network and realize distribution operation; grading optimization, namely classifying and grading the scene resources according to complexity and customer requirements, and taking service orientation as a key point to enhance the loading performance of the batch resources and improve the utilization rate of the resources; the hierarchical network comprises a central controller, a gateway and heterogeneous equipment; the central controller is used for controlling the route allocation and the resource selection of the gray wolf optimization algorithm; the gateway is used for receiving data sent by the cluster nodes and the receiving point nodes; the heterogeneous equipment is used for receiving a plurality of server resources, processing the sudden flow change condition in the server resources and sending standby data to the central controller; and processing the dynamically and efficiently delivered scene resources by adopting a dynamic weighting service level decision mode, and performing real-time rendering dynamic loading, wherein the dynamic weighting service level decision mode in the step S4 comprises the following specific contents: dynamic processing, namely accurately predicting the type and the quantity of resources required by executing a task according to the actual user requirements, so that the resource utilization rate can be improved, and the cost is reduced; the method comprises the steps of carrying out differentiation processing, selecting a resource allocation mode according to service weight, and carrying out monitoring service quality parameters including static, dynamic, static/dynamic mixing and user self-service, wherein the monitoring service quality parameters include availability, reliability, response time, throughput and safety performance.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A scene resource dynamic loading method in real-time cloud rendering based on AI is characterized by comprising the following steps:
s1, constructing an open cloud rendering knowledge system, generating different scenes, iteratively generating domain knowledge and application rules, and generating corresponding scene resources;
s2, adopting a composite apprentice model mode, and according to the maturity characteristics of the scene resources, combining inheritance of the existing scene resources to carry out innovation so as to ensure continuous learning through domain knowledge;
s3, adopting an improved wolf optimization algorithm to enhance the loading performance of resources in batches on the premise of accurately mastering the actual situation of a scene;
and S4, processing dynamic high-efficiency release scene resources by adopting a dynamic weighting service level decision mode, and performing real-time rendering dynamic loading.
2. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 1, wherein: the scenes in the step S1 are divided into scenes of movie and television animation, game development, industrial design and building design according to industry types, and corresponding different places and similar places exist in domain knowledge according to different scene resources and industries.
3. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 1, wherein: the scene resources in the step S1 comprise a core body, a high-level body and a field body;
the scene resource core body comprises a film scene resource, a game scene resource and a building design scene resource;
the high-level body of the scene resources comprises model library resources, material library resources and database resources;
the field ontology of the scene resources comprises a scene model and a three-dimensional model; lighting, graphics, camera resources; version data and behavior log resources.
4. The method for dynamically loading scene resources in AI-based real-time cloud rendering as recited in claim 1, wherein: the composite apprenticeship model in the step S2 includes the following contents:
the multivariate learning mode comprises diversification of the business main body, namely source data and knowledge data of other fields;
the multi-direction learning mode comprises unidirectional, bidirectional and multidirectional business direction, namely inheriting learning and innovative learning, and business objects can also realize turnover type bidirectional learning;
and (4) a multi-level learning mode comprising an important, skilled and understood form of the business teaching degree.
5. The method for dynamically loading scene resources in AI-based real-time cloud rendering as recited in claim 1, wherein: the improved gray wolf optimization algorithm in the step S3 comprises the following steps:
layering optimization, namely layering the processed cloud resources according to the requirements of rendering services to form a layering network and realize distribution operation;
and (4) grading optimization, namely classifying and grading the scene resources according to complexity and customer requirements, and taking the service orientation as a key point, so that the loading performance of the batch resources is enhanced, and the utilization rate of the resources is improved.
6. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 1, wherein: the dynamic weighting service level decision-making mode in the step S4 includes the following specific contents:
the dynamic processing is carried out, the types and the quantity of resources required by the execution of tasks are accurately predicted according to the actual user requirements, the resource utilization rate can be improved, and the cost is reduced;
and performing differentiation processing, namely selecting a resource allocation mode according to the service weight, wherein the resource allocation mode comprises static, dynamic, static/dynamic mixing and user self-service, and monitoring the service quality parameters.
7. The method for dynamically loading scene resources in AI-based real-time cloud rendering as recited in claim 6, wherein: the monitoring service quality parameters comprise availability, reliability, response time, throughput and safety performance.
8. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 3, wherein:
the model library resources comprise a three-dimensional model, a scene model and a task model;
the material library resources comprise agent data, camera data, geometric data, graphic data and light data;
the database resources include version data, behavior logs, and user data.
9. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 5, wherein: the hierarchical network comprises a central controller, a gateway and heterogeneous equipment;
the central controller is used for controlling the route allocation and the resource selection of the gray wolf optimization algorithm;
the gateway is used for receiving data sent by the cluster nodes and the receiving point nodes;
the heterogeneous device is used for receiving a plurality of server resources, processing sudden flow change conditions in the server resources and sending standby data to the central controller.
10. The method for dynamically loading scene resources in AI-based real-time cloud rendering according to claim 1, wherein: the open cloud rendering knowledge system in the step S1 is based on the interior of a cloud rendering platform, a control terminal is installed outside the cloud rendering platform, and the cloud rendering platform is in communication connection with the control terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146246.0A CN115373761A (en) | 2022-09-20 | 2022-09-20 | AI-based dynamic loading method for scene resources in real-time cloud rendering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211146246.0A CN115373761A (en) | 2022-09-20 | 2022-09-20 | AI-based dynamic loading method for scene resources in real-time cloud rendering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115373761A true CN115373761A (en) | 2022-11-22 |
Family
ID=84071037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211146246.0A Pending CN115373761A (en) | 2022-09-20 | 2022-09-20 | AI-based dynamic loading method for scene resources in real-time cloud rendering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115373761A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117331622A (en) * | 2023-10-16 | 2024-01-02 | 中教畅享(北京)科技有限公司 | Webpage version museum scene loading method based on AssetBundle |
-
2022
- 2022-09-20 CN CN202211146246.0A patent/CN115373761A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117331622A (en) * | 2023-10-16 | 2024-01-02 | 中教畅享(北京)科技有限公司 | Webpage version museum scene loading method based on AssetBundle |
| CN117331622B (en) * | 2023-10-16 | 2024-05-17 | 中教畅享科技股份有限公司 | AssetBundle-based webpage version museum scene loading method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Etemadi et al. | Resource provisioning for IoT services in the fog computing environment: An autonomic approach | |
| Asim et al. | A review on computational intelligence techniques in cloud and edge computing | |
| Sittón-Candanedo et al. | Edge computing architectures in industry 4.0: A general survey and comparison | |
| Walia et al. | AI-empowered fog/edge resource management for IoT applications: A comprehensive review, research challenges and future perspectives | |
| US11172035B2 (en) | Data management for edge computing environment | |
| Boudi et al. | AI-based resource management in beyond 5G cloud native environment | |
| CN112581578A (en) | Cloud rendering system based on software definition | |
| Ferrer et al. | Private local automation clouds built by CPS: Potential and challenges for distributed reasoning | |
| Senjab et al. | A survey of Kubernetes scheduling algorithms | |
| Kondratenko et al. | Multi-criteria decision making and soft computing for the selection of specialized IoT platform | |
| CN115373761A (en) | AI-based dynamic loading method for scene resources in real-time cloud rendering | |
| WO2022225565A1 (en) | Performance testing of a test application in a network-as-a-service environment | |
| CN110705891A (en) | Data processing method based on high-allocable changeability | |
| Gupta et al. | Toward intelligent resource management in dynamic Fog Computing‐based Internet of Things environment with Deep Reinforcement Learning: A survey | |
| US11829799B2 (en) | Distributed resource-aware training of machine learning pipelines | |
| Lefrançois et al. | An object-oriented knowledge representation for intelligent control of manufacturing workstations | |
| da Silva et al. | Online machine learning for auto-scaling in the edge computing | |
| Khanh et al. | Fuzzy‐Based Mobile Edge Orchestrators in Heterogeneous IoT Environments: An Online Workload Balancing Approach | |
| CN116996941A (en) | Calculation force unloading method, device and system based on cooperation of cloud edge ends of distribution network | |
| Gowri et al. | An agent based resource provision for iot through machine learning in fog computing | |
| Rashidifar et al. | Reinforcement learning-based model for optimization of cloud manufacturing-based multi objective resource scheduling: a review | |
| Arif et al. | A model-driven framework for optimum application placement in fog computing using a machine learning based approach | |
| Stepanova et al. | Universal Multi-platform Interaction Approach for Distributed Internet of Things | |
| Oikonomou et al. | On the use of intelligent models towards meeting the challenges of the edge mesh | |
| Gao | [Retracted] The Human‐in‐the‐Loop Data Sensing Architecture Based on Edge Cloud Computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |