Equipment access module

Abstract

The invention relates to an equipment access module, the equipment access module is used for accessing computing energy equipment to cloud equipment, the equipment access module comprises a network communication unit, a signaling processing unit and an algorithm reasoning unit, the cloud equipment is connected with the network communication unit, the network communication unit is connected with the signaling processing unit, and the signaling processing unit is connected with the algorithm reasoning unit. The network communication unit is connected with the signaling processing unit, the signaling processing unit is connected with the algorithm reasoning unit, the algorithm reasoning unit is connected with the computing energy equipment, and the network communication unit is used for receiving signaling from the cloud equipment and sending the signaling to the signaling processing unit; the signaling processing unit is used for receiving the signaling sent by the network communication unit and sending an algorithm execution instruction obtained after the signaling is processed to the algorithm reasoning unit; and the algorithm reasoning unit is used for receiving the algorithm execution instruction sent by the signaling processing unit and the data frame sent by the computing energy equipment, and performing back-end reasoning on the data frame based on the algorithm execution instruction. The equipment access module saves time and resource consumption.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a device access module. Background Art

[0002] The cloud-edge mode is a common computing management method. In this mode, computing tasks and resource management are distributed between the cloud and edge devices. There are various computing devices, each with its own specific hardware and software features. In order to enable a variety of different computing devices to communicate normally with the cloud, it is necessary to adapt the devices, that is, to customize the development according to the specific characteristics of the devices. Since different devices and projects need to develop their own communication logic independently, a large number of similar functions have been developed multiple times, wasting resources and time. Summary of the invention

[0003] The present invention is intended to provide a device access module to solve the deficiencies in the prior art. The technical problem to be solved by the present invention is achieved through the following technical solutions.

[0004] According to a first aspect of the present disclosure, a device access module is provided, the device access module is used to connect a computing device to a cloud device, the device access module comprises: a network communication unit, a signaling processing unit and an algorithm reasoning unit, the cloud device is connected to the network communication unit, the network communication unit is connected to the signaling processing unit, the signaling processing unit is connected to the algorithm reasoning unit, and the algorithm reasoning unit is connected to the computing device, wherein: The network communication unit is used to receive signaling from the cloud device and send the signaling to the signaling processing unit; The signaling processing unit is used to receive the signaling sent by the network communication unit, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit; The algorithm reasoning unit is used to receive the algorithm execution instructions sent by the signaling processing unit and the data frames sent by the computing device, and perform back-end reasoning on the data frames based on the algorithm execution instructions.

[0005] Furthermore, the network communication unit receives signaling from the cloud device via a Transmission Control Protocol TCP long connection, and sends the signaling to a signaling processing unit via the TCP long connection.

[0006] Furthermore, the network communication unit uses the open source encryption library mbedtls to provide Hypertext Transfer Protocol Security HTTP support to download files from a remote end.

[0007] Furthermore, the signaling processing unit is used to receive the signaling sent by the network communication unit through a single consumer queue, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit through the single consumer queue.

[0008] Furthermore, the algorithm reasoning unit includes a plug-in management subunit, a front-end frame pushing subunit and a back-end reasoning subunit, wherein: The plug-in management subunit is used to manage computing power plug-ins; The front-end frame pushing subunit is used to receive the data frame sent by the computing device, and send the data frame to the back-end reasoning subunit; The back-end reasoning subunit is used to receive the data frames sent by the front-end frame pushing subunit and perform algorithmic reasoning on the data frames.

[0009] Furthermore, the plug-in management subunit is provided with a standard access specification, and the standard access specification includes at least one of the following: Set the inference result callback; Plugin initialization; Plugin deinitialization; Create an algorithm instance; Destroy the algorithm instance; Asynchronous reasoning; Synchronous reasoning.

[0010] Furthermore, the device access module is integrated on the computing device in the form of a software development kit SDK to enable the computing device to access the cloud device.

[0011] The embodiments of the present invention include the following advantages: The device access module provided in the embodiment of the present invention is used to connect the computing device to the cloud device, and the device access module includes: a network communication unit, a signaling processing unit and an algorithm reasoning unit, the cloud device is connected to the network communication unit, the network communication unit is connected to the signaling processing unit, the signaling processing unit is connected to the algorithm reasoning unit, and the algorithm reasoning unit is connected to the computing device, wherein: the network communication unit is used to receive signaling from the cloud device and send the signaling to the signaling processing unit; the signaling processing unit is used to receive the signaling sent by the network communication unit, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit; the algorithm reasoning unit is used to receive the algorithm execution instruction sent by the signaling processing unit and the data frame sent by the computing device, and perform back-end reasoning on the data frame based on the algorithm execution instruction. In this embodiment, the device access module encapsulates a network communication unit, a signaling processing unit, and an algorithm reasoning unit. Different computing devices can reuse these units, and there is no need to develop a new communication logic for each computing device. The network communication unit can support basic network communication functions, and there is no need to repeatedly develop the basic network communication part, thereby saving time and resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a structural schematic diagram of an embodiment of a device access module of the present invention; Figure 2 It is a flow chart of algorithm reasoning in an algorithm reasoning unit of the present invention; Figure 3 It is a schematic diagram of a computing device connected to a cloud device according to the present invention. DETAILED DESCRIPTION

[0013] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0014] Figure 1 A schematic diagram of the structure of a device access module according to an embodiment of the present disclosure is shown. Specifically, the device access module is used to connect a computing device to a cloud device. The device access module includes: a network communication unit, a signaling processing unit, and an algorithm reasoning unit. The cloud device is connected to the network communication unit, the network communication unit is connected to the signaling processing unit, the signaling processing unit is connected to the algorithm reasoning unit, and the algorithm reasoning unit is connected to the computing device, wherein: The network communication unit is used to receive signaling from the cloud device and send the signaling to the signaling processing unit; In some embodiments, the network communication unit receives signaling from the cloud device via a Transmission Control Protocol TCP long connection, and sends the signaling to a signaling processing unit via the TCP long connection.

[0015] In the above embodiment, the network communication unit is implemented based on the embedded ultra-lightweight network library Mongoose. The network communication unit maintains continuous two-way communication with the cloud device through a Transmission Control Protocol (TCP) long connection to ensure that data and signaling can be transmitted in real time, and sends the signaling to the signaling processing unit through a TCP long connection.

[0016] TCP long connection can maintain a stable communication channel without the need to frequently re-establish the connection, which can reduce the time and resource consumption in the communication process. The TCP protocol provides reliable data transmission guarantees, ensuring that all information packets arrive in the correct order without loss or duplication.

[0017] In some embodiments, the network communication unit uses the open source encryption library mbedtls to provide Hypertext Transfer Protocol Security (HTTP) support to download files from a remote end.

[0018] In the above embodiment, an embedded Transport Layer Security (TLS) module mbedtls may be introduced into the network communication unit, so that the network communication unit can download files from a remote end via HyperText Transfer Protocol (HTTP) to ensure the security of data transmission.

[0019] By choosing lightweight libraries such as Mongoose and mbedtls, you can reduce the resources occupied by the device access module, improve the performance of the device access module, and ensure efficient operation on resource-constrained embedded devices (such as cameras).

[0020] The signaling processing unit is used to receive the signaling sent by the network communication unit, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit; In some embodiments, the signaling processing unit is used to receive the signaling sent by the network communication unit through a single consumer queue, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit through the single consumer queue.

[0021] In the above embodiment, the signaling processing unit can use a single consumer queue to process the sending and receiving of signaling, thereby improving processing efficiency and simplifying concurrency control. The core business signaling mainly includes the start and stop instructions of the algorithm, which are used to determine the execution status of the computing task.

[0022] The algorithm reasoning unit is used to receive the algorithm execution instructions sent by the signaling processing unit and the data frames sent by the computing device, and perform back-end reasoning on the data frames based on the algorithm execution instructions.

[0023] In the prior art, due to the differences in equipment from different manufacturers, the same business requirements may be implemented differently on different computing devices, increasing the overall complexity and inconsistency of the system. The device access module of the embodiment of the present application encapsulates a signaling processing unit for upper and lower layer communications, which efficiently manages the sending and receiving of signals through a single consumer queue, and starts or terminates the algorithm through algorithm execution instructions, so that developers no longer need to focus on the business, but only need to focus on specific algorithm development.

[0024] In some embodiments, the algorithm reasoning unit includes a plug-in management subunit, a front-end frame pushing subunit, and a back-end reasoning subunit, wherein: The plug-in management subunit is used to manage computing power plug-ins; The front-end frame pushing subunit is used to receive the data frame sent by the computing device, and send the data frame to the back-end reasoning subunit; The back-end reasoning subunit is used to receive the data frames sent by the front-end frame pushing subunit and perform algorithmic reasoning on the data frames.

[0025] In the above embodiment, the plug-in management subunit is responsible for loading and managing the computing energy plug-ins, which is the part that is fully implemented by the device access module. This part can ensure that various types of computing energy plug-ins can be effectively loaded and managed, and is independent of specific computing energy devices. The front-end frame pushing subunit is used to receive data frames (such as image frames and video frames, etc.) collected by the computing energy device, and send the video frames to the back-end reasoning subunit. The back-end reasoning subunit performs actual algorithm reasoning and calculation on the received data frames. The front-end frame pushing subunit and the back-end reasoning subunit depend on the characteristics of the specific computing energy device, and need to be customized and developed and adapted for different computing energy devices to meet the computing power and task requirements of different computing energy devices.

[0026] See also Figure 2 , Figure 2 It is the process of algorithm reasoning in the algorithm reasoning unit, specifically: (1) The caller decodes the image to obtain the image frame and sends the image frame to the algorithm SDK; (2) The algorithm SDK calls the plug-in reasoning capability and sends the image frame to the algorithm capability plug-in (i.e., the computing plug-in mentioned above) so that the algorithm capability plug-in can reason about the image frame; (3) The algorithm capability plug-in sends the inference results to the algorithm SDK; (4) The algorithm SDK sends the inference results to the caller.

[0027] In addition, the plug-in management subunit can load and manage computing plug-ins of different computing devices. Different algorithms can be loaded and executed as independent plug-ins, which facilitates the rapid expansion of new functions on computing devices.

[0028] In some embodiments, the plug-in management subunit is provided with a standard access specification, and the standard access specification includes at least one of the following: Set the inference result callback; Plugin initialization; Plugin deinitialization; Create an algorithm instance; Destroy the algorithm instance; Asynchronous reasoning; Synchronous reasoning.

[0029] In the above embodiment, the plug-in management subunit provides a set of standardized access specifications for the management of computing energy plug-ins. The standard access specifications include at least one of the following: Set the inference result callback (Infer_Plugin_SelnferResultCallBack); Plugin initialization (Infer_Plugin_Initialize); Plugin deinitialization (Infer_Plugin_Delnitialize); Create an algorithm instance (Infer_Plugin_CreateAlgorithminstance); Destroy algorithm instance (Infer_Plugin_DestroyAlgorithminstance); Asynchronous inference (Infer_Plugin_Async_Infer); Synchronous inference (Infer_Plugin_Sync_Infer).

[0030] In this way, the inference plug-in on the computing device only needs to implement specific interfaces according to the specification requirements, and can be easily integrated into the system, and then uniformly managed and scheduled by the cloud device, thereby simplifying maintenance and operation.

[0031] In some embodiments, the device access module is integrated on the computing device in the form of a software development kit (SDK) to enable the computing device to access the cloud device.

[0032] In the above embodiments, the standardized software development kit (SDK) provides predefined interfaces and functions, and developers can directly use these functions without writing code from scratch, thereby improving development efficiency. Therefore, the device access module is integrated into the computing device in the form of a software development kit SDK, which can greatly simplify the development process. In addition, the SDK is generally rigorously tested, and its reliability and security have been verified, which helps to improve the stability of the overall system.

[0033] See also Figure 3 , Figure 3 This is a diagram of how computing devices are connected to cloud devices. In the cloud-edge collaborative computing mode, the device access module can provide a standardized and unified way to enable each computing device to quickly and consistently access the cloud environment. By integrating this device access module into the computing device in the form of an SDK, developers can focus on the development of reasoning functions related to the computing device hardware, that is, the implementation of the computing plug-in, without having to worry about other business logic or underlying communication issues.

[0034] According to an embodiment of the present disclosure, a device access module is used to connect a computing device to a cloud device, and the device access module includes: a network communication unit, a signaling processing unit and an algorithm reasoning unit, the cloud device is connected to the network communication unit, the network communication unit is connected to the signaling processing unit, the signaling processing unit is connected to the algorithm reasoning unit, and the algorithm reasoning unit is connected to the computing device, wherein: the network communication unit is used to receive signaling from the cloud device and send the signaling to the signaling processing unit; the signaling processing unit is used to receive signaling sent by the network communication unit, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit; the algorithm reasoning unit is used to receive the algorithm execution instruction sent by the signaling processing unit and the data frame sent by the computing device, and perform back-end reasoning on the data frame based on the algorithm execution instruction. In this embodiment, the device access module encapsulates a network communication unit, a signaling processing unit, and an algorithm reasoning unit. Different computing devices can reuse these units, and there is no need to develop a new communication logic for each computing device. The network communication unit can support basic network communication functions, and there is no need to repeatedly develop the basic network communication part, thereby saving time and resource consumption.

[0035] It should be noted that the above detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.

[0036] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0038] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0039] For ease of description, spatially relative terms, such as "above", "above", "on the upper surface of", "above", etc., may be used herein to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" may include both "above" and "below". The device may also be positioned in other different ways, such as rotated 90 degrees or in other orientations, and the spatially relative descriptions used herein are interpreted accordingly.

[0040] In the above detailed description, reference is made to the accompanying drawings, which form a part of this document. In the accompanying drawings, similar symbols typically identify similar components unless the context indicates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

[0041] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A device access module, characterized in that: The device access module is used to connect the computing device to the cloud device. The device access module includes: a network communication unit, a signaling processing unit and an algorithm reasoning unit. The cloud device is connected to the network communication unit, the network communication unit is connected to the signaling processing unit, the signaling processing unit is connected to the algorithm reasoning unit, and the algorithm reasoning unit is connected to the computing device, wherein: The network communication unit is used to receive signaling from the cloud device and send the signaling to the signaling processing unit; The signaling processing unit is used to receive the signaling sent by the network communication unit, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit; The algorithm reasoning unit is used to receive the algorithm execution instructions sent by the signaling processing unit and the data frames sent by the computing device, and perform back-end reasoning on the data frames based on the algorithm execution instructions.

2. The device access module according to claim 1, characterized in that: The network communication unit receives signaling from the cloud device via a Transmission Control Protocol TCP long connection, and sends the signaling to a signaling processing unit via the TCP long connection.

3. The device access module according to claim 1, characterized in that: The network communication unit uses the open source encryption library mbedtls to provide Hypertext Transfer Protocol Security HTTP support to download files from a remote end.

4. The device access module according to claim 1, characterized in that: The signaling processing unit is used to receive the signaling sent by the network communication unit through the single consumption queue, and send the algorithm execution instruction obtained after processing the signaling to the algorithm reasoning unit through the single consumption queue.

5. The device access module according to claim 1, characterized in that: The algorithm reasoning unit includes a plug-in management subunit, a front-end frame pushing subunit and a back-end reasoning subunit, wherein: The plug-in management subunit is used to manage computing power plug-ins; The front-end frame pushing subunit is used to receive the data frame sent by the computing device, and send the data frame to the back-end reasoning subunit; The back-end reasoning subunit is used to receive the data frames sent by the front-end frame pushing subunit and perform algorithmic reasoning on the data frames.

6. The device access module according to claim 5, characterized in that: The plug-in management subunit is provided with a standard access specification, and the standard access specification includes at least one of the following: Set the inference result callback; Plugin initialization; Plugin deinitialization; Create an algorithm instance; Destroy the algorithm instance; Asynchronous reasoning; Synchronous reasoning.

7. The device access module according to any one of claims 1 to 6, characterized in that: The device access module is integrated on the computing device in the form of a software development kit SDK to enable the computing device to access the cloud device.

Images