Vehicle-mounted flexible computing equalization method and related device

Abstract

The present application belongs to the technical field of vehicle-mounted resource allocation, and discloses a vehicle-mounted flexible computing balancing method and related device, which comprises the following steps: obtaining a user portrait based on a vehicle-end intelligent observer and a cloud-end large model server; evaluating the use priority of a function according to the user portrait and outputting function priority information; and dynamically adjusting the resource allocation of the function in combination with the function priority information and the load rate information of each vehicle-mounted controller. The present application can realize intelligent and flexible allocation of computing load demand in each domain controller and central computing unit, dynamically divide the computing load to each controller by analyzing intelligent scene and identifying the resource demand of the user, and realize full utilization of computing resources and decoupling between software and hardware.

Description

Technical Field

[0001] This invention belongs to the field of vehicle resource allocation technology, and specifically relates to a vehicle-mounted flexible computational balancing method and related devices. Background Technology

[0002] The explosive growth of automotive functions has directly led to a major contradiction in current vehicle software development: the existing vehicle architecture, computing, and networking resources are no longer sufficient to meet the demands of this functional growth. While the evolution of vehicle electronic and electrical architecture towards centralization, service-oriented architecture, and virtualization, the application of automotive Ethernet, and the steady improvement of chip computing power have alleviated this contradiction to some extent, vehicle development is a market-driven activity and is also constrained by factors such as cost. Therefore, measures to make fuller and more effective use of current resources are always invaluable. Currently, the relationship between vehicle hardware and software remains statically bound, and the computational load between controllers varies greatly in different scenarios, resulting in many idle computing resources not being fully utilized and low resource utilization. Summary of the Invention

[0003] The purpose of this invention is to provide an on-board flexible computational equalization method and related device to solve the problem of low utilization rate of vehicle resources.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] In a first aspect, the present invention provides an on-board flexible computational equalization method, comprising:

[0006] Based on vehicle-side intelligent observers and cloud-based large model servers, user profiles are obtained.

[0007] Based on user profiles, prioritize the use of features and output feature priority information;

[0008] By combining functional priority information and load rate information of each vehicle controller, the resource allocation of functions is dynamically adjusted.

[0009] Furthermore, based on the vehicle-side intelligent observer and the cloud-based large model server, user profiles are obtained, including:

[0010] The vehicle-mounted intelligent observer collects user usage habits and functional interaction frequency information through data embedding, and uploads the collected information to the cloud big model to build user profiles; the big model uses real-time data to dynamically and automatically learn, build, mine and update the user's deep-level characteristics.

[0011] Furthermore, user usage habits and frequency of functional interactions include: basic user information, user behavior data, user preference information, and user social information.

[0012] Further, the use priority of the function is evaluated according to the user portrait, and function priority information is output, including:

[0013] The user portrait information is fed back to the vehicle end, user behavior data of the user for the vehicle function is derived, the priority is sorted based on the time of using the function and the use frequency of the function in the user behavior data, the function priority information is output, and the personalized demand of the user for the computing resource is obtained.

[0014] Further, the load rate information of each vehicle-mounted controller is collected through a load module, the load module includes a load balancing server and a load balancing client, the load balancing server collects the data of the current load rate of each controller reported by the load balancing client; the load balancing client collects the resource load information of the current controller through a virtual abstraction layer, and undertakes the computing task distributed by the load balancing server, and distributes different types of computing tasks to appropriate virtual machine resources.

[0015] Further, the resource allocation of the function is dynamically adjusted in combination with the function priority information and the load rate information of each vehicle-mounted controller, including:

[0016] More computing resources are allocated to the function with a higher use frequency, and the resource allocation is as follows:

[0017] The function with a high priority is allocated a high network priority and a high forwarding priority of the switch;

[0018] The process associated with the function with a high priority is allocated a higher priority;

[0019] The survival rate of the function with a high priority in the memory is improved, and the starting time of the function is improved.

[0020] Further, the load rate of each controller is dynamically monitored through the virtual abstraction layer while the resource allocation is performed; when the load rate demand difference between different controllers is greater than a set threshold, resource balancing scheduling is initiated, and a newly triggered function is allocated to a controller with a low load rate demand, and the load demand between the controllers is coordinated.

[0021] In a second aspect, the present application provides a vehicle-mounted flexible computing balancing system, comprising:

[0022] A data acquisition module is configured to acquire a user portrait based on a vehicle end intelligent observer and a cloud end large model server;

[0023] A priority evaluation module is configured to evaluate the use priority of the function according to the user portrait, and output function priority information;

[0024] A resource allocation module is configured to dynamically adjust the resource allocation of the function in combination with the function priority information and the load rate information of each vehicle-mounted controller.

[0025] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle-mounted flexible computing balancing method when executing the computer program.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, wherein the computer program implements the steps of the vehicle-mounted flexible computing balancing method when executed by a processor.

[0027] Compared with the prior art, the present application has the following technical effects:

[0028] The present application can realize intelligent flexible distribution of computing load demand among various domain controllers and central computing units through a vehicle-mounted flexible computing balancing method, dynamically distribute computing load to various controllers by analyzing intelligent scene to identify user resource demand, and realize full utilization of computing resources and decoupling between software and hardware.

[0029] Specifically, by combining the vehicle-end intelligent observer and the cloud-end large model server, personalized resource distribution based on user portrait is realized to improve the computing efficiency of the vehicle-mounted system and the user experience.

[0030] The vehicle-end intelligent observer and the cloud-end large model server collect user usage habits and function interaction frequency information, construct a user portrait, and evaluate the usage priority of functions according to the user portrait. This method can more accurately understand the personalized needs of users, thereby providing more vehicle-mounted services that meet their usage habits.

[0031] The resource allocation of functions is dynamically adjusted in combination with the function priority information and the load rate information of each vehicle-mounted controller. This method can ensure that high-priority functions obtain sufficient computing resources, while avoiding low-priority functions from occupying too many resources, thereby improving the overall performance and response speed of the system.

[0032] Through the cooperative work of the load balancing server and the load balancing client, the load rate information of each vehicle-mounted controller is collected in real time, and computing tasks are dynamically allocated according to the load condition. This method can ensure efficient utilization of computing resources and avoid waste and idleness of resources.

[0033] By improving the survival rate of high-priority functions in memory, the loading time required when these functions are started again can be significantly reduced, thereby improving the user experience.

[0034] For high-priority functions, high network priority and switch forwarding priority are assigned, which can reduce network delay and ensure real-time and stability of data transmission.

[0035] In summary, this technical solution combines on-board intelligent observers and cloud-based large model servers to achieve personalized resource allocation based on user portraits, effectively improving the computing efficiency and user experience of the vehicle-mounted system. At the same time, this technical solution also has the advantages of efficient computing resource utilization, improved function startup time, network optimization, scalability, and maintainability. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 The flowchart of the present application.

[0037] Figure 2 The logic block diagram of user portrait analysis based on big data.

[0038] Figure 3 The schematic diagram of computing balance scheduling result.

[0039] Figure 4 The working timing diagram of the flexible computing balance system. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0041] In the description of the present application, it should be understood that the terms "include" and "contain" indicate the presence of described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0042] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0043] It should be further understood that the term "and / or" as used in the specification and in the claims, if any, means any of the conjunctive or disjunctive sense, i.e., it represents a combination of one or more of the associated listed items and includes all possible combinations, e.g., A and / or B can mean only A, or only B, or both A and B. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.

[0044] It should be understood that, although the terms first, second, third, etc. can be employed in the embodiments of the application to describe various ranges, etc., these ranges should not be limited to these terms. These terms are only used to distinguish one range from another. For example, a first range can be termed a second range without departing from the scope of the embodiments of the application, and similarly, a second range can be termed a first range.

[0045] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]."

[0046] Various structural diagrams according to the disclosed embodiments of the application are shown in the accompanying drawings. These diagrams are not drawn to scale, in which certain details are shown in a somewhat exaggerated manner for the purpose of clarity and understanding, and certain details can be omitted. The shapes of various regions, layers shown in the drawings, and their relative sizes and positional relationships are only exemplary, and in actuality, they can deviate due to manufacturing tolerances or technical limitations, and a person skilled in the art can additionally design regions / layers with different shapes, sizes, relative positions according to actual needs.

[0047] Embodiment 1, please refer to Figure 1 The application provides a vehicle-mounted flexible computing balancing method, comprising:

[0048] Based on the vehicle-side intelligent observer and the cloud-side large model server, a user portrait is obtained;

[0049] According to the user portrait, a use priority of a function is evaluated, and function priority information is output;

[0050] In combination with the function priority information and load rate information of each vehicle-mounted controller, resource allocation of the function is dynamically adjusted.

[0051] The application can realize intelligent flexible distribution of computing load demand in various domain controllers and central computing units, dynamically divide computing load to various controllers by analyzing intelligent scene to identify user's demand for resources, and realize full utilization of computing resources and decoupling between software and hardware.

[0052] In embodiment 2, the application provides a vehicle-mounted flexible computing balancing method, which specifically comprises the following steps:

[0053] Firstly, the vehicle-end intelligent observer collects user's usage habits and function interaction frequency and the like, mainly including user basic information, user behavior data, user preference information and user social information, wherein the behavior data such as the time of using a certain function and the usage frequency of the function are the core data of the flexible computing balancing technology; secondly, the user data collected by the vehicle-end intelligent observer is uploaded to a cloud-side large model, a user portrait is constructed based on a big data and deep learning artificial intelligence model, and the user's deep features and demands are dynamically and automatically learned, constructed, mined and updated by using real-time data, so as to improve the accuracy and coverage of the user portrait; thirdly, the user portrait information is fed back to the vehicle-end, the function clusters that the user likes and the function clusters that the user does not often use are screened out according to the user portrait, the functions are evaluated in terms of usage priority according to the user's preference for the functions, and then the personalized demand of the user for computing resources is obtained according to the priority evaluation result; the computing balancing subsystem receives the function priority information and the load rate information of each controller output by the intelligent scene observer, dynamically adjusts the resource allocation of the functions according to the priority information, and allocates more computing resources to the functions with higher usage frequency, so as to improve the experience of the functions; the resource allocation mainly involves the following aspects:

[0054] 1. The functions with high priority are allocated higher network priority, the switches are allocated higher forwarding priority, and the data interaction rate is improved;

[0055] 2. The processes associated with the functions with high priority are allocated higher priority, and the data processing rate is improved;

[0056] 3. The survival rate of the functions with high priority in the memory is improved, and the starting time of the functions is improved;

[0057] Meanwhile, the virtual abstraction subsystem dynamically monitors the load rate of each controller; when the load rate demand difference between different controllers is greater than a certain threshold value, the load balancing subsystem initiates resource balancing scheduling, the newly triggered functions are allocated to the controllers with lower load rate demand, the computing load demand between the controllers is coordinated, the imbalance of the computing resources between the controllers is reduced, and the overall function experience is improved.

[0058] Computing balancing system

[0059] Load balancing is a computer network technology widely used to distribute load among multiple computers, network connections, CPUs, disk drives, or other resources to optimize resource utilization, maximize throughput, minimize response time, and avoid overload. In the vehicle controller, there is also a phenomenon of uneven load between controllers in different scenarios. Reducing this imbalance between controllers and maximizing resource utilization can greatly reduce costs and improve user experience. The load balancing system mainly includes a load balancing server and a load balancing client. The load balancing server collects data on the current load rate of each controller reported by the load balancing client and the function priority information output by the intelligent scene observer, allocates computing resources to user functions according to the load balancing algorithm, and maximizes the use of computing resources and the best combination of user usage habits.

[0060] The load balancing client collects the current resource load information of the controller through the virtual abstraction layer and undertakes the computing tasks allocated by the load balancing server, distributing different types of computing tasks to appropriate virtual machine resources. The virtual machine abstraction layer can automatically subscribe and publish the services required by the computing task through the service list when the computing task is published, so as to quickly start the computing task.

[0061] Each controller needs to have virtualization technology, allowing real-time or non-real-time virtual machine containers to be deployed on each controller. Vehicle services can be deployed in virtual machine containers, and virtual machine containers can undertake standardized computing tasks. Standardized computing tasks include a Manifest declaration file that publishes the services required and provided by the computing task, as well as information such as CPU resources and storage. The virtual abstraction layer automatically subscribes and publishes the required services by parsing the file information, enabling the computing task to be quickly started and automatically adapted to resources.

[0062] User profiling, or the labeled description of users, is an effective tool that can help us analyze user needs, preferences, behaviors, and values in depth. However, with the increase in user data and the complexity of traditional user profiling methods, it has become difficult to meet our needs. In the era of intelligent vehicles integrating vehicles and the cloud, large models, or artificial intelligence models based on large-scale data and deep learning, can improve the accuracy, reduce the cost, and improve the real-time performance of user profiling.

[0063] The intelligent scene observer system analyzes the personalized needs of the user, and accurately and timely obtains the user portrait information, by two parts: a vehicle-end intelligent observer and a cloud-end large model server. The vehicle-end intelligent observer collects user usage habits and function interaction frequency information through data burying points, mainly including: user basic information, user behavior data, user preference information, and user social information, wherein the user behavior data of the usage function is the core data of the flexible computing balancing technology. The user data is uploaded to the cloud-end large model to construct the user portrait of the user. The large model uses large-scale data, complex algorithms, real-time data, dynamic and automatic learning, construction, mining and updating of deep features and needs of the user, to improve the quality and coverage of the user portrait. The user portrait information is fed back to the vehicle-end, the usage priority of the user for the function is derived, and then the personalized needs of the user for the computing resources are obtained.

[0064] In another embodiment of the present application, a vehicle-mounted flexible computing balancing system is provided, which can be used to implement the above-mentioned vehicle-mounted flexible computing balancing method. Specifically, the system comprises:

[0065] A data acquisition module is configured to acquire a user portrait based on the vehicle-end intelligent observer and the cloud-end large model server.

[0066] A priority evaluation module is configured to evaluate the usage priority of the function according to the user portrait, and output function priority information.

[0067] A resource allocation module is configured to dynamically adjust the resource allocation of the function in combination with the function priority information and the load rate information of each vehicle-mounted controller.

[0068] The division of the modules in the embodiments of the present application is illustrative, and is only a logical function division. In actual implementation, another division mode can be used. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0069] In another embodiment of the present application, a computer device is provided, which comprises a processor and a memory, the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, and are suitable for implementing one or more instructions, and are particularly suitable for loading and executing one or more instructions in the computer storage medium to implement a corresponding method process or a corresponding function; the processor in the embodiments of the present application can be used for the operation of the vehicle-mounted flexible computing balancing method.

[0070] In another embodiment of the present application, the present application further provides a storage medium, specifically a computer readable storage medium (Memory), which is a memory device in a computer device, and is configured to store programs and data. It can be understood that the computer readable storage medium herein can include an internal storage medium in the computer device, and of course can also include an expansion storage medium supported by the computer device. The computer readable storage medium provides a storage space, and the storage space stores an operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory. One or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the vehicle-mounted flexible computing balancing method in the above embodiments.

[0071] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0072] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0073] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0075] Finally, it should be noted that the above-mentioned embodiments are merely intended for describing the technical solutions of the present application, but not for limiting it. Although the present application is described in detail with reference to the above embodiments, those skilled in the art should understand that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement without departing from the spirit and scope of the present application should be covered in the protection scope of the claims of the present application.

Claims

1. A method for in-vehicle flexible computing equalization, the method comprising: The method comprises the following steps: Based on the intelligent observer at the vehicle end and the large model server in the cloud, the user portrait is obtained; According to the user portrait, the use priority of the function is evaluated, and the function priority information is output; The resource allocation of the function is dynamically adjusted by combining the function priority information and the load rate information of each vehicle-mounted controller; According to the user portrait, the use priority of the function is evaluated, and the function priority information is output, which comprises: The user portrait information is fed back to the vehicle end, the user behavior data of the user for the vehicle function is exported, the use function time and the use frequency of the function in the user behavior data are prioritized, the function priority information is output, and the personalized demand of the user for the computing resource is obtained; The resource allocation of the function is dynamically adjusted by combining the function priority information and the load rate information of each vehicle-mounted controller, which comprises: More computing resources are allocated to the function with high use frequency, and the resource allocation is as follows: The function with high priority is allocated high network priority and high forwarding priority of the switch; The process associated with the function with high priority is allocated higher priority; The survival rate of the function with high priority in the memory is improved, and the starting time of the function is improved.

2. The method of claim 1, wherein, Based on the intelligent observer at the vehicle end and the large model server in the cloud, the user portrait is obtained, which comprises: The intelligent observer at the vehicle end collects the use habit and function interaction frequency information of the user through data burying point information, uploads the collected information to the large model in the cloud, and constructs the user portrait; the large model uses real-time data to dynamically and automatically learn, construct, mine and update the deep features of the user.

3. The method of claim 2, wherein, The use habit and function interaction frequency information of the user comprises: user basic information, user behavior data, user preference information and user social information.

4. The method of claim 1, wherein, The load rate information of each vehicle-mounted controller is collected by a load module, the load module comprises a load balancing server and a load balancing client, and the load balancing server collects the current load rate data of each controller reported by the load balancing client; The load balancing client collects the resource load information of the current controller through a virtual abstraction layer, and undertakes the computing task allocated by the load balancing server, and allocates different types of computing tasks to appropriate virtual machine resources.

5. The method of claim 1, wherein, The resource allocation is dynamically monitored through the virtual abstraction layer; when the load rate demand difference between different controllers is greater than a set threshold, resource balancing scheduling is initiated, and the newly triggered function is allocated to the controller with low load rate demand, and the load demand between the controllers is coordinated.

6. An in-vehicle flexible computing balancing system for implementing the steps of the in-vehicle flexible computing balancing method according to any one of claims 1 to 5, characterized in that, The method comprises the following steps: A data acquisition module is used to obtain the user portrait based on the intelligent observer at the vehicle end and the large model server in the cloud; A priority evaluation module is used to evaluate the use priority of the function according to the user portrait, and output the function priority information; A resource allocation module is used to dynamically adjust the resource allocation of the function by combining the function priority information and the load rate information of each vehicle-mounted controller.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the vehicle-mounted flexible computing balancing method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by the processor to realize the steps of the vehicle-mounted flexible computing balancing method according to any one of claims 1 to 5.

Images