Data computing acceleration method, device, equipment and computer readable storage medium
By using the HLS language to implement the FPGA computing acceleration board in hardware devices, and directly execute software function logic, solving the problems of low efficiency and high cost of data computing acceleration in the prior art, and achieving fast and efficient data processing.
Patent Information
- Application Number
- CN202211347659.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-10-31
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-10-31
AI Technical Summary
The prior art is limited by the serial execution of the CPU in terms of data computing acceleration, and cannot effectively meet the rapidly growing data processing needs. Using GPUs to accelerate computing requires data standardization and complex preparation processes, resulting in reduced efficiency and high labor costs.
By implementing the second preset function based on the HLS language in the hardware device, using FPGA computing to accelerate the board for data processing, directly executing the original software function logic in the hardware, avoiding data standardization and memory copying, and improving computing efficiency.
It realizes faster and more efficient data calculation than software calculations, with significant acceleration effects, reducing labor and computing costs, and simplifying the data preparation process without changing the C/C++ language.
Smart Images

Figure CN115686845B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to a data computing acceleration method, device, equipment, and computer-readable storage medium. Background Art
[0002] With the continuous development of big data, the growth of data volume and the diversification of data types have put forward higher and higher requirements for data processing, and the demand for data calculation speed is also increasing day by day.
[0003] In order to achieve computing acceleration, the current better technology is to use software parallel computing, which achieves acceleration by memory mapping and parallel computing of data. This method still needs to follow the serial rules of the central processing unit (CPU) during the specific execution process, and can only increase the computing speed by several times at most, which still cannot meet the demand for computing acceleration. Summary of the invention
[0004] In order to solve the above technical problems, the present disclosure provides a data calculation acceleration method, device, equipment and computer-readable storage medium to improve data calculation speed.
[0005] In a first aspect, an embodiment of the present disclosure provides a data computing acceleration method, including:
[0006] Based on the calculation logic of the first preset function, a second preset function is implemented in the hardware device, wherein the calculation logic of the first preset function is the same as that of the second preset function;
[0007] In response to a data processing request from a user side, calling the second preset function to obtain a data processing result corresponding to the data processing request;
[0008] The data processing result is sent to the user side.
[0009] In some embodiments, before the calculation logic based on the first preset function implements the second preset function in the hardware device, the method further includes:
[0010] A first preset function is obtained, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold.
[0011] In some embodiments, the calculation logic based on the first preset function implements the second preset function in the hardware device, including:
[0012] Based on the calculation logic of the first preset function, the second preset function is implemented in the hardware device through the HLS language.
[0013] In some embodiments, based on the calculation logic of the first preset function, after implementing the second preset function in the hardware device, the method further includes:
[0014] Defining a calling rule of the second preset function;
[0015] The step of responding to the data processing request from the user side and calling the second preset function to obtain the data processing result corresponding to the data processing request includes:
[0016] In response to a data processing request from the user side, the second preset function is called according to a calling rule of the second preset function to obtain a data processing result corresponding to the data processing request.
[0017] In some embodiments, in response to the data processing request from the user side, calling the second preset function to obtain the data processing result corresponding to the data processing request includes:
[0018] Determining the amount of data included in the data processing request;
[0019] If the data volume is greater than or equal to a second preset threshold, the second preset function is called to obtain a data processing result corresponding to the data processing request.
[0020] In a second aspect, an embodiment of the present disclosure provides a data computing acceleration device, including:
[0021] An implementation module, configured to implement a second preset function in a hardware device based on the calculation logic of the first preset function, wherein the calculation logic of the first preset function is the same as that of the second preset function;
[0022] A calling module, configured to, in response to a data processing request from a user side, call the second preset function to obtain a data processing result corresponding to the data processing request;
[0023] The sending module is used to send the data processing result to the user side.
[0024] In some embodiments, the apparatus further comprises:
[0025] The acquisition module is used to acquire a first preset function, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold.
[0026] In some embodiments, the apparatus further comprises:
[0027] A definition module is used to define the calling rules of the second preset function.
[0028] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
[0029] Memory;
[0030] Processor; and
[0031] Computer programs;
[0032] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect.
[0033] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method described in the first aspect.
[0034] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the data calculation acceleration method as described above is implemented.
[0035] The data calculation acceleration method, device, equipment and computer-readable storage medium provided by the embodiments of the present disclosure implement the first preset function of serialized calculation by software in hardware, which is faster and more efficient than calculating by software, and can achieve the effect of data calculation acceleration without changing to C / C++ language, and there is no need to standardize the source data, which reduces data preparation time, while reducing labor and computing power costs, greatly improving data calculation speed. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0037] In order to more clearly illustrate the embodiments of the present invention 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0038] Figure 1 A flow chart of a data calculation acceleration method provided in an embodiment of the present disclosure;
[0039] Figure 2 A schematic diagram of an application scenario provided by an embodiment of the present disclosure;
[0040] Figure 3 A schematic diagram of hardware device connection provided in an embodiment of the present disclosure;
[0041] Figure 4 A flow chart of a data calculation acceleration method provided by another embodiment of the present disclosure;
[0042] Figure 5 A schematic diagram of the structure of a data computing acceleration device provided in an embodiment of the present disclosure;
[0043] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0044] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0046] In the prior art, software parallel computing or graphics processing unit (GPU) boards are generally used for data acceleration computing. Software parallel computing is accelerated by memory mapping and parallel computing of data. It is limited by the serial execution of CPU and can only increase the computing acceleration by several times at most; the GPU board implementation scheme is to use the multiple CUDA (Compute Unified Device Architecture) cores of the GPU itself for parallel acceleration. Developers can use C language to write programs for the CUDA architecture, and the written programs can run on processors that support CUDA. However, using GPU for computing acceleration requires standardization of input data, and complex calculations require data copying each time, which prolongs the data preparation time and reduces the efficiency of computing acceleration.
[0047] In addition, the algorithm can be verified in Python first, and then the Python implementation can be converted into C / C++ to implement the calculation, so as to improve the execution efficiency. However, this method requires C / C++ developers to fully understand the algorithm logic implemented by Python developers and perform multiple debugging to achieve the corresponding effect. It is inefficient and requires developers of two programming languages, which has high labor costs.
[0048] In view of the above problems, the embodiments of the present disclosure provide a method for accelerating data calculation, which is introduced below in conjunction with specific embodiments.
[0049] Figure 1 The data calculation acceleration method provided in the embodiment of the present disclosure is a flow chart. The method can be applied to Figure 2 The application scenario shown includes a terminal device 21, which includes an application-side service or algorithm program, a software development kit (SDK), and an FPGA computing acceleration board. The terminal device can be a smart phone, a handheld computer, a tablet computer, a wearable device with a display screen, a desktop computer, a laptop computer, an all-in-one machine, a smart home device, etc. It can be understood that the data computing acceleration method provided in the embodiment of the present disclosure can also be applied in other scenarios.
[0050] Figure 3 This is a schematic diagram of hardware device connection provided by the embodiment of the present disclosure. Figure 3 As shown, Figure 1 The FPGA computing acceleration board in the system is installed on the server through the high-speed serial computer expansion bus standard (Peripheral Component Interconnect express, PCIe), and the PCIe interface exchanges data with the software SDK. Peripheral Component Interconnect (PCI) is a standard for defining local buses. This standard allows expansion cards that comply with the PCI standard to be installed in the computer. The PCI bus system requires a PCI controller card, which must be installed in a PCI slot. PCIe uses the existing PCI programming concepts and signal standards, and builds a higher-speed serial communication system standard.
[0051] Combine the following Figure 2 The application scenarios shown and Figure 3 The hardware device connection diagram shown in the figure is Figure 1 The data calculation acceleration method shown in FIG. 1 is introduced, and the specific steps of the method are as follows:
[0052] S101. Based on the calculation logic of the first preset function, implement a second preset function in a hardware device, where the calculation logic of the first preset function is the same as that of the second preset function.
[0053] The first preset function is a function that needs to be accelerated in the user service or algorithm program. First, the calculation logic of the first preset function is obtained, and the second preset function with the same calculation logic is implemented in the hardware device. The calculation logic of the first preset function is the same as that of the second preset function, but the languages used by the first preset function and the second preset function are different.
[0054] In some embodiments, the first preset function commonly used in the user service or algorithm program can be implemented in the hardware device using the High Level Synthesis (HLS) language. HLS is to synthesize the software algorithm written in C / C++ / SystemC into a register transfer level (RTL) code, such as Very-High-Speed Integrated Circuit Hardware Description Language (VHDL) or Hardware Description Language (HDL), etc., to achieve hardware acceleration of software algorithm design and abstract level design and verification of hardware circuit design.
[0055] In some embodiments, the hardware device may be Figure 2 or Figure 3 The FPGA (Field Programmable Gate Array) computing acceleration board shown in the figure. FPGA is an integrated circuit that appears as a semi-custom circuit in the field of application-specific integrated circuits (ASIC). The so-called integrated circuit is a circuit built with various discrete components (such as resistors, diodes, and transistors) integrated into a chip. FPGA computing acceleration boards are professional boards for specific fields and applications, usually deployed in the form of PCIe expansion cards. The board is designed with a wealth of high-speed I / O interfaces and storage resources for data exchange with the software SDK.
[0056] It can be understood that the number of first preset functions can be one or more, and the embodiment of the present disclosure is not limited to this. The operation logic of each first preset function can be different, and each first preset function is implemented in the hardware device as a one-to-one corresponding second preset function, so that the operation logic of each first preset function and its corresponding second preset function are the same. The embodiment of the present disclosure only takes any one of the first preset functions as an example for illustration, and it is not a limitation of the embodiment of the present disclosure.
[0057] S102: In response to a data processing request from a user side, calling the second preset function to obtain a data processing result corresponding to the data processing request.
[0058] The user initiates a service request to the application-side service or algorithm program on the user side. The application-side service or algorithm program on the user side responds to the service request sent by the user, forms a corresponding data processing request, calls the second preset function in the hardware device through the software SDK, processes the data processing request, and obtains the data processing result corresponding to the data processing request.
[0059] Specifically, an application programming interface (API) that can be called is pre-configured in the software SDK, and the second preset function in the hardware device (such as an FPGA computing acceleration board) is implemented by calling the pre-configured API interface, thereby performing corresponding processing on the data processing request to obtain the data processing result.
[0060] S103: Send the data processing result to the user side.
[0061] After the data processing result corresponding to the data processing request is calculated by the hardware device, the data processing result is returned to the software SDK, and the software SDK sends the final data processing result to the user side, which can be the application-side business or algorithm program on the user side, to achieve the purpose of accelerating data calculation.
[0062] The disclosed embodiment implements a second preset function in a hardware device through a calculation logic based on a first preset function, wherein the calculation logic of the first preset function is the same as that of the second preset function; in response to a data processing request from a user side, the second preset function is called to obtain a data processing result corresponding to the data processing request; the data processing result is sent to the user side, and the first preset function that is serially calculated by software is implemented in hardware, which is faster and more efficient than calculating by software, and can achieve the effect of accelerating data calculation without changing to C / C++ language, and there is no need to standardize the source data, which reduces data preparation time, while reducing labor and computing power costs, greatly improving data calculation speed.
[0063] Figure 4 A flow chart of a data calculation acceleration method provided by another embodiment of the present disclosure is as follows: Figure 3 As shown, the method includes the following steps:
[0064] S401: Acquire a first preset function, where the calculation time required for the first preset function in a software calculation process is greater than or equal to a first preset threshold.
[0065] The calculation time required for each function in the software calculation process is investigated in advance, and the time-consuming functions in the user service or algorithm program are determined as preset functions. For example, each function whose calculation time required in the calculation process of the user service or algorithm program is greater than or equal to the first preset threshold is respectively used as the first preset function.
[0066] S402: Based on the calculation logic of the first preset function, implement a second preset function in a hardware device, wherein the calculation logic of the first preset function is the same as that of the second preset function.
[0067] Optionally, based on the calculation logic of the first preset function, the second preset function is implemented in the hardware device through the HLS language.
[0068] Specifically, the implementation process and principle of S402 and S101 are the same, and will not be repeated here.
[0069] S403: Define a calling rule for the second preset function.
[0070] Pre-configure the callable API interface in the software SDK, and define the calling rules of the second function. The calling rules define the correspondence between the first preset function and the second preset function. Since one or more different first preset functions may be included in the application-side business or algorithm program, when the application-side business or algorithm program includes multiple different first preset functions, each first preset function corresponds to a second preset function with the same calculation logic in the hardware device. When calling, it is necessary to call the specific second preset function corresponding to the required first preset function to implement the corresponding calculation logic.
[0071] S404, determining whether the amount of data included in the data processing request on the user side is greater than or equal to a second preset threshold; if so, executing S406; if not, executing S405;
[0072] S405: Call the second preset function according to the calling rule of the second preset function to obtain a data processing result corresponding to the data processing request.
[0073] S406: Call a first preset function to obtain a data processing result corresponding to the data processing request.
[0074] The software SDK determines the amount of data contained in the data processing request transmitted by the API interface. If the amount of data contained in the data processing request is small, such as less than the second preset threshold, the original first preset function in the application-side business or algorithm program can be directly used to process the data processing request; if the amount of data contained in the data processing request is large, such as greater than or equal to the second preset threshold, the second preset function in the hardware device is called according to the pre-defined calling rules of the second preset function to process the data processing request to obtain the final data processing result.
[0075] S407: Send the data processing result to the user side.
[0076] In some embodiments, the user pre-adds the software SDK library function ysnumpy or yspandas to the business program of the application layer. Taking ysnumpy as an example, in some business scenarios, it is necessary to call the array function in the library function numpy, and it is found in the prior investigation that the calculation time required for the function to run in the software is greater than the first preset threshold, then the array function is hardwareized, that is, the array function is implemented in the FPGA computing acceleration board using the HLS language, and then the calling rules related to the software SDK definition are defined, such as adding the software SDK library function ysnumpy to the business program of the application layer, where ys- is a custom function name identifier, which is used to identify that the function is implemented in hardware. When the array function is needed in the data processing request on the user side, such as ysnumpy.array(), the software SDK receives the data processing request through the interface, and the amount of data contained therein is greater than the second preset threshold, the software SDK determines that the calculation process needs to be performed by the FPGA computing acceleration board, and then calls the FPGA hardware array function. After the FPGA computing acceleration board is executed, the obtained data processing result is returned to the software SDK, and finally the software SDK sends the data processing result to the user side to complete the data calculation acceleration.
[0077] The disclosed embodiment obtains a first preset function, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold; based on the calculation logic of the first preset function, implements a second preset function in a hardware device, wherein the calculation logic of the first preset function is the same as that of the second preset function; defines a calling rule for the second preset function; when the amount of data contained in the data processing request on the user side is greater than or equal to the second preset threshold, calls the second preset function according to the calling rule of the second preset function to obtain a data processing result corresponding to the data processing request; sends the data processing result to the user side, and selects functions with longer calculation time to be implemented in the hardware device by screening the functions used in the software calculation process, thereby making data calculation faster and more efficient; data acceleration in hardware does not require memory copying, and has higher execution efficiency; hardware-based implementation of functions based on the HLS language does not require standardization of original data, thereby reducing data preparation time, saving labor costs, and further improving the effect of data calculation acceleration.
[0078] Figure 5 The data computing acceleration device provided in the embodiment of the present disclosure is a schematic diagram of the structure of the data computing acceleration device. The data computing acceleration device may be the terminal device described in the above embodiment, or the data computing acceleration device may be a component or assembly in the terminal device. The data computing acceleration device provided in the embodiment of the present disclosure may execute the processing flow provided in the data computing acceleration method embodiment, such as Figure 5 As shown, the data computing acceleration device 50 includes: an implementation module 51, a calling module 52, and a sending module 53; wherein the implementation module 51 is used to implement a second preset function in a hardware device based on the calculation logic of the first preset function, and the calculation logic of the first preset function is the same as that of the second preset function; the calling module 52 is used to respond to a data processing request from the user side, call the second preset function to obtain a data processing result corresponding to the data processing request; the sending module 53 is used to send the data processing result to the user side.
[0079] Optionally, the data calculation acceleration device 50 further includes an acquisition module 54 for acquiring a first preset function, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold.
[0080] Optionally, the implementation module 51 is further configured to implement a second preset function in the hardware device by using the HLS language based on the calculation logic of the first preset function.
[0081] Optionally, the data computing acceleration device 50 also includes a definition module 55 for defining a calling rule of the second preset function; the calling module 52 is also used to respond to a data processing request from the user side, and call the second preset function according to the calling rule of the second preset function to obtain a data processing result corresponding to the data processing request.
[0082] Optionally, the calling module 52 includes a determination unit 521 and a processing unit 522; the determination unit 521 is used to determine the amount of data contained in the data processing request; the processing unit 522 is used to call the second preset function to obtain the data processing result corresponding to the data processing request when the amount of data is greater than or equal to a second preset threshold.
[0083] Figure 5 The data computing acceleration device of the illustrated embodiment can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.
[0084] Figure 6 The electronic device provided in the embodiment of the present disclosure may be a terminal device as described in the above embodiment. The electronic device provided in the embodiment of the present disclosure may execute the processing flow provided in the data calculation acceleration method embodiment, such as Figure 6 As shown, the electronic device 60 includes: a memory 61, a processor 62, a computer program and a communication interface 63; wherein the computer program is stored in the memory 61 and is configured so that the processor 62 executes the data calculation acceleration method as described above.
[0085] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the data calculation acceleration method described in the above embodiment.
[0086] In addition, an embodiment of the present disclosure also provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the data calculation acceleration method as described above is implemented.
[0087] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0088] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0089] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0090] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A data calculation acceleration method, characterized in that: The method comprises: Based on the calculation logic of the first preset function, a second preset function is implemented in the hardware device, wherein the calculation logic of the first preset function is the same as that of the second preset function, and the languages used by the first preset function and the second preset function are different; In response to a data processing request from a user side, calling the second preset function to obtain a data processing result corresponding to the data processing request; Sending the data processing result to the user side; The calling of the second preset function to obtain the data processing result corresponding to the data processing request includes: determining the amount of data contained in the data processing request; if the amount of data is greater than or equal to a second preset threshold, calling the second preset function to obtain the data processing result corresponding to the data processing request.
2. The method according to claim 1, characterized in that The calculation logic based on the first preset function, before implementing the second preset function in the hardware device, the method further includes: A first preset function is obtained, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold.
3. The method according to claim 1, characterized in that The calculation logic based on the first preset function implements the second preset function in the hardware device, including: Based on the calculation logic of the first preset function, the second preset function is implemented in the hardware device through the HLS language.
4. The method according to claim 1, characterized in that: Based on the calculation logic of the first preset function, after implementing the second preset function in the hardware device, the method further includes: Defining a calling rule of the second preset function; The step of responding to the data processing request from the user side and calling the second preset function to obtain the data processing result corresponding to the data processing request includes: In response to a data processing request from the user side, the second preset function is called according to a calling rule of the second preset function to obtain a data processing result corresponding to the data processing request.
5. A data calculation acceleration device, characterized in that: include: an implementation module, configured to implement a second preset function in a hardware device based on a calculation logic of the first preset function, wherein the calculation logic of the first preset function is the same as that of the second preset function, and the languages used by the first preset function and the second preset function are different; A calling module, configured to, in response to a data processing request from a user side, call the second preset function to obtain a data processing result corresponding to the data processing request; A sending module, used for sending the data processing result to the user side; The calling module includes a determination unit and a processing unit; the determination unit is used to determine the amount of data contained in the data processing request; the processing unit is used to call the second preset function to obtain the data processing result corresponding to the data processing request when the amount of data is greater than or equal to a second preset threshold.
6. The device according to claim 5, characterized in that The device also includes: The acquisition module is used to acquire a first preset function, wherein the calculation time required for the first preset function in the software calculation process is greater than or equal to a first preset threshold.
7. The device according to claim 5, characterized in that The device also includes: A definition module is used to define the calling rules of the second preset function.
8. An electronic device, characterized in that: include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and is configured to be executed by the processor to implement the method according to any one of claims 1 to 4.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
