WO2022213538A1

WO2022213538A1 - Method and apparatus for establishing simulation test platform, and electronic device

Info

Publication number: WO2022213538A1
Application number: PCT/CN2021/116634
Authority: WO
Inventors: 曾捷; 粟欣; 李红鑫; 骆杰; 韩莹; 周世东; 赵明; 钟晓峰; 许希斌
Original assignee: 清华大学
Priority date: 2021-03-30
Filing date: 2021-09-06
Publication date: 2022-10-13
Also published as: CN113515837A

Abstract

Disclosed in the present application are a method and apparatus for establishing a simulation test platform, and an electronic device. The method comprises: constructing a three-dimensional model of a terminal device on the basis of a geometric structure and a shape parameter of the terminal device in a physical entity world, and constructing a three-dimensional model of an edge server on the basis of a geometric structure and a shape parameter of the edge server in the physical entity world; generating a digital twin model of the terminal device on the basis of application usage data of the terminal device and the three-dimensional model of the terminal device, and generating a digital twin model of the edge server on the basis of capability feature data of the edge server and the three-dimensional model of the edge server; and establishing a simulation test platform on the basis of the digital twin model of the terminal device and the digital twin model of the edge server.

Description

Method, device and electronic device for establishing simulation test platform

cross reference

The present invention requires the priority of the Chinese patent application with the application number of 202110369351.X and the title of the invention "Method, Apparatus and Electronic Equipment for Establishing a Simulation Test Platform" submitted to the Chinese Patent Office on April 6, 2021. The contents are incorporated herein by reference.

technical field

The present application belongs to the technical field of wireless communication, and in particular relates to a method, apparatus and electronic device for establishing a simulation platform.

Background technique

With the high deployment of IoT devices and terminal devices, network communication technologies are serving a large number of terminal devices with different functions. In order to provide better services to terminal devices, a simulation test platform is usually established to simulate and test intelligent algorithms deployed at the edge of the network.

The existing communication software simulation test platform mainly simulates the network environment by constructing mathematical models and fitting communication characteristics. On the one hand, the existing communication software simulation test platform lacks interaction with the real world, and the simulated network environment is also different from the real world network environment; The terminal equipment is simulated. To sum up, the simulation test effect of the existing communication software simulation test platform is poor, and the universality is poor.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a method, device and electronic device for establishing a simulation platform, which can solve the problems of poor simulation test effect and poor universality of the existing communication software simulation test platform.

In order to solve the above technical problems, this application is implemented as follows:

In a first aspect, an embodiment of the present application provides a method for establishing a simulation test platform, the method comprising: constructing a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and, based on the The geometric structure and shape parameters of the edge server in the physical entity world construct a three-dimensional model of the edge server; based on the application usage data of the terminal device and the three-dimensional model of the terminal device, a digital twin model of the terminal device is generated, wherein all the The application usage data is obtained by monitoring the terminal device; and, based on the capability feature data of the edge server and the three-dimensional model of the edge server, an edge server digital twin model is generated, wherein the capability feature data is obtained by monitoring the data. The edge server is obtained; based on the terminal device digital twin model and the edge server digital twin model, a simulation test platform is established.

In a second aspect, an embodiment of the present application provides a device for establishing a simulation test platform, the device comprising: a three-dimensional model building module for constructing a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world model; and, constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world; a digital twin model generation module for the terminal device based on application usage data and the terminal A three-dimensional model of the device to generate a digital twin model of a terminal device, wherein the application usage data is obtained by monitoring the terminal device; and, based on the capability feature data of the edge server and the three-dimensional model of the edge server, generate an edge A server digital twin model, wherein the capability feature data is obtained by monitoring the edge server; a simulation test platform establishment module is used to establish a simulation test platform based on the terminal device digital twin model and the edge server digital twin model.

In a third aspect, an electronic device is proposed, the electronic device comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations: based on constructing a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world; based on the The application usage data of the terminal device and the three-dimensional model of the terminal device are used to generate a digital twin model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; and, based on the capability feature data of the edge server and the three-dimensional model of the edge server to generate a digital twin model of the edge server, wherein the capability characteristic data is obtained by monitoring the edge server; based on the digital twin model of the terminal device and the digital twin model of the edge server, establish a simulation testing platform.

In a fourth aspect, a computer-readable storage medium is proposed, the computer-readable storage medium stores one or more programs, the one or more programs, when executed by an electronic device including a plurality of application programs, cause all The electronic device performs the following operations: constructing a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and constructing the edge based on the geometric structure and shape parameters of the edge server in the physical entity world A three-dimensional model of a server; based on the application usage data of the terminal device and the three-dimensional model of the terminal device, a digital twin model of a terminal device is generated, wherein the application usage data is obtained by monitoring the terminal device; and, based on The capability feature data of the edge server and the three-dimensional model of the edge server generate an edge server digital twin model, wherein the capability feature data is obtained by monitoring the edge server; based on the terminal device digital twin model and the edge server The edge server digital twin model is established to establish a simulation test platform.

By using the method for establishing a simulation test platform provided by the embodiments of this specification, a three-dimensional model of the terminal device can be constructed based on the geometric structure and shape parameters of the terminal device in the physical entity world; and, based on the geometric structure and shape parameters of the edge server in the physical entity world. constructing a three-dimensional model of the edge server; and then generating a digital twin model of the terminal device based on the application usage data of the terminal device and the three-dimensional model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; and, based on the edge The capability feature data of the server and the 3D model of the edge server are used to generate a digital twin model of the edge server, wherein the capability feature data is obtained by monitoring the edge server; finally, a simulation test is established based on the digital twin model of the terminal device and the digital twin model of the edge server. platform. The characteristics of the digital twin technology can be used, that is, the data of the physical entity world can be acquired in real time and the reference for the update of the physical entity world can be provided, so that the simulation test platform provided in this manual is closer to the physical entity world, and the simulation test effect is improved.

Description of drawings

1 is a schematic flow diagram of the realization of a method for establishing a simulation test platform provided by an embodiment of the present application;

2 is a schematic diagram of the architecture of the digital twin world and the physical entity world in the method for establishing a simulation test platform provided by an embodiment of the present application;

3 is a schematic flow chart of a practical application of a method for establishing a simulation test platform provided by an embodiment of the present application;

4 is a schematic structural diagram of a device for establishing a simulation test platform provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

The terms "first", "second" and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that embodiments of the application can be practiced in sequences other than those illustrated or described herein. In addition, "and/or" in the description and claims indicates at least one of the connected objects, and the character "/" generally indicates that the associated objects are in an "or" relationship.

It should be noted that, in the method for establishing a simulation test platform provided by the embodiment of the present application, the execution body may be a device for establishing a simulation test platform, or a device for executing a method for loading a simulation test platform in the device for establishing a simulation test platform. control module. In the embodiment of the present application, the device for establishing a simulation test platform provided by the embodiment of the present application is described by taking the method for establishing a simulation test platform to perform loading of the simulation test platform as an example.

The method for establishing the simulation test platform provided by the embodiments of the present specification will be described in detail below through specific embodiments and application scenarios with reference to the accompanying drawings.

Step 110 , construct a 3D model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and construct a 3D model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world.

Among them, the established 3D model can also include outdoor physical entities such as cars, lanes, buildings, trees, etc., indoor physical entities such as walls, columns, doors and windows, roofs, stairs, tables and chairs, base stations, servers, sensors, etc. communication equipment, and people.

Step 120, based on the application usage data of the terminal device and the three-dimensional model of the terminal device, generate a digital twin model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; The 3D model generates a digital twin model of the edge server, wherein the capability characteristic data is obtained by monitoring the edge server.

Among them, the digital twin model is a digital model based on the physical entity object in the physical entity world, through real-time testing, simulation and data analysis to perceive, diagnose and predict the state of the physical entity object in real time. When the algorithms in the digital twin are better than those in the physical world, the algorithms in the digital twin can be applied to the physical world to optimize the federated learning model in the physical world. A digital twin has the following characteristics.

Dynamic: The digital virtual body constructed in digital space is very similar to the physical entity in physical space, but it is not only a mirror image of the physical entity world, but also receives real-time information from the physical entity world, and in turn drives the physical entity world in real time, that is, Saying that the digital twin is dynamic.

Bidirectionality: The flow of data between the ontology in the physical world and the twin in the digital twin is bidirectional. The ontology in the physical entity world can output data to the twin in the digital twin model, and the twin in the digital twin model can also feed back information to the ontology in the physical entity world. For example, the decision maker can take some intervention operations on the ontology in the physical entity world to optimize the behavior of the ontology in the physical entity world according to the information fed back by the twin in the digital twin model.

2 is a schematic diagram of the architecture of the digital twin world and the physical entity world in the method for establishing a simulation test platform provided by an embodiment of the present application. Relevant communication data can be obtained through data flow interaction between the physical entity world and the digital twin world. And stored in the database of the physical physical world and the digital twin world.

Among them, the physical entity world can provide training data and real-time monitoring data to the digital twin world, including four types of environmental information, user information, network information and business information. The environmental information includes information such as wireless propagation environment, spectrum detection, channel information, and transmit power. User information includes information such as user preferences, user needs, user intentions, geographic information, and mobile information. The service information may refer to the type of service provided by the wireless network to the end user and the corresponding performance requirements. The network information may include network type, network topology, interface protocol, available resources, network traffic and other network working status messages that affect the end-to-end transmission performance. At the same time, the digital twin world can also feed back the environmental information, user information, network information and business information and real-time performance in the built digital twin world to the physical entity world.

Optionally, generating a digital twin model of the edge server based on the capability feature data of the edge server and the three-dimensional model of the edge server includes the following steps.

A first data analysis neural network model is generated based on the application usage data of the terminal device, wherein the first data analysis neural network model is used to predict the user's preferred usage of the application of the terminal device; the first data analysis neural network model is encapsulated into In the 3D model of the terminal device, a digital twin model of the terminal device is generated.

Among them, the first data analysis neural network model can analyze the relationship between geographic locations (business districts, office buildings and residential buildings), time periods and user browsing video content (education, technology, entertainment, etc.) through unsupervised learning algorithms such as clustering Trained to get. The first data analysis neural network model is used to analyze the internal relationship among user information, browsing content, time and geographic location, so as to determine the user's preferred usage of the application of the terminal device.

The first data analysis neural network model is encapsulated into the three-dimensional model of the terminal device, and after the digital twin model of the terminal device is generated, some characteristic parameters in the terminal device or edge server can be adjusted to simulate different types of users of the terminal device. Characteristic Parameters. For example, the user age in the user data of the terminal device can be set to simulate the preferences of users in different age groups.

A second data analysis neural network model is generated based on the capability feature data, and the second data analysis neural network model is used to predict the capability characteristics of the edge server; the second data analysis neural network model is encapsulated into the three-dimensional model of the edge server to generate the edge server digital twin model.

Wherein, the second data analysis neural network model is used to analyze the relationship between the signal strength transmitted by the edge server and the occluder. The relationship between the signal strength transmitted by the edge server and the occluders can be analyzed by collecting the signal strength transmitted by the edge server, the intermediate occluders (vehicles, buildings, etc.), the received signal strength, and through unsupervised learning algorithms such as clustering.

Optionally, after the edge server digital twin model is generated, the method provided in this embodiment of the present specification further includes the following steps.

Obtain multiple first popular content prediction models of multiple terminal device digital twin models, wherein one terminal device digital twin model corresponds to one first popular content prediction model, and the first popular content prediction model is based on the first popular content prediction model in the terminal device digital twin model. A data analysis neural network model and preset feature parameters are generated; a plurality of first popular content prediction models are aggregated to obtain a second popular content prediction model corresponding to the region to which the edge server belongs; simulation tests are performed on the second popular content prediction model to determine Predictive effects of multiple first popular content prediction models and second popular content prediction models.

Optionally, before acquiring multiple first popular content prediction models of multiple terminal device digital twin models, the method provided by the embodiment of this specification further includes the following steps.

Obtain the global model of popular content from the digital twin model of the edge server; based on the global model of popular content and the first data in the digital twin model of the terminal device, analyze the neural network model and the preset feature parameters of the digital twin model of the terminal device, and generate the digital twin of the terminal device Model's #1 trending content prediction model.

Among them, the popular content global model is an untrained popular content prediction model.

Among them, the first popular content prediction model can deploy digital twins of edge servers, user equipment and other objects in the simulation test platform to build a simulation test environment. The first data analysis neural network model may be used to predict the video content browsed by the user on the terminal device based on the user's geographic location, time period, and the relationship between the user's browsing video content.

Optionally, in order to determine the prediction effects of the multiple first popular content prediction models and the second popular content prediction models, a simulation test is performed on the second popular content prediction models to determine a plurality of first popular content prediction models and second popular content prediction models. The prediction effect of the content prediction model includes the following steps.

Based on the second popular content prediction model and the multiple content samples to be tested, the multiple content samples to be tested are predicted to determine at least one popular content among the multiple content samples to be tested, and the multiple content samples to be tested include at least one Preset popular content samples; determine the effect of the second popular content prediction model according to at least one popular content and at least one preset popular content sample.

Optionally, after the simulation test is performed on the second popular content prediction model, the method provided by the embodiment of the present specification further includes the following steps.

If it is determined that the accuracy rate of the second popular content prediction model is higher than the third popular content prediction model generated by the corresponding edge server in the physical physical world, the third popular content prediction model is updated based on the second popular content prediction model.

In step 130, a simulation test platform is established based on the terminal device digital twin model and the edge server digital twin model.

Based on the digital twin model of the terminal equipment and the digital twin model of the edge server, a simulation test platform is established. Specifically, the established simulation test platform can be used to build a simulation test environment in the virtual space, deploy equipment, and realize the simulation test of edge intelligent algorithms. For example, the simulation test of federated learning is shown in Figure 3. Deploy user terminals such as smartphones and laptops, and edge servers in edge scenarios. The user terminal downloads the global model from the edge server and uses local data for training. After several rounds of updates, the results are uploaded to the edge server for global aggregation, and a simulation test platform is established.

The embodiment of the present application further provides an apparatus 400 for establishing a simulation test platform, as shown in FIG. 4 , which includes the following modules.

A three-dimensional model building module 401 is used to construct a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and, based on the geometric structure and shape parameters of the edge server in the physical entity world. The three-dimensional model of the edge server; the digital twin model generation module 402 is used to generate a digital twin model of the terminal device based on the application usage data of the terminal device and the three-dimensional model of the terminal device, wherein the application usage data is passed through Obtained by monitoring the terminal device; and generating an edge server digital twin model based on the capability feature data of the edge server and the three-dimensional model of the edge server, wherein the capability feature data is obtained by monitoring the edge server; simulating A test platform establishment module 403 is configured to establish a simulation test platform based on the terminal device digital twin model and the edge server digital twin model.

Optionally, in an embodiment, the digital twin model generation module 402 is configured to: generate a first data analysis neural network model based on application usage data of the terminal device, wherein the first data analysis The neural network model is used to predict the user's preference and usage of the application of the terminal device; the first data analysis neural network model is encapsulated into a three-dimensional model of the terminal device to generate a digital twin model of the terminal device.

Optionally, in an embodiment, the digital twin model generation module 402 is configured to: generate a second data analysis neural network model based on the capability feature data, and the second data analysis neural network model is used for prediction Capability features of the edge server; encapsulating the second data analysis neural network model into a three-dimensional model of the edge server to generate the edge server digital twin model.

Optionally, in an embodiment, after the digital twin model generation module 402 generates the edge server digital twin model, the apparatus further includes: a model acquisition module, configured to acquire the digital twins of the multiple terminal devices Multiple first popular content prediction models of the model, wherein a terminal device digital twin model corresponds to a first popular content prediction model, and the first popular content prediction model is based on the first data analysis in the terminal device digital twin model A neural network model and preset feature parameters are generated; a model aggregation module is used to aggregate the plurality of first popular content prediction models to obtain a second popular content prediction model corresponding to the region to which the edge server belongs; a simulation test module is used for A simulation test is performed on the second popular content prediction model to determine the prediction effects of the plurality of first popular content prediction models and the second popular content prediction model.

Optionally, in one embodiment, the simulation test module is configured to: based on the second popular content prediction model and a plurality of content samples to be tested, predict the plurality of content samples to be tested to Determine at least one popular content among the multiple content samples to be tested, the multiple content samples to be tested include at least one preset popular content sample; according to the at least one popular content and the at least one preset popular content sample , and determine the effect of the second popular content prediction model.

Optionally, in an embodiment, after the simulation test module performs a simulation test on the second popular content prediction model, the device further includes: a model update module, configured to determine if the second popular content is determined. If the accuracy of the prediction model is higher than the third popular content prediction model generated by the corresponding edge server in the physical entity world, the third popular content prediction model is updated based on the second popular content prediction model.

Optionally, in an embodiment, before the model acquisition module acquires multiple first popular content prediction models of the multiple terminal device digital twin models, the apparatus includes: a popular content global model acquisition module, which uses obtains a global model of popular content from the edge server digital twin model; a model generation module is used to analyze the neural network model and the digital The preset feature parameters of the twin model are used to generate the first popular content prediction model of the digital twin model of the terminal device.

The apparatus 400 for establishing a simulation test platform can implement the methods of the method embodiments shown in FIGS. 1 to 3 . For details, reference may be made to the method for establishing a simulation test platform of the embodiments shown in FIGS. 1 to 3 , and details are not repeated here.

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present specification. Referring to FIG. 5 , at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The memory may include memory, such as high-speed random-access memory (Random-Access Memory, RAM), or may also include non-volatile memory (non-volatile memory), such as at least one disk memory. Of course, the electronic equipment may also include hardware required for other services.

The processor, network interface and memory can be connected to each other through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Component Interconnect Standard) bus. Industry Standard Architecture, extended industry standard structure) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one bidirectional arrow is shown in FIG. 5, but it does not mean that there is only one bus or one type of bus.

memory for storing programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include memory and non-volatile memory and provide instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into the memory and runs it, forming a device for establishing a simulation test platform on a logical level. The processor executes the program stored in the memory, and is specifically configured to perform the following operations.

Build a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical entity world; and construct a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world; The application usage data of the terminal device and the three-dimensional model of the terminal device are used to generate a digital twin model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; and, based on the capability characteristics of the edge server data and the three-dimensional model of the edge server to generate an edge server digital twin model, wherein the capability feature data is obtained by monitoring the edge server; based on the terminal device digital twin model and the edge server digital twin model, establish Simulation test platform.

The above-mentioned method for establishing a simulation test platform disclosed in the embodiments shown in FIG. 1 to FIG. 3 of this specification may be applied to a processor, or implemented by a processor. A processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above-mentioned method can be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software. The above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), dedicated integrated Circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps and logic block diagrams disclosed in one or more embodiments of this specification can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in conjunction with one or more embodiments of this specification may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.

The electronic device can also execute the method for establishing the simulation test platform shown in FIG. 1 to FIG. 3 , which will not be repeated in this specification.

The embodiments of the present specification also provide a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and the one or more programs include instructions, and the instructions, when used by a portable electronic device including a plurality of application programs When executed, the portable electronic device can be made to execute the method of the embodiment shown in FIG. 1 to FIG. 3 , and is specifically used to execute the following operations.

Of course, in addition to software implementations, the electronic devices in this specification do not exclude other implementations, such as logic devices or the combination of software and hardware, etc. That is to say, the execution subjects of the following processing procedures are not limited to each logic unit. It can also be a hardware or logic device.

In a word, the above descriptions are only preferred embodiments of the present specification, and are not intended to limit the protection scope of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the protection scope of one or more embodiments of this specification.

The systems, devices, modules or units described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or A combination of any of these devices.

Computer readable media includes both persistent and non-permanent, removable and non-removable media and can be implemented by any method or technology for storage of information. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture, or device that includes the element.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments.

Claims

A method for establishing a simulation test platform, wherein the method comprises:

constructing a three-dimensional model of the terminal device based on the geometry and shape parameters of the terminal device in the physical physical world; and,

constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world;

generating a digital twin model of a terminal device based on application usage data of the terminal device and a three-dimensional model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; and,

generating an edge server digital twin model based on the capability feature data of the edge server and the three-dimensional model of the edge server, wherein the capability feature data is obtained by monitoring the edge server;

Based on the terminal device digital twin model and the edge server digital twin model, a simulation test platform is established.
The method of claim 1, wherein generating a digital twin model of a terminal device based on application usage data of the terminal device and a three-dimensional model of the terminal device, comprising:

generating a first data analysis neural network model based on the application usage data of the terminal device, wherein the first data analysis neural network model is used to predict the user's preferred usage of the application of the terminal device;

The first data analysis neural network model is encapsulated into a three-dimensional model of the terminal device to generate a digital twin model of the terminal device.
The method according to claim 1, wherein the generating an edge server digital twin model based on the capability characteristic data of the edge server and the three-dimensional model of the edge server comprises:

generating a second data analysis neural network model based on the capability feature data, where the second data analysis neural network model is used to predict the capability feature of the edge server;

The second data analysis neural network model is encapsulated into the three-dimensional model of the edge server, and the digital twin model of the edge server is generated.
The method of claim 3, wherein after generating the edge server digital twin model, the method further comprises:

Obtain multiple first popular content prediction models of the multiple terminal device digital twin models, wherein one terminal device digital twin model corresponds to one first popular content prediction model, and the first popular content prediction model is based on the terminal device. The first data analysis neural network model in the digital twin model and the generation of preset feature parameters;

Aggregating the plurality of first popular content prediction models to obtain a second popular content prediction model corresponding to the region to which the edge server belongs;

A simulation test is performed on the second popular content prediction model to determine the prediction effects of the plurality of first popular content prediction models and the second popular content prediction model.
The method according to claim 4, wherein the simulation test is performed on the effect of the second popular content prediction model to determine the relationship between the plurality of first popular content prediction models and the second popular content prediction model. Predicted performance, including:

Based on the second popular content prediction model and multiple content samples to be tested, predict the multiple content samples to be tested to determine at least one popular content among the multiple content samples to be tested, the multiple content samples to be tested The content sample to be tested includes at least one preset popular content sample;

Determine the effect of the second popular content prediction model according to the at least one popular content and the at least one preset popular content sample.
The method according to claim 4 or 5, wherein after the simulation test is performed on the second popular content prediction model, the method further comprises:

If it is determined that the accuracy rate of the second popular content prediction model is higher than the third popular content prediction model generated by the corresponding edge server in the physical physical world, the third popular content prediction model is updated based on the second popular content prediction model Model.
The method according to claim 4, wherein before acquiring a plurality of first popular content prediction models of the plurality of terminal device digital twin models, the method further comprises:

Obtain a global model of popular content from the edge server digital twin model;

Based on the global model of popular content, the first data analysis neural network model in the digital twin model of the terminal device, and the preset feature parameters of the digital twin model of the terminal device, the first trend of the digital twin model of the terminal device is generated. Content prediction model.
A device for establishing a simulation test platform, wherein the device comprises:

a three-dimensional model building module for constructing a three-dimensional model of the terminal device based on the geometric structure and shape parameters of the terminal device in the physical physical world; and,

constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world;

a digital twin model generation module, configured to generate a digital twin model of a terminal device based on application usage data of the terminal device and a three-dimensional model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; as well as,

generating an edge server digital twin model based on the capability feature data of the edge server and the three-dimensional model of the edge server, wherein the capability feature data is obtained by monitoring the edge server;

A simulation test platform establishment module is used to establish a simulation test platform based on the terminal device digital twin model and the edge server digital twin model.
An electronic device comprising:

processor; and

memory arranged to store computer-executable instructions which, when executed, cause the processor to:

constructing a three-dimensional model of the terminal device based on the geometry and shape parameters of the terminal device in the physical physical world; and,

constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world;

Based on the application usage data of the terminal device and the three-dimensional model of the terminal device, a digital twin model of the terminal device is generated, wherein the application usage data is obtained by monitoring the terminal device; and,

generating an edge server digital twin model based on the capability feature data of the edge server and the three-dimensional model of the edge server, wherein the capability feature data is obtained by monitoring the edge server;

Based on the terminal device digital twin model and the edge server digital twin model, a simulation test platform is established.
A computer-readable storage medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the following operations :

constructing a three-dimensional model of the terminal device based on the geometry and shape parameters of the terminal device in the physical physical world; and,

constructing a three-dimensional model of the edge server based on the geometric structure and shape parameters of the edge server in the physical entity world;

generating a digital twin model of a terminal device based on application usage data of the terminal device and a three-dimensional model of the terminal device, wherein the application usage data is obtained by monitoring the terminal device; and,

generating an edge server digital twin model based on the capability feature data of the edge server and the three-dimensional model of the edge server, wherein the capability feature data is obtained by monitoring the edge server;

Based on the terminal device digital twin model and the edge server digital twin model, a simulation test platform is established.