CN116489152A

CN116489152A - Linkage control method and device for Internet of things equipment, electronic equipment and medium

Info

Publication number: CN116489152A
Application number: CN202310736186.6A
Authority: CN
Inventors: 王电; 王嘉忆; 谢东
Original assignee: Beijing Defeng Xinzheng Technology Co ltd
Current assignee: Beijing Defeng Xinzheng Technology Co ltd
Priority date: 2023-06-21
Filing date: 2023-06-21
Publication date: 2023-07-25
Anticipated expiration: 2043-06-21
Also published as: CN116489152B

Abstract

The embodiment of the invention discloses a linkage control method and device of internet of things equipment, electronic equipment and a medium. One embodiment of the method comprises the following steps: identifying the edge node set to obtain an edge node characteristic information set; according to the edge node characteristic information set, determining an edge node corresponding to the acquisition task information; acquiring edge state information corresponding to a task edge node; determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information; in response to determining that the resource requirement is not met, performing resource scheduling processing on the task edge node to obtain a scheduled edge node; receiving the collected data sent by the edge node after the dispatching; and controlling and executing the operation of determining the linkage rule information of the preset internet of things equipment in response to determining that the abnormal data exists in the acquired data. According to the embodiment, the linkage rule is issued to the edge node through the cloud edge collaborative framework, so that the transmission delay and cloud load can be reduced, and the management efficiency of the Internet of things equipment is improved.

Description

Linkage control method and device for Internet of things equipment, electronic equipment and medium

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a linkage control method and device of internet of things equipment, electronic equipment and a medium.

Background

The internet of things platform utilizes communication and network, automatic control and artificial intelligence and other technologies to connect, control and manage various internet of things devices, and provides a more comfortable, convenient, safe and environment-friendly internet of things environment for users. The internet of things platform can also control the internet of things equipment to carry out the linkage control of the internet of things equipment. For linkage control of the internet of things equipment, the following modes are generally adopted: and executing preset Internet of things equipment linkage rule information through cloud control of corresponding Internet of things equipment.

However, the inventor finds that when the linkage of the internet of things device is controlled in the above manner, the following technical problems often exist:

firstly, the cloud control internet of things device is utilized to execute corresponding preset internet of things device linkage rules, so that transmission delay and cloud data processing load are high, and the management efficiency of the internet of things device is low.

Secondly, only the resources of the edge nodes with sufficient resources or cloud resources are scheduled to the edge nodes with insufficient resources, the consideration factors are single, and the quality of the resources cannot be guaranteed, so that the difficulty and the transmission load of resource scheduling are increased, and the task completion stability is low.

Thirdly, the existing named entity model basically takes a static word vector as input, however, the static word vector cannot be dynamically adjusted according to text context, and the association relationship between words and sentences cannot be fully considered, so that the accuracy of the named entity model is low, further, the identification accuracy of internet of things equipment is low, and the cloud security is low.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a linkage control method, a linkage control device, an electronic device, and a medium for an internet of things device, so as to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide an image segmentation method, including: identifying each edge node in the accessed edge node set to generate edge node characteristic information, and obtaining an edge node characteristic information set; determining an edge node corresponding to the acquisition task information as a task edge node according to the edge node characteristic information set, wherein the acquisition task information is the task information which is sent to the task edge node and used for controlling the task edge node to acquire data; acquiring edge state information corresponding to the task edge node; determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information; responding to the fact that the task edge node does not meet the resource requirement corresponding to the collected task information, and carrying out resource scheduling processing on the task edge node to obtain a scheduled edge node; transmitting the acquisition task information to the scheduled edge node, and receiving acquisition data transmitted by the scheduled edge node; and in response to determining that abnormal data exists in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set.

In a second aspect, some embodiments of the present disclosure provide an image segmentation apparatus including: the identifying unit is configured to identify each edge node in the accessed edge node set so as to generate edge node characteristic information and obtain an edge node characteristic information set; a first determining unit configured to determine, as a task edge node, an edge node corresponding to acquisition task information according to the edge node feature information set, wherein the acquisition task information is task information sent to the task edge node to control the task edge node to acquire data; the acquisition unit is configured to acquire the edge state information corresponding to the task edge node; the second determining unit is configured to determine whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information; the resource scheduling processing unit is configured to perform resource scheduling processing on the task edge node to obtain a scheduled edge node in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information; a transmitting unit configured to transmit the acquisition task information to the scheduled edge node, and to receive acquisition data transmitted by the scheduled edge node; the control unit is configured to trigger alarm information and control at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information in response to determining that the abnormal data exists in the acquired data, wherein the preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a method as described in any of the implementations of the first aspect.

The above embodiments of the present disclosure have the following advantages: according to the linkage control method for the Internet of things equipment, disclosed by the embodiment of the invention, the linkage rule is issued to the edge node through the cloud edge collaborative frame, so that the transmission delay and cloud load can be reduced, and the management efficiency of the Internet of things equipment is improved. Specifically, the reason why the related transmission delay is higher, the cloud data processing load is higher and the management efficiency of the internet of things device is lower is that: and the cloud control internet of things device is utilized to execute corresponding preset internet of things device linkage rules, so that transmission delay and cloud data processing load are high, and the management efficiency of the internet of things device is low. Based on this, the linkage control method of the internet of things device according to some embodiments of the present disclosure may first identify each edge node in the accessed edge node set to generate edge node feature information, and obtain an edge node feature information set. Here, identifying the accessed edge node may improve the security of the cloud. And secondly, determining an edge node corresponding to the acquisition task information as a task edge node according to the edge node characteristic information set, wherein the acquisition task information is the task information which is sent to the task edge node and used for controlling the task edge node to acquire data. Here, determining the edge node corresponding to the acquisition task information, that is, issuing the acquisition task information to the edge node can reduce the data transmission delay and improve the transmission stability. And obtaining the edge state information corresponding to the task edge node. Here, acquiring the edge state information facilitates a subsequent determination of whether the edge node can perform the data acquisition task information. And then, determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information. And then, in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information, performing resource scheduling processing on the task edge node to obtain the scheduled edge node. Here, the problem of unbalanced load of the edge node can be solved by carrying out resource scheduling processing, and the resource utilization rate of the edge node is improved. And then, sending the acquisition task information to the scheduled edge node, and receiving the acquisition data sent by the scheduled edge node. And finally, in response to determining that abnormal data exists in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute at least one operation of determining preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set. The abnormal data triggers the linkage rule information of the preset Internet of things equipment, so that the Internet of things equipment can cooperatively work, timely response of the Internet of things equipment is realized, and management efficiency of the Internet of things equipment is improved. Therefore, the linkage control method of the Internet of things equipment can send the linkage rule to the edge node through the cloud edge collaborative frame, so that the transmission delay and cloud load can be reduced, and the management efficiency of the Internet of things equipment is improved.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of an linked control method of an Internet of things device according to the present disclosure;

FIG. 2 is a schematic structural view of some embodiments of an linked control of an Internet of things device according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a flow 100 of some embodiments of an internet of things device linkage control method according to the present disclosure. The linkage control method of the Internet of things equipment comprises the following steps:

Step 101, identifying each edge node in the accessed edge node set to generate edge node characteristic information, and obtaining an edge node characteristic information set.

In some embodiments, an execution body (e.g., a cloud server) of the linkage control method of the internet of things device may identify each edge node in the accessed edge node set to generate edge node feature information, so as to obtain an edge node feature information set. The access mode of the accessed edge node set may be an access mode through an MQTT (Message Queuing Telemetry Transport, message queue telemetry transport) protocol. The edge node may be a node that is located at a distance from the internet of things device, provides resources such as limited storage, computation, and network, and cooperatively communicates with the cloud server. For example, the edge node may include at least one of: vehicle terminal, router and border gateway. The certain distance may be 500 meters. The internet of things device can be a device which is connected with the Internet and can collect data and transmit the data. For example, the above-mentioned internet of things device may include at least one of: intelligent electrical equipment, sensors and cameras. The edge node characteristic information may be information characterizing the identity of the edge node. For example, the edge node characteristic information may be an edge node number. In practice, the executing body may first receive response information sent by an edge node in the accessed edge node set, to obtain a response information set. The response information may be response information of the edge node to a probe packet sent by the cloud server. And then, carrying out identification processing on each response information in the response information set to generate edge node characteristic information representing the edge node, and obtaining an edge node characteristic information set.

Step 102, according to the edge node characteristic information set, determining an edge node corresponding to the acquired task information as a task edge node.

In some embodiments, the executing body may determine, as the task edge node, an edge node corresponding to the collected task information according to the edge node feature information set. The task information is the task information which is sent to the task edge node and used for controlling the task edge node to collect data. The task edge node may be an edge node corresponding to the acquisition task information.

As an example, the execution subject may first analyze the collected task information to obtain analyzed task information. The parsed task information may be information including characteristic information of a designated edge node. And secondly, screening out edge node characteristic information matched with the task identification information from the edge node characteristic information set to obtain a task edge node.

And step 103, obtaining edge state information corresponding to the task edge node.

In some embodiments, the execution body may obtain edge state information corresponding to the task edge node. The edge state information may represent information of an operation state of an edge node. The edge state information may include at least one of: edge node memory information, CPU (Central Processing Unit ) information, and disk information.

Step 104, determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information.

In some embodiments, the execution body may determine, according to the edge state information, whether the task edge node meets a resource requirement corresponding to the acquisition task information. The resource requirement may be a requirement for an operation resource or a storage resource.

As an example, the execution body may first compare the edge state information with the resource requirement required for collecting the task information, and determine whether the task edge node meets the resource requirement corresponding to the task information.

And step 105, in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information, performing resource scheduling processing on the task edge node to obtain a scheduled edge node.

In some embodiments, the execution body may perform resource scheduling processing on the task edge node to obtain the scheduled edge node in response to determining that the task edge node does not meet the resource requirement corresponding to the collected task information. The scheduled edge node may be an edge node capable of running the acquisition task information.

As an example, the execution body may utilize an ant colony algorithm to perform resource scheduling processing on the task edge node in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information, so as to obtain the scheduled edge node.

In some optional implementations of some embodiments, the performing resource scheduling on the task edge node to obtain a scheduled edge node may include the following steps:

and the first step, determining an edge node set within a preset range of the task edge node as an area edge node set. The preset range is a range with the task edge node as a center and a preset threshold as a radius. The predetermined threshold may be 200 meters.

And a second step of obtaining the state information of each regional edge node in the regional edge node set to obtain a state information set as a regional state information set. The area state information in the area state information set may be operation state information of a CPU and a memory of the area edge node.

And thirdly, determining the idle resources of each regional edge node in the regional edge node set by using the regional state information set to obtain an idle resource set. The idle resources may be resources that are needed by the area edge node to remove resources needed by the edge node to run the corresponding task information.

And step four, screening out the region edge nodes meeting the preset idle resource threshold value from the idle resource set as target region edge nodes to obtain a target region edge node set. The preset idle resource threshold may be thirty percent of the resources included in the edge node.

And fifthly, acquiring a historical task information set of each target area edge node in the target area edge node set, and obtaining a historical task information set. The historical task information in the historical task information group may be task information executed by the target area edge node before the current time.

And step six, generating the task completion rate of each target area edge node in the target area edge node set according to the historical task information set to obtain a task completion rate set. The task completion rate may be the efficiency of completing task information on time and successfully by the target area edge node.

As an example, the execution subject may execute the following determination step for each of the historical task information groups in the set of historical task information groups: and determining the ratio of the number of the historical task information which is completed in time and successfully to the number of the historical task information included in the historical task information group as the task completion rate of the edge of the target area.

And seventh, screening out target area edge nodes meeting a preset task completion rate threshold from the task completion rate set to serve as task area edge nodes, and obtaining a task area edge node set. The preset task completion rate threshold may be 0.8.

And eighth step, constructing dynamic resource scheduling rule information. The dynamic resource scheduling rule information may represent information of a resource scheduling rule constructed according to a task completion rate of each task area edge node in the task area edge node set. In practice, the executing entity may first determine an initial priority set for the task area edge node set. Wherein each initial priority in the set of initial priorities is the same. Then, in response to determining that the task area edge node can complete the assigned task information on time and successfully each time, the priority of the corresponding task area edge node is increased by one level. And finally, in response to determining that the task area edge node receives the allocated task information each time, and the task completion rate is smaller than a preset task completion rate threshold, reducing the priority of the corresponding task area edge node by one level.

And ninth, determining the task area edge nodes for providing idle resources in the task area edge node set according to the dynamic resource scheduling rule information, and obtaining a resource area edge node set.

As an example, the execution body may first determine, according to the dynamic resource scheduling rule information, a priority of each task area edge node in the task area edge node set at a current time, to obtain a current priority set. And then comparing the current priority set with the initial priority set to obtain a comparison result set. And finally, determining the comparison result with the current priority higher than or equal to the initial priority in the comparison result set as a target comparison result set. And determining the task area edge node set corresponding to the target comparison result set as a resource area edge node set.

And tenth, scheduling the idle resource information set corresponding to the resource area edge node set to the task edge node to obtain the scheduled edge node.

The related content of the technical scheme is taken as an invention point of the embodiment of the disclosure, so that the technical problem mentioned in the background art is solved, namely, only the resource of the edge node with sufficient resources or the cloud resource is scheduled to the edge node with insufficient resources, the consideration factor is single, and the quality of the resources cannot be ensured, thereby increasing the difficulty and the transmission load of resource scheduling and having lower task completion stability. Factors causing greater difficulty in resource scheduling and transmission load and lower task completion stability are often as follows: only the edge node with more sufficient resources or cloud resources are scheduled to the edge node with insufficient resources, the consideration factor is single, and the quality of the resources cannot be guaranteed, so that the difficulty and the transmission load of resource scheduling are increased, and the task completion stability is low. If the above factors are solved, the effects of reducing the resource scheduling difficulty and the transmission load and improving the task completion stability can be achieved. To achieve this, the present disclosure first determines, as a region edge node set, an edge node set that is within a preset range of the task edge node described above. Here, determining the edge node within the preset range may reduce the difficulty of resource scheduling and the transmission load of long-distance transmission. And secondly, acquiring the state information of each region edge node in the region edge node set to obtain a state information set as a region state information set. And determining the idle resources of each regional edge node in the regional edge node set by using the regional state information set to obtain an idle resource set. The obtained idle resource set can reduce the waste of idle resources and improve the utilization rate of the resources. And thirdly, screening out the region edge nodes meeting the preset idle resource threshold value from the idle resource set as target region edge nodes to obtain a target region edge node set. Here, the screening of the regional edge nodes meeting the preset idle resource threshold can ensure that each regional edge node normally processes task information, and the reasonable utilization of resources is improved. And then, acquiring a historical task information set of each target area edge node in the target area edge node set to obtain a historical task information set. And generating the task completion rate of each target area edge node in the target area edge node set according to the historical task information set to obtain a task completion rate set. And screening out target area edge nodes meeting a preset task completion rate threshold from the task completion rate set to serve as task area edge nodes, and obtaining a task area edge node set. Here, screening out the target area edge nodes that meet the preset task completion rate threshold can improve the quality of the provided resources, so that the task completion stability can be improved. Then, dynamic resource scheduling rule information is constructed. Here, constructing dynamic resource scheduling rule information facilitates subsequent resource scheduling. And finally, determining the task area edge nodes for providing idle resources in the task area edge node set according to the dynamic resource scheduling rule information to obtain a resource area edge node set. Here, determining the edge node of the resource area through the priority can improve the quality of the scheduling resource and improve the efficiency of task completion. And scheduling the idle resource information set corresponding to the resource region edge node set to the task edge node to obtain a scheduled edge node. Therefore, by considering the position information of the edge node, idle resources, task completion rate and other factors, the resource scheduling difficulty and the transmission load can be reduced, and the task completion stability can be improved.

And step 106, sending the acquisition task information to the scheduled edge node, and receiving the acquisition data sent by the scheduled edge node.

In some embodiments, the executing body may send the acquisition task information to the scheduled edge node, and receive the acquisition data sent by the scheduled edge node. The collected data may be data corresponding to the collected task information.

In some alternative implementations of some embodiments, the collected data may be obtained by:

the first step, in response to receiving the acquisition task information, analyzing the acquisition task information to obtain analyzed task information.

And secondly, determining the Internet of things equipment set accessed to the scheduled edge node as the accessed Internet of things equipment set. The internet of things equipment in the internet of things equipment set can be equipment which is connected with the internet and can collect data and transmit the data. For example, the above-mentioned internet of things device may include at least one of: intelligent electrical equipment, sensors and cameras.

And thirdly, identifying each access internet-of-things device in the access internet-of-things device set to generate access internet-of-things device characteristic information, and obtaining an access internet-of-things device characteristic information set.

As an example, the executing body may identify each access internet of things device in the access internet of things device set by using a device identification model, so as to generate access internet of things device feature information, and obtain an access internet of things device feature information set. The device identification model may be a CNN (Convolutional Neural Network ) model or an RNN (Recurrent Neural Networks, recurrent neural network) model.

And step four, determining the access internet of things equipment corresponding to the acquired data as target internet of things equipment according to the analyzed task information and the access internet of things equipment characteristic information set.

As an example, the executing body may screen out the access internet of things device feature information matched with the parsed task information from the access internet of things device feature information set, to obtain the target access internet of things device feature information. And determining the access internet-of-things equipment corresponding to the characteristic information of the target access internet-of-things equipment as target internet-of-things equipment.

And fifthly, receiving the video data sent by the target internet of things device. The video data may be video data to be identified.

And sixthly, acquiring a target detection model file after training. The object detection model file may be a file of a model for identifying the video data.

And seventhly, inputting the video data into a target detection model corresponding to the target detection model file to obtain acquisition data.

In some alternative implementations of some embodiments, the target detection model may be trained by:

the first step, a sample set is obtained, wherein samples in the sample set comprise: video, a sample tag set corresponding to the video. The sample tags in the sample tag set may be tags for identifying the categories of the objects in the video.

Second, for each sample in the sample set, the following training steps are performed:

and step 1, performing key frame extraction processing on the video corresponding to the sample to obtain a key frame sequence. Wherein, the key frames in the key frame sequence may be video frames containing main semantic information in the video. In practice, the execution body may perform key frame extraction processing on the video corresponding to the sample by using an optical flow method, so as to obtain a key frame sequence.

And 2, inputting the key frame sequence into an initial target detection model to obtain a detection result set corresponding to the sample. The initial object detection model may be a model for identifying an object in the video. For example, the initial object detection model may be an R-CNN (Region with CNN features) model or an SSD (Single Short multibox Detector, single pass polygon detection) model. The detection result in the detection result set may be an object type result obtained by identifying an object in the video by using an initial target detection model.

And 3, comparing the sample label set corresponding to the sample with the detection result set to obtain a comparison result set. Wherein, the comparison result in the comparison result set may include: the detection result is represented to be the same as the corresponding sample label, and the detection result is represented to be different from the corresponding sample label.

And step 4, determining whether the initial target detection model reaches a preset optimization target according to the comparison result set. The preset optimization target may be the accuracy of the initial target detection model. For example, the preset optimization objective may be 0.9.

As an example, the execution body may first determine the number of detection results in the comparison result set that is the same as the number of sample tags, and obtain the correct number of samples. Then, the ratio of the number of correct samples to the number of comparison results included in the comparison result set is determined as a loss value. And finally, determining whether the initial target detection model reaches a preset optimization target or not through the loss value.

And a sub-step 5 of determining the initial target detection model as the trained target detection model in response to determining that the initial target detection model reaches the optimal target.

And thirdly, in response to determining that the initial target detection model does not reach the optimal target, adjusting relevant parameters of the initial target detection model, and re-selecting samples from the sample set, taking the adjusted initial target detection model as the initial target detection model, so as to execute the training step again. In practice, the executing entity may employ a back propagation algorithm (Back Propgation Algorithm, BP) and a gradient descent method (e.g., a small batch gradient descent algorithm) to adjust the relevant parameters of the initial target detection model.

In some optional implementations of some embodiments, the identifying each access internet of things device in the access internet of things device set to generate access internet of things device feature information, to obtain an access internet of things device feature information set may include the following steps:

The first step, for each access internet of things device in the access internet of things device set, the following named entity identification processing steps are executed:

and 1, transmitting a first detection message to the access internet-of-things equipment, and receiving first response information transmitted by the access internet-of-things equipment. The first detection message may be information for detecting whether the access internet-of-things device is connected to a network. The first response information may be information that the access internet of things device receiving the first detection message responds to the first detection message.

And 2, in response to determining that the first response information characterizes that the connection of the access internet-of-things equipment is successful, sending a second detection message to a plurality of ports of the access internet-of-things equipment, and receiving the second response information sent by the access internet-of-things equipment. The second probe packet may be a packet for detecting whether a plurality of ports of the access internet of things device can communicate. The second response information may be information of a response second detection message sent by a port that can be communicated by the access internet of things device.

And 3, responding to the fact that the second response information represents the ports with successful connection in the ports, and acquiring the access equipment slogan information of the access internet of things equipment by utilizing the ports with successful connection. The plurality of ports may be ports through which the access internet of things device communicates with other access internet of things devices. For example, the plurality of ports may be port 21, port 22, port 23, port 80, and port 443. The access device tagline information may be identity information characterizing the access internet of things device. In practice, the executing body may analyze the second response information by using an Nmap (Network Mapper) tool to obtain the access device slogan information. The Namp tool may be a tool that scans a device port.

And step 4, cleaning the access equipment slogan information to obtain first identity information representing the access internet-of-things equipment. The first identity information may be a type of the access internet of things device, a device model of the access internet of things device, and a manufacturer of the access internet of things device. The above-described cleaning process may include: analyzing the special format data, removing escape characters, special characters and punctuation characters, removing stop words and performing duplication removal processing. The special format data may be HTML (HyperText Markup Language ) format data.

And 5, acquiring the communication flow data of the access internet-of-things equipment. The communication traffic data may be data sent and received by the access internet of things device.

And step 6, extracting the characteristic field of the communication flow data to obtain second identity information representing the access internet-of-things equipment. The second identity information may be identity information of the token internet of things device. The second identity information may include: the type of the access internet of things equipment, the equipment model of the access internet of things equipment and the manufacturer of the access internet of things equipment. The feature field extraction process may be extraction of a feature field characterizing identity information of the access internet of things device. The characteristic field may be a characteristic field based on a different communication protocol. The different communication protocols may include at least one of: HTTP (Hyper Text Transfer Protocol )/XML (Extensible Markup Language, extensible markup language) protocol, SSDP (Simple Service Discovery Protocol ) protocol, DHCP (Dynamic Host Configuration Protocol, dynamic host configuration protocol) protocol. For example, the above-mentioned feature field may include at least one of: host name, vendor class identifier, and manufacture.

And 7, generating a device query link for the access internet of things device according to the first identity information in response to the fact that the first identity information is identical to the second identity information. The device query link may be a query link of the access internet of things device. For example, the device query links may be https: com/search q=chuangmi_camera_ipc 019& btn gsearch. Wherein, "? "means the end of the URL. "≡" indicates a separation parameter. "q" indicates the beginning of the query. "btnsresearch" means clicking the search button.

As an example, the executing body may generate a device query link for the access internet of things device using the device model in the first identity information.

And 8, crawling the webpage information related to the access internet-of-things equipment according to the equipment query link to obtain equipment text data. The web page information may be web page information related to the detailed information of the access internet of things device. The device text data may be crawled content related to the access internet of things device.

As an example, the execution body may first obtain, by querying a link through the device, page information of the access internet-of-things device. And then, crawling the text data related to the access internet-of-things device in the webpage information by utilizing a crawler frame to obtain device text data.

And 9, preprocessing the device text data to obtain the processed device text data. The processed device text data may be information that is not related to the access internet of things device. The irrelevant content information may be advertising content information.

And a sub-step 10, carrying out named entity recognition on the processed equipment text data to obtain a target named entity which is used as the characteristic information of the access internet of things equipment. The target named entity can be a triplet named entity for representing the manufacturer, model and type of the access internet of things equipment. In practice, the execution subject may input the processed device text data into a named entity model, to obtain a target named entity, which is used as the feature information of the access internet of things device. The named entity model may be an HMM (Hidden Markov Model ).

In some optional implementations of some embodiments, the identifying a named entity of the processed text data of the device to obtain a target named entity as feature information of the internet of things device includes:

and the first step, performing double-byte coding processing on the processed text data of the equipment to obtain a word vector sequence. Wherein the word vectors in the sequence of word vectors may be vectorized representations of words.

As an example, the execution body may first perform chinese sentence segmentation processing on the processed device text data by using the WordPiece algorithm in the dynamic byte encoding model, to obtain a word sequence. The dynamic byte encoding model may be a model that encodes logical relationships between clauses. Then, each word in the word sequence is converted into a one-dimensional vector by querying a word vector table, and a word vector sequence is obtained. The word vectors in the word vector sequence are composed of word vectors, segment vectors and position vectors. The segment vectors may be vectors that are automatically learned during model training, used to divide clauses, and fused with semantic information of word vectors. The position vector is used for representing that semantic information carried by words at different positions of the text is different.

And secondly, inputting the word vector sequence into a bidirectional self-care coding network included in the internet of things equipment identification model to obtain a dynamic word feature vector. The internet of things equipment identification model can be a model for identifying a target entity of the processed equipment text data. The input of the identification model of the Internet of things equipment is processed equipment text data, and the processed equipment text data is output as a model of the equipment name of the Internet of things equipment. The bi-directional self-care encoding network comprises a preset threshold number of transformers encoders. The predetermined threshold may be 12. The above-described transformer encoder may include a word vector and position coding layer, a multi-headed self-attention mechanism layer, a residual connection layer, a normalization layer, and a feed-forward network layer. The word vector and position coding layer may be a network layer that provides position information for each word in the processed device text data and identifies the dependency and timing relationships of each word in the processed device text data. The head self-attention mechanism layer may be a network layer that determines the interrelationship of each word in the processed device text data with the remaining words in the sentence such that each word vector contains information for the word vector included in the processed device text data. The normalization layer may be a network layer that accelerates the model training speed and the model convergence speed. The residual connection layer may be a network layer that solves the problems of gradient extinction and network degradation. The feed-forward network comprises two network layers, wherein the activation function of the first layer of feed-forward network is a ReLU (Rectified Linear Unit, linear rectification function), and the activation function of the second layer of feed-forward network is a nonlinear activation function. The dynamic word feature vector described above may characterize the context and semantic features.

And thirdly, inputting the dynamic character feature vector into a forward long-short term memory network included in the internet of things equipment identification model to obtain a forward time sequence feature vector. Wherein, the forward timing feature vector may be a feature vector characterizing the above semantic information.

And fourthly, inputting the dynamic character feature vector into a backward long-short-term memory network included in the internet of things equipment identification model to obtain a backward time sequence feature vector. Wherein, the backward time sequence feature vector can represent the feature vector of the semantic information below. The state of the forward long-short-term memory network and the state of the backward long-short-term memory network are not shared, the state of the forward long-short-term memory network is transferred along the positive sequence direction, and the state of the forward long-short-term memory network is transferred along the reverse sequence direction.

And fifthly, performing splicing processing on the forward time sequence feature vector and the backward time sequence feature vector to obtain a global time sequence feature vector. The global timing feature vector may be a feature vector containing context semantic information.

And sixthly, inputting the global time sequence feature vector into a multi-head attention mechanism layer included in the internet of things equipment identification model to obtain a weighted global time sequence feature vector. The multi-head attention mechanism layer may be a network layer that assigns different attention weights to the global timing feature vector and considers text context information. The weighted global timing feature vector may be a global timing feature vector characterizing different weight information. The weighted global timing feature vector may be obtained by: the global time sequence feature vector is respectively subjected to three linear transformations to obtain an inquiry vector, a key vector and a value vector. The query vector may be a vector corresponding to a product of the global timing feature vector and a preset query weight vector. The key vector may be a vector corresponding to a product of the global timing feature vector and a preset key vector. The value vector may be a vector corresponding to a product of the global timing feature vector and a preset value vector. And secondly, linearly projecting the query vector, the key vector and the value vector to obtain a preset threshold number of parallel subspaces. The preset threshold may be a dimension value corresponding to the query vector, the key vector, and the value vector. And then, calculating the attention weights of the preset threshold number of parallel subspaces by utilizing the multi-head attention to obtain preset threshold number of weight vectors. And finally, splicing the preset threshold value weight vectors to obtain a weight global time sequence feature vector.

And seventhly, inputting the dynamic character feature vector into a first convolution extraction layer included in the internet of things equipment identification model to obtain a first local feature perception vector. Wherein, the first convolution extracting layer may be a convolution layer of 3*3. The first local feature perception vector may be a feature vector characterizing a local feature of the dynamic word feature vector.

And eighth step, inputting the first local feature perception vector into a first gating unit included in the internet of things equipment identification model to obtain a first local feature vector. The first gating unit can be used for controlling the first local feature perception vector transmission force, relieving the gradient dispersion problem and enhancing the local feature. The first local feature vector may be a feature vector that is time dependent between feature vectors.

And a ninth step of inputting the dynamic character feature vector into a second convolution extraction layer included in the internet of things equipment identification model to obtain a second local feature perception vector. Wherein, the second convolution extracting layer may be a convolution layer of 5*5. The second local feature perception vector may be a feature vector characterizing a local feature of the dynamic word feature vector.

And tenth, inputting the second local feature perception vector into a second gating unit included in the internet of things equipment identification model to obtain a second local feature vector. The second local feature vector may be a feature vector representing time dependence between word vectors.

And eleventh step, inputting the dynamic character feature vector into a third convolution extraction layer included in the internet of things equipment identification model to obtain a third local feature perception vector. Wherein, the third convolution extracting layer may be a convolution layer of 7*7. The third local feature perception vector may be a feature vector characterizing a local feature of the dynamic word feature vector.

And twelfth step, inputting the third dynamic word vector matrix into a third gating unit included in the internet of things equipment identification model to obtain a third local feature vector. The third local feature vector may be a feature vector representing time dependence between word vectors.

And thirteenth step, inputting the first local feature vector, the second local feature vector and the third local feature vector into an average pooling layer included in the internet of things equipment identification model to obtain multi-granularity local feature vectors. Wherein the multi-granularity local feature vector may be a feature vector characterizing different local features.

And fourteenth step, carrying out feature fusion on the global time sequence feature vector and the multi-granularity local feature vector to obtain a multi-level semantic feature vector. The multi-level semantic feature vector may be a feature vector obtained by fusing multi-granularity local features.

And fifteenth, inputting the multi-semantic feature vector into a classification layer included in the internet of things equipment identification model to obtain a first prediction result. Wherein, the classification layer can be a full connection layer. The first prediction result may be a classification result of the processed text data of the device.

Sixteenth, inputting the first prediction result into a conditional random field layer included in the internet of things equipment identification model to obtain a second prediction result. Wherein the conditional random field layer may be a network layer considering context semantic information. The second prediction result may be a classification prediction result including context semantic information.

Seventeenth, determining a target named entity as characteristic information of the internet of things device according to the second prediction result.

As an example, the execution body may determine a named entity corresponding to the maximum predicted value in the second predicted result as the target named entity, as the feature information of the internet of things device.

The technical scheme and the related content are taken as an invention point of the embodiment of the disclosure, so that the technical problem mentioned in the background art is solved, namely the existing named entity model basically takes a static word vector as input, however, the static word vector cannot be dynamically adjusted according to text context, and the association relationship between words and sentences cannot be fully considered, so that the accuracy of the named entity model is low, the identification accuracy of internet of things equipment is low, and the cloud security is low. Factors causing lower accuracy of identification of the Internet of things equipment and lower safety of the cloud tend to be as follows: the existing named entity model basically takes a static word vector as input, however, the static word vector cannot be dynamically adjusted according to text context, and the association relationship between words and sentences cannot be fully considered, so that the accuracy of the named entity model is low, further the identification accuracy of internet of things equipment is low, and the cloud security is low. If the factors are solved, the effects of improving the identification accuracy of the Internet of things equipment and the safety of the cloud end can be achieved. To achieve this, the present disclosure first performs a double-byte encoding process on the above-described processed device text data to obtain a word vector sequence. The text data of the processed equipment is coded, and the dynamic word vector with stronger characterization capability is obtained. The character vector sequence is input into a bidirectional self-attention coding network included in the internet of things equipment identification model to obtain dynamic character feature vectors, so that the problem that static character vectors cannot be dynamically adjusted according to the context of a specific task is solved. And secondly, the bidirectional self-attention coding network is adopted to extract different types of features, so that the feature extraction capability of the identification model of the Internet of things equipment can be enhanced, and the identification accuracy of the named entity can be improved. And inputting the dynamic word feature vector into a forward long-short term memory network included in the internet of things equipment identification model to obtain a forward time sequence feature vector. And inputting the dynamic word feature vector into a backward long-short-term memory network included in the internet of things equipment identification model to obtain a backward time sequence feature vector. And performing splicing processing on the forward time sequence feature vector and the backward time sequence feature vector to obtain a global time sequence feature vector. And inputting the global time sequence feature vector into a multi-head attention mechanism layer included in the internet of things equipment identification model to obtain a weighted global time sequence feature vector. Here, the deep semantic information of the context can be fully mined through the two-way long-short term memory network and the multi-head attention mechanism layer, and the key feature vectors are highlighted. And then, inputting the dynamic word feature vector into a first convolution extraction layer included in the internet of things equipment identification model to obtain a first local feature perception vector. And inputting the first local feature perception vector into a first gating unit included in the internet of things equipment identification model to obtain a first local feature vector. And inputting the dynamic word feature vector into a second convolution extraction layer included in the identification model of the internet of things equipment to obtain a second local feature perception vector. And inputting the second local feature perception vector into a second gating unit included in the internet of things equipment identification model to obtain a second local feature vector. And inputting the dynamic word feature vector into a third convolution extraction layer included in the internet of things equipment identification model to obtain a third local feature perception vector. And inputting the third dynamic word vector matrix into a third gating unit included in the internet of things equipment identification model to obtain a third local feature vector. The local perception capability of the identification model of the internet of things equipment can be improved through convolution extraction layers of different convolution kernels, and different gating units can control the strength of local feature vector transmission, alleviate gradient dispersion problem and enhance local feature semantic information to fully extract local features of different granularities of the processed text data. And then, inputting the first local feature vector, the second local feature vector and the third local feature vector into an average pooling layer included in the internet of things equipment identification model to obtain multi-granularity local feature vectors. The average pooling layer can reduce the parameter number of the internet of things equipment identification model and improve the convergence rate of the internet of things equipment identification model. And finally, carrying out feature fusion on the global time sequence feature vector and the multi-granularity local feature vector to obtain a multi-level semantic feature vector. And inputting the multi-semantic feature vector into a classification layer included in the identification model of the Internet of things equipment to obtain a first prediction result. And inputting the first prediction result into a conditional random field layer included in the identification model of the Internet of things equipment to obtain a second prediction result. Here, the relation between adjacent tags can be considered through the conditional random field layer, the constraint conditions of the front tag and the rear tag are enhanced, a global optimal prediction result is obtained, and the identification accuracy of the Internet of things equipment and the cloud communication safety can be improved. And determining a target named entity as characteristic information of the Internet of things equipment according to the second prediction result. Therefore, the double-byte coding and bidirectional self-attention coding network can transfer and learn rich linguistic knowledge features learned from massive non-labeling corpuses, solve the problem of low data resources, and perform fine adjustment on a labeling data set in the small-scale motor field to obtain dynamic word vectors with strong characterization capability, so that the problem of insufficient text semantic information of the small-scale motor is solved. The two-way long-short-term memory network and the multi-window gating CNN unit branch sense the global time sequence feature and the multi-granularity local feature, and splice the global time sequence feature and the multi-granularity local feature to form the integral feature of the sentence. And the full-connection layer is adopted to map the integral features to a classification space, constraint information of text contents before and after learning of the conditional random field layer is utilized, and prediction classification with the maximum probability is output and used as the feature information of the Internet of things equipment, so that the accuracy of the identification model of the Internet of things equipment and the safety of cloud communication are improved.

And step 107, in response to determining that abnormal data exists in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute at least one operation determined by preset Internet of things device linkage rule information.

In some embodiments, the executing body may trigger the alarm information in response to determining that the acquired data includes abnormal data, and control at least one internet of things device set corresponding to the abnormal data to execute the operation determined by the at least one preset internet of things device linkage rule information. The preset internet of things device linkage rule information in the at least one preset internet of things device linkage rule information has a one-to-one correspondence with the internet of things device set in the at least one internet of things device set. The abnormal data may be data whose value corresponding to the data exceeds a preset threshold. The preset threshold value can be determined according to specific environmental conditions. For example, the abnormal data may be smoke concentration data in which the smoke concentration exceeds a preset threshold. The predetermined threshold of smoke may be 15% of the smoke. The alarm information may be information for reminding the relevant person. The preset linkage rule information of the internet of things equipment can be preset rule information of linkage between the internet of things equipment. For example, the preset linkage rule information of the internet of things device may be rule information for controlling the dropper internet of things device to irrigate crops when the detected soil humidity is lower than 12%. The triggering and controlling modes comprise at least one of the following steps: timing triggers and controls, high level variable triggers and controls, low level variable triggers and controls, and station triggers and controls. The above-described common variable triggering and control may be the triggering and control of simple comparison of data. For example, simple comparisons may be greater than, equal to, and less than. The above-described advanced variable triggering and control may be the triggering and control of custom processing of data. The custom process may be a user-defined model process. The measuring points can represent attribute information of the Internet of things equipment. For example, the above-mentioned station triggering and control may be triggering and control performed by the rotational speed of the transmitter of the internet of things device.

In some optional implementations of some embodiments, the controlling the at least one internet of things device set corresponding to the abnormal data to perform the operation of determining the at least one preset internet of things device linkage rule information may include the following steps:

first, determining linkage rule information of at least one preset Internet of things device corresponding to the abnormal data.

Second, for each piece of preset internet of things equipment linkage rule information in the at least one piece of preset internet of things equipment linkage rule information, executing the following control steps:

and step 1, determining an Internet of things equipment set corresponding to the preset Internet of things equipment linkage rule information as an associated Internet of things equipment set. The associated internet of things device in the associated internet of things device set can be an internet of things device related to the preset internet of things device linkage rule information. In practice, the execution body may extract the information of the internet of things device from the preset linkage rule information of the internet of things device, so as to obtain an internet of things device set corresponding to the preset linkage rule information of the internet of things device, and use the internet of things device set as the associated internet of things device set. The extracting of the information of the internet of things device may be extracting an equipment identification field in the preset linkage rule information of the internet of things device.

And 2, determining at least one associated Internet of things device accessed to the cloud as at least one target associated Internet of things device in response to determining that the associated Internet of things devices accessed to the cloud exist in the set of associated Internet of things devices. The above-mentioned access manner of the cloud-access related internet of things device may be through MQTT, MODBUS (serial communication) protocol, TCP (Transmission Control Protocol, transmission control) protocol, OPC UA (OPC Unified Architecture ) protocol, and S7 protocol.

And 3, controlling the at least one target associated internet of things device to execute the operation of determining the linkage rule information of the preset internet of things device.

Optionally, after the controlling the at least one target associated internet of things device to perform the operation of determining the preset internet of things device linkage rule information, the method may further include the following steps:

and in the first step, in response to determining that the edge nodes to which the associated Internet of things equipment belongs exist in the set of the associated Internet of things equipment are the scheduled edge nodes, the preset Internet of things equipment linkage rule information is sent to the scheduled edge nodes.

And a second step of determining at least one edge node corresponding to at least one associated Internet of things device in the associated Internet of things device set, which is different from the edge node to which the associated Internet of things device belongs, as a target edge node set in response to determining that the edge node to which the associated Internet of things device belongs in the associated Internet of things device set is not the scheduled edge node. In practice, the executing body may determine, through information sent by the at least one associated internet of things device, at least one edge node corresponding to the at least one associated internet of things device as a target edge node.

And thirdly, transmitting the linkage rule information of the preset Internet of things equipment to each target edge node in the target edge node set.

With further reference to fig. 2, as an implementation of the method shown in the foregoing figures, the present disclosure provides some embodiments of an linkage control device for an internet of things device, where the embodiments of the device correspond to those method embodiments shown in fig. 1, and the linkage control device for an internet of things device may be specifically applied to various electronic devices.

As shown in fig. 2, an linkage control device 200 for an internet of things device includes: an identification unit 201, a first determination unit 202, an acquisition unit 203, a second determination unit 204, a resource scheduling processing unit 205, a transmission unit 206, and a control unit 207. Wherein the identification unit 201 is configured to: and identifying each edge node in the accessed edge node set to generate edge node characteristic information, and obtaining an edge node characteristic information set. The first determination unit 202 is configured to: and determining an edge node corresponding to the acquisition task information as a task edge node according to the edge node characteristic information set, wherein the acquisition task information is the task information which is sent to the task edge node and used for controlling the task edge node to acquire data. The acquisition unit 203 is configured to: and acquiring the edge state information corresponding to the task edge node. The second determination unit 204 is configured to: and determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information. The resource scheduling processing unit 205 is configured to: and in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information, performing resource scheduling processing on the task edge node to obtain a scheduled edge node. The transmission unit 206 is configured to: and sending the acquisition task information to the scheduled edge node, and receiving acquisition data sent by the scheduled edge node. The control unit 207 is configured to: and in response to determining that abnormal data exists in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set.

It will be appreciated that the elements described in the linkage control 200 of the internet of things device correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features, and beneficial effects described above with respect to the method are equally applicable to the linkage control device 200 of the internet of things device and the units contained therein, and are not described herein again.

Referring now to fig. 3, a schematic diagram of an electronic device (e.g., electronic device) 300 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 301 that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, in some embodiments of the present disclosure, the computer readable medium may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: identifying each edge node in the accessed edge node set to generate edge node characteristic information, and obtaining an edge node characteristic information set; determining an edge node corresponding to the acquisition task information as a task edge node according to the edge node characteristic information set, wherein the acquisition task information is the task information which is sent to the task edge node and used for controlling the task edge node to acquire data; acquiring edge state information corresponding to the task edge node; determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information; responding to the fact that the task edge node does not meet the resource requirement corresponding to the collected task information, and carrying out resource scheduling processing on the task edge node to obtain a scheduled edge node; transmitting the acquisition task information to the scheduled edge node, and receiving acquisition data transmitted by the scheduled edge node; and in response to determining that abnormal data exists in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an identification unit, a first determination unit, an acquisition unit, a second determination unit, a resource scheduling processing unit, a transmission unit, and a control unit. The names of these units do not in some cases limit the unit itself, for example, the identifying unit may also be described as "a unit that identifies each edge node in the accessed edge node set to generate edge node feature information, and obtains the edge node feature information set".

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a Complex Programmable Logic Device (CPLD), and the like.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A linkage control method of an Internet of things device comprises the following steps:

identifying each edge node in the accessed edge node set to generate edge node characteristic information, and obtaining an edge node characteristic information set;

according to the edge node characteristic information set, determining an edge node corresponding to acquisition task information as a task edge node, wherein the acquisition task information is the task information which is sent to the task edge node and used for controlling the task edge node to acquire data;

acquiring edge state information corresponding to the task edge node;

determining whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information;

responding to the fact that the task edge node does not meet the resource requirement corresponding to the collected task information, and carrying out resource scheduling processing on the task edge node to obtain a scheduled edge node;

the acquisition task information is sent to the scheduled edge node, and acquisition data sent by the scheduled edge node is received;

and responding to the fact that abnormal data exist in the acquired data, triggering alarm information, and controlling at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information has a one-to-one correspondence with the Internet of things device set in the at least one Internet of things device set.

2. The method of claim 1, wherein the controlling at least one internet of things device set corresponding to the anomaly data to perform at least one operation of determining preset internet of things device linkage rule information comprises:

determining linkage rule information of at least one preset Internet of things device corresponding to the abnormal data;

for each piece of preset internet of things equipment linkage rule information in the at least one piece of preset internet of things equipment linkage rule information, executing the following control steps:

determining an Internet of things equipment set corresponding to the preset Internet of things equipment linkage rule information as an associated Internet of things equipment set;

in response to determining that the associated internet of things devices accessed to the cloud are concentrated in the associated internet of things devices, determining at least one associated internet of things device accessed to the cloud as at least one target associated internet of things device;

and controlling the at least one target associated internet of things device to execute the operation of determining the linkage rule information of the preset internet of things device.

3. The method of claim 2, wherein after the controlling the at least one target associated internet of things device to perform the operation determined with the preset internet of things device linkage rule information, the method further comprises:

Responding to the fact that the edge nodes to which the associated Internet of things equipment belong exist in the associated Internet of things equipment set to be the scheduled edge nodes, and sending the preset Internet of things equipment linkage rule information to the scheduled edge nodes;

in response to determining that the edge nodes to which the associated internet of things equipment belongs exist in the associated internet of things equipment set and are not the scheduled edge nodes, determining at least one edge node which is different in the edge nodes and corresponds to at least one associated internet of things equipment in the associated internet of things equipment set as a target edge node set;

and sending the linkage rule information of the preset Internet of things equipment to each target edge node in the target edge node set.

4. The method of claim 1, wherein the acquired data is obtained by:

analyzing the acquired task information in response to receiving the acquired task information to obtain analyzed task information;

determining the Internet of things equipment set accessed to the scheduled edge node as an accessed Internet of things equipment set;

identifying each access internet-of-things device in the access internet-of-things device set to generate access internet-of-things device characteristic information, and obtaining an access internet-of-things device characteristic information set;

Determining access internet of things equipment corresponding to the acquired data as target internet of things equipment according to the analyzed task information and the access internet of things equipment characteristic information set;

receiving video data sent by the target internet of things device;

acquiring a target detection model file after training;

and inputting the video data into a target detection model corresponding to the target detection model file to obtain acquisition data.

5. The method of claim 4, wherein the object detection model is trained by:

obtaining a sample set, wherein samples in the sample set comprise: video, sample label set corresponding to video;

for each sample in the set of samples, performing the following training steps:

performing key frame extraction processing on the video corresponding to the sample to obtain a key frame sequence;

inputting the key frame sequence into an initial target detection model to obtain a detection result set corresponding to a sample;

comparing the sample label set corresponding to the sample with the detection result set to obtain a comparison result set;

determining whether the initial target detection model reaches a preset optimization target according to the comparison result set;

In response to determining that the initial target detection model reaches the optimal target, determining the initial target detection model as a trained target detection model;

and in response to determining that the initial target detection model does not reach the optimal target, adjusting relevant parameters of the initial target detection model, and re-selecting samples from the sample set, taking the adjusted initial target detection model as the initial target detection model, so as to execute the training step again.

6. The method of claim 4, wherein the identifying each access internet of things device in the set of access internet of things devices to generate access internet of things device feature information, obtaining the set of access internet of things device feature information, comprises:

for each access internet of things device in the access internet of things device set, the following named entity identification processing steps are executed:

sending a first detection message to the access internet-of-things equipment, and receiving first response information sent by the access internet-of-things equipment;

responding to the fact that the first response information represents that the access internet-of-things equipment is successfully connected, sending a second detection message to a plurality of ports of the access internet-of-things equipment, and receiving second response information sent by the access internet-of-things equipment;

Responding to the second response information to represent the ports with successful connection in the plurality of ports, and acquiring access equipment slogan information of the access internet of things equipment by utilizing the ports with successful connection;

cleaning the access equipment slogan information to obtain first identity information representing the access internet of things equipment;

acquiring communication flow data of the access internet-of-things equipment;

extracting a characteristic field from the communication flow data to obtain second identity information representing the access internet-of-things equipment;

generating a device query link for the access internet of things device according to the first identity information in response to determining that the first identity information and the second identity information are the same;

according to the equipment query link, crawling webpage information related to the access internet-of-things equipment to obtain equipment text data;

preprocessing the equipment text data to obtain processed equipment text data;

and carrying out named entity recognition on the processed equipment text data to obtain a target named entity which is used as the characteristic information of the access internet of things equipment.

7. An internet of things device linkage control device, comprising:

the identifying unit is configured to identify each edge node in the accessed edge node set so as to generate edge node characteristic information and obtain an edge node characteristic information set;

A first determining unit configured to determine, as a task edge node, an edge node corresponding to acquisition task information according to the edge node feature information set, wherein the acquisition task information is task information sent to the task edge node to control the task edge node to acquire data;

the acquisition unit is configured to acquire the edge state information corresponding to the task edge node;

the second determining unit is configured to determine whether the task edge node meets the resource requirement corresponding to the acquisition task information according to the edge state information;

the resource scheduling processing unit is configured to perform resource scheduling processing on the task edge node to obtain a scheduled edge node in response to determining that the task edge node does not meet the resource requirement corresponding to the acquired task information;

a transmitting unit configured to transmit the acquisition task information to the scheduled edge node, and to receive acquisition data transmitted by the scheduled edge node;

the control unit is configured to respond to the fact that abnormal data exist in the acquired data, trigger alarm information and control at least one Internet of things device set corresponding to the abnormal data to execute operation of determining at least one preset Internet of things device linkage rule information, wherein preset Internet of things device linkage rule information in the at least one preset Internet of things device linkage rule information and an Internet of things device set in the at least one Internet of things device set have a one-to-one correspondence.

8. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-6.

9. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-6.