A cloud terminal simulation control method, device, storage medium and electronic device

Abstract

The embodiment of the present application discloses a cloud terminal simulation control method, device, storage medium and electronic device, wherein the method comprises: obtaining processor simulation information matching the cloud terminal to be created, obtaining entity configuration information corresponding to the cloud terminal to be created, the entity configuration information being the software and hardware configuration information corresponding to the cloud terminal to be created, and creating a cloud terminal module corresponding to the cloud terminal to be created based on the entity configuration information and the processor simulation information. The accuracy of cloud terminal simulation control can be improved by adopting the embodiment of the present application.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a cloud terminal simulation control method, device, storage medium and electronic device. Background Art

[0002] With the rapid development of cloud computing technology, cloud computing scenarios are becoming more and more common. Cloud terminals based on cloud computing (such as cloud phones, cloud TVs, etc.) can be deployed and run on cloud service platforms. Users can access the service platform through the network based on the client. The service platform can also provide users with diversified and comprehensive virtual cloud terminal business services. Through cloud terminals, various terminal applications and terminal services on simulated physical devices can be supported, including display, download, maintenance and management. Summary of the invention

[0003] The present application provides a cloud terminal simulation control method, device, storage medium and electronic device, and the technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides a cloud terminal simulation control method, the method comprising:

[0005] Get the processor simulation information that matches the cloud terminal to be created;

[0006] Acquire entity configuration information corresponding to the cloud terminal to be created, where the entity configuration information is software and hardware configuration information corresponding to the cloud terminal to be created;

[0007] A cloud terminal module corresponding to the cloud terminal to be created is created based on the entity configuration information and the processor simulation information.

[0008] In a second aspect, an embodiment of the present application provides a cloud terminal simulation control device, the device comprising:

[0009] An information determination module, used to obtain processor simulation information matching the cloud terminal to be created, and to obtain entity configuration information corresponding to the cloud terminal to be created;

[0010] A cloud terminal creation module is used to create a cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information.

[0011] In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0012] In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0013] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0014] In one or more embodiments of the present application, the service platform obtains the processor simulation information matching the cloud terminal to be created; and obtains the entity configuration information corresponding to the cloud terminal, and then creates a cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information. So as to run the business service corresponding to the cloud terminal based on the cloud terminal module in the subsequent practical application stage. During the entire cloud terminal simulation control process, the creation is based on the processor simulation information and entity configuration information corresponding to the cloud terminal that is closer to the required simulation entity (such as a physical mobile phone, a physical computer, etc.), which can avoid the problem of simulation control being separated from the actual environment of the physical simulation and the inaccuracy of simulation control caused by only constructing a virtual software operating environment in a template-like manner on the cloud or directly running business services based on server resources, thereby improving the accuracy of cloud terminal simulation control. The cloud terminal simulation control process is closer to the hardware and software operating environment of the physical device, and can achieve accurate measurement of the performance, status, consumption and other test dimensions of the simulated entity in the cloud terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of a cloud terminal simulation control method provided in an embodiment of the present application;

[0017] Figure 2 It is a flowchart of another cloud terminal simulation control method provided in an embodiment of the present application;

[0018] Figure 3 It is a schematic diagram of interaction between a client and a cloud service platform involved in this application;

[0019] Figure 4 It is a schematic diagram of an interface for customizing device settings involved in this application;

[0020] Figure 5 It is a flowchart of another cloud terminal simulation control method provided in an embodiment of the present application;

[0021] Figure 6 It is a schematic diagram of a model training scenario involved in this application;

[0022] Figure 7 It is a schematic diagram of the architecture of a cloud terminal simulation control system provided in an embodiment of the present application;

[0023] Figure 8 It is a structural schematic diagram of a cloud terminal simulation control device provided in an embodiment of the present application;

[0024] Fig. 9 is a structural diagram of an information determination module provided in an embodiment of the present application;

[0025] Fig.10 It is a structural schematic diagram of another cloud terminal simulation control device provided in an embodiment of the present application;

[0026] Fig.11 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] In the description of the present application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood in specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are an "or" relationship.

[0029] The present application is described in detail below with reference to specific embodiments.

[0030] In one embodiment, Figure 1 As shown, a cloud terminal simulation control method is proposed, which can be implemented by a computer program and can be run on a cloud terminal simulation control device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application. Specifically, the cloud terminal simulation control method includes:

[0031] S101: Acquire processor simulation information that matches the cloud terminal to be created.

[0032] The cloud terminal can be understood as a new type of cloud application technology based on cloud technology. The cloud terminal can be deployed and run on a cloud service platform. The software and hardware operating environment (processor operating environment) corresponding to the physical terminal can be simulated and controlled based on the software and hardware resources of the service platform. In actual applications, cloud technologies such as virtualization can be used to simulate and control business services of the physical terminal on the service platform. The client program can be installed on the physical device used by the user and connected to the cloud service platform through the network. Any user corresponding to the physical device equipped with the client can use the business services provided by the cloud terminal on the cloud service platform, such as supporting the display, download, and service management of application screens of various types of cloud terminals.

[0033] Furthermore, the cloud terminal can be a cloud phone, which is a new type of mobile phone technology. The "cloud phone" can run on a cloud service platform. The service platform uses simulation and virtualization technology to make the running screen, running parameters, operating system, application services, etc. seen are similar to a physical mobile phone. The cloud service platform can be a server such as x86 or arm architecture, or it can be some service arrays based on real machines. By simulating the cloud real machine in the form of cloud terminal virtualization on the cloud service platform, based on the convenience of cloud computing virtual applications and the Internet, it can break through the advantages that existing physical terminals do not have in large-scale computing, storage, virtualization applications, etc., and can provide users with diversified and comprehensive virtual terminal applications and services. In some scenarios, it is possible to host the corresponding business services of physical devices on the cloud service platform to maintain an all-weather online state and realize the virtualization of physical device applications.

[0034] In some embodiments, a user can trigger a simulation control instruction for a cloud terminal simulation on the client used, and the client can send the simulation control instruction to a service platform on the cloud. The service platform on the cloud can respond to the simulation control instruction, execute the code for performing simulation control of the cloud terminal, and start creating a cloud terminal module for the cloud terminal. The cloud terminal module is used to host the operating environment of the cloud terminal.

[0035] Specifically, the client program can be installed on the physical device corresponding to the user. At this time, the physical device can be understood as a client. The client can be connected to the cloud service platform through the network in advance. Any user corresponding to the physical device equipped with the client can use the business services provided by the cloud terminal on the cloud service platform. The user can input the simulation control instructions for the cloud terminal simulation through the client used. In this way, the simulation control instructions input by the user for the cloud terminal can be sent to the cloud service platform through the network. The service platform receives the simulation control instructions and then responds to the simulation control, starts to execute the code for the cloud terminal simulation control, and starts to create a cloud terminal module for the cloud terminal. In the process of creating the cloud terminal module, the service platform needs to load or call the corresponding resources to initialize the cloud terminal module and complete the simulation of the cloud terminal.

[0036] In the process of creating a cloud terminal module, the service platform needs to determine the processor simulation information that matches the cloud terminal based on the simulation control instruction. It can be understood that the processor simulation information is used to actually simulate the operation of the processor of the cloud terminal in the actual application environment. In this application, based on the perspective of the actual application scenario of the cloud terminal, in order to be closer to the actual cloud terminal simulation control scenario, a processor simulation model close to the device processor operation control scenario can be created based on the matched processor simulation information. Based on the processor simulation model as part of the subsequent cloud terminal module, the processor architecture of the cloud terminal in the actual application scenario is simulated, which can more accurately feedback the service operation and performance consumption in the actual application of the cloud terminal. In some embodiments, the processor simulation model is obtained by simulating the processor of the actual physical device using a neural network based on the training sample.

[0037] In a feasible implementation, when the user inputs a simulation control instruction created for a cloud terminal simulation through the client used, the user can select the physical device that he wants to simulate. For example, if the user wants to simulate a certain model of terminal, the simulation control instruction can carry a simulation terminal identifier when the client generates the simulation control instruction. The simulation terminal identifier is used to characterize the type or model of the physical terminal that the user wants to simulate. The service platform can obtain the simulation terminal identifier carried by the simulation control instruction based on the simulation control instruction, and then determine the specific type or model of the cloud terminal that the user wants to simulate based on the simulation terminal identifier.

[0038] Based on the simulation terminal identifier, the processor simulation information of the corresponding physical terminal can be obtained. It can be understood that there is a unique mapping relationship between the processor simulation information corresponding to a physical terminal indicated by the actual application simulation terminal identifier. The service platform can pre-store a large number of model samples, which contain processor simulation information and physical configuration information corresponding to the cloud terminal that can support simulation control. Based on this, the service platform can quickly determine the processor simulation information corresponding to the cloud terminal that the user wants to create based on the simulation terminal identifier.

[0039] The processor simulation information is used to construct a processor model in a cloud terminal module for a cloud terminal. The processor model can make the operation or operation state of the cloud terminal on the service platform closer to the actual operation scene by simulating the processor of the corresponding entity of the cloud terminal in the actual application environment. In some embodiments, the processor simulation information may include a processor simulation model of one or more processing cores, and the processor simulation model may be implemented by simulating at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA) in the actual scene. The processor simulation model can integrate simulations including but not limited to one or more processor combinations in a central processing unit (CPU), an image processor (GPU), and a modem. The processor simulation information can be a processor model, a processor architecture, a number of processors, and the operation configuration information of the processor. Furthermore, processor simulation information can be divided into processor simulation models in simulation hardware dimension and model configuration information for the processor simulation model in simulation software dimension. The model configuration information can be processor configuration information such as information in processor scheduling policy dimension, information in processor core binding policy dimension, information in processor frequency locking policy dimension, etc.

[0040] In a feasible implementation, when the user inputs a simulation control instruction for the cloud terminal simulation through the client used, the user can select the entity type that he wants to simulate (in some embodiments, it can also be understood as the entity device type). If the user wants to simulate a certain type of terminal, the entity type can be understood as a refinement of a type of terminal. For example, the entity type can be a terminal with a certain device function. The service platform can determine the target model of cloud terminal that matches the entity type based on the simulation control instruction carrying the entity type (for example, a certain device function can correspond to one model of cloud terminal that supports creation), and then obtain the processor simulation information of the target model of cloud terminal.

[0041] In a feasible implementation, when the user inputs the simulation control instruction for the cloud terminal simulation creation through the client used, the entity requirement parameters (which have the same meaning as the creation requirement information in some implementations) that the user desires to simulate can be selected accordingly. The entity requirement parameters can be understood as detailed specification parameter information for a certain terminal, such as camera, resolution, screen size, processor combination, etc. Then, the service platform can determine the target model of cloud terminal that matches the entity requirement parameters based on the simulation control instruction carrying the entity requirement parameters. The matching process can be based on calculating the similarity between the entity specification parameters and the entity requirement parameters of all reference models of cloud terminals, taking a certain model of cloud terminal indicated by the highest similarity as the "target model of cloud terminal", and then obtaining the processor simulation information of the target model of cloud terminal.

[0042] S102: Acquire entity configuration information corresponding to the cloud terminal to be created, and create a cloud terminal module corresponding to the cloud terminal to be created based on the entity configuration information and the processor simulation information.

[0043] According to some embodiments, the entity configuration information is the hardware and software configuration information for the entity simulated by the cloud terminal, and the entity configuration information may be one or more of the configuration information such as the resolution, hardware specification information (such as camera specifications, microphone specifications, etc.), software specification information (such as system version specifications, application version specifications, firmware software specifications), memory information, sensor information, etc. of the entity simulated by the cloud terminal. In the present application, obtaining the entity configuration information corresponding to the cloud terminal can be closer to the entity configuration of the entity in the actual environment when the cloud terminal module is subsequently created. For example, taking the cloud terminal as a cloud phone, the entity configuration information can feedback the configuration parameters of the cloud phone corresponding to the mobile phone entity, such as mobile phone resolution, mobile phone sensor composition, mobile phone software version, hardware specifications, mobile phone attributes, etc.

[0044] Specifically, after the service platform obtains the entity configuration information and the processor simulation information corresponding to the cloud terminal to be created, it can create a cloud terminal module for the cloud terminal. In some embodiments, the entity configuration information can usually be represented in the form of a determined matching target simulation system image. The target simulation system image can be used to represent the virtual machine system image for the cloud terminal to be created in the cloud terminal simulation stage, and can feedback the entity configuration corresponding to the cloud terminal to be simulated, such as system version, software application, resolution, software specification information, etc. That is to say, in some implementation methods, the entity configuration information can actually be a virtual machine system image for the cloud terminal to be created.

[0045] The cloud terminal (or cloud terminal template) can be initialized first through the aforementioned entity configuration information and the processor simulation information, such as initializing a virtual machine for creating a cloud terminal, and performing module configuration optimization on the initialized cloud terminal based on the processor simulation information during the whole process, such as optimizing the processor architecture, processor scheduling strategy, core binding strategy, frequency limiting strategy, control group strategy (Cgroup strategy) and so on within the module. After the initialization is completed, the processor simulation model of the cloud terminal is adjusted, and a cloud terminal module containing the adjusted processor simulation model for the cloud terminal can be obtained. The cloud terminal module can be understood as a virtual machine for creating a cloud terminal, and includes a processor simulation model obtained by simulating and training a physical device using a neural network, which is closer to the operating environment of the physical device and has a more accurate simulation control effect.

[0046] In addition, the process of obtaining the above-mentioned entity configuration information is similar to the process of obtaining the aforementioned processor simulation information. Usually, when determining the processor simulation information for the cloud terminal, since the processor simulation information and entity configuration information of a certain model of cloud terminal are strongly correlated, the service platform can retrieve or match the entity configuration information associated with it based on the processor simulation information of the cloud terminal. In some embodiments, the processor simulation information and entity configuration information of the entity terminal of each stored sample cloud terminal can be correspondingly stored in the device simulation library, that is, there is a one-to-one mapping relationship between the entity terminal of each sample cloud terminal and the "processor simulation information and entity configuration information". Based on this mapping relationship, the "processor simulation information and entity configuration information" corresponding to the cloud terminal that the current user expects to create can be matched in the device simulation library. In other words, the aforementioned steps of determining the processor simulation information matching the cloud terminal and the steps of obtaining the entity configuration information corresponding to the cloud terminal are executed in no particular order.

[0047] In some embodiments, the processor simulation information matched to the cloud terminal can be used to subsequently create a processor simulation model for the cloud terminal. The processor simulation model can be determined only based on the processor environment of the physical device corresponding to the cloud terminal to be simulated. For example, for a certain model of cloud terminal, it can be a processor simulation model determined by collecting the processor environment (such as processor specifications, processor configuration information, etc.) of its corresponding physical device (which can be understood as the terminal processor information of the physical terminal in some embodiments), and then stored in the form of processor simulation information. In the actual application stage, the model can be loaded based on the processor simulation information to complete the initialization of the processor simulation model; further, the processor simulation model can also include the platform processor dimension information of the service platform for reference. The platform processor dimension information (which can also be understood as platform processor information in some embodiments) can be information such as the number of processors, processor frequency, processor core distribution, and processor scheduling strategy of the service platform. By integrating the platform processor dimension information of the service platform on the basis of the processor environment of the physical device corresponding to the cloud terminal, a processor simulation model for the cloud terminal that conforms to the physical application environment and the application environment of the service platform can be simulated and trained. After the processor simulation model is trained, it can be passed to the model library management part (such as the model library management unit) contained in the service platform for storage.

[0048] In a specific implementation scenario, after the creation, the business service corresponding to the cloud terminal can also be run based on the cloud terminal module.

[0049] The business service may be an application service, system service, communication service or other business service developed based on business logic requirements of the cloud terminal.

[0050] In the actual application stage, after the cloud terminal module is created, at least one business service program corresponding to a business service can be configured in the cloud terminal module based on business needs. The business service program can be derived from an application developed by a third party. The business service can be compatible with the physical device corresponding to the cloud terminal, that is, the business service can be run on the physical device. By pre-configuring at least one business service program corresponding to a business service in the cloud terminal module, after the cloud terminal module is built, the business service that the user on the client expects to run can be run based on the interactive instructions with the client. For example, the cloud terminal module can be configured with many different business service programs. The user on the client can select the corresponding business service program when he expects to run a certain target business service. The service platform can automatically call the processor simulation model included in the service platform on the cloud to run the business service corresponding to the business service program by obtaining the service running instructions input for the business service program selected by the user, and responding to the service running instructions.

[0051] During the process of the cloud terminal running business services, it can receive machine executable instructions (such as touch instructions) sent by the user's corresponding client, and respond to the machine executable instructions to process the corresponding business services. In this process, based on the corresponding business services, the audio and video stream data generated when the cloud terminal is currently running the business service can be sent to the client, and the client can display audio and video based on the audio and video stream data.

[0052] It can be understood that the cloud service platform involved in the present application can simulate the control of multiple independent cloud terminals synchronously or asynchronously, and the simulation control process of each cloud terminal is the same or similar. In some embodiments, the cloud service platform can be configured with a terminal factory, which can be understood as a collection of multiple cloud terminals. Centralized operation and management of multiple cloud terminals are performed based on the form of a terminal factory.

[0053] In some embodiments, the cloud terminal module can update the business service during operation. After the business service on the cloud terminal module is updated, some business functions can be correspondingly expanded or deleted. For example, some game business functions can be adjusted in the game business service. The cloud terminal module only needs to perform differential or incremental updates on the program code of the business service program corresponding to the business service. The updated business service program is reconfigured and run on the cloud terminal. The entire process can realize the automatic operation of the business service without the assistance of the user on the client.

[0054] In an embodiment of the present application, the service platform obtains the processor simulation information that matches the cloud terminal to be created; and obtains the entity configuration information corresponding to the cloud terminal, and then creates a cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information. So as to run the business service corresponding to the cloud terminal based on the cloud terminal module in the subsequent practical application stage. During the entire cloud terminal simulation control process, the creation is based on the processor simulation information and entity configuration information corresponding to the cloud terminal that is closer to the required simulation entity (such as a physical mobile phone, a physical computer, etc.), which can avoid the problem of simulation control being separated from the actual environment of the physical simulation and the inaccuracy of simulation control caused by only constructing a virtual software operating environment in a cloud template or directly running business services based on server resources, thereby improving the accuracy of cloud terminal simulation control. The cloud terminal simulation control process is closer to the hardware and software operating environment of the physical device, and can achieve accurate measurement of the performance, status, consumption and other test dimensions of the simulated entity in the cloud terminal.

[0055] See also Figure 2 , Figure 2 This is a flow chart of another embodiment of a cloud terminal simulation control method proposed in this application. Specifically:

[0056] S201: Acquire creation requirement information for a cloud terminal to be created, and determine processor simulation information corresponding to the creation requirement information.

[0057] In some embodiments, the creation requirement information is input by a user on the client before the cloud terminal simulation, and the creation requirement information is usually used to instruct the service platform to simulate and create a cloud terminal that matches or fits the creation requirement information. Optionally, the creation requirement information can be a refinement of the physical device to be simulated for a single cloud terminal, specifically the physical device type, for example, the physical device type can be a model of a specified physical type for the cloud terminal.

[0058] In some implementations, the processor simulation information may be determined based on a pre-maintained device simulation library, where the device simulation library may be understood as a cloud terminal setting that includes processor simulation information for multiple entity device types.

[0059] It can be understood that during the maintenance and creation stage of the device simulation library, corresponding processor simulation information (including processor simulation models and model configuration information) has been pre-set for cloud terminals of a large number of physical device types. In the actual use stage, after obtaining the creation requirement information for the cloud terminal, based on the physical device type in the creation requirement information, the processor simulation information corresponding to the physical device type can be retrieved from the device simulation library. In some embodiments, the device simulation library can be further subdivided into multiple libraries that store different information, such as a device simulation library that stores processor simulation information and an image library that stores virtual machine images. In other words, the processor simulation information corresponding to the physical device type can be retrieved from the processor model library in the device simulation.

[0060] Optionally, the device simulation library may include a processor model library. The processor model library may serve as a sub-library of the device simulation library for storing data related to the processor simulation model. Based on the processor model library, the maintenance and update of processor simulation information configured for a large number of cloud terminals can be achieved.

[0061] In a feasible implementation, when the user inputs a simulation control instruction created for a cloud terminal simulation through the client used, the user can select the physical terminal model or physical terminal type that he or she expects to simulate. For example, if the user expects to simulate a certain model of terminal, the simulation control instruction can carry a simulation terminal identifier when the client generates the simulation control instruction. The simulation terminal identifier is used to characterize the type or model of the physical terminal that the user expects to simulate. The service platform can then obtain the simulation terminal identifier carried by the simulation control instruction based on the simulation control instruction, and then determine the specific type or model of the cloud terminal that the user expects to simulate based on the simulation terminal identifier.

[0062] Indicatively, Figure 3 As shown, Figure 3This is a schematic diagram of the interaction between a client and a cloud service platform involved in this application. Figure 3 As shown, the client displays a cloud terminal creation interface, which is used by the user to input the desired simulated entity device type on the cloud terminal. Figure 3 In the process of creating a cloud terminal, the user can input the type of physical device to be created on the cloud terminal creation interface by touching the finger to trigger the simulation control instruction. For example, input "oppK5" on the cloud terminal creation interface and then click Figure 3 , and then clicks the "OK" button. At this time, the client 100 recognizes the simulation control instruction input by the user, and sends the simulation control instruction carrying the physical device type to the service platform through the network transmission channel with the service platform. After the service platform receives the simulation control instruction, it can then obtain the physical device type "opp K5" input by the user for the cloud terminal.

[0063] Furthermore, after the service platform obtains the physical device type for the cloud terminal, it then obtains the processor simulation information corresponding to the physical device creation type to be created locally (such as in the aforementioned processor model library). During implementation, matching processing can be performed in the processor model library based on the physical device type to obtain the processor simulation information corresponding to the physical device type. Furthermore, the processor simulation information includes but is not limited to the processor simulation model subsequently used to create the cloud terminal module and the model configuration information for the model operation.

[0064] According to some embodiments, the processor simulation information may include a processor simulation model of one or more processing cores, and the processor simulation model may be implemented by simulating the actual scene using at least one of the hardware forms of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor may simulate a combination of one or more processors such as an integrated central processing unit (CPU), a graphics processing unit (GPU), and a modem.

[0065] The model configuration information may be model configuration information for the aforementioned processor simulation model, such as processor configuration information in the dimension of processor scheduling policy, information in the dimension of processor core binding policy, information in the dimension of processor frequency locking policy, and the like.

[0066] In a feasible implementation, when the user inputs simulation control instructions for cloud terminal simulation through the client used, the device customization settings of the cloud terminal to be created can be performed, that is, the client can provide a human-computer interaction interface, and the user can input the selected custom device configuration of the desired simulation in the human-computer interaction interface, where the device positioning configuration can be understood as the entity requirement parameters of the desired simulation, and the entity requirement parameters can be understood as detailed specification parameter information for a certain cloud terminal, such as camera, resolution, screen size, processor combination, microphone, etc.

[0067] Indicatively, Figure 4 As shown, Figure 4 This is a schematic diagram of the interface of a device custom setting involved in this application. Figure 4 As shown, the client displays a cloud terminal customization interface. The cloud terminal creation interface is used by the user to enter the detailed customization parameters of the cloud terminal that the user expects to simulate on the cloud terminal. For example, the user can select appropriate customization parameters for options such as processor platform, resolution, screen size, operating system, etc. Figure 4 In the cloud terminal creation interface, users can input the parameter configuration of the cloud terminal they want to create by touching their fingers. For example, they can select the processor platform as A1 model, the resolution as 720p, the screen size as 10 inches, the operating system as A system, etc. After the user completes the selection on the current interface, a custom device configuration containing the above parameter configuration data for the cloud terminal can be generated. In this process, the user can click Figure 4 , and then the client recognizes the simulated control instruction (carrying the custom device configuration) input by the user, and sends the simulated control instruction carrying the custom device configuration to the service platform through the network transmission channel with the service platform. After the service platform receives the simulated control instruction, it can then obtain the custom device configuration for the cloud terminal input by the user.

[0068] Furthermore, the service platform obtains the custom device configuration for the cloud terminal, and then determines the processor simulation information matching the custom device configuration in the processor model library; wherein, in some embodiments, the processor simulation information includes a processor simulation model and model configuration information.

[0069] It is understandable that the processor model library mainly queries matching processor simulation information based on custom processor configuration parameters related to the processor in the custom device configuration, such as the number of processors, processor architecture, processor platform, processor frequency, etc.

[0070] The matching process can be based on calculating the similarity between the "processor simulation information" of the processor simulation models of all reference models and the "custom processor configuration parameters", and taking the "processor simulation information" of a processor simulation model of a certain model indicated by the highest similarity as the processor simulation information in matching, and subsequently creating the processor model of the cloud terminal module based on the matching processor simulation information.

[0071] In a specific implementation scenario, if the processor simulation information corresponding to the creation requirement information does not exist in the device simulation library, such as the model of the cloud terminal that the user wants to create is "opp k5", and the processor simulation information corresponding to "oppk5" does not exist in the device simulation library. At this time, the service platform can determine the physical device corresponding to the cloud terminal of the model "opp k5", that is, the physical device corresponding to the cloud terminal determined by the creation requirement information, and then obtain the physical device and establish a communication connection with the physical device, deploy an information collection toolkit (SDK package) on the physical device, and collect data on the physical device through the information collection toolkit to obtain the comprehensive processor information on the physical device, and the comprehensive processor information includes processor data, processor configuration data, processor scheduling data, and processor stress test data.

[0072] Then, based on the processor comprehensive information, processor simulation information for the physical device is created. In some embodiments, based on the processor comprehensive information and platform processor information on the physical device, the processor simulation information for the physical device is determined separately. The specific execution steps can be referred to the explanations in other embodiments and will not be elaborated here.

[0073] S202: Determine entity configuration information corresponding to the cloud terminal based on the creation requirement information.

[0074] According to some embodiments, the entity configuration information is the hardware and software configuration information for the entity simulated by the cloud terminal, and the entity configuration information may be one or more of the configuration information such as the resolution, hardware specification information (such as camera specifications, microphone specifications, etc.), software specification information (such as system version specifications, application version specifications, firmware software specifications), memory information, sensor information, etc. of the entity simulated by the cloud terminal. In the present application, obtaining the entity configuration information corresponding to the cloud terminal can be closer to the entity configuration of the entity in the actual environment when subsequently creating the cloud terminal module. For example, taking the cloud terminal as a cloud phone as an example, the entity configuration information can feedback the configuration parameters of the cloud phone corresponding to the mobile phone entity, such as mobile phone resolution, mobile phone sensor composition, mobile phone software version, hardware specifications, mobile phone attributes, etc.

[0075] Optionally, in the present application, the entity configuration information is used to simulate the hardware and software environment of the entity corresponding to the cloud terminal. During actual use, the target simulation system image that matches the cloud terminal can be determined based on the creation requirement information. The target simulation system image can be used to characterize the virtual machine system image for the cloud terminal that needs to be created in the cloud terminal simulation stage, and can provide feedback on the entity configuration that needs to be simulated corresponding to the cloud terminal, such as system version, software application, resolution, software specification information, etc. That is to say, in some implementations, the entity configuration information can actually be a virtual machine system image for the cloud terminal that needs to be created.

[0076] That is to say, in some embodiments, the device simulation library may include a system image library, which may serve as a sub-library of the device simulation library to store data related to the simulated system image. Based on the system image library, the system image information corresponding to a large number of cloud terminals may be maintained and updated.

[0077] In a feasible implementation, the process of determining the entity configuration information may be that the service platform matches the creation requirement information with at least one reference configuration information to obtain the target configuration information after the information matching process; and then uses the target configuration information as the entity configuration information for the cloud terminal.

[0078] In the actual application stage, at least one reference configuration information can be stored in the device simulation library of the service platform, which can be a system image library (virtual machine system image library) in the device simulation library. The service platform matches the creation requirement information with the reference creation configuration information represented by each simulated system image in the system image library to obtain the target creation configuration information; it can be understood that the actual manifestation of the target creation configuration information is a virtual machine system image, and the hardware and software environment of the entity corresponding to the simulated cloud terminal can be fed back based on the target creation configuration information. In actual application, the virtual machine system image corresponding to the target creation configuration information is used as the entity configuration information that needs to be created.

[0079] Among them, the reference configuration information can be a fit of one or more configuration information such as reference resolution of the entity simulated supported by the cloud terminal, reference hardware specification information (such as camera specifications, microphone specifications, etc.), reference software specification information (such as system version specifications, application version specifications, firmware software specifications), reference memory information, reference sensor information, etc.

[0080] The matching process may be to calculate the information similarity between each reference creation configuration information and the user's creation requirement information, and after obtaining the information similarity corresponding to each simulated system image, select the target creation configuration information indicated by the highest information similarity;

[0081] The service platform then uses the target simulation system image represented by the target creation configuration information as entity configuration information for the cloud terminal.

[0082] S203: Creating a cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information;

[0083] In the embodiments of the present application, it can be understood that the entity configuration information determined based on the creation requirement information is actually the software and hardware configuration environment of the cloud terminal, and can also be understood as a target simulation (virtual machine) system image represented by the entity configuration information. The target simulation system image represented by the integration of the entity configuration information and the processor simulation model can further create a cloud terminal module for the cloud terminal.

[0084] According to some embodiments, the target simulation system image represented by the aforementioned entity configuration information and the processor simulation information can first initialize the cloud terminal (or cloud terminal template), that is, first generate an initialized virtual machine of the cloud terminal (which includes an initialized processor simulation model), and perform module configuration optimization on the initialized cloud terminal based on the processor simulation information during the entire process. The module configuration optimization focuses on optimizing the model parameters of the initialized virtual machine (which includes the initialized processor simulation model), such as optimizing the processor architecture, processor scheduling strategy, core binding strategy, frequency limiting strategy, control group strategy (Cgroup strategy) and so on within the module. After the initialization is completed, the initialized virtual machine of the cloud terminal (which includes the initialized processor simulation model) completes the adjustment, and a cloud terminal module containing the adjusted processor simulation model for the cloud terminal can be obtained.

[0085] S204: Starting and running the business service corresponding to the cloud terminal based on the cloud terminal module, and collecting model status information of the cloud terminal module.

[0086] The model status information is equivalent to the virtual device status information of the simulated cloud terminal, which can be feedback of the performance information of the current cloud terminal, comprehensive resource information (resource consumption, resource surplus information, etc.), power of the simulated terminal, network information of the cloud terminal, business processing status information, simulated processor status information, etc. In this application, the simulation control process of the cloud terminal can be reflected in starting the cloud terminal module as a carrier, starting the business service corresponding to the cloud terminal of the cloud terminal, such as starting the game business that the user expects to start. In the process of starting and running the business service, the service platform automatically collects the model status information of the cloud terminal module.

[0087] Real-time acquisition of model status information is used to automatically adjust the processor simulation model in the cloud terminal module, such as adjusting the frequency parameters of a processor core based on the model status information, modifying the status parameters of a processor core, adjusting the priority parameters of the processor execution thread, etc. The above process can be understood as the cloud terminal module dynamically running business services, and dynamically adjusting the performance of the processor model based on the simulated actual cloud terminal business service running environment, so that the cloud terminal module after the current adjustment of the processor simulation model can better adapt to and run the business services in the simulation environment.

[0088] Optionally, the service platform can control the cloud terminal to create a monitoring process for the monitoring module running in the corresponding cloud terminal module, and allocate resources to the monitoring process, so that the model status information of the cloud terminal module can be collected in real time during the actual implementation process.

[0089] S205: Adjusting model parameters of the processor simulation model included in the cloud terminal module based on the model status information.

[0090] In a feasible implementation manner, the service platform may be pre-configured with a model training network. The model training network may generate processor simulation models corresponding to each different type of cloud terminal in the device simulation library based on actual application conditions. In the actual application stage, the processor simulation model corresponding to the current cloud terminal may be adjusted based on the model status information, such as adjusting the frequency parameters of a processor core based on the model status information, modifying the status parameters of a processor core, adjusting the priority parameters of the processor execution thread, and so on.

[0091] In some embodiments, the model training network can be a functional module configured by the service platform. In some embodiments, the functional module can be called an AI Runtime module. The AI ​​Runtime module that carries the model training network can be understood as a collection of AI (artificial intelligence) functions. The AI ​​Runtime module can be designed in the form of a plug-in. The AI ​​Runtime module that carries the model training network supports multiple AI frameworks during configuration, including but not limited to the TensorFlow framework, the Torch framework, etc. It is understandable that each AI framework is integrated into the AI ​​framework as an Element plug-in. In the training phase of the AI ​​Runtime module, the initial model training network is trained by obtaining the associated training data corresponding to the processor simulation model in the actual application environment. The model training network can be a network with integrated AI (artificial intelligence) functions after the introduction of a neural network. The neural network is based on a convolutional neural network (CNN) model, a deep neural network (DNN) model, a recurrent neural network (RNN) model, an embedding model, a gradient boosting decision tree (GBDT) model, a logistic regression (LR) model, and other models. One or more of these models are implemented by fitting. In the actual application phase, an initial reference processor simulation model can be selected for training calculations. In this application, the framework of the AI ​​Runtime module can generally be scalable and easy to use.

[0092] The service platform can perform model network calculation based on the AI ​​Runtime module according to the front-end trained processor simulation model stored in this end (such as the device simulation library in some embodiments) and the real-time data collected above (i.e., model state information) to obtain a set of model state adjustment parameters that can dynamically adjust the internal processor strategy of the cloud terminal, and then update the model parameters of the front-end processor simulation model of the cloud terminal module based on the model state adjustment parameters.

[0093] During the actual usage phase, the service platform can input the model state information into the model training network, that is, into the AI ​​Runtime module that carries the model training network, output the model state adjustment parameters for the processor simulation model included in the cloud terminal module, and then perform model adjustment on the processor simulation model based on the model state adjustment parameters.

[0094] In the embodiment of the present application, the service platform obtains the processor simulation information matching the cloud terminal to be created; and obtains the entity configuration information corresponding to the cloud terminal, and then creates the cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information. So as to run the business service corresponding to the cloud terminal based on the cloud terminal module in the subsequent practical application stage. In the whole cloud terminal simulation control process, the creation is based on the processor simulation information and entity configuration information corresponding to the cloud terminal that is closer to the required simulation entity (such as a physical mobile phone, a physical computer, etc.), which can avoid the problem of simulation control being separated from the actual environment of the physical simulation and the inaccuracy of simulation control caused by only constructing a virtual software operating environment in the cloud template or directly running business services based on server resources, thereby improving the accuracy of cloud terminal simulation control. The cloud terminal simulation control process is closer to the hardware and software operating environment of the physical device, and can realize the accurate measurement of the performance, state, consumption and other test dimensions of the simulated entity in the cloud terminal; the cloud terminal simulated in the cloud terminal can further improve the accuracy of the simulation because it fully considers the hardware and software configuration environment of the physical processor, etc., and the universality and speciality of the cloud terminal have been greatly improved, which can be closer to the physical terminal operation environment.

[0095] See also Figure 5 , Figure 5 It is a flow chart of another embodiment of a cloud terminal simulation control method proposed in the present application. In the embodiment of the present application, the main focus is on explaining the generation process of each reference processor simulation information stored in the device simulation library.

[0096] Specific:

[0097] S301: Acquire terminal processor information of each of the at least one physical terminal, and acquire platform processor information of the service platform;

[0098] Specifically, in an embodiment of the present application, the at least one physical terminal can serve as a sample collection end of the device simulation library, and by collecting terminal processor information of each physical terminal for reference, reference processor simulation information of the cloud terminal corresponding to the simulated physical terminal is generated on the service platform side.

[0099] The following is an explanation of how to obtain terminal processor information:

[0100] The service platform can configure an information collection toolkit, such as a collection SDK (software development kit), on each physical terminal that serves as a sample collection terminal. For a single physical terminal, the physical terminal obtains the current terminal processor information based on the information collection toolkit. The terminal processor information can be understood as data associated with the physical terminal processor, including but not limited to the physical terminal's processor data, processor configuration data (core binding dimension information, CPUset (processor setting) dimension information, frequency locking dimension information, etc.), processor scheduling data (such as scheduling algorithm dimension information), processor stress test data, etc.;

[0101] Among them, the processor dimension information of the physical terminal can be understood as the number of main collection processors, processor frequency, processor size core information, processor model and other hardware-related information; for example: a physical mobile phone has 8 cores, 4 of which are Qualcomm A75 chips with a core frequency of 3.0GHz, and 4 of which are Qualcomm A55 chips with a core frequency of 1.8GHZ.

[0102] It is understandable that in this application, the purpose of collecting the core binding dimension information, CPUset dimension information, frequency locking dimension information, etc. in the terminal processor information is to provide real feedback to certain terminal manufacturers. In order to improve the performance of UI (user interface) or custom services, there will be tuning operations for certain processes. After the above information is collected, it can be used as a reference for the AIruntime module, and it will also be directly stored locally as the model configuration information in the subsequent processor simulation information, such as stored in the device simulation library of the service platform, for subsequent service platforms to create cloud terminal modules.

[0103] It can be understood that in the present application, the scheduling algorithm dimension information collection can be used for the kernel scheduling strategy (such as the Linux kernel) running at the bottom layer of the operating system of the physical terminal, and further used for service platform reference to ensure that the cloud terminal module corresponding to the cloud terminal is coupled with the processor scheduling behavior on the physical terminal, that is, to ensure a higher consistency.

[0104] It can be understood that in the present application, the processor stress test data is a benchmark operation performed on the processor of the physical terminal, so that the stress test data of the processor core and the performance score data of the CPU in the scenario corresponding to the benchmark operation can be obtained.

[0105] Furthermore, after the physical terminal collects the above-mentioned terminal processor information, it is uploaded to the service platform through the network. Similarly, when there are multiple physical terminals, the terminal processor information of each physical terminal can be collected in the above manner. In some embodiments, the terminal processor information is used for the subsequent model training network to train the processor simulation model for the cloud terminal.

[0106] The following is an explanation of how to obtain platform processor information:

[0107] Optionally, the service platform may be: determining platform processor information of the service platform when the terminal processor information is acquired;

[0108] Among them, the platform processor information can be the platform processor data of the service platform, the platform processor (kernel) configuration data (binding core dimension information, CPUset dimension information, locking frequency dimension information, etc.), the platform processor scheduling data (such as scheduling algorithm dimension information), the platform processor stress test data, etc.; by integrating the platform processor dimension information of the service platform on the basis of the processor environment of the physical device corresponding to the cloud terminal, a processor simulation model that conforms to the physical application environment and the service platform side application environment and is targeted at the cloud terminal can be simulated and trained. After the processor simulation model is trained, it can be passed to the model library management part (such as the model library management unit) contained in the service platform for storage.

[0109] It is understandable that platform processor data collection mainly collects hardware-related information such as the number of CPUs, CPU frequency, CPU size, core signal, CPU model, etc.

[0110] Platform processor (kernel) configuration data collection mainly collects information such as the operating system version and kernel of the service platform. There are some characteristics of the kernel version in the AI ​​training module, which can be used to assist in the training of the AI ​​model.

[0111] The platform processor scheduling data collection is similar to the scope corresponding to the physical terminal, which can ensure the consistency of the scheduling behavior of the processor on the cloud terminal and the real machine.

[0112] Platform processor stress test data can provide stress test data of each processor core and processor score information in various scenarios.

[0113] The service platform can be responsible for transmitting the platform processor information to the model training network through the included communication module to train the processor simulation model for the cloud terminal.

[0114] S302: Based on the terminal processor information and the platform processor information, respectively determine reference processor simulation information for each of the physical terminals.

[0115] Specifically, after obtaining the terminal processor information and the platform processor information, the service platform can input them into the model training network, train the processor simulation model for each cloud terminal based on the model training network, and determine the reference processor simulation information for each of the physical terminals.

[0116] According to some embodiments, the model training network can be characterized based on the AI ​​Runtime module. The AI ​​Runtime module that carries the model training network can be understood as a collection of AI (artificial intelligence) functions. The AI ​​Runtime module can be designed in the form of a plug-in. The AI ​​Runtime module that carries the model training network supports multiple AI frameworks during configuration, including but not limited to the TensorFlow framework, the Torch framework, etc. In this application, the service platform inputs the terminal processor information and the platform processor information into the model training network, such as Figure 6 As shown, Figure 6 This is a schematic diagram of a model training scenario involved in this application. The terminal processor information based on the physical terminal (which may be a real machine as shown in the figure) and the platform processor information based on the current cloud service platform are used as input data sources and input into the model training network for "AI training". For example, in actual applications, it can be input into the AI ​​Runtime module that carries the model training network. After the model training network performs data processing, the data output source corresponding to the current data input source can be output. The data output source is also Figure 6 The reference processor model shown; and so on, the network can be trained based on the model to determine the reference processor simulation information for each of the physical terminals.

[0117] Specifically, determining the reference processor simulation information for each of the physical terminals based on the model training network includes:

[0118] 1. Loading the initial processor simulation model based on the model training network; the initial processor simulation model can be understood as an initial processor template created based on the terminal processor information;

[0119] 2. Performing performance testing on the initial processor simulation model based on the terminal processor information and the platform processor information to determine a performance simulation difference value;

[0120] 3. Based on the simulation difference value, the performance of the initial processor simulation model is adjusted to obtain an adjusted reference processor model for the physical terminal;

[0121] In the specific implementation, the algorithm injection part in the model training network is responsible for loading the processor simulation algorithm, so that the initial processor simulation model can be obtained after loading. Furthermore, in the aforementioned process, expert intervention can be used to further optimize the initial processor simulation model by adjusting the model based on actual conditions.

[0122] In the specific implementation, the algorithm training part in the model training network uses stress testing software to perform performance testing on the real machine and cloud phone. The corresponding model parameters in the initial processor simulation model are adjusted based on the model training network. During the whole process, the service platform can obtain the performance comparison value between the cloud phone and the physical terminal, that is, the aforementioned performance simulation difference value. The performance simulation difference value is used to characterize the difference between the performance of the processor simulation model and the actual processor performance, and can be characterized by the difference characteristic parameters that feedback the difference.

[0123] The parameter sorting part in the model training network is responsible for integrating and matching the data of the processor simulation model simulated on the cloud terminal and the data of the real machine processor fed back on the physical terminal during the whole process. Finally, the reference processor model for the physical terminal is adjusted based on the model training network.

[0124] In the above process, the model training network can automatically train a set of cloud physical machine processors based on the input data (terminal processor information and platform processor information) and use it to simulate the model program data of the real machine processor, that is, the reference processor model. The training of the model training network can be, for example: dynamically adjusting the frequency of the cloud CPU to achieve the same performance effect as the physical CPU. For example, for the physical high-frequency CPU, the algorithm simulation of multi-CPU stacking can be used in the cloud, etc.

[0125] Finally, this set of reference processor models and the terminal processor information of each entity end, such as the core binding strategy, will be saved in the service platform, such as saved in the device simulation library of the service platform. In other words, the process of determining the reference processor simulation information of each entity terminal based on the reference processor model and the terminal processor information can be completed in the above manner.

[0126] S303: Save the simulation information of each reference processor.

[0127] Optionally, the service platform usually adds the reference processor simulation information to the processor model library in the device simulation library. In some embodiments, the reference entity configuration information for each physical terminal can also be obtained. The reference entity configuration information mainly includes a reference simulation system image for each physical terminal. These reference simulation system images are then saved as reference entity configuration information in the system image library in the device simulation library.

[0128] S304: Acquire processor simulation information matching the cloud terminal to be created;

[0129] S305: Acquire entity configuration information corresponding to the cloud terminal to be created, where the entity configuration information is software and hardware configuration information corresponding to the cloud terminal to be created.

[0130] S306: Creating a cloud terminal module corresponding to the cloud terminal to be created based on the entity configuration information and the processor simulation information.

[0131] Among them, S304-S306 can refer to the interpretation of the execution steps in other embodiments of the present application, and will not be repeated here.

[0132] In the embodiment of the present application, the service platform obtains the processor simulation information matching the cloud terminal by responding to the simulation control instruction for the cloud terminal; and obtains the entity configuration information corresponding to the cloud terminal, and then creates the cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information. In the actual application stage, the business service corresponding to the cloud terminal can be run based on the cloud terminal module. In the whole cloud terminal simulation control process, the creation is based on the processor simulation information and entity configuration information corresponding to the cloud terminal that is closer to the required simulation entity, which can avoid the problem of simulation control being separated from the actual environment of the physical simulation and the inaccurate simulation control caused by only constructing a virtual software operating environment in a cloud template or directly running business services based on server resources, thereby improving the accuracy of cloud terminal simulation control. The cloud terminal simulation control process is closer to the hardware and software operating environment of the physical device, and can realize the accurate measurement of the performance, state, consumption and other test dimensions of the simulated entity in the cloud terminal; the cloud terminal simulated in the cloud terminal can further improve the accuracy of the simulation because it fully considers the hardware and software configuration environment of the physical processor, etc. The universality and specialization of the cloud terminal have been greatly improved, which can be closer to the physical terminal operation environment.

[0133] See also Figure 7 , is a schematic diagram of the architecture of a cloud terminal simulation control system provided in an embodiment of the present application. Figure 7 As shown, the cloud terminal simulation control system 10 includes a service platform 120 and a client cluster. The service platform can be used to simulate and control each cloud terminal in the cloud terminal cluster in the platform based on the cloud terminal simulation control method involved in this application.

[0134] The client cluster may include multiple clients, such as Figure 7 As shown, it specifically includes client 1, client 2, ..., client n, where n is an integer greater than 0; for ease of understanding, the embodiment of the present invention is based on Figure 7 The description is made by taking the client terminal 110, the service platform 120 and the client terminal 1 in the example.

[0135] The service platform 120 has a cloud terminal simulation control function and can be a separate server device, such as: rack-mounted, blade, tower, or cabinet-type server equipment, or a workstation, mainframe computer and other hardware devices with strong computing capabilities; it can also be a server cluster composed of multiple servers. The servers in the service cluster can be composed in a symmetrical manner, in which each server has equivalent functions and status in the business link, and each server can provide services to the outside world independently. The independent service can be understood as no need for the assistance of other servers.

[0136] Each client in the client cluster may be an electronic device with communication functions, including but not limited to: wearable devices, handheld devices, personal computers, tablet computers, vehicle-mounted devices, smart phones, computing devices or other processing devices connected to wireless modems, etc. Electronic devices may be called different names in different networks, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), terminal equipment in 5G network or future evolution network, etc.

[0137] The cloud terminal cluster controlled by the service platform simulation may include multiple cloud terminals, such as Figure 7 As shown, it specifically includes cloud terminal 1, cloud terminal 2, ..., cloud terminal n, where n is an integer greater than 0; wherein the cloud terminal is different from the aforementioned client in that the cloud terminal is not a physical device, but a virtual terminal simulated in the platform by the service platform based on the cloud terminal simulation control method involved in this application.

[0138] The clients in the client cluster and the service platform 120 communicate interactively through a network, which may be a wireless network or a wired network. Wireless networks include but are not limited to cellular networks, wireless local area networks, infrared networks or Bluetooth networks, and wired networks include but are not limited to Ethernet, universal serial bus (USB) or controller area network.

[0139] Further, the communication connection between the user's client and the service platform 120 can usually be a communication connection service established by using a preset communication architecture, wherein the communication architecture refers to a communication structure for data communication, and the communication architecture defines various aspects of the data network communication system, including the type of communication interface, the network protocol used, the data framework implemented, the type of communication wiring, etc. Commonly used communication architectures can be TCP / IP architecture, Netty architecture, C / S architecture, SOA architecture, etc. For example, one of the communication architectures can be to use the Netty framework based on java open source, and cooperate with WebSocket technology to establish a communication connection between the service platform and the user client in the communication network, and realize the interaction of communication data between the two ends based on the communication connection. Among them, the type of communication connection is different in different implementation scenarios, such as a long communication connection can be established in some implementation scenarios, and a short communication connection can be established in some implementation scenarios; preferably, in the present application, the communication connection between the client and the service platform in the cloud terminal simulation control scenario can be a short connection or a long connection, and the specific communication connection mode is determined based on the interaction type between the two ends.

[0140] The following is a detailed explanation of the communication link based on the long connection and the communication connection based on the short connection, as follows:

[0141] The established communication connection may be a communication link of an http long connection or a communication link of an http short connection.

[0142] A long connection means that multiple data packets can be sent continuously on a connection. If no data packet is sent during the connection, both parties need to send a link detection packet.

[0143] The operation steps of a long connection are: establish connection - data transmission...(maintain connection)...data transmission - close connection.

[0144] A short connection means that when the two communicating parties have data exchange, a connection is established. After the data is sent, the connection is disconnected, that is, each connection only completes the sending of one business.

[0145] The operation steps of short connection are: establish connection - data transmission - close connection...establish connection - data transmission - close connection.

[0146] Long connections are mostly used for frequent operations and point-to-point communication. Each communication connection (such as TCP connection) requires a three-step handshake, which takes time. If each operation is a short connection, the processing speed will be much lower. Therefore, it is not disconnected after each operation. The next time the data packet is processed, it will be OK without establishing a TCP connection. For example: the database connection uses a long connection. If short connections are used for frequent communication, socket errors will occur, and frequent socket creation is also a waste of resources.

[0147] HTTP services like WEB websites generally use short links, because long links consume certain resources for the server, and short links save more resources for frequent connections of tens of thousands or even hundreds of millions of clients like WEB websites. If long links are used and there are tens of thousands of users at the same time, if each user occupies a connection, you can imagine how much time it would take. Therefore, when the concurrency is large but each user does not need to operate frequently, it is better to use short links.

[0148] Long connections can save a lot of TCP establishment and closing operations, reduce waste, and save time. In practical applications, when the communication data transmitted by the communication link is a real-time online scenario with high requirements for communication transmission quality, a communication link based on long connections can be used. At this time, long connections are relatively simple to manage for the service platform, and all existing connections are useful connections, without the need for additional control measures.

[0149] In addition, the cloud terminal simulation control system embodiment provided in the above embodiment belongs to the same concept as the cloud terminal simulation control method in some embodiments, and its embodiment and implementation process are detailed in the method embodiment. For example, client 1 interacts with service platform 120, and during the interaction, service platform 120 can simulate and control cloud terminal 1 in the cloud terminal cluster by executing the cloud terminal simulation control method involved in the present application; for example, client 2 interacts with service platform 120, and during the interaction, service platform 120 can simulate and control cloud terminal 2 in the cloud terminal cluster by executing the cloud terminal simulation control method involved in the present application;... For example, client n interacts with service platform 120, and during the interaction, service platform 120 can simulate and control cloud terminal n in the cloud terminal cluster by executing the cloud terminal simulation control method involved in the present application;

[0150] Furthermore, the cloud terminal simulation control system embodiment provided in the above embodiment and the cloud terminal simulation control method in some embodiments belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.

[0151] The following will be combined Figure 8, the cloud terminal simulation control device provided in the embodiment of the present application is introduced in detail. It should be noted that the cloud terminal simulation control device shown in 8 is used to execute the present application Figure 1 to Figure 7 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 to Figure 6 The embodiment shown.

[0152] See also Figure 8 , which shows a schematic diagram of the structure of the cloud terminal simulation control device of an embodiment of the present application. The cloud terminal simulation control device 1 can be implemented as all or part of the user terminal through software, hardware or a combination of both. According to some embodiments, the cloud terminal simulation control device 1 includes an information determination module 11 and a cloud terminal creation module 12, which are specifically used to:

[0153] The information determination module 11 is used to obtain the processor simulation information matching the cloud terminal to be created and to obtain the entity configuration information corresponding to the cloud terminal to be created;

[0154] A cloud terminal creation module 12, configured to create a cloud terminal module corresponding to the cloud terminal based on the entity configuration information and the processor simulation information;

[0155] Optional, such as Fig. 9 As shown, the information determination module 11 includes:

[0156] The model information determining unit 111 is used to obtain creation requirement information for a cloud terminal to be created, and determine processor simulation information corresponding to the creation requirement information;

[0157] The configuration information determining unit 112 is used to determine the entity configuration information corresponding to the cloud terminal based on the creation requirement information.

[0158] Optionally, the model information determining unit 111 is specifically configured to:

[0159] Obtaining a physical device type for a cloud terminal to be created, and determining processor simulation information corresponding to the physical device type; and / or,

[0160] Obtaining a custom device configuration for a cloud terminal to be created, and determining processor simulation information matching the custom device configuration;

[0161] The processor simulation information includes a processor simulation model and model configuration information for the processor simulation model.

[0162] Optionally, the configuration information determining unit 112 is specifically configured to:

[0163] Performing information matching processing on the creation requirement information and at least one reference configuration information to obtain target configuration information after information matching processing;

[0164] The target configuration information is used as entity configuration information for the cloud terminal.

[0165] Optional, such as Fig.10 As shown, the device 1 also includes:

[0166] The simulation library maintenance module 14 is used to determine reference processor simulation information for at least one physical terminal and save each reference processor simulation information.

[0167] The step of obtaining processor simulation information matching the cloud terminal to be created includes:

[0168] Processor simulation information matching the cloud terminal to be created is obtained from each of the reference processor simulation information.

[0169] The reference processor simulation information includes a reference processor simulation model and model configuration information for the reference processor simulation model.

[0170] Optionally, the simulation library maintenance module 14 is specifically used for:

[0171] Acquire terminal processor information of each of the at least one physical terminal, and acquire platform processor information of the service platform; the terminal processor information includes at least one of terminal processor data, terminal processor configuration data, terminal processor scheduling data, and terminal processor stress test data; the platform processor information includes at least one of platform processor data, platform processor configuration data, platform processor scheduling data, and platform processor stress test data;

[0172] Based on the terminal processor information and the platform processor information, reference processor simulation information for each of the physical terminals is determined respectively.

[0173] Optionally, the simulation library maintenance module 14 is specifically used for:

[0174] An information collection toolkit is deployed on at least one physical terminal, and terminal processor information on each of the physical terminals is acquired based on the information collection toolkit.

[0175] Optionally, the simulation library maintenance module 14 is specifically used for:

[0176] The terminal processor information and the platform processor information are respectively input into a model training network, and reference processor simulation information for each of the physical terminals is determined based on the model training network.

[0177] Optionally, the simulation library maintenance module 14 is specifically used for:

[0178] Loading an initial processor simulation model based on the model training network;

[0179] Performing performance testing on the initial processor simulation model based on the terminal processor information and the platform processor information to determine a performance simulation difference value;

[0180] Performing performance adjustment on the initial processor simulation model based on the simulation difference value to obtain an adjusted reference processor model for the physical terminal;

[0181] Based on the reference processor model and the terminal processor information, reference processor simulation information of each of the physical terminals is determined respectively.

[0182] Optional, such as Fig.10 As shown, the device 1 also includes:

[0183] The service running module 13 is used to run the business service corresponding to the cloud terminal based on the cloud terminal module.

[0184] Optionally, the service running module 13 is specifically used for:

[0185] Starting and running the business service corresponding to the cloud terminal based on the cloud terminal module, and collecting model status information of the cloud terminal module;

[0186] Model adjustment is performed on the processor simulation model included in the cloud terminal module based on the model status information.

[0187] Optionally, the device 1 is specifically used for:

[0188] Inputting the module state information into a model training network, and outputting a model state adjustment parameter for the cloud terminal module, wherein the model state adjustment parameter is a model adjustment parameter for a processor simulation model of the cloud terminal module;

[0189] Model parameters of the processor simulation model are adjusted based on the model state adjustment parameters.

[0190] It should be noted that the cloud terminal simulation control device provided in the above embodiment only uses the division of the above functional modules as an example when executing the cloud terminal simulation control method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the cloud terminal simulation control device provided in the above embodiment and the cloud terminal simulation control method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0191] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0192] The present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 1 to Figure 7 The cloud terminal simulation control method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 to Figure 7 The specific description of the illustrated embodiment will not be repeated here.

[0193] The present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figure 1 to Figure 7 The cloud terminal simulation control method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 to Figure 7 The specific description of the illustrated embodiment will not be repeated here.

[0194] See also Fig.11 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.11 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0195] The communication bus 1002 is used to realize the connection and communication between these components.

[0196] The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

[0197] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0198] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0199] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Fig.11 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a cloud terminal simulation control application.

[0200] exist Fig.11In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the cloud terminal simulation control application stored in the memory 1005, and specifically perform the following operations:

[0201] Get the processor simulation information that matches the cloud terminal to be created;

[0202] Acquire entity configuration information corresponding to the cloud terminal to be created, where the entity configuration information is software and hardware configuration information corresponding to the cloud terminal to be created;

[0203] A cloud terminal module corresponding to the cloud terminal to be created is created based on the entity configuration information and the processor simulation information.

[0204] In one embodiment, when the processor 1001 executes the steps of obtaining the processor simulation information matching the cloud terminal to be created and obtaining the entity configuration information corresponding to the cloud terminal to be created, the processor 1001 specifically performs the following steps:

[0205] Acquire creation requirement information for a cloud terminal to be created, and determine processor simulation information corresponding to the creation requirement information;

[0206] Entity configuration information corresponding to the cloud terminal is determined based on the creation requirement information.

[0207] In one embodiment, the processor 1001 obtains creation requirement information for a cloud terminal to be created, and when determining processor simulation information corresponding to the creation requirement information, specifically performs the following steps:

[0208] Obtaining a physical device type for a cloud terminal to be created, and determining processor simulation information corresponding to the physical device type; and / or,

[0209] Obtaining a custom device configuration for a cloud terminal to be created, and determining processor simulation information matching the custom device configuration;

[0210] The processor simulation information includes a processor simulation model and model configuration information for the processor simulation model.

[0211] In one embodiment, when the processor 1001 determines the entity configuration information corresponding to the cloud terminal based on the creation requirement information, the processor 1001 specifically performs the following steps:

[0212] Performing information matching processing on the creation requirement information and at least one reference configuration information to obtain target configuration information after information matching processing;

[0213] The target configuration information is used as entity configuration information for the cloud terminal.

[0214] In one embodiment, when executing the cloud terminal simulation control method, the processor 1001 further specifically performs the following steps:

[0215] Determine reference processor simulation information for at least one physical terminal, and save each of the reference processor simulation information;

[0216] The step of obtaining processor simulation information matching the cloud terminal to be created includes:

[0217] Processor simulation information matching the cloud terminal to be created is obtained from each of the reference processor simulation information.

[0218] The reference processor simulation information includes a reference processor simulation model and model configuration information for the reference processor simulation model.

[0219] In one embodiment, the processor 1001, when executing the determining of reference processor simulation information for at least one physical terminal, includes:

[0220] Acquire terminal processor information of each of the at least one physical terminal, and acquire platform processor information of the service platform; the terminal processor information includes at least one of terminal processor data, terminal processor configuration data, terminal processor scheduling data, and terminal processor stress test data; the platform processor information includes at least one of platform processor data, platform processor configuration data, platform processor scheduling data, and platform processor stress test data;

[0221] Based on the terminal processor information and the platform processor information, reference processor simulation information for each of the physical terminals is determined respectively.

[0222] In one embodiment, when the processor 1001 executes the step of obtaining the terminal processor information of each of the at least one physical terminal, the processor 1001 specifically performs the following steps:

[0223] An information collection toolkit is deployed on at least one physical terminal, and terminal processor information on each of the physical terminals is acquired based on the information collection toolkit.

[0224] In one embodiment, when the processor 1001 determines the reference processor simulation information for each of the physical terminals based on the terminal processor information and the platform processor information, the processor 1001 specifically performs the following steps:

[0225] The terminal processor information and the platform processor information are respectively input into a model training network, and reference processor simulation information for each of the physical terminals is determined based on the model training network.

[0226] In one embodiment, when the processor 1001 determines the reference processor simulation information for each of the physical terminals based on the model training network, it specifically performs the following steps:

[0227] Loading an initial processor model based on the model training network;

[0228] Performing performance testing on the initial processor model based on the terminal processor information and the platform processor information to determine performance difference parameters;

[0229] Performing performance adjustment on the initial processor model based on the performance difference parameter to obtain an adjusted reference processor model for the physical terminal;

[0230] Based on the reference processor model and the terminal processor information, reference processor simulation information of each of the physical terminals is determined respectively.

[0231] In one embodiment, the processor 1001 further executes the step of running the business service corresponding to the cloud terminal based on the cloud terminal module;

[0232] In one embodiment, when the processor 1001 executes the business service corresponding to the cloud terminal based on the cloud terminal module, it specifically performs the following steps:

[0233] Running the business service corresponding to the cloud terminal based on the cloud terminal module, and collecting module status information of the cloud terminal module;

[0234] Model parameters of the processor simulation model of the cloud terminal module are adjusted based on the module status information.

[0235] In one embodiment, when the processor 1001 performs the step of adjusting the model parameters of the processor simulation model of the cloud terminal module based on the module status information, the processor 1001 specifically performs the following steps:

[0236] Inputting the module state information into a model training network, and outputting a model state adjustment parameter for the cloud terminal module, wherein the model state adjustment parameter is a model adjustment parameter for a processor simulation model of the cloud terminal module;

[0237] Model parameters of the processor simulation model are adjusted based on the model state adjustment parameters.

[0238] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0239] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A cloud terminal simulation control method, characterized in that: Applied to a service platform, the method comprises: Acquire processor simulation information matching the cloud terminal to be created; wherein the processor simulation information includes a processor simulation model; Acquire entity configuration information corresponding to the cloud terminal to be created, wherein the entity configuration information is software and hardware configuration information corresponding to the cloud terminal to be created; wherein the entity configuration information is a target simulation system image for the cloud terminal; Creating a cloud terminal module corresponding to the cloud terminal to be created based on the entity configuration information and the processor simulation information; The step of creating a cloud terminal module corresponding to the cloud terminal to be created based on the entity configuration information and the processor simulation information includes: creating the cloud terminal module based on the target simulation system image and the processor simulation model.

2. The method according to claim 1, characterized in that The step of obtaining processor simulation information matching the cloud terminal to be created and obtaining entity configuration information corresponding to the cloud terminal to be created includes: Acquire creation requirement information for a cloud terminal to be created, and determine processor simulation information corresponding to the creation requirement information; Entity configuration information corresponding to the cloud terminal is determined based on the creation requirement information.

3. The method according to claim 2, characterized in that The obtaining creation requirement information for a cloud terminal to be created and determining processor simulation information corresponding to the creation requirement information includes: Obtaining a physical device type for a cloud terminal to be created, and determining processor simulation information corresponding to the physical device type; and / or, Obtaining a custom device configuration for a cloud terminal to be created, and determining processor simulation information matching the custom device configuration; The processor simulation information includes model configuration information for the processor simulation model.

4. The method according to claim 2, characterized in that: The determining the entity configuration information corresponding to the cloud terminal based on the creation requirement information includes: Performing information matching processing on the creation requirement information and at least one reference configuration information to obtain target configuration information after information matching processing; The target configuration information is used as entity configuration information for the cloud terminal.

5. The method according to claim 1, characterized in that The method further comprises: Determine reference processor simulation information for at least one physical terminal, and save each of the reference processor simulation information; The step of obtaining processor simulation information matching the cloud terminal to be created includes: Acquire processor simulation information matching the cloud terminal to be created from each of the reference processor simulation information; The reference processor simulation information includes a reference processor simulation model and model configuration information for the reference processor simulation model.

6. The method according to claim 5, characterized in that The determining of reference processor simulation information for at least one physical terminal includes: Acquire terminal processor information of each of the at least one physical terminal, and acquire platform processor information of the service platform; the terminal processor information includes at least one of terminal processor data, terminal processor configuration data, terminal processor scheduling data, and terminal processor stress test data; the platform processor information includes at least one of platform processor data, platform processor configuration data, platform processor scheduling data, and platform processor stress test data; Based on the terminal processor information and the platform processor information, reference processor simulation information for each of the physical terminals is determined respectively.

7. The method according to claim 6, characterized in that The acquiring terminal processor information of each of the at least one physical terminal includes: An information collection toolkit is deployed on at least one physical terminal, and terminal processor information on each of the physical terminals is acquired based on the information collection toolkit.

8. The method according to claim 6, characterized in that The determining, based on the terminal processor information and the platform processor information, reference processor simulation information for each of the physical terminals, respectively, includes: The terminal processor information and the platform processor information are respectively input into a model training network, and reference processor simulation information for each of the physical terminals is determined based on the model training network.

9. The method according to claim 8, characterized in that The determining the reference processor simulation information for each of the physical terminals based on the model training network includes: Loading an initial processor model based on the model training network; Performing performance testing on the initial processor model based on the terminal processor information and the platform processor information to determine performance difference parameters; Performing performance adjustment on the initial processor model based on the performance difference parameter to obtain an adjusted reference processor model for the physical terminal; Based on the reference processor model and the terminal processor information, reference processor simulation information of each of the physical terminals is determined respectively.

10. The method according to claim 1, characterized in that The method further comprises: The business service corresponding to the cloud terminal is run based on the cloud terminal module.

11. The method according to claim 10, characterized in that The running of the business service corresponding to the cloud terminal based on the cloud terminal module includes: Running the business service corresponding to the cloud terminal based on the cloud terminal module, and collecting module status information of the cloud terminal module; Model parameters of the processor simulation model of the cloud terminal module are adjusted based on the module status information.

12. The method according to claim 11, characterized in that The adjusting model parameters of the processor simulation model of the cloud terminal module based on the module status information includes: Inputting the module state information into a model training network, and outputting a model state adjustment parameter for the cloud terminal module, wherein the model state adjustment parameter is a model adjustment parameter for a processor simulation model of the cloud terminal module; Model parameters of the processor simulation model are adjusted based on the model state adjustment parameters.

13. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 12.

Images