Information processing method based on IoT devices, related devices and storage media
The method addresses resource constraints in IoT devices by abstracting them into nodes and generating a resource knowledge graph, optimizing task assignment and resource utilization, thus enhancing edge computing efficiency and privacy.
Patent Information
- Application Number
- JP2023547756
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2021-02-10
- Filing Date
- 2022-02-08
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2042-02-08
AI Technical Summary
Existing IoT devices face resource constraints and high heterogeneity, making it challenging to perform computationally intensive computing tasks efficiently, especially in edge computing scenarios that require high computing power and storage space.
An information processing method that discovers IoT devices, abstracts them into nodes based on capabilities, generates a resource knowledge graph to manage and coordinate available capabilities, and monitors changes to optimize task assignment and resource utilization.
Enables efficient management and flexible scheduling of resource-constrained IoT devices, reducing the need for data transmission to cloud centers, enhancing privacy protection and user experience.
Smart Images

Figure 0007581535000001 
Figure 0007581535000002 
Figure 0007581535000003
Abstract
Description
[Technical field]
[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This disclosure is filed based on and claims priority to a Chinese patent application having application number 202110184830.4 and filing date February 10, 2021, the entire contents of which are incorporated herein by reference.
[0002] The present disclosure relates to the field of IoT (Internet of Things), and in particular to an information processing method, device, system, electronic device, and storage medium based on IoT devices. [Background technology]
[0003] Edge computing, as a computing method for processing data at the edge of a network, has been attracting more and more attention, and has become a new research focus following cloud computing, especially in the field of IoT. Compared with cloud computing, edge computing does not need to transmit a large amount of user raw data to a cloud data center, so edge computing solves problems such as delay, reliability, energy consumption, communication bandwidth consumption, user privacy, and security in the data processing process, and has great value and broad application prospects in application scenarios (e.g., smart home scenarios) based on artificial intelligence (AI) that are sensitive (i.e., have high demands) to requirements such as data processing delay and user privacy.
[0004] However, intelligent applications and / or services for implementing AI-based application scenarios generally require high computing power and / or storage space requirements and need to perform computing-intensive computing tasks, which brings great challenges to the edge side where resources are constrained (i.e., computing power and / or storage space are limited) and isomerization is high. In other words, how to utilize resource-constrained and highly isomerized IoT devices to perform computing tasks has become an urgent problem to be solved. Summary of the Invention [Problem to be solved by the invention]
[0005] To solve problems in the related art, embodiments of the present disclosure provide an information processing method, device, system, electronic device, and storage medium based on an IoT device. [Means for solving the problem]
[0006] The technical solutions of the embodiments of the present disclosure are realized as follows:
[0007] An embodiment of the present disclosure provides an information processing method based on an IoT device, the method comprising: Discovering IoT devices and detecting the capabilities of the IoT devices; for each IoT device, abstracting the IoT device into a corresponding node based on a capability of the corresponding IoT device; generating a resource knowledge graph based on the abstracted nodes; The nodes represent capabilities of at least some of the IoT devices, and the edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or coordinate available capabilities on isomeric IoT devices.
[0008] In some alternative embodiments of the present disclosure, the available capacity includes: Computing power and Memory ability and and communication capabilities.
[0009] In some alternative embodiments of the present disclosure, generating a resource knowledge graph based on the abstracted nodes includes: Determining characteristics of each node and determining relationships between a plurality of nodes, the characteristics being at least used to describe IoT device information corresponding to the corresponding node and at least some capability information of the IoT devices; generating a resource knowledge graph based on the determined characteristics and relationships between the nodes.
[0010] In some alternative embodiments of the present disclosure, the edges in the resource knowledge graph include: The communication relationship between two IoT devices and and representing at least one of the relationships between at least some of the capabilities on the IoT device.
[0011] In some alternative embodiments of the present disclosure, the method further comprises: Monitoring IoT devices and When monitoring for occurrence of a change in an IoT device, updating the resource knowledge graph based on the change status of the monitored IoT device is included.
[0012] In some optional embodiments of the present disclosure, monitoring that a change has occurred in the IoT device includes: Discover new IoT devices and Monitoring when IoT devices are disconnected from the network; Monitoring changes in the computing power of IoT devices; and Monitoring changes in the memory capacity of IoT devices; Monitoring changes in relationships between IoT devices and and monitoring changes in relationships between at least some of the capabilities on the IoT device.
[0013] In some alternative embodiments of the present disclosure, the method further comprises: Obtaining a task to be processed; and assigning at least one node to the task to be processed based on the resource knowledge graph; The at least one node is used to execute the task to be processed.
[0014] In some alternative embodiments of the present disclosure, allocating at least one node to the task to be processed based on the resource knowledge graph includes: determining resource requirements for the task to be processed; determining at least one node from the resource knowledge graph that matches the resource requirement; The resource requirements are the resources required to execute the task to be processed, i.e. Computing resources; Storage resources; and a communication resource.
[0015] In some alternative embodiments of the present disclosure, determining at least one node from the resource knowledge graph that matches the resource requirement comprises: retrieving the resource requirements based on characteristics of each node and relationships between nodes in the resource knowledge graph; and determining at least one node that matches the resource requirement based on the search results.
[0016] An embodiment of the present disclosure further provides an information processing device based on an IoT device, the device comprising: a detection unit configured to discover IoT devices and detect capabilities of the IoT devices; a first processing unit configured for each IoT device to abstract the IoT device into a corresponding node based on a capability of the corresponding IoT device; and a second processing unit configured to generate a resource knowledge graph based on the abstracted nodes; The nodes represent capabilities of at least some of the IoT devices, and the edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or coordinate available capabilities on isomeric IoT devices.
[0017] An embodiment of the present disclosure further provides an information processing system based on an IoT device, the system comprising: A first functional component configured to discover IoT devices and detect capabilities of the IoT devices; a second functional component configured to, for each IoT device, abstract the IoT device into a corresponding node based on a capability of the corresponding IoT device, and generate a resource knowledge graph based on the abstracted nodes; Here, the first functional component and the second functional component are provided in two electronic devices.
[0018] An embodiment of the present disclosure further provides an electronic device, the electronic device including a processor and a memory configured to store a computer program executable by the processor; Here, the processor is configured to perform the steps of any one of the above methods when executing the computer program.
[0019] An embodiment of the present disclosure further provides a storage medium having a computer program stored therein, the computer program implementing the steps of any one of the above methods when executed by a processor. Effect of the Invention
[0020] According to an information processing method, apparatus, system, electronic device, and storage medium based on an IoT device according to an embodiment of the present disclosure, an IoT device is discovered, capabilities of the IoT devices are detected, and for each IoT device, the IoT device is abstracted into a corresponding node based on the capabilities of the corresponding IoT device, and a resource knowledge graph is generated based on the abstracted nodes, the nodes represent capabilities of at least some of the IoT devices, and an edge in the resource knowledge graph represents a relationship between two adjacent nodes, and the resource knowledge graph is used to manage and / or adjust available capabilities on isomeric IoT devices. According to the means of the embodiments of the present disclosure, intelligent sensing is performed on IoT devices and their capabilities (i.e., idle resources of IoT devices), and through virtualization and software-defined technologies, the IoT devices are abstracted into corresponding nodes based on the sensing capabilities, and a resource knowledge graph is generated based on the abstracted nodes, and the generated resource knowledge graph can be used to realize management and / or adjustment of available capabilities on isomeric IoT devices. In this way, based on the resource knowledge graph, efficient management and flexible scheduling can be performed on resource-constrained and highly isomeric IoT devices, which can provide a prerequisite for realizing edge computing (i.e., realizing computing-intensive computing tasks) in AI-based application scenarios. Furthermore, users no longer need to transmit data related to personal privacy to cloud data centers, which enhances privacy protection, reduces transmission delays, and improves user experience. [Brief description of the drawings]
[0021] [Figure 1] 1 is a schematic diagram of a flow of an information processing method according to an embodiment of the present disclosure. [Diagram 2] FIG. 1 is a schematic diagram of IoT's edge infrastructure. [Diagram 3] 1 is a schematic diagram of a system structure in which a resource sensing and management platform according to an application embodiment of the present disclosure manages IoT devices. [Figure 4]FIG. 2 is a schematic diagram of an application scene of a service capability abstraction module according to an application embodiment of the present disclosure; [Diagram 5] FIG. 2 is a schematic diagram of a resource knowledge graph construction module according to an application embodiment of the present disclosure; [Figure 6] FIG. 2 is a schematic diagram of an application scenario of a resource sensing and management platform according to an application embodiment of the present disclosure; [Figure 7] FIG. 2 is a schematic diagram of an interaction flow between a resource sensing and management platform and an IoT device according to an application embodiment of the present disclosure. [Figure 8] FIG. 2 is a schematic diagram of the interaction flow between a resource sensing and management platform and a computing task server according to an application embodiment of the present disclosure; [Figure 9] 1 is a schematic diagram of a structure of an information processing device according to an embodiment of the present disclosure. [Figure 10] 1 is a schematic diagram of a structure of an electronic device according to an embodiment of the present disclosure. [Figure 11] FIG. 1 is a schematic diagram of a structure of an information processing system according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0022] The present disclosure will now be described in more detail with reference to the accompanying drawings and examples.
[0023] As the number and intelligence of IoT devices increases rapidly, in order to fully utilize the resource-constrained and highly heterogeneous IoT devices, it is conceivable to utilize the idle resources on widely distributed IoT devices and perform computing-intensive computing tasks in parallel in a distributed manner through resource sharing and device collaboration. In practical application, realizing intelligent sensing and unified management of heterogeneous IoT device resources is the prerequisite for fully utilizing heterogeneous IoT devices.
[0024] Based on this, various embodiments of the present disclosure perform intelligent sensing of IoT devices and their capabilities (i.e., idle resources of IoT devices), abstract the IoT devices into corresponding nodes based on the sensing capabilities through virtualization and software-defined technologies, and generate a resource knowledge graph based on the abstracted nodes, which can be used to realize management and / or adjustment of available capabilities on isomeric IoT devices. In this way, based on the resource knowledge graph, efficient management and flexible scheduling can be performed for resource-constrained and highly isomeric IoT devices, which can provide a prerequisite for realizing edge computing (i.e., realizing computing-intensive computing tasks) in AI-based application scenarios. Furthermore, users no longer need to transmit data related to personal privacy to cloud data centers, which enhances privacy protection, reduces transmission delays, and improves user experience.
[0025] An embodiment of the present disclosure provides an information processing method based on an IoT device, and as shown in FIG.
[0026] In step 101, IoT devices are discovered and their capabilities are detected.
[0027] In step 102, for each IoT device, abstract the IoT device into a corresponding node based on the capabilities of the corresponding IoT device.
[0028] In step 103, a resource knowledge graph (also called a resource diagram or a resource knowledge diagram) is generated based on the abstracted nodes.
[0029] Here, the nodes represent at least some capabilities of an IoT device, the edges in the resource knowledge graph represent relationships between two adjacent nodes (also called association relationships between two adjacent nodes), which may include communication relationships and subordination relationships, and the communication relationships may be embodied to include information that may represent communication strength, such as information transmission rate and transmission delay, between two adjacent nodes, and the resource knowledge graph is used to manage and / or orchestrate available capabilities on heterogeneous IoT devices.
[0030] In practical application, the IoT devices of the embodiments of the present disclosure may be isomeric IoT devices. Here, isomeric IoT devices means that in a network including a plurality of IoT devices and servers, the hardware of one IoT device is different from the hardware of another IoT device, and / or the server of one IoT device is different from the server of another IoT device. Here, the difference in hardware between one IoT device and another IoT device means that the model of processing hardware such as a central processor (CPU, Central Processing Unit), a graphics processor (GPU, Graphics Processing Unit), a bus interface chip (BIC, Bus Interface Chip), a digital signal processor (DSP, Digital Signal Processor), or the model of storage hardware such as a random access memory (RAM, Random Access Memory), a read only memory (ROM, Read Only Memory), of one IoT device is different from the model of hardware of another IoT device. The fact that the server of one IoT device is different from the server of another IoT device means that the backend program corresponding to one IoT device is different from the backend program corresponding to the other IoT device, or that the operating system of one IoT device is different from the operating system of the other IoT device; in other words, there are differences in the software between the two IoT devices.
[0031] In practical applications, the IoT devices may include mobile phones, personal computers (PCs), wearable smart devices, smart gateways, computing boxes, etc., the PCs may include desktops, laptops, tablets, etc., and the wearable smart devices may include smart watches, smart glasses, etc.
[0032] In practical applications, the information processing method according to the embodiment of the present disclosure can be applied to electronic devices such as servers.
[0033] In step 101, in practical application, discovering the IoT device can also be referred to as sensing the IoT device in an edge network. The edge network refers to the edge of a telecommunication network (an edge network includes a part or all of a convergence layer network and an access layer network, and is the last part of a network that accesses a user). Here, the discovery or sensing can also be understood as detection. For example, an electronic device (which may be a server in particular) can detect an IoT device in an edge network using a zero configuration networking (ZEROCONF, ZERO CONFiguration networking) technology based on a Dynamic Host Configuration Protocol (DHCP, Dynamic Host Configuration Protocol). Of course, the electronic device may be configured to discover or sense an IoT device using other methods according to needs, and the embodiments of the present disclosure are not limited thereto.
[0034] After discovering an IoT device, the electronic device can detect the capabilities of the corresponding IoT device through information interaction with the corresponding IoT device. Exemplarily, the electronic device can send a capability request message to the corresponding IoT device, and determine the capabilities of the corresponding IoT device based on a response message from the corresponding IoT device to the capability request message.
[0035] Here, the capabilities of IoT devices are: Computing power and and memory capability.
[0036] Here, the capability of the IoT device refers to the service capability of the IoT device and can be understood as the resource of the corresponding IoT device. Correspondingly, at least some capability of the IoT device can be understood as at least some resource of the IoT device, and the available capability on the IoT device can be understood as the available resource, i.e., the idle resource (also called idle capability, free capability or free resource), on the IoT device. That is, the computing capability is the computing resource available to the corresponding IoT device, and the storage capability is the storage resource (i.e., storage space) available to the corresponding IoT device.
[0037] Furthermore, in order to realize a communication relationship between nodes, communication between the nodes is necessary.
[0038] Based on this, in the resource knowledge graph, the available capabilities on the isomeric IoT devices are Computing power and Memory ability and and communication capabilities.
[0039] Here, the communication capability can be understood as the communication strength between two nodes, and includes, for example, the bandwidth resource for communication between IoT devices provided by the edge network, the information transmission speed (i.e., transmission rate), transmission delay, etc. Also includes, for example, the transmission rate and transmission delay between the capabilities of one part of an IoT device and the capabilities of another part.
[0040] In step 102, the software-defined technology is used to abstract the IoT devices of the entities into virtualized nodes, which may include the capability information of the corresponding IoT devices. Different capabilities of the IoT devices can be abstracted into different nodes. Specifically,
[0041] Based on the computing and storage capabilities of the corresponding IoT devices, the IoT devices of the entities can be abstracted into virtualized device nodes, which can include the computing and storage capabilities information of the corresponding IoT devices, i.e., the device nodes can represent the computing and storage capabilities of the corresponding IoT devices.
[0042] According to the computing capabilities of the corresponding IoT devices, the IoT devices of the entities can be abstracted into fine-grained virtualized computing nodes, which can include computing capability information of the corresponding IoT devices, i.e., the computing nodes can represent the computing capabilities of the corresponding IoT devices.
[0043] Based on the storage capabilities of the corresponding IoT devices, the IoT devices of the entities can be abstracted into fine-grained virtualized storage nodes, which can include storage capability information of the corresponding IoT devices, i.e., the storage nodes can represent the storage capabilities of the corresponding IoT devices.
[0044] Thus, in step 102, based on different capabilities of the corresponding IoT devices represented, the types of abstracted nodes may include device nodes, computing nodes and storage nodes. In practical application, for one IoT device, the abstracted nodes may include at least one of device nodes, computing nodes and storage nodes.
[0045] Accordingly, the relationship between two nodes may include at least one of the following relationships 1) to 6).
[0046] 1) A communication relationship between one device node and another device node, which represents the communication strength between one IoT device and another IoT device.
[0047] 2) A dependency relationship between a device node and a computing node, which represents a dependency relationship between an IoT device and at least some of its computing capabilities.
[0048] 3) A dependency relationship between a device node and a storage node, which represents a dependency relationship between an IoT device and at least some of its own storage capabilities.
[0049] 4) A communication relationship between one computing node and one storage node, which represents the communication intensity between at least a part of the computing capacity and at least a part of the storage capacity of the same IoT device, or between at least a part of the computing capacity of one IoT device and at least a part of the storage capacity of another IoT device.
[0050] 5) A communication relationship between one computing node and another computing node, which represents the communication intensity between at least a part of the computing power of the same IoT device, or between at least a part of the computing power of one IoT device and at least a part of the computing power of another IoT device.
[0051] 6) A communication relationship between one storage node and another storage node, which represents the communication strength between at least a portion of the storage capacity of the same IoT device, or between at least a portion of the storage capacity of one IoT device and at least a portion of the storage capacity of another IoT device.
[0052] Regarding step 103, in one embodiment, generating a resource knowledge graph based on the abstracted nodes includes: Determining characteristics of each node and determining relationships between a plurality of nodes, the characteristics being at least used to describe IoT device information corresponding to the corresponding node and capability information of at least a portion of the IoT devices; generating a resource knowledge graph based on the determined characteristics and relationships between the nodes.
[0053] Here, in practical application, since the features of a node include a plurality of features, the features can also be called a feature vector, a feature set, or a feature collection. Since the features include a plurality of description information (i.e., IoT device information corresponding to the corresponding node and at least some capability information of the IoT device), the features can also be called information, an information set, or an information collection. In practical application, the features of a node can be used to characterize an ontology description model. The ontology description model can also be called an entity description model.
[0054] Here, the IoT device information corresponding to the corresponding node may include information such as a device identity identifier (ID), a device type, a device location, a device status, a device Internet Protocol (IP) address, a device function, a device owner, a device interface, etc. The device status may include an on state, an off state, and a fault state. The capability information of at least a part of the IoT device corresponding to the corresponding node may include computing capability information of the corresponding IoT device and / or memory capability information of the corresponding IoT device. Here, the computing capability information may include available computing resource information such as a CPU, a GPU, a field programmable gate array (FPGA), a DSP, etc. The memory capability information may include available memory resource information such as a volatile memory (e.g., a Ferromagnetic Random Access Memory (FRAM)), a non-volatile memory (e.g., a RAM), etc.
[0055] In practical application, after determining the characteristics of each node for the abstracted nodes, it is necessary to connect related nodes, i.e., determine the edges between two nodes to generate a resource knowledge graph.
[0056] where the edges in the resource knowledge graph are The communication relationship between two IoT devices and and relationships between at least some of the capabilities on the IoT device.
[0057] Here, the communication relationship between two IoT devices can be understood as the communication strength between the two IoT devices, and is used to describe the communication conditions between the two IoT devices, such as the bandwidth, information transmission speed, transmission delay, etc. The information transmission speed is also called the information transmission rate.
[0058] The relationships between at least some of the capabilities on an IoT device are: A communication relationship between at least some capabilities on an IoT device and other capabilities of the same IoT device; a communication relationship between at least some capabilities on one IoT device and at least some capabilities on another IoT device; and a dependency relationship between all capabilities on one IoT device and some capabilities of the same IoT device.
[0059] Specifically, if the electronic device senses (i.e., detects) that wired or wireless communication is possible between two IoT devices, the electronic device can determine that there is a communication relationship between the two IoT devices, i.e., that there is a relationship between the two corresponding device nodes.
[0060] When the electronic device senses (i.e., detects) that there is wired or wireless communication between a first processor of a first IoT device and a first memory of a second IoT device, the electronic device can determine that there is a communication relationship between the first processor and the first memory, i.e., that there is a relationship between a first computing node corresponding to the first processor and a first storage node corresponding to the first memory.
[0061] When the electronic device senses (i.e., detects) that communication exists between the second processor of the first IoT device and the second memory of the first IoT device, the electronic device can determine that there is a communication relationship between the second processor and the second memory, i.e., that there is a relationship between a second computing node corresponding to the second processor and a second storage node corresponding to the second memory.
[0062] When the electronic device senses (i.e., detects) that communication exists between the third processor of the first IoT device and the fourth processor of the second IoT device, the electronic device can determine that there is a communication relationship between the third processor and the fourth processor, i.e., that there is a relationship between the third computing node corresponding to the third processor and the fourth computing node corresponding to the fourth processor.
[0063] When the electronic device senses (i.e., detects) that communication exists between the third memory of the first IoT device and the fourth memory of the second IoT device, the electronic device can determine that there is a communication relationship between the third memory and the fourth memory, i.e., that there is a relationship between the third storage node corresponding to the third memory and the fourth storage node corresponding to the fourth memory.
[0064] When the electronic device senses (i.e., detects) that communication exists between the fifth processor and the sixth processor of the first IoT device, the electronic device can determine that there is a communication relationship between the fifth processor and the sixth processor, i.e., that there is a relationship between a fifth computing node corresponding to the fifth processor and a sixth computing node corresponding to the sixth processor.
[0065] If the electronic device senses (i.e., detects) that communication exists between the fifth memory and the sixth memory of the second IoT device, the electronic device can determine that there is a communication relationship between the fifth memory and the sixth memory, i.e., that there is a relationship between the fifth memory node corresponding to the fifth memory and the sixth memory node corresponding to the sixth memory.
[0066] When sensing (i.e., detecting) an IoT device and its computing capability, the electronic device can determine that there is a dependency relationship between the sensed IoT device and the computing capability, that is, there is a relationship between the corresponding one device node and at least one computing node. In practical application, it may be selected whether to explicitly embody such a relationship in the resource knowledge graph in the form of an "edge".
[0067] When sensing (i.e., detecting) an IoT device and its memory capability, the electronic device can determine that there is a dependency relationship between the sensed IoT device and the memory capability, that is, there is a relationship between the corresponding device node and at least one memory node. In practical application, it may be selected whether to explicitly embody such a relationship in the resource knowledge graph in the form of an "edge".
[0068] In practical application, the capabilities of IoT devices and the relationships between IoT devices change dynamically. Therefore, in order to keep the information corresponding to the virtualized resource knowledge graph consistent with the information corresponding to the entity's IoT devices and to improve the accuracy of the resource knowledge graph, it is necessary to monitor changes in IoT devices and dynamically update the resource knowledge graph according to changes in IoT devices.
[0069] Based on this, in one embodiment, the method further comprises: Monitoring IoT devices and When monitoring for occurrence of a change in an IoT device, the method may include updating the resource knowledge graph based on the change status of the monitored IoT device.
[0070] In practical application, the monitoring method of the IoT device may be set according to needs, and the embodiment of the present disclosure is not limited thereto. For example, the changes of the IoT device can be monitored by periodic polling.
[0071] Here, monitoring that a change has occurred in the IoT device is Discover new IoT devices and Monitoring when IoT devices are disconnected from the network; Monitoring changes in the computing power of IoT devices; and Monitoring changes in the memory capacity of IoT devices; Monitoring changes in relationships between IoT devices and and monitoring changes in relationships between at least some of the capabilities on the IoT device.
[0072] Here, when a new IoT device is discovered, updating the resource knowledge graph is Detecting the capabilities of newly discovered IoT devices; Abstracting the detected new IoT device into a corresponding node based on a capability of the new IoT device, the node including at least one of a device node, a computing node, and a storage node; determining a characteristic of each node of the at least one new node and detecting relationships between the new IoT device and other IoT devices; determining a relationship between at least one new node and other nodes based on the detected relationships between the new IoT device and other IoT devices; and updating the resource knowledge graph by connecting the at least one new node to other nodes based on characteristics of each of the determined at least one new node and relationships between the determined at least one new node and other nodes.
[0073] updating the resource knowledge graph when monitoring that an IoT device is disconnected from a network; determining a node in the resource knowledge graph that corresponds to an IoT device that has been disconnected from a network, the node including at least one of a device node, a computing node, and a storage node; Detecting a change in a relationship between the IoT device whose connection to the network has been disconnected and other IoT devices, and detecting a change in a relationship between a capability of the IoT device whose connection to the network has been disconnected and a capability of the other IoT devices; updating relationships between at least one node corresponding to the IoT device whose connection to the network has been disconnected and other nodes in the resource knowledge graph based on the detected change in relationship between the IoT device whose connection to the network has been disconnected and other IoT devices, and the detected change in relationship between the capability of the IoT device whose connection to the network has been disconnected and the capability of the other IoT devices; When it is determined that a communication connection between the IoT device whose connection to the network has been disconnected and other IoT devices is disconnected, and also a communication connection between the capabilities of the IoT device whose connection to the network has been disconnected and the capabilities of the other IoT devices is disconnected, removing from the resource knowledge graph at least one node in the resource knowledge graph corresponding to the IoT device whose connection to the network has been disconnected.
[0074] updating the resource knowledge graph when monitoring changes in computing capabilities of IoT devices; updating characteristics of each node in the resource knowledge graph among at least one node corresponding to a corresponding IoT device based on the monitored changes in computing capacity; updating the relationships between the corresponding equipment nodes and the computing nodes based on the monitored changes in computing power; and updating relationships between the corresponding computing node and other capacity nodes (which may also be referred to as resource nodes, including computing nodes and storage nodes) based on changes in the monitored computing capacity.
[0075] updating the resource knowledge graph when monitoring changes in memory capabilities of the IoT device; updating a feature of each node in the resource knowledge graph among at least one node corresponding to a corresponding IoT device based on the monitored change in memory capacity; updating the relationships between the corresponding device nodes and the storage nodes based on the monitored changes in the storage capacity; and updating relationships between the corresponding storage nodes and other capacity nodes (which may also be referred to as resource nodes, including computing nodes and storage nodes) based on changes in the monitored storage capacity.
[0076] Monitoring changes in relationships between IoT devices may include monitoring changes in communication strength between the IoT devices. In this case, updating the resource knowledge graph may include: determining at least two nodes in the resource knowledge graph that correspond to the IoT devices; determining a change in a relationship between the at least two nodes based on a change in communication strength between the monitored IoT devices; and updating the resource knowledge graph based on a change in a relationship between the at least two nodes.
[0077] Monitoring for changes in relationships between at least some of the capabilities on the IoT device Monitoring changes in communication strength between at least some capabilities on an IoT device and other capabilities of the same IoT device; Monitoring changes in communication strength between at least some capabilities on one IoT device and at least some capabilities on another IoT device in a communication relationship; and monitoring changes in dependencies between all capabilities on one IoT device and some capabilities of the same IoT device.
[0078] Accordingly, updating the resource knowledge graph may include determining a change in a relationship between two corresponding nodes based on a change in a relationship between at least some of the capabilities on the monitored IoT devices, and updating the resource knowledge graph based on the change in the relationship between the at least two nodes.
[0079] In step 103, in practical application, by providing a unified structured representation and organic coupling for multiple isomeric IoT devices and each IoT device with respect to managing the available capabilities (i.e., idle resources) on the isomeric IoT devices, the barrier of resource sharing caused by the isomerization of entity hardware is broken down; thus, it can be understood that the system can globally control the IoT devices in the environment, the capabilities of the IoT devices, the relationships between the IoT devices, and the relationships between at least some capabilities on the IoT devices.
[0080] With regard to adjusting the available capabilities on the isomeric IoT devices, it can be understood that the IoT devices are efficiently scheduled based on the resource knowledge graph, that is, different IoT devices and their capabilities are rationally scheduled based on the IoT devices, the capabilities of the IoT devices, the relationships between the IoT devices, the relationships between at least some capabilities on the IoT devices, and the matching relationships between the capability requirements of the task to be processed and the available capabilities provided by the resource knowledge graph, thereby meeting the task requirements for resources and finally completing the efficient execution of the entire task.
[0081] Based on this, in one embodiment, the method further comprises: Obtaining a task to be processed; and assigning at least one node to the task to be processed based on the resource knowledge graph; The at least one node is used to execute the task to be processed.
[0082] Here, the task to be processed can also be called a task to be executed, and the type of the task to be processed can be set according to needs, for example, training or inferring a deep model (which can also be called a machine learning model, a machine learning task, a deep learning model, a deep learning task, a deep neural network, or a deep neural network model). The acquisition manner of the task to be processed can be set according to needs, for example, acquiring the task to be processed from a local area, or acquiring the task to be processed from another electronic device.
[0083] In practical application, in order to improve the efficiency of executing the task to be processed, at least one node can be allocated to the task to be processed based on the resource requirement of the task to be processed.
[0084] Based on this, in one embodiment, allocating at least one node to the task to be processed based on the resource knowledge graph includes: determining resource requirements for the task to be processed; determining at least one node from the resource knowledge graph that matches the resource requirement; The resource requirements are the resources required to execute the task to be processed, i.e. Computing resources; Storage resources; and a communication resource.
[0085] Here, the communication resources may include the bandwidth used for information interaction or data transmission between at least two nodes during the execution of the task to be processed (i.e., communication bandwidth consumption).
[0086] wherein, in one embodiment, determining at least one node from the resource knowledge graph that matches the resource requirement comprises: retrieving the resource requirements based on characteristics of each node and relationships between nodes in the resource knowledge graph; and determining at least one node that matches the resource requirement based on the search results.
[0087] An information processing method based on IoT devices according to an embodiment of the present disclosure includes: discovering IoT devices and detecting capabilities of the IoT devices; for each IoT device, abstracting the IoT device into a corresponding node based on the capabilities of the corresponding IoT device; and generating a resource knowledge graph based on the abstracted nodes, where the nodes represent capabilities of at least some of the IoT devices, and edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or adjust available capabilities on isomeric IoT devices. According to the means of the embodiments of the present disclosure, intelligent sensing is performed on IoT devices and their capabilities (i.e., idle resources of IoT devices), and through virtualization and software-defined technologies, the IoT devices are abstracted into corresponding nodes based on the sensing capabilities, and a resource knowledge graph is generated based on the abstracted nodes, and the generated resource knowledge graph can be used to realize management and / or adjustment of available capabilities on isomeric IoT devices. In this way, based on the resource knowledge graph, efficient management and flexible scheduling can be performed on resource-constrained and highly isomeric IoT devices, which can provide a prerequisite for realizing edge computing (i.e., realizing computing-intensive computing tasks) in AI-based application scenarios. Furthermore, users no longer need to transmit data related to personal privacy to cloud data centers, which enhances privacy protection, reduces transmission delays, and improves user experience.
[0088] The present disclosure will now be described in further detail with reference to application examples.
[0089] As shown in FIG. 2, multiple types of IoT devices are distributed spatially (geographically), and these IoT devices (e.g., smartphones, smart cameras, smart watches, computing boxes, PCs, tablet computers, robots, etc.) can be interconnected through technologies such as WiFi, Bluetooth, ZigBee protocol, narrowband IoT (NB-IoT), near-field communication (NFC), etc., to form an IoT edge infrastructure. In such a scenario, device resources refer to the available computing resources on the IoT device, the available storage resources on the IoT device, and the bandwidth resources used for device-to-device communication provided by the edge computing network. The resources on one IoT device are extremely limited, so it cannot complete (i.e., execute or process) a computing-intensive computing task, such as a deep learning task (especially a computing task for training a deep model), on its own.
[0090] Therefore, in order for multiple types of IoT devices to work together to perform computing-intensive computing tasks, i.e., to realize distributed (or centerless) computing via IoT edge infrastructure as shown in Figure 2, it is necessary to unify and efficiently schedule the distributed devices (i.e., IoT devices for realizing distributed computing) in the scene as shown in Figure 2, thereby solving the problems of complexity and uncertainty caused by resource collaboration and interaction between heterogeneous IoT devices. In this application embodiment, a service capability abstraction module and a resource knowledge graph construction module are constructed using technologies such as virtualization, software definition, and knowledge graph. Through the service capability abstraction module and the resource knowledge graph construction module, intelligent sensing and unified management of computing resources, storage resources, and communication resources on multiple types of distributed heterogeneous IoT devices are realized. By using the dynamic update mechanism based on the resource knowledge graph, intelligent automatic adaptive adjustment to the frequent entry and exit system of devices (i.e., frequent switching of devices between connected network states and unconnected network states) and dynamic changes of device resources is realized. Furthermore, it provides the possibility to fully utilize the available resources on smart devices to maximize resource utilization, and provides conditions for the IoT devices to efficiently perform computing tasks based on resource sharing and device collaboration.
[0091] This application example provides a resource awareness and management platform (RAMP), and as shown in FIG. 3, in the process of unifying management of isomeric IoT devices, the RAMP mainly relates to the interaction between the RAMP and a local resource platform installed in the IoT device. Here, the core of RAMP is a service capability abstraction module and a resource knowledge graph construction module. RAMP is used to perform computing-intensive tasks, such as training and reasoning of deep learning models, in a collaborative and distributed manner by fully utilizing the free resources on isomeric IoT devices in edge computing scenarios where the resources of a single device are limited.
[0092] The functions of RAMP are explained in detail below.
[0093] First, the function of the service capability abstraction module will be described with reference to FIG.
[0094] Here, the service capability abstraction module is used to abstract the service capability of an IoT device. The IoT device refers to an IoT intelligent terminal device having a certain computing capability and / or memory capability, such as a smart gateway, a computing box, a service robot, a smart camera, a smart phone, a personal computer, an intelligent wearable device, etc. These IoT devices are generally highly isomorphic and resource-constrained (i.e., limited computing capability, memory capability, and communication capability). The service capability abstraction module is mainly used to solve the problem of isomorphism between IoT devices, and its role is to break the limitation between isomorphic hardware, realize sensing, abstraction, and virtualization of resources on a variety of entity IoT devices, and further realize mapping to virtual resource nodes on logical devices that can be scheduled by RAMP.
[0095] With the explosive development trend of IoT and intelligent hardware, the need to introduce intelligent applications to widely distributed IoT devices is also increasing. Mapping the workload of computing tasks (e.g., machine learning models) to these isomeric devices (i.e., these isomeric devices cooperate to perform computing tasks) faces the challenge of the diversity of hardware characteristics. These isomeric hardware include embedded CPUs, GPUs, FPGAs, application specific integrated circuits (ASICs), etc. These hardware have differences in memory organization, computing function units, etc. On the other hand, by using the service capability abstraction module, it is possible to realize unified management and scheduling of these distributed isomeric resources through technologies such as virtualization and software definition.
[0096] As shown in FIG. 4, based on different types of processors, the computing resources on the IoT device may include CPU, GPU, FPGA, ARM, AI chip, etc., and the memory resources (i.e., storage resources) may include buffer, RAM, etc. Resource pooling can realize scheduling, sharing, and collaboration of computing resources and storage resources. Software-defined technology can further virtualize or abstract computing resources and storage resources into corresponding computing nodes and storage nodes, thereby realizing unified management and / or coordination of resources. Thus, the service capability abstraction module facilitates resource scheduling between isomeric IoT devices and contributes to finding appropriate resources that meet the specific computing requirements of computing-intensive computing tasks. The service capability abstraction module can sense, reuse, or share multiple types of device resources (i.e., multiple types of processing capabilities of devices), thereby improving resource utilization and improving the overall service capabilities of the IoT device side.
[0097] Next, the function of the resource knowledge graph construction module will be described with reference to FIG.
[0098] In order for IoT's edge computing system to dynamically sense and fully understand available device resources (device resources are available computing resources on IoT devices, available storage resources on IoT devices, and bandwidth resources provided by the edge computing network for device-to-device communication), the resource knowledge graph construction module uses semantic and knowledge lookup techniques to describe and model these IoT devices, and further constructs a resource knowledge graph based on the nodes abstracted by the service capability abstraction module. As shown in FIG. 5, in the resource knowledge graph, the nodes represent different IoT devices or finer-grained computing or storage capabilities abstracted from devices, that is, the nodes in FIG. 5 include virtualized device nodes, computing nodes, and storage nodes. Each node corresponds to one ontology description model (i.e., the above characteristics) and is used to describe at least the device information and at least some capability information of one IoT device represented by the corresponding node. For example, for an equipment node, the ontology description model may include IoT equipment information (including equipment ID, location, type, state value, function, owner, interface, IP information, etc.), capability information (including CPU, GPU, FPGA, DSP, memory resources, etc.). The edges in the resource knowledge graph represent the association relationships between adjacent nodes, such as communication relationships (i.e., wired or wireless communication relationships) and / or dependency relationships. The IoT equipment resources represented by the association relationships are useful for illustrating the internal collaboration and sharing mechanisms of multiple isomerized equipment.
[0099] In order to adapt to the dynamic IoT edge scene, meet the challenges of available resource fluctuations, and maintain the consistency between entity IoT devices and virtualized device resources, it is necessary to consider the automatic construction and dynamic update mechanism of the resource knowledge graph. With such a mechanism, when a terminal device accesses the system, changes its state, or exits the system, the corresponding resource knowledge graph is also synchronously updated. In addition, some scheduling and coordination policies (e.g., preferentially scheduling nodes whose storage capabilities meet preset conditions) and sharing and collaboration mechanisms can be pre-configured to improve resource utilization and overall service capability. Based on the resource knowledge graph construction module, the edge computing system can realize efficient management and flexible scheduling of limited available resources on heterogeneous distributed (or centerless) IoT devices to meet the resource requirements of computing tasks.
[0100] Fig. 6 shows an application scenario in which RAMP realizes a smart home. Based on the application scenario shown in Fig. 6, as shown in Fig. 7, the interaction process between RAMP and IoT devices may include the following steps 701 to 707.
[0101] In step 701, the IoT device connects to a network. Then, step 702 is executed.
[0102] Specifically, an IoT device accesses a network.
[0103] In step 702, RAMP performs device recognition. If the recognition is successful, step 703 is executed.
[0104] Specifically, RAMP may perform device recognition (i.e., detection) based on a preset scheme. If the recognition fails, it may return recognition failure information to the IoT device; if the recognition succeeds, it may continue to execute step 703.
[0105] Here, RAMP interacts with the local resource platform on the IoT device to recognize the device.
[0106] In step 703, RAMP detects whether the device has turned on the resource sharing privilege. If the detection result indicates that the device has turned on the resource sharing privilege, it executes step 704.
[0107] Specifically, RAMP can detect whether the device has turned on resource sharing authority based on a preset method. If the detection result indicates that the device has not turned on resource sharing authority, the node cannot be created, and RAMP returns creation failure information to the IoT device. If the detection result indicates that the device has turned on resource sharing authority, step 704 can be continued.
[0108] In step 704, RAMP performs resource sensing, abstraction, and virtualization to create software-defined device nodes. Then, step 705 is executed.
[0109] Specifically, RAMP can sense (i.e., detect) the resources of IoT devices based on a preset scheme and abstract the IoT device resources (i.e., capabilities) of an entity into a virtualized node using software-defined techniques.
[0110] Here, RAMP interacts with a local resource platform on the IoT device to sense resources.
[0111] In step 705, RAMP generates a device ontology description model, followed by step 706.
[0112] Specifically, RAMP can generate a device ontology description model based on the resources of a corresponding IoT device.
[0113] In step 706, RAMP senses association relationships between devices. Then, step 707 is performed.
[0114] In step 707, RAMP adds equipment nodes and resource information to the knowledge graph.
[0115] Based on the application scenario shown in FIG. 6, as shown in FIG. 8, the interaction process between RAMP and a task server may include the following steps 801-804.
[0116] In step 801, the task server sends a resource search request to RAMP, and RAMP determines whether the task type is supported. If the determination result indicates that the task type is supported, step 802 is executed.
[0117] In step 802, RAMP analyzes the request to retrieve a resource from the resource knowledge graph. If the resource is retrieved, step 803 is executed.
[0118] In step 803, RAMP performs resource task matching. If matching is successful, it executes step 804.
[0119] In step 804, RAMP adds the matching resource information to a result list.
[0120] The means according to this application example has the following advantages 1) to 3).
[0121] 1) It is possible to perform fine-grained intelligent sensing, virtualization, and software definition for multiple types of computing resources (CPU, GPU, FPGA, DSP, etc.) and storage resources (Memory, RAM, etc.) on IoT devices.
[0122] 2) In dynamically changing IoT scenarios, in the case of frequent device entry and exit systems (i.e., frequent switching of devices between connected network states and unconnected network states) and dynamic changes in device resources, it is possible to realize dynamic sensing of resources through intelligent automatic adaptation and automatic updating of resource knowledge graphs.
[0123] 3) By providing a structured representation and unified management of multi-type idle resources on multiple isomeric IoT devices, the system can fully understand and efficiently schedule the available resources on widely distributed multiple isomeric IoT devices when performing computing-intensive computing tasks, and improve system performance through maximizing resource utilization.
[0124] To realize the method of the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing device based on an IoT device, as shown in FIG. 9 , the device includes: a detection unit 901 configured to discover IoT devices and detect the capabilities of the IoT devices; a first processing unit 902 configured for each IoT device to abstract the IoT device into a corresponding node based on the capabilities of the corresponding IoT device; and a second processing unit 903 configured to generate a resource knowledge graph based on the abstracted nodes; The nodes represent capabilities of at least some of the IoT devices, and the edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or coordinate available capabilities on isomeric IoT devices.
[0125] wherein the available capacity is: Computing power and Memory ability and and communication capabilities.
[0126] In one embodiment, the second processing unit 903 is Determining characteristics of each node and determining relationships between a plurality of nodes, the characteristics being at least used to describe IoT device information corresponding to the corresponding node and capability information of at least a portion of the IoT devices; generating a resource knowledge graph based on the determined characteristics and relationships between the nodes.
[0127] where the edges in the resource knowledge graph are The communication relationship between two IoT devices and and representing at least one of the relationships between at least some of the capabilities on the IoT device.
[0128] In one embodiment, the detection unit 901 is configured to monitor an IoT device, The second processing unit 903 is configured to update the resource knowledge graph based on the change status of the IoT device monitored by the detection unit 901 when the detection unit 901 monitors that a change has occurred in the IoT device.
[0129] Here, the detection unit 901 is Discover new IoT devices and Monitoring when IoT devices are disconnected from the network; Monitoring changes in the computing power of IoT devices; and Monitoring changes in the memory capacity of IoT devices; Monitoring changes in relationships between IoT devices and and monitoring changes in relationships between at least some of the capabilities on the IoT device.
[0130] In one embodiment, the apparatus further comprises: an acquisition unit configured to acquire a task to be processed; and a third processing unit configured to assign at least one node to the task to be processed based on the resource knowledge graph; The at least one node is used to execute the task to be processed.
[0131] Here, in one embodiment, the third processing unit: determining resource requirements for the task to be processed; determining at least one node from the resource knowledge graph that matches the resource requirement; The resource requirements are the resources required to execute the task to be processed, i.e. Computing resources; Storage resources; and a communication resource.
[0132] In one embodiment, the third processing unit comprises: retrieving the resource requirements based on characteristics of each node and relationships between nodes in the resource knowledge graph; determining at least one node that matches the resource requirement based on the search results.
[0133] In practical application, the detection unit 901 and the acquisition unit can be realized by a combination of a processor and a communication interface within an information processing device, and the first processing unit 902, the second processing unit 903 and the third processing unit can be realized by a processor within an information processing device.
[0134] In addition, when the information processing device according to the above embodiment performs information processing, only the division of each of the above program modules is taken as an example for explanation, and in actual application, the above processing can be assigned to different program modules to complete as necessary, that is, the internal structure of the device can be divided into different program modules to complete all or part of the above processing. In addition, the information processing device according to the above embodiment and the information processing method embodiment belong to the same concept, and the specific realization process can be referred to the method embodiment, and will not be further described here.
[0135] In order to realize the method of the embodiments of the present disclosure based on the hardware implementation of the above program modules, the embodiments of the present disclosure further provide an electronic device, as shown in FIG. 10, the electronic device 1000 includes a communication interface 1001, a processor 1002 and a memory 1003.
[0136] The communication interface 1001 is capable of performing information interaction with other electronic devices. The processor 1002 is connected to the communication interface 1001 to realize information interaction with other electronic devices, and is configured to execute the methods related to the one or more technical solutions described above when executing a computer program.
[0137] The memory 1003 is configured to store a computer program executable by the processor 1002 .
[0138] Specifically, the processor 1002: Discovering IoT devices via the communication interface 1001 and detecting the capabilities of the IoT devices; for each IoT device, abstracting the IoT device into a corresponding node based on a capability of the corresponding IoT device; generating a resource knowledge graph based on the abstracted nodes; The nodes represent capabilities of at least some of the IoT devices, and the edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or coordinate available capabilities on isomeric IoT devices.
[0139] wherein the available capacity is: Computing power and Memory ability and and communication capabilities.
[0140] In one embodiment, the processor 1002 is Determining characteristics of each node and determining relationships between a plurality of nodes, the characteristics being at least used to describe IoT device information corresponding to the corresponding node and capability information of at least a portion of the IoT devices; generating a resource knowledge graph based on the determined characteristics and relationships between the nodes.
[0141] where the edges in the resource knowledge graph are The communication relationship between two IoT devices and and representing at least one of the relationships between at least some of the capabilities on the IoT device.
[0142] In one embodiment, the processor 1002 is Monitoring an IoT device via the communication interface 1001; When monitoring for occurrence of a change in an IoT device, updating the resource knowledge graph based on the change status of the monitored IoT device.
[0143] In one embodiment, the processor 1002 is Discover new IoT devices and Monitoring when IoT devices are disconnected from the network; Monitoring changes in the computing power of IoT devices; and Monitoring changes in the memory capacity of IoT devices; Monitoring changes in relationships between IoT devices and and monitoring changes in relationships between at least some of the capabilities on the IoT device.
[0144] In one embodiment, the processor 1002 is Obtaining a task to be processed; assigning at least one node to the task to be processed based on the resource knowledge graph; The at least one node is used to execute the task to be processed.
[0145] In one embodiment, the processor 1002 is determining resource requirements for the task to be processed; determining at least one node from the resource knowledge graph that matches the resource requirement; The resource requirements are the resources required to execute the task to be processed, i.e. Computing resources; Storage resources; and a communication resource.
[0146] In one embodiment, the processor 1002 is retrieving the resource requirements based on characteristics of each node and relationships between nodes in the resource knowledge graph; determining at least one node that matches the resource requirement based on the search results.
[0147] The specific process of the processor 1002 performing the above operations can be referred to in the method embodiments, and the description thereof will be omitted here.
[0148] Of course, in practical applications, each component in the electronic device 1000 is coupled via a bus system 1004. It is understandable that the bus system 1004 is used to realize the connection and communication between these components. The bus system 1004 includes a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, various buses are referred to as the bus system 1004 in FIG. 10.
[0149] Memory 1003 in the embodiments of the present disclosure is used to store various types of data to support the operation of electronic device 1000, including any computer programs for running on electronic device 1000.
[0150] The method described in the embodiment of the present disclosure above may be applied to or realized by the processor 1002. The processor 1002 may be an integrated circuit chip having a signal processing capability. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware or an instruction in the form of software in the processor 1002. The above processor 1002 may be a general-purpose processor, a DSP, a GPU, or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The processor 1002 may realize or execute each method, step, and logic block diagram described in the embodiment of the present disclosure. The general-purpose processor may be a microprocessor or any conventional processor, etc. With respect to the steps of the method described in the embodiment of the present disclosure, they may be directly embodied as execution completion by a hardware decoding processor, or execution completion by a combination of hardware and software modules in the decoding processor. The software module is located in a storage medium, which may be located in a memory 1003, and the processor 1002 reads the information in the memory 1003 and combines with the hardware to complete the steps of the above method.
[0151] In an exemplary embodiment, the electronic device 1000 may be implemented by one or more ASICs, DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), FPGAs, general-purpose processors, GPUs, controllers, microcontrollers (MCUs), microprocessors, various AI chips, class brain chips, or other electronic elements to perform the methods described above.
[0152] It should be noted that the memory 1003 of the embodiment of the present disclosure may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Here, the non-volatile memory may be a ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a FRAM, a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM). The magnetic surface memory may be a magnetic disk memory or a magnetic tape memory. The volatile memory may be a RAM used as an external cache. By way of example and not limitation, many forms of RAM can be used.Examples include static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synclink dynamic random access memory (SLDRAM), and direct memory bus random access memory (DRRAM). The memory described in the embodiments of the present disclosure is intended to include, but is not limited to, these and any other suitable types of memory.
[0153] To realize the method according to the embodiment of the present disclosure, the embodiment of the present disclosure further provides an information processing system based on an IoT device, the system including: A first functional component configured to discover IoT devices and detect capabilities of the IoT devices; a second functional component configured to, for each IoT device, abstract the IoT device into a corresponding node based on a capability of the corresponding IoT device, and generate a resource knowledge graph based on the abstracted nodes; Here, the first functional component and the second functional component are provided in two electronic devices.
[0154] 11, the system may include a first electronic device 1101 and a second electronic device 1102. The first electronic device 1101 is provided with the first functional component, and the second electronic device 1102 is provided with the second functional component.
[0155] Here, the specific processing steps of the first functional component and the second functional component are the same as those described above, and therefore will not be described here.
[0156] In an exemplary embodiment, the embodiment of the present disclosure further provides a storage medium, i.e., a computer storage medium, specifically a computer readable storage medium, for example including a memory 1003 for storing a computer program, the computer program being executed by the processor 1002 of the electronic device 1000 to complete the steps of the method described above. The computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM.
[0157] It should be noted that the use of terms such as "first" and "second" does not necessarily denote any particular order or priority, but rather is intended to distinguish between similar objects.
[0158] In addition, the technical solutions described in the embodiments of the present disclosure may be arbitrarily combined if they do not conflict with each other.
[0159] The above are merely preferred embodiments of the present disclosure, and are not intended to limit the scope of protection of the present disclosure.
Claims
1. An information processing method based on an IoT device, comprising: Discovering IoT devices and detecting capabilities of the IoT devices; For each IoT device, abstracting the IoT device into a corresponding node based on the capability of the corresponding IoT device; generating a resource knowledge graph based on the abstracted nodes; An information processing method based on IoT devices, wherein the nodes represent at least some capabilities of IoT devices, and edges in the resource knowledge graph represent relationships between two adjacent nodes, and the resource knowledge graph is used to manage and / or adjust available capabilities on isomeric IoT devices.
2. generating a resource knowledge graph based on the abstracted nodes, Determining characteristics of each node and determining relationships between a plurality of nodes, wherein the characteristics are used at least to describe IoT device information corresponding to the corresponding node and capability information of at least some of the IoT devices; generating a resource knowledge graph based on the determined characteristics and relationships between the nodes. The method of claim 1.
3. The edges in the resource knowledge graph are: A communication relationship between two IoT devices; and representing at least one of the relationships between at least some capabilities on the IoT device. The method of claim 1.
4. The method further comprises: Monitoring IoT devices; When monitoring that a change has occurred in the IoT device, updating the resource knowledge graph based on the change status of the monitored IoT device.
4. The method according to any one of claims 1 to 3.
5. Monitoring that a change has occurred in the IoT device includes: Discovering new IoT devices and Monitoring for disconnection of an IoT device from a network; Monitoring changes in the computing power of IoT devices; and Monitoring changes in memory capabilities of IoT devices; and Monitoring changes in relationships between IoT devices; and and monitoring changes in relationships between at least some capabilities on the IoT device. The method of claim 4.
6. The method further comprises: Obtaining a task to be processed; assigning at least one node to the task to be processed based on the resource knowledge graph; The at least one node is used to execute the task to be processed.
4. The method according to any one of claims 1 to 3.
7. assigning at least one node to the task to be processed based on the resource knowledge graph; determining resource requirements for the task to be processed; determining at least one node from the resource knowledge graph that matches the resource requirement; The resource requirements are the resources required to execute the task to be processed, i.e. Computing resources; Storage resources; and a communication resource. The method of claim 6.
8. Determining at least one node from the resource knowledge graph that matches the resource requirement comprises: retrieving the resource requirements based on characteristics of each node and relationships between nodes in the resource knowledge graph; determining at least one node that matches the resource requirement based on the search results. The method of claim 7.
9. An electronic device, a processor and a memory configured to store a computer program executable by the processor; 9. An electronic device, wherein the processor, when executing the computer program, is configured to perform the steps of the method according to any one of claims 1 to 8.
10. A storage medium on which a computer program is stored, A storage medium, the computer program causing the steps of the method according to any one of claims 1 to 8 to be implemented when executed by a processor.
Citation Information
Patent Citations
Internet of Things capability and knowledge mapping and construction method thereof
CN108021718A
Internet of Things security event identification method and device thereof and computer equipment
CN111641621A
Distributed mapping capabilities for large-scale media clouds
JP2015503146A
Incident effect range estimation device, incident effect range estimation method, storage medium, and system
WO2018079439A1
