CN114938349B - Internet of things data processing method and device, computer equipment and storage medium - Google Patents
Internet of things data processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114938349B CN114938349B CN202210553801.5A CN202210553801A CN114938349B CN 114938349 B CN114938349 B CN 114938349B CN 202210553801 A CN202210553801 A CN 202210553801A CN 114938349 B CN114938349 B CN 114938349B
- Authority
- CN
- China
- Prior art keywords
- data
- internet
- data processing
- things
- rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Communication Control (AREA)
Abstract
The application relates to a data processing method, a device, computer equipment and a storage medium of the Internet of things, and in particular relates to the field of data processing. The method comprises the following steps: acquiring first Internet of things data sent by first Internet of things equipment and characteristic information corresponding to the first Internet of things data; processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate corresponding to the first Internet of things data; acquiring a first data processing channel corresponding to the first Internet of things data according to the first data processing rate; and carrying out data processing on the first Internet of things data through the first data processing channel. Through the scheme, the data processing rate of the Internet of things data can be directly determined according to the characteristics of the first Internet of things device, and the accuracy of shunting the Internet of things data according to the data processing rate is improved.
Description
Technical Field
The present disclosure relates to the field of data processing, and in particular, to a method and apparatus for processing data in the internet of things, a computer device, and a storage medium.
Background
Along with the rapid development of the technology of the Internet of things, the problem of big data of the Internet of things is highlighted, the number of devices is particularly huge, the variety is various, the data reported by the devices are heterogeneous and the flow is huge, and the processing performance of the cloud system is challenged.
In the related art, due to the fact that the types of the devices of the internet of things are various, the flow is huge, when the cloud internet of things system processes heterogeneous data sent by heterogeneous data sources, the heterogeneous data can be distributed to a plurality of processing channels according to the characteristics of the heterogeneous data in a hard coding mode, and therefore the overall throughput of the system is improved.
However, in the related art, the characteristics affecting the data processing are more, and the accuracy of data splitting by the hard coding method is lower.
Disclosure of Invention
The embodiment of the application provides a data processing method, a device, computer equipment and a storage medium of the Internet of things, which can improve the accuracy of data distribution processing, and the technical scheme is as follows:
in one aspect, there is provided a method for processing data of the internet of things, the method comprising:
acquiring first Internet of things data sent by first Internet of things equipment and characteristic information corresponding to the first Internet of things data; the characteristic information comprises at least one of a communication protocol, a data format, a compression mode, a message body size, a device position, a device address, a transmission time and a transmission frequency;
Processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate of the first Internet of things data;
acquiring a first data processing channel corresponding to the first Internet of things data according to the first data processing rate;
performing data processing on the first Internet of things data through the first data processing channel;
the data classification model is a machine learning model obtained through training based on characteristic information of sample Internet of things data and the data processing rate of the sample Internet of things data.
In yet another aspect, there is provided an internet of things data processing apparatus, the apparatus comprising:
the first data acquisition module is used for acquiring first Internet of things data sent by first Internet of things equipment and characteristic information corresponding to the first Internet of things data; the characteristic information comprises at least one of a communication protocol, a data format, a compression mode, a message body size, a device position, a device address, a transmission time and a transmission frequency;
the first rate acquisition module is used for processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate of the first Internet of things data;
The first channel acquisition module acquires a first data processing channel corresponding to the first Internet of things data according to the first data processing rate;
the first data processing module is used for performing data processing on the first Internet of things data through a data processing channel corresponding to the first Internet of things data;
the data classification model is a machine learning model obtained through training based on characteristic information of sample Internet of things data and the data processing rate of the sample Internet of things data.
In one possible implementation, the apparatus further includes:
the second rate acquisition module is used for acquiring a second data processing rate; the second data processing rate is the rate of data processing on the first Internet of things data through the first data processing channel;
and the parameter updating module is used for updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a data processing channel corresponding to the second data processing rate;
and when the data processing channel corresponding to the second data processing rate is other data processing channels except the first data processing channel, updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
and when the first data processing channel is different from the second data processing channel, updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a loss function value based on the second data processing rate and the first data processing rate;
and updating parameters of the data classification model based on the loss function value.
In one possible implementation, the first data processing module is configured to, in response to a request from the first data processing module,
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
when the first data processing channel is different from the second data processing channel and the internet of things data corresponding to the first internet of things device in the second data processing channel meets a first specified condition, performing data processing on the first internet of things data through the first data processing channel.
In one possible implementation, the first specified condition includes at least one of the following conditions:
in the second data processing channel, the data quantity of the Internet of things corresponding to the first Internet of things device is larger than a first threshold value;
and in the second data processing channel, the sum of processing time of the Internet of things data corresponding to the first Internet of things device is larger than a second threshold value.
In one possible implementation, the apparatus further includes:
the device comprises a first sample acquisition module, a second sample acquisition module and a second sample acquisition module, wherein the first sample acquisition module is used for acquiring first sample Internet of things data sent by first sample Internet of things equipment and characteristic information corresponding to the first sample Internet of things data respectively;
the sample channel acquisition module is used for acquiring a data processing channel corresponding to the first sample Internet of things equipment;
the sample rate acquisition module is used for processing the first sample internet of things data based on a data processing channel corresponding to the first sample internet of things device to acquire a data processing rate corresponding to the first sample internet of things data;
and the model pre-training module is used for training the data classification model based on the characteristic information of the first sample Internet of things data and the data processing rate corresponding to the first sample Internet of things data.
In yet another aspect, a computer device is provided, the computer device including a processor and a memory, the memory storing at least one computer instruction, the at least one computer instruction loaded and executed by the processor to implement the data processing method of the internet of things described above.
In yet another aspect, a computer readable storage medium is provided, where at least one computer instruction is stored, where the at least one computer instruction is loaded and executed by a processor to implement the above-mentioned data processing method of the internet of things.
In yet another aspect, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the data processing method of the internet of things.
The technical scheme that this application provided can include following beneficial effect:
because the data classification model is obtained through training according to the characteristic information of the sample Internet of things data and the data processing rate corresponding to the sample Internet of things data, when the first Internet of things data produced by the first Internet of things equipment is required to be processed, the characteristic information corresponding to the first Internet of things data is processed according to the data classification model, the data processing rate of the first Internet of things data is predicted, the predicted value distributes the first Internet of things data to the first data processing channel for data processing, the data processing rate of the Internet of things data can be directly determined according to a plurality of characteristics of the first Internet of things equipment, and the accuracy of shunting the Internet of things data according to the data processing rate is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram of an Internet of things data processing system, according to an exemplary embodiment;
FIG. 2 is a flow chart of a method of processing data of the Internet of things, according to an exemplary embodiment;
FIG. 3 is a method flow diagram of a method for processing data of the Internet of things, according to an exemplary embodiment;
FIG. 4 illustrates a model initialization training schematic according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a data classification process according to an embodiment of the present application;
FIG. 6 illustrates a model update diagram according to an embodiment of the present application;
FIG. 7 illustrates a model update diagram according to an embodiment of the present application;
FIG. 8 is a block diagram illustrating a data classification model training and data processing method according to an exemplary embodiment;
FIG. 9 is a block diagram illustrating a data classification model training and data processing method according to an exemplary embodiment;
Fig. 10 is a schematic diagram of a computer device, according to an example embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
Before describing the various embodiments shown in this application, several concepts related to this application will be described first:
1) Internet of things (The Internet of Things IOT)
The internet of things refers to collecting any object or process needing to be monitored, connected and interacted in real time through various devices and technologies such as various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors and laser scanners, collecting various needed information such as sound, light, heat, electricity, mechanics, chemistry, biology and positions, and realizing ubiquitous connection of objects and people through various possible network access, and realizing intelligent sensing, identification and management of objects and processes. The internet of things is an information carrier based on the internet, a traditional telecommunication network and the like, and enables all common physical objects which can be independently addressed to form an interconnection network.
2) AI (Artificial Intelligence )
Artificial intelligence is a new technical science to research, develop theories, methods, techniques and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the nature of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence, research in this field including robotics, language recognition, image recognition, natural language processing, and expert systems. Since birth, the theory and technology are mature, and the application field is expanding, and it is supposed that the technological product brought by artificial intelligence in the future will be a "container" of human intelligence. Artificial intelligence is a very broad science that consists of different fields such as machine learning, computer vision, etc.
3) Cloud technology (Cloud technology)
The cloud technology is a generic term of network technology, information technology, integration technology, management platform technology, application technology and the like based on cloud computing business model application, can form a resource pool, and is flexible and convenient as required. Cloud computing technology will become an important support. Background services of technical networking systems require a large amount of computing, storage resources, such as video websites, picture-like websites, and more portals. Along with the high development and application of the internet industry, each article possibly has an own identification mark in the future, the identification mark needs to be transmitted to a background system for logic processing, data with different levels can be processed separately, and various industry data needs strong system rear shield support and can be realized only through cloud computing.
FIG. 1 is a schematic diagram illustrating the architecture of an Internet of things data processing system, according to an exemplary embodiment. The system comprises: the internet of things device 120 and the data processing device 140.
The internet of things device 120 may include a data storage module (not shown in the figure), where data generated by the internet of things device may be stored in advance; the internet of things device 120 may be directly connected with a sensor, where the sensor may be one sensor or may be a plurality of sensors, and the sensor generates corresponding time sequence data through a change of an external environment and sends the time sequence data to the data storage device for storage; or, the internet of things device 120 is a sensor device, and the sensor device acquires the time sequence data and stores the time sequence data in a data storage module corresponding to the sensor device for storage.
The data processing device 140 may include a data transmission module and a data processing module. The data transmission module is configured to receive data sent to each internet of things device 120; or the data transmission module is further configured to send the data after the data processing to each internet of things device 120. The data processing module may process the data uploaded by the internet of things device 120.
Alternatively, the data storage device 120 may be a server, or include a plurality of servers, or be a distributed computer cluster formed by a plurality of servers, or be a virtualization platform, or be a cloud computing service center, or the like, which is not limited in this application.
The internet of things device 120 is connected with the data processing device 140 through a communication network. Optionally, the communication network is a wired network or a wireless network.
Alternatively, the wireless network or wired network described above uses standard communication techniques and/or protocols. The network is typically the Internet, but may be any network including, but not limited to, a local area network (Local Area Network, LAN), metropolitan area network (Metropolitan Area Network, MAN), wide area network (Wide Area Network, WAN), a mobile, wired or wireless network, a private network, or any combination of virtual private networks. In some embodiments, data exchanged over the network is represented using techniques and/or formats including HyperText Mark-up Language (HTML), extensible markup Language (Extensible Markup Language, XML), and the like. All or some of the links may also be encrypted using conventional encryption techniques such as secure socket layer (Secure Socket Layer, SSL), transport layer security (Transport Layer Security, TLS), virtual private network (Virtual Private Network, VPN), internet protocol security (Internet Protocol Security, IPsec), and the like. In other embodiments, custom and/or dedicated data communication techniques may also be used in place of or in addition to the data communication techniques described above.
Fig. 2 is a flow chart illustrating a method of processing data of the internet of things according to an exemplary embodiment. The method may be performed by a computer device, which may be the server 140 in the embodiment shown in fig. 1. As shown in fig. 2, the flow of the data processing method of the internet of things may include the following steps:
step 21, obtaining first internet of things data sent by first internet of things equipment and feature information corresponding to the first internet of things data.
The characteristic information includes at least one of a communication protocol, a data format, a compression scheme, a message body size, a device location, a device address, a transmission time, and a transmission frequency.
Optionally, the first internet of things device may be a sensor device used in a new energy scenario, and the first internet of things data is time sequence data information acquired by the sensor device when the first internet of things device acquires new energy (for example, wind power generation).
Optionally, the feature information corresponding to the first internet of things data may indicate a message processing rate corresponding to the first internet of things data.
When the feature information corresponding to the first internet of things data includes at least one of a communication protocol, a data format, a compression mode, a message body size, a device location, a device address, a transmission time, and a transmission frequency, the communication protocol, the data format, the compression mode, the message body size, the device location, the device address, the transmission time, and the transmission frequency may affect a rate of processing the data corresponding to the first internet of things device.
When the first internet of things data is the data information generated by the first internet of things device, the processing rate corresponding to the first internet of things data may also be related to the attribute of the first internet of things device, so that at least one of the information such as the IP address information, the sending time and the sending frequency corresponding to the first internet of things device can be obtained and determined as the feature information corresponding to the first internet of things data.
And 22, processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate corresponding to the first Internet of things data.
Step 23, according to the first data processing rate, a first data processing channel corresponding to the first internet of things data is obtained.
That is, after the feature information of the first internet of things data is obtained, the feature information corresponding to the first internet of things data can be processed according to the data classification model, the processing rate corresponding to the first internet of things data is predicted, and the data processing channel corresponding to the first internet of things data is determined according to the data processing rate corresponding to the first internet of things data.
And step 24, performing data processing on the first Internet of things data through a data processing channel corresponding to the first Internet of things data.
The data classification model is a machine learning model obtained through training based on characteristic information corresponding to the sample Internet of things data and a data processing rate corresponding to the sample Internet of things data.
After determining the data processing channel corresponding to the first internet of things data, other data except the data processing channel corresponding to the first internet of things data can exist in the first data processing channel, the difference between the data processing rates of the other data in the first data processing channel and the data processing rate corresponding to the first internet of things data is smaller than a threshold value, namely, the processing rates of the data in the first data processing channel are not different, so that through the scheme, various different data to be processed can be classified according to the processing rates through a data classification model, and the data in the different data processing channels are processed through different processing devices, so that the occurrence of data processing time sequence confusion caused by large data processing rate difference is avoided as much as possible.
In summary, in the scheme shown in the embodiment of the present application, since the data classification model is obtained by training according to the feature information of the sample internet of things data and the data processing rate corresponding to the sample internet of things data, when the first internet of things data produced by the first internet of things device needs to be processed, the feature information corresponding to the first internet of things data is processed according to the data classification model, the data processing rate of the first internet of things data is predicted, and the predicted value distributes the first internet of things data to the first data processing channel for data processing, so that the data processing rate of the internet of things data can be directly determined according to a plurality of features of the first internet of things device, and the accuracy of splitting the internet of things data according to the data processing rate is improved.
Fig. 3 is a method flowchart of an internet of things data processing method according to an exemplary embodiment. The method may be performed by a computer device, which may be the server 140 in the embodiment shown in fig. 1. As shown in fig. 3, the data processing method of the internet of things may include the following steps:
step 301, obtaining first sample internet of things data sent by first sample internet of things equipment and feature information corresponding to the first sample internet of things data.
Optionally, the first sample internet of things device may be a sensor device used in a new energy scenario, and the first sample internet of things data may be time sequence data information acquired by the sensor device when the first sample internet of things device acquires new energy (for example, wind power generation).
Optionally, the feature information corresponding to the first sample internet of things data may be used to indicate a message processing rate corresponding to the first sample internet of things data.
Wherein the characteristic information includes at least one of a communication protocol, a data format, a compression scheme, a message body size, a device location, a device address, a transmission time, and a transmission frequency.
Optionally, the first sample internet of things device and the first internet of things device may be the same type of device (e.g., a sensor device).
Step 302, processing the first sample internet of things data, and obtaining a data processing rate corresponding to the first sample internet of things data.
In one possible implementation manner, the computer device processes the first sample internet of things data to obtain a data processing rate corresponding to the first sample internet of things data.
In one possible implementation manner, the computer device includes a plurality of data processing components, each data processing component may correspond to one data processing channel, and the computer device processes the first sample internet of things data according to the plurality of data processing components, so as to obtain a data processing rate corresponding to the first sample internet of things data.
The processor corresponding to the computer equipment is usually of a multithreading architecture, so each core (or thread) in the processor can be used as a data processing component of the computer equipment, and a plurality of cores (or threads) can respectively process data of a plurality of samples of internet of things data in parallel to respectively obtain data processing results corresponding to the samples of internet of things data and data processing rates corresponding to the samples of internet of things data.
In one possible implementation, the plurality of data processing components in the computer device are identical. I.e. the plurality of data processing components in the computer device may be identical, and thus the data processing capabilities of the individual data processing components in the computer device may be considered identical, within the tolerance of the error.
In another possible implementation, the computer device includes at least one first data processing component and at least one second data processing component; wherein the data processing capacity of the first data processing component is higher than the data processing capacity of the data processing component.
For example, there may be cores of differing computational power in a CPU architecture, 8 large cores (i.e., first data processing components) and 4 small cores (i.e., second data processing components) in a CPU of a 12-core architecture, with the computational power of the large cores being higher than that of the small cores.
In one possible implementation manner, the data processing rate corresponding to the first sample internet of things data includes first sample rate information and second sample rate information, and when the data processing rate is obtained, the computer device may perform data processing through the first data processing component based on the first sample internet of things data to obtain the first sample rate information; correspondingly, the computer equipment can perform data processing through the second data processing component based on the first sample Internet of things data to obtain second sample rate information.
In one possible implementation, the data processing rate corresponding to the first sample internet of things data is obtained by performing weighted summation based on the first sample rate and the second sample rate.
Step 303, training a data classification model based on the feature information of the first sample internet of things data and the data processing rate corresponding to the first sample internet of things data.
After the characteristic information of the first sample internet of things data and the data processing rate corresponding to the first sample internet of things data are obtained, the characteristic information corresponding to the first sample internet of things data can be used as a sample of a data classification model, the data processing rate corresponding to the first sample internet of things data can be used as labeling information of the data classification model, so that the data classification model can be trained, and the data processing rate corresponding to the internet of things data can be predicted according to the characteristic information of the input internet of things data through the trained data classification model.
For example, when the data classification model is trained, the computer device can process the feature information corresponding to the first sample internet of things data through the data classification model to obtain a predicted data processing rate, then calculate a loss function value through the predicted data processing rate and the data processing speed corresponding to the first sample internet of things data, and update parameters of the data classification model through the loss function value so as to achieve the purpose of training the data classification model.
The data classification model may be a deep learning model constructed based on a residual network.
In one possible implementation manner, according to the first sample internet of things device, a data processing channel corresponding to the first sample internet of things data is determined, and according to the data processing channel corresponding to the first sample internet of things data, data processing is performed on the first sample internet of things data.
Before training the data classification model, a data processing channel may be predetermined according to the first sample internet of things device, so as to process the first sample internet of things data. For example, the data processing channel may be determined according to the ID of the first sample internet of things device.
Referring to fig. 4, a model initialization training diagram according to an embodiment of the present application is shown. As shown in fig. 4, each piece of internet-of-things equipment (taking internet-of-things equipment 1 and internet-of-things equipment 5 as an example) selects a corresponding data processing channel according to ID information of each piece of internet-of-things equipment, for example, the data processing channel 1 corresponding to the internet-of-things equipment 1 and the internet-of-things equipment 2, the data processing channel 2 corresponding to the internet-of-things equipment 3, and the data processing channel 3 corresponding to the internet-of-things equipment 4 and the internet-of-things equipment 5; and then, respectively corresponding each data processing channel, processing the plurality of internet of things data in each data processing channel through the data processing component respectively corresponding to each data processing channel, and training the data classification model 401 by using the processed data processing rate corresponding to each internet of things data and the characteristic information corresponding to each internet of things data as a sample.
In a possible implementation manner, the computer device may determine a data processing channel corresponding to each piece of internet of things device by taking a model of an ID of the internet of things device, input the internet of things data sent by each piece of internet of things device into the corresponding data processing channel for processing, and simultaneously, use the internet of things data sent by each piece of internet of things device and a data processing rate processed by each data processing channel as the first sample internet of things data and a data processing rate of the first sample internet of things data for subsequent training of a data classification model.
Step 304, obtaining first internet of things data sent by a first internet of things device and feature information corresponding to the first internet of things data.
Optionally, the first internet of things device may be a sensor device used in a new energy scenario, and the first internet of things data may be time sequence data information acquired by the sensor device when the first internet of things device acquires new energy (for example, wind power generation).
Optionally, the feature information corresponding to the first internet of things data is used for indicating a message processing rate corresponding to the first internet of things data.
Optionally, the first internet of things device and the first sample internet of things device may be the same type of device (for example, both are sensor devices) or may be different types of devices.
And 305, processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate corresponding to the first Internet of things data.
Before processing the first internet of things data, the computer device may input the feature information corresponding to the first internet of things data into the data classification model, and the data classification model may process the feature information corresponding to the first internet of things data, and predict and obtain a first data processing rate corresponding to the first internet of things data.
For example, a convolution layer structure with an encoder function may exist in the data classification model, the data classification model may encode feature information of the first internet of things data through a plurality of convolution layers to obtain feature vectors corresponding to the feature information of the first internet of things data, and predict a first data processing rate corresponding to the first internet of things data according to the feature vectors corresponding to the feature information of the first internet of things data.
Step 306, according to the first data processing rate, a first data processing channel corresponding to the first internet of things data is obtained.
In one possible implementation, there are at least two data processing channels in the computer device, and the computer device may determine, according to the first data processing rate, a first data processing channel corresponding to the first internet of things data in the at least two data processing channels.
In one possible implementation, a specified rate value corresponding to each data processing channel is obtained; and determining a first data processing channel corresponding to the first Internet of things data in the at least two data processing channels based on the specific speed value corresponding to each data processing channel and the first data processing speed.
For example, after the first data processing rate corresponding to the first data of the internet of things is obtained, the designated rate value closest to the first data processing rate in the designated rate values corresponding to the at least two data processing channels may be determined according to the first data processing rate, and the data processing channel corresponding to the designated rate value closest to the first data processing rate may be determined as the first data processing channel.
In one possible implementation manner, the specified rate interval corresponding to each data processing channel is obtained, and the data processing channel corresponding to the specified rate interval containing the first data processing rate in the specified rate interval corresponding to each data processing channel is determined to be the first data processing channel.
In one possible implementation, the data processing components corresponding to the respective data processing channels are identical. I.e. the data processing capacity of the data processing component corresponding to each data processing channel may be the same within the allowed error range.
In another possible implementation, the data processing channels include at least one first type channel and at least one second type channel; wherein the first data processing component processes data in the first type of channel; the second data processing component processes data in the second type of channel.
Therefore, after determining the data processing rate corresponding to the first internet of things data sent by the first internet of things device according to the data classification model, the data processing channel corresponding to the first internet of things data and the type of the data processing component corresponding to the first internet of things data can be determined according to the data processing rate corresponding to the first internet of things data. For example, when the data processing rate corresponding to the first internet of things data is smaller, that is, the first internet of things data is harder to process, the first internet of things data can be processed through a first data processing component (such as a big core in a CPU), so that the processing efficiency of more complex data is ensured; when the data processing rate corresponding to the first internet of things data is high, that is, the first internet of things data is easy to process, the second data processing component (for example, a small core in a CPU) can process the first internet of things data, so that the power consumption of the computer equipment is reduced.
Step 307, performing data processing on the first internet of things data through a data processing channel corresponding to the first internet of things data.
Referring to fig. 5, a schematic diagram of a data classification process according to an embodiment of the present application is shown. As shown in fig. 5, each piece of internet of things equipment (taking the internet of things equipment 1 as an example) sends the respectively generated internet of things data to the data classification model 501, groups the internet of things data generated by each piece of internet of things equipment according to the data processing rate corresponding to each piece of internet of things data predicted by the data classification model 501, determines each data processing channel corresponding to each piece of internet of things data, and processes the plurality of pieces of internet of things data in each data processing channel through the data processing component corresponding to each data processing channel respectively so as to realize the processing flow of the internet of things data corresponding to each piece of internet of things equipment.
In one possible implementation manner, after performing data processing on the first internet of things data according to the data processing channel corresponding to the first internet of things data, the computer device may further obtain a second data processing rate; the second data processing rate is the rate of data processing on the first internet of things data through the first data processing channel; and updating parameters of the data classification model based on the second data processing rate to obtain an updated data classification model.
After acquiring the first internet of things data sent by the first internet of things device and completing classification and processing of the first internet of things data, the computer device can acquire a real processing rate (namely the second data processing rate) corresponding to the first internet of things data; at this time, the computer device may update the parameters of the data classification model again by using the real processing rate corresponding to the first internet of things data and the feature information corresponding to the first internet of things data as samples.
In one possible implementation, the computer device may acquire a data processing channel corresponding to the second data processing rate; when the data processing channel corresponding to the second data processing rate is the other data processing channel except the first data processing channel, the data classification model is updated with parameters based on the second data processing rate.
In this embodiment of the present application, after obtaining the real processing rate corresponding to the first data of the internet of things, the computer device may determine a data processing channel corresponding to the real processing rate, and if the data processing channel corresponding to the real processing rate is different from the first data processing channel, it may be determined that a large deviation occurs in the prediction of the data classification model on the processing rate of the first data of the internet of things, and at this time, the data processing model needs to be updated to improve accuracy of the data processing model.
In one possible implementation, the computer device may acquire a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time; and when the first data processing channel is different from the second data processing channel, updating parameters of the data classification model based on the second data processing rate.
In this embodiment of the present application, after determining the first data processing channel, the computer device may compare the first data processing channel with a data processing channel corresponding to the last data of the internet of things sent by the first internet of things device, if the first data processing channel and the data processing channel are inconsistent, it may be that a data mode of the data of the internet of things sent by the first internet of things device is changed, and the changed data mode may be a new data mode, so as to ensure accuracy of predicting a processing rate of the data of the internet of things in the new data mode by the data classification model, and may update, as a sample, a real processing rate corresponding to the first internet of things data and feature information corresponding to the first internet of things data, a parameter of the data classification model.
In a possible implementation manner, third internet of things data sent by the first internet of things device and feature information corresponding to the third internet of things data are obtained; processing according to the characteristic information corresponding to the third Internet of things data through the updated data classification model to obtain a third data processing rate corresponding to the third Internet of things data; acquiring a third data processing channel according to the third data processing rate; and carrying out data processing on the third Internet of things data according to the third data processing channel.
After the data classification model updates the first internet of things data sent by the first internet of things device and the real processing rate corresponding to the first internet of things data, the data classification model processes third internet of things data sent by the first internet of things device, obtains a third data processing rate corresponding to the third internet of things data, and determines a third data processing channel corresponding to the third internet of things data according to the third data processing rate.
In one possible implementation, the second data processing channel is identical to the first data processing channel.
When the first internet of things device is a sensor device, the difference of the time sequence data uploaded by the sensor device is generally smaller, that is, the difference between the first internet of things data and the second internet of things data is smaller, and the second data processing channel may be the same data processing channel as the first data processing channel.
In one possible implementation, the computer device may obtain the loss function value based on the second data processing rate and the first data processing rate when updating parameters of the data classification model based on the second data processing rate; and updating parameters of the data classification model based on the loss function value.
In this embodiment of the present application, since the computer device has already acquired the real processing rate of the first data of the internet of things (i.e. the second data processing rate described above), the loss function value may be calculated directly according to the real processing rate and the predicted processing rate (i.e. the first data processing rate described above), and the parameter update may be performed on the data classification model according to the calculated loss function value.
In one possible implementation, the computer device may acquire a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time; when the first data processing channel is different from the second data processing channel and the internet of things data corresponding to the first internet of things device in the second data processing channel meets a first specified condition, performing data processing on the first internet of things data through the first data processing channel.
In one possible implementation, the first specified condition includes at least one of the following conditions:
in the second data processing channel, the data quantity of the Internet of things corresponding to the first Internet of things device is larger than a first threshold value;
in the second data processing channel, the sum of processing time of the internet of things data corresponding to the first internet of things device is larger than a second threshold.
When data sent by the first internet of things device is subjected to channel separation processing through the data classification model, in order to avoid the disorder of processing time sequence caused by frequent channel switching of one device, when the device needs to switch channels, the switching can be allowed after the number of the original channels is accumulated to a certain value or a certain time end.
Referring to fig. 6, a schematic diagram of model updating according to an embodiment of the present application is shown. As shown in fig. 6, for the internet of things device 1, firstly, the generated first internet of things data is subjected to data processing through the data classification model 601 to obtain a first data processing rate corresponding to the first internet of things data, and a data processing channel 1 corresponding to the first internet of things data is determined according to the first data processing rate, then the first internet of things data is input into the data processing channel 1, and the first internet of things data is processed according to the data processing component 1, and a real processing rate corresponding to the first internet of things data processing by the data processing component 1 is obtained.
And training the data classification model 601 according to the real processing rate corresponding to the first internet of things data to obtain a trained data classification model 601.
At this time, the internet of things device inputs the generated second internet of things data into the trained data classification model 601, and the trained data classification model processes the feature data of the second internet of things data to obtain a second data processing rate corresponding to the second internet of things data, and inputs the second internet of things data into the data processing channel 2 according to the second data processing rate, so that the data processing component 2 processes the second internet of things data.
Referring to fig. 7, a model update schematic diagram according to an embodiment of the present application is shown, as shown in fig. 7, for an internet of things device 1, firstly, data processing is performed on generated first internet of things data through a data classification model 701 to obtain a first data processing rate corresponding to the first internet of things data, a data processing channel 1 corresponding to the first internet of things data is determined according to the first data processing rate, then the first internet of things data is input into the data processing channel 1, the first internet of things data is processed according to a data processing component 1, and a real processing rate corresponding to the first internet of things data processing by the data processing component 1 is obtained.
And training the data classification model 701 according to the real processing rate corresponding to the first internet of things data to obtain a trained data classification model 701.
At this time, the internet of things device inputs the generated second internet of things data into the trained data classification model 701, processes the feature data of the second internet of things data, determines a second data processing rate of the second internet of things data, and determines a data processing channel corresponding to the second internet of things data as a data processing channel 2 according to the second data processing rate. I.e. the data processing channel 2 is now the correct bypass channel for this second networking data. In order to avoid the confusion of processing time sequence caused by frequent channel switching of one device due to training, the quantity of corresponding internet of things data in the first internet of things device in the data processing channel 1 can be detected, and when the quantity of corresponding internet of things data in the first internet of things device in the data processing channel 1 is larger than a threshold value, the second internet of things data is sent to the data processing channel 2 for processing.
In summary, in the scheme shown in the embodiment of the present application, since the data classification model is obtained by training according to the feature information of the sample internet of things data and the data processing rate corresponding to the sample internet of things data, when the first internet of things data produced by the first internet of things device needs to be processed, the feature information corresponding to the first internet of things data is processed according to the data classification model, the data processing rate of the first internet of things data is predicted, and the predicted value distributes the first internet of things data to the first data processing channel for data processing, so that the data processing rate of the internet of things data can be directly determined according to a plurality of features of the first internet of things device, and the accuracy of splitting the internet of things data according to the data processing rate is improved.
Referring to FIG. 8, a block diagram of a data classification model training and data processing method is shown according to an exemplary embodiment. The data classification model training and the data processing method are jointly executed by at least two pieces of Internet of things equipment and data processing equipment; the at least two internet of things devices comprise sample internet of things devices and first internet of things devices; the data processing device may be a server.
As shown in fig. 8, a sample internet of things device is selected, sample internet of things data 801 generated by the sample internet of things device is obtained, a corresponding data processing channel is selected according to the sample internet of things device, the sample internet of things device is processed according to a data processing component corresponding to the data processing channel, a data processing rate corresponding to the sample internet of things data is obtained, and a data classification model 800 is obtained through training according to the data processing rate corresponding to the sample internet of things data and characteristic information corresponding to the sample internet of things data.
After the training of the data classification model 800 is completed, the first internet of things data 802 generated by the first internet of things device may be input into the data classification model 800, and the characteristic information corresponding to the first internet of things data is processed through the data classification model 800, so as to obtain the predicted data processing rate of the first internet of things data, determine the data processing channel corresponding to the first internet of things data according to the predicted data processing rate, and then process the first internet of things data according to the data processing channel corresponding to the first internet of things data, so that the internet of things data produced by the internet of things device may be classified into different data processing channels according to the data processing rate, and process the data in the different data processing channels through different processing devices, thereby avoiding the occurrence of data timing sequence processing confusion caused by large data processing rate difference as much as possible.
Fig. 9 is a block diagram illustrating a structure of an internet of things data processing apparatus according to an exemplary embodiment. The data processing device of the internet of things can implement all or part of the steps in the method provided by the embodiment shown in fig. 2 or fig. 3. The internet of things data processing device may include:
the first data acquisition module 901 is configured to acquire first internet of things data sent by a first internet of things device and feature information corresponding to the first internet of things data; the characteristic information comprises at least one of a communication protocol, a data format, a compression mode, a message body size, a device position, a device address, a transmission time and a transmission frequency;
the first rate obtaining module 902 is configured to process, through a data classification model, feature information of the first internet of things data, to obtain a first data processing rate of the first internet of things data;
the first channel obtaining module 903 obtains a first data processing channel corresponding to the first internet of things data according to the first data processing rate;
the first data processing module 904 is configured to perform data processing on the first internet of things data through a data processing channel corresponding to the first internet of things data;
The data classification model is a machine learning model obtained through training based on characteristic information of sample Internet of things data and the data processing rate of the sample Internet of things data.
In one possible implementation, the apparatus further includes:
the second rate acquisition module is used for acquiring a second data processing rate; the second data processing rate is the rate of data processing on the first Internet of things data through the first data processing channel;
and the parameter updating module is used for updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a data processing channel corresponding to the second data processing rate;
and when the data processing channel corresponding to the second data processing rate is other data processing channels except the first data processing channel, updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
And when the first data processing channel is different from the second data processing channel, updating parameters of the data classification model based on the second data processing rate.
In one possible implementation, the parameter updating module is configured to, in response to a request from the user,
acquiring a loss function value based on the second data processing rate and the first data processing rate;
and updating parameters of the data classification model based on the loss function value.
In one possible implementation, the first data processing module 904 is configured to,
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
when the first data processing channel is different from the second data processing channel and the internet of things data corresponding to the first internet of things device in the second data processing channel meets a first specified condition, performing data processing on the first internet of things data through the first data processing channel.
In one possible implementation, the first specified condition includes at least one of the following conditions:
In the second data processing channel, the data quantity of the Internet of things corresponding to the first Internet of things device is larger than a first threshold value;
and in the second data processing channel, the sum of processing time of the Internet of things data corresponding to the first Internet of things device is larger than a second threshold value.
In one possible implementation, the apparatus further includes:
the device comprises a first sample acquisition module, a second sample acquisition module and a second sample acquisition module, wherein the first sample acquisition module is used for acquiring first sample Internet of things data sent by first sample Internet of things equipment and characteristic information corresponding to the first sample Internet of things data respectively;
the sample channel acquisition module is used for acquiring a data processing channel corresponding to the first sample Internet of things equipment;
the sample rate acquisition module is used for processing the first sample internet of things data based on a data processing channel corresponding to the first sample internet of things device to acquire a data processing rate corresponding to the first sample internet of things data;
and the model pre-training module is used for training the data classification model based on the characteristic information of the first sample Internet of things data and the data processing rate corresponding to the first sample Internet of things data.
In summary, in the scheme shown in the embodiment of the present application, since the data classification model is obtained by training according to the feature information of the sample internet of things data and the data processing rate corresponding to the sample internet of things data, when the first internet of things data produced by the first internet of things device needs to be processed, the feature information corresponding to the first internet of things data is processed according to the data classification model, the data processing rate of the first internet of things data is predicted, and the predicted value distributes the first internet of things data to the first data processing channel for data processing, so that the data processing rate of the internet of things data can be directly determined according to a plurality of features of the first internet of things device, and the accuracy of splitting the internet of things data according to the data processing rate is improved.
Fig. 10 is a schematic diagram of a computer device, according to an example embodiment. The computer device may be implemented as a model search device and/or an image segmentation device in the various method embodiments described above. The computer apparatus 1000 includes a central processing unit (CPU, central Processing Unit) 1001, a system Memory 1004 including a random access Memory (Random Access Memory, RAM) 1002 and a Read-Only Memory (ROM) 1003, and a system bus 1005 connecting the system Memory 1004 and the central processing unit 1001. The computer device 1000 also includes a basic input/output system 1006, which helps to transfer information between various devices within the computer, and a mass storage device 1007 for storing an operating system 1013, application programs 1014, and other program modules 1015.
The mass storage device 1007 is connected to the central processing unit 1001 through a mass storage controller (not shown) connected to the system bus 1005. The mass storage device 1007 and its associated computer-readable media provide non-volatile storage for the computer device 1000. That is, the mass storage device 1007 may include a computer readable medium (not shown) such as a hard disk or a compact disk-read Only Memory (CD-ROM) drive.
The computer readable medium may include computer storage media and communication media without loss of generality. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, flash memory or other solid state memory technology, CD-ROM, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will recognize that the computer storage medium is not limited to the one described above. The system memory 1004 and mass storage devices 1007 described above may be collectively referred to as memory.
The computer device 1000 may be connected to the internet or other network device through a network interface unit 1011 connected to the system bus 1005.
The memory also includes one or more programs stored in the memory, and the central processor 1001 implements all or part of the steps of the method shown in fig. 2 or 3 by executing the one or more programs.
In exemplary embodiments, a non-transitory computer readable storage medium comprising instructions, such as a memory comprising a computer program (instructions) executable by a processor of a computer device to perform a method performed by a server or a user terminal in the methods shown in the various embodiments of the present application, is also provided. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the methods shown in the above embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. The data processing method of the Internet of things is characterized by comprising the following steps of:
acquiring first Internet of things data sent by first Internet of things equipment and characteristic information corresponding to the first Internet of things data; the characteristic information comprises at least one of a communication protocol, a data format, a compression mode, a message body size, a device position, a device address, a transmission time and a transmission frequency;
processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate of the first Internet of things data;
acquiring a first data processing channel corresponding to the first Internet of things data according to the first data processing rate;
performing data processing on the first Internet of things data through the first data processing channel;
the data classification model is a machine learning model obtained through training based on characteristic information of sample Internet of things data and the data processing rate of the sample Internet of things data.
2. The method according to claim 1, wherein the method further comprises:
acquiring a second data processing rate; the second data processing rate is the rate of data processing on the first Internet of things data through the first data processing channel;
and updating parameters of the data classification model based on the second data processing rate.
3. The method of claim 2, wherein the parameter updating the data classification model based on the second data processing rate comprises:
acquiring a data processing channel corresponding to the second data processing rate;
and when the data processing channel corresponding to the second data processing rate is other data processing channels except the first data processing channel, updating parameters of the data classification model based on the second data processing rate.
4. The method of claim 2, wherein the parameter updating the data classification model based on the second data processing rate comprises:
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
And when the first data processing channel is different from the second data processing channel, updating parameters of the data classification model based on the second data processing rate.
5. The method of any of claims 2 to 4, wherein said parameter updating the data classification model based on the second data processing rate comprises:
acquiring a loss function value based on the second data processing rate and the first data processing rate;
and updating parameters of the data classification model based on the loss function value.
6. The method of claim 1, wherein the data processing the first internet of things data through the first data processing channel comprises:
acquiring a second data processing channel; the second data processing channel is a data processing channel for processing second internet data; the second internet of things data is internet of things data which is transmitted by the first internet of things device last time;
when the first data processing channel is different from the second data processing channel and the internet of things data corresponding to the first internet of things device in the second data processing channel meets a first specified condition, performing data processing on the first internet of things data through the first data processing channel.
7. The method of claim 6, wherein the first specified condition comprises at least one of:
in the second data processing channel, the data quantity of the Internet of things corresponding to the first Internet of things device is larger than a first threshold value;
and in the second data processing channel, the sum of processing time of the Internet of things data corresponding to the first Internet of things device is larger than a second threshold value.
8. An internet of things data processing apparatus, the apparatus comprising:
the first data acquisition module is used for acquiring first Internet of things data sent by first Internet of things equipment and characteristic information corresponding to the first Internet of things data; the characteristic information comprises at least one of a communication protocol, a data format, a compression mode, a message body size, a device position, a device address, a transmission time and a transmission frequency;
the first rate acquisition module is used for processing the characteristic information of the first Internet of things data through a data classification model to obtain a first data processing rate of the first Internet of things data;
the first channel acquisition module acquires a first data processing channel corresponding to the first Internet of things data according to the first data processing rate;
The first data processing module is used for performing data processing on the first Internet of things data through a data processing channel corresponding to the first Internet of things data;
the data classification model is a machine learning model obtained through training based on characteristic information of sample Internet of things data and the data processing rate of the sample Internet of things data.
9. A computer device comprising a processor and a memory having stored therein at least one computer instruction that is loaded and executed by the processor to implement the internet of things data processing method of any of claims 1 to 7.
10. A computer readable storage medium having stored therein at least one computer instruction that is loaded and executed by a processor to implement the internet of things data processing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210553801.5A CN114938349B (en) | 2022-05-20 | 2022-05-20 | Internet of things data processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210553801.5A CN114938349B (en) | 2022-05-20 | 2022-05-20 | Internet of things data processing method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114938349A CN114938349A (en) | 2022-08-23 |
| CN114938349B true CN114938349B (en) | 2023-07-25 |
Family
ID=82864105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210553801.5A Active CN114938349B (en) | 2022-05-20 | 2022-05-20 | Internet of things data processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114938349B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100295A (en) * | 2020-10-12 | 2020-12-18 | 平安科技（深圳）有限公司 | User data classification method, device, equipment and medium based on federal learning |
| CN112926436A (en) * | 2021-02-22 | 2021-06-08 | 上海商汤智能科技有限公司 | Behavior recognition method and apparatus, electronic device, and storage medium |
| CN112948373A (en) * | 2021-01-26 | 2021-06-11 | 浙江吉利控股集团有限公司 | Internet of things equipment data processing method, device, equipment and storage medium |
| CN113099410A (en) * | 2021-04-23 | 2021-07-09 | 广东电网有限责任公司江门供电局 | 5G power edge data transmission processing method, device, terminal and medium |
| CN113705809A (en) * | 2021-09-07 | 2021-11-26 | 北京航空航天大学 | Data prediction model training method, industrial index prediction method and device |
| CN114333899A (en) * | 2021-09-01 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment, storage medium and computer program product |
-
2022
- 2022-05-20 CN CN202210553801.5A patent/CN114938349B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100295A (en) * | 2020-10-12 | 2020-12-18 | 平安科技（深圳）有限公司 | User data classification method, device, equipment and medium based on federal learning |
| CN112948373A (en) * | 2021-01-26 | 2021-06-11 | 浙江吉利控股集团有限公司 | Internet of things equipment data processing method, device, equipment and storage medium |
| CN112926436A (en) * | 2021-02-22 | 2021-06-08 | 上海商汤智能科技有限公司 | Behavior recognition method and apparatus, electronic device, and storage medium |
| CN113099410A (en) * | 2021-04-23 | 2021-07-09 | 广东电网有限责任公司江门供电局 | 5G power edge data transmission processing method, device, terminal and medium |
| CN114333899A (en) * | 2021-09-01 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment, storage medium and computer program product |
| CN113705809A (en) * | 2021-09-07 | 2021-11-26 | 北京航空航天大学 | Data prediction model training method, industrial index prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114938349A (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114362367B (en) | Cloud-edge-cooperation-oriented power transmission line monitoring system and method, and cloud-edge-cooperation-oriented power transmission line identification system and method | |
| CN112990211B (en) | Training method, image processing method and device for neural network | |
| WO2018234789A1 (en) | Systems and devices for compressing neural network parameters | |
| CN108924198A (en) | A kind of data dispatching method based on edge calculations, apparatus and system | |
| CN113011282A (en) | Graph data processing method and device, electronic equipment and computer storage medium | |
| CN116506474B (en) | Electric power micro-service layering system based on cloud edge cooperation | |
| CN113505883A (en) | Neural network training method and device | |
| CN111967271A (en) | Analysis result generation method, device, equipment and readable storage medium | |
| CN116489152A (en) | Linkage control method and device for Internet of things equipment, electronic equipment and medium | |
| Selvam et al. | Nelder–Mead Simplex Search Method-A Study | |
| Zhang et al. | Af-dndf: Asynchronous federated learning of deep neural decision forests | |
| CN114938349B (en) | Internet of things data processing method and device, computer equipment and storage medium | |
| WO2024066697A1 (en) | Image processing method and related apparatus | |
| CN113259145B (en) | End-to-end networking method and device for network slicing and network slicing equipment | |
| CN116545871A (en) | Multi-mode network traffic prediction method, device and medium | |
| CN111814044A (en) | Recommendation method and device, terminal equipment and storage medium | |
| CN117009885A (en) | Method, device, equipment and medium for training prediction model and network prediction | |
| CN115049730B (en) | Component mounting method, component mounting device, electronic apparatus, and storage medium | |
| CN112738225B (en) | Edge calculation method based on artificial intelligence | |
| CN114330239A (en) | Text processing method and device, storage medium and electronic equipment | |
| CN112702397B (en) | Data service processing method suitable for intelligent gateway | |
| Li et al. | Distributed computing framework of intelligent sensor network for electric power internet of things | |
| CN117173719B (en) | Text recognition method, device, equipment and storage medium | |
| CN111582482B (en) | Method, apparatus, device and medium for generating network model information | |
| CN117251035B (en) | Heat dissipation control method, heat dissipation control device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |