CN116186595B - Data processing method and device based on industrial Internet of things and computer equipment - Google Patents
Data processing method and device based on industrial Internet of things and computer equipment Download PDFInfo
- Publication number
- CN116186595B CN116186595B CN202310462733.6A CN202310462733A CN116186595B CN 116186595 B CN116186595 B CN 116186595B CN 202310462733 A CN202310462733 A CN 202310462733A CN 116186595 B CN116186595 B CN 116186595B
- Authority
- CN
- China
- Prior art keywords
- data
- parameter
- training
- value set
- elements
- 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to the technical field of industrial Internet of things, and provides a data processing method, a device and computer equipment based on the industrial Internet of things, which comprise the following steps: the industrial robot is connected with the industrial Internet of things system through an Internet protocol; acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot; classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result; training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot. The invention respectively carries out corresponding processing on the equipment parameter data and the product detection data, thereby realizing unified management on the equipment parameters and the product parameters.
Description
Technical Field
The invention relates to the technical field of industrial Internet of things, in particular to a data processing method, device, computer equipment and storage medium based on the industrial Internet of things.
Background
The industrial robot equipment plays a vital role in an industrial Internet of things system, the industrial robot can realize various product processing on a product line, equipment parameters adopted by the industrial robot equipment are different when different products are processed, product parameter data detected by the products are also different, the number of the parameters is large, and the unified management of the parameters is inconvenient; in actual production, the parameters are simply recorded by the personnel in the production line by using related equipment, and unified management is not performed.
Disclosure of Invention
The invention mainly aims to provide a data processing method, a device, computer equipment and a storage medium based on industrial Internet of things, and aims to overcome the defect that unified management of equipment parameters and product parameters is not carried out at present.
In order to achieve the above object, the present invention provides a data processing method based on industrial internet of things, comprising the following steps:
the industrial robot is connected with the industrial Internet of things system through an Internet protocol;
acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result;
training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot.
Further, the step of training the preset deep learning model based on the device parameter data to obtain a corresponding classification model includes:
acquiring characteristic information of the equipment parameter data and acquiring a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
forming a training pair by the type characteristic and the numerical characteristic of the equipment parameter data and the classification label of the industrial robot, and inputting the training pair into an initial first deep learning model for training to obtain a first weight parameter of the first deep learning model;
matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and updating the first weight parameter of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
Further, the step of performing aggregation calculation on the first weight parameter and each second weight parameter to obtain a corresponding aggregation value includes:
communication negotiation is carried out together with each robot management device, and a trusted third party terminal is determined from a third party database; wherein, a plurality of trusted third party terminals are stored in the third party database;
generating a random interference parameter and adding a mark to the interference parameter; combining the interference parameter with the first weight parameter to obtain a combined weight parameter, and sending the combined weight parameter to the third-party terminal;
transmitting the second weight parameters to the third party terminal based on each robot management device;
performing mark recognition on the combining weight parameters based on the third-party terminal, and removing interference parameters corresponding to the marks from the combining weight parameters when the marks are recognized to obtain the first weight parameters; fusion calculation is carried out on the first weight parameter and the second weight parameter, and a corresponding fusion value is obtained;
and combining the fusion value and the interference parameter based on the third party terminal to obtain the aggregation value.
Further, the step of updating the first weight parameter of the first deep learning model based on the aggregate value includes:
receiving the aggregate value fed back by the third party terminal;
performing mark recognition on the aggregation value; if the mark is identified, deleting the interference parameter corresponding to the mark from the aggregation value to obtain the fusion value;
and updating the first weight parameter of the first deep learning model to the fusion value.
Further, the step of performing communication negotiation with each robot management device and determining a trusted third party terminal from a third party database includes:
sequentially acquiring the credibility of each credible third-party terminal in the third-party database, and sorting the credibility to select a pre-selected third-party terminal in the first three of the arrangement;
sequentially sending the information of the selected preselected third party terminal to each robot management device to obtain feedback of each robot management device; wherein the feedback includes trusted and untrusted;
and if the feedback of each robot management device is credible, taking the corresponding preselected third party terminal as a third party terminal determined through negotiation.
Further, the step of classifying and summarizing the product detection data according to a preset mode includes:
selecting a plurality of specified data from the product detection data; sorting the specified data according to a preset sorting to obtain a data sequence; wherein the specified data is specified core data;
acquiring the value of each appointed data in the data sequence, and characterizing the value of the appointed data as a corresponding first numerical value set;
acquiring a second stored value set in a preset cloud database; the cloud database is stored with a plurality of second value sets, elements in the second value sets are values obtained by product parameters based on preset hash function operation, and each second value set corresponds to one product classification;
mapping elements in the first numerical value set to a target hash table based on a plurality of preset hash functions; the elements in the target hash table are hash values corresponding to all elements in the first numerical value set; each hash function only carries out hash mapping on one element at a corresponding position in the first numerical value set;
comparing the elements in the target hash table with the elements in the second value set; wherein, during comparison, only elements at the same position are compared;
acquiring the number of elements in the target hash table which are the same as the number of elements in the second value set; acquiring a second numerical value set with the most identical elements as a target numerical value set;
and obtaining the product classification corresponding to the target numerical value set, and taking the product classification as the classification of the products detected by the industrial robot.
The invention also provides a data processing device based on the industrial Internet of things, which comprises:
the connecting unit is used for connecting the industrial robot through an internet protocol and accessing an industrial Internet of things system;
an acquisition unit for acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
the classification unit is used for classifying and summarizing the product detection data according to a preset mode and classifying the products detected by the industrial robot according to a summarizing result;
the training unit is used for training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot.
Further, the training unit is specifically configured to:
acquiring characteristic information of the equipment parameter data and acquiring a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
forming a training pair by the type characteristic and the numerical characteristic of the equipment parameter data and the classification label of the industrial robot, and inputting the training pair into an initial first deep learning model for training to obtain a first weight parameter of the first deep learning model;
matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and updating the first weight parameter of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
The invention also provides a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of any of the methods described above when the computer program is executed.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.
The invention provides a data processing method, a device, a computer device and a storage medium based on industrial Internet of things, which comprise the following steps: the industrial robot is connected with the industrial Internet of things system through an Internet protocol; acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot; classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result; training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot. The invention respectively carries out corresponding processing on the equipment parameter data and the product detection data, thereby realizing unified management on the equipment parameters and the product parameters.
Drawings
FIG. 1 is a schematic diagram of steps of a data processing method based on an industrial Internet of things according to an embodiment of the present invention;
FIG. 2 is a block diagram of a data processing device based on the Internet of things industry in accordance with an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, in one embodiment of the present invention, a data processing method based on industrial internet of things is provided, including the following steps:
step S1, connecting an industrial robot through an Internet protocol and accessing an industrial Internet of things system;
s2, acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
step S3, classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result;
step S4, training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot.
In this embodiment, the method is applied to data management of an industrial robot by a management terminal in an industrial internet of things system. Specifically, as described in the above step S1, the industrial robots are connected through the internet protocol and connected to the industrial internet of things system, so that each industrial robot can transmit data information through the network; industrial robots may also be controlled by management devices through a network for remote interaction. Acquiring data on the industrial robot, wherein the data mainly comprises equipment parameter data and product detection data, as described in the step S2; the device parameter data refer to parameter data of the industrial robot, and the product detection data are data corresponding to products detected by the industrial robot. Different industrial robots have different parameter data, and the same industrial robot can also be suitable for detecting different products, and different products have different product detection data; the data are acquired, so that the classification management of the work of the industrial robot is facilitated.
And (3) classifying and summarizing the product detection data, and classifying the products detected by the industrial robot according to the summarizing result. Because different products have different product detection data, after the product detection data is obtained, the detected products can be classified according to the characteristics of the product detection data, so that the products detected by the industrial robot can be classified and managed conveniently.
As described in the above step S4, different industrial robots have different equipment parameter data, and thus the industrial robots can be classified according to the equipment parameter data; further, training a preset deep learning model by using the equipment parameter data to obtain a corresponding classification model; the classification model can be used to classify industrial robots subsequently. The input data of the classification model is the equipment parameter data of the industrial robot.
In an embodiment, the step S4 of training the preset deep learning model based on the device parameter data to obtain a corresponding classification model includes:
step S41, obtaining characteristic information of the equipment parameter data and obtaining a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
step S42, training pairs are formed by the type features and the numerical features of the equipment parameter data and the classification labels of the industrial robots, and are input into an initial first deep learning model for training, so that first weight parameters of the first deep learning model are obtained;
step S43, matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
step S44, training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
step S45, performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and step S46, updating the first weight parameters of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
In this embodiment, when the deep learning model is trained by using the above device parameter data, a training pair is required to be constructed, specifically, feature information of the device parameter data is acquired, and a classification label of the industrial robot is acquired, the feature information includes type features and numerical features of the device parameter data, the type features and the numerical features of the device parameter data and the classification label of the industrial robot form the training pair, and the training pair is input into an initial first deep learning model to perform training, so as to obtain a first weight parameter of the first deep learning model. Because the data of the training pair is limited, the effect of training the model is poor, and in order to improve the training effect, the training pair can be combined with other manufacturers for combined training.
Therefore, a plurality of corresponding robot management devices can be matched according to the type characteristics and the numerical characteristics of the device parameter data; each robot management device is management devices of other manufacturers and stores corresponding training data, wherein each training data comprises type characteristics and numerical characteristics corresponding to the device parameter data; and when matching, matching is carried out according to the type characteristics and the numerical characteristics of the equipment parameter data, and the management equipment with the same type characteristics and numerical characteristics is selected as the robot management equipment. Further, training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model, and performing aggregation calculation on the first weight parameters and each second weight parameter to obtain corresponding aggregation values; the aggregate value fuses a plurality of weight parameters, which is equivalent to carrying out multiple times of training, and training data on each industrial robot management device has corresponding differences, based on the training mode, not only training data are expanded, but also training data are not required to be exchanged during joint training, only the weight parameters are required to be interacted, so that leakage of the training data on each management device is not caused, and the data safety is ensured. And finally, updating the first weight parameters of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model. Based on the combined training mode, the confidence of the classification model is improved.
In an embodiment, the step of performing an aggregation calculation on the first weight parameter and each second weight parameter to obtain a corresponding aggregate value includes:
communication negotiation is carried out together with each robot management device, and a trusted third party terminal is determined from a third party database; wherein, a plurality of trusted third party terminals are stored in the third party database;
generating a random interference parameter and adding a mark to the interference parameter; combining the interference parameter with the first weight parameter to obtain a combined weight parameter, and sending the combined weight parameter to the third-party terminal; in this embodiment, in order to further weight security and privacy during data interaction, a random interference parameter is generated, and the random interference parameter is combined with the first weight parameter and then sent to the third party terminal. In order to avoid that the interference parameters affect the final training effect, the interference parameters need to be marked for subsequent identification.
Transmitting the second weight parameters to the third party terminal based on each robot management device;
performing mark recognition on the combining weight parameters based on the third-party terminal, and removing interference parameters corresponding to the marks from the combining weight parameters when the marks are recognized to obtain the first weight parameters; fusion calculation is carried out on the first weight parameter and the second weight parameter, and a corresponding fusion value is obtained;
and combining the fusion value and the interference parameter based on the third party terminal to obtain the aggregation value. Since the aggregate value needs to be fed back to the management terminal, in order to avoid data leakage, the aggregate value needs to be obtained by combining the fused value and the interference parameter. Due to the existence of the interference parameters, the model parameters can be interfered, and parameter leakage is avoided.
In an embodiment, the step of updating the first weight parameter of the first deep learning model based on the aggregate value includes:
receiving the aggregate value fed back by the third party terminal;
performing mark recognition on the aggregation value; if the mark is identified, deleting the interference parameter corresponding to the mark from the aggregation value to obtain the fusion value;
and updating the first weight parameter of the first deep learning model to the fusion value.
In this embodiment, in order to enhance the effect of the first deep learning model, the first weight parameter obtained by preliminary training needs to be updated, and when updating, the aggregate value fed back by the third party terminal is marked and identified, the interference parameter is identified, and the interference parameter is deleted from the aggregate value, so as to obtain the fusion value, and then the first weight parameter of the first deep learning model is updated to the fusion value.
In one embodiment, the step of performing communication negotiation with each of the robot management devices and determining a trusted third party terminal from a third party database includes:
sequentially acquiring the credibility of each credible third-party terminal in the third-party database, and sorting the credibility to select a pre-selected third-party terminal in the first three of the arrangement;
sequentially sending the information of the selected preselected third party terminal to each robot management device to obtain feedback of each robot management device; wherein the feedback includes trusted and untrusted;
and if the feedback of each robot management device is credible, taking the corresponding preselected third party terminal as a third party terminal determined through negotiation.
In another embodiment, the step S3 of classifying and summarizing the product detection data according to a preset manner includes:
selecting a plurality of specified data from the product detection data; sorting the specified data according to a preset sorting to obtain a data sequence; in order to avoid excessive data volume in subsequent processing, in this embodiment, a plurality of designated core data may be selected, and the designated data may be sequenced according to a preset sequence, so as to obtain a data sequence.
Acquiring the value of each appointed data in the data sequence, and characterizing the value of the appointed data as a corresponding first numerical value set; the first set of values may be characterized by the values of the specified data, for example a, b, c, d, and the first set of values may be expressed as { a, b, c, d }.
Acquiring a second stored value set in a preset cloud database; the cloud database is stored with a plurality of second value sets, elements in the second value sets are values obtained by product parameters based on preset hash function operation, and each second value set corresponds to one product classification;
mapping elements in the first numerical value set to a target hash table based on a plurality of preset hash functions; the elements in the target hash table are hash values corresponding to all elements in the first numerical value set; each hash function only carries out hash mapping on one element at a corresponding position in the first numerical value set; it can be understood that the preset hash function is consistent with the hash functions in the cloud database, and each hash function performs hash mapping on only one element at a specific position. For example, for the first value set { a, B, C, D }, the functions may be a function a, a function B, a function C, and a function D, respectively, based on four preset hash functions, where the function a is used for performing hash computation on the element a of the first bit in the first value set, the function B is used for performing hash computation on the element B of the second bit in the first value set, the function C is used for performing hash computation on the element C of the third bit in the first value set, and the function D is used for performing hash computation on the element D of the fourth bit in the first value set.
Comparing the elements in the target hash table with the elements in the second value set; wherein, during comparison, only elements at the same position are compared; in this embodiment, direct comparison of the original data is not performed, but the corresponding hash map values are compared, so that data leakage can be avoided.
Acquiring the number of elements in the target hash table which are the same as the number of elements in the second value set; acquiring a second numerical value set with the most identical elements as a target numerical value set; it may be understood that, when the element in the target hash table is the same as the element in the second value set, it indicates that the original data corresponding to the element in the target hash table and the element in the second value set are also the same; if a plurality of elements are the same, the similarity between the two products is higher, and the higher the number of the same elements is, the higher the similarity is.
And obtaining the product classification corresponding to the target numerical value set, and taking the product classification as the classification of the products detected by the industrial robot. In this embodiment, when the classification of the product detected by the industrial robot is obtained, the interaction of the detection data of the original product is not required, and only the transmission of the corresponding hash value is performed, so that the data leakage is not caused.
Referring to fig. 2, in an embodiment of the present invention, there is further provided a data processing device based on industrial internet of things, including:
the connecting unit is used for connecting the industrial robot through an internet protocol and accessing an industrial Internet of things system;
an acquisition unit for acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
the classification unit is used for classifying and summarizing the product detection data according to a preset mode and classifying the products detected by the industrial robot according to a summarizing result;
the training unit is used for training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot.
In an embodiment, the training unit is specifically configured to:
acquiring characteristic information of the equipment parameter data and acquiring a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
forming a training pair by the type characteristic and the numerical characteristic of the equipment parameter data and the classification label of the industrial robot, and inputting the training pair into an initial first deep learning model for training to obtain a first weight parameter of the first deep learning model;
matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and updating the first weight parameter of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
In this embodiment, the specific implementation manner of each unit in the embodiment of the apparatus is described in the embodiment of the method, and will not be described herein.
Referring to fig. 3, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing internet of things data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a data processing method based on the industrial Internet of things.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present invention further provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements a data processing method based on industrial internet of things. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the method, the device, the computer device and the storage medium for processing data based on the industrial internet of things provided in the embodiments of the present invention include: the industrial robot is connected with the industrial Internet of things system through an Internet protocol; acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot; classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result; training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; wherein the classification model is used for classifying the industrial robot. The invention respectively carries out corresponding processing on the equipment parameter data and the product detection data, thereby realizing unified management on the equipment parameters and the product parameters.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (9)
1. The data processing method based on the industrial Internet of things is characterized by comprising the following steps of:
the industrial robot is connected with the industrial Internet of things system through an Internet protocol;
acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
classifying and summarizing the product detection data according to a preset mode, and classifying the products detected by the industrial robot according to a summarizing result;
training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; the classification model is used for classifying the industrial robot;
the step of classifying and summarizing the product detection data according to a preset mode comprises the following steps:
selecting a plurality of specified data from the product detection data; sorting the specified data according to a preset sorting to obtain a data sequence; wherein the specified data is specified core data;
acquiring the value of each appointed data in the data sequence, and characterizing the value of the appointed data as a corresponding first numerical value set;
acquiring a second stored value set in a preset cloud database; the cloud database is stored with a plurality of second value sets, elements in the second value sets are values obtained by product parameters based on preset hash function operation, and each second value set corresponds to one product classification;
mapping elements in the first numerical value set to a target hash table based on a plurality of preset hash functions; the elements in the target hash table are hash values corresponding to all elements in the first numerical value set; each hash function only carries out hash mapping on one element at a corresponding position in the first numerical value set;
comparing the elements in the target hash table with the elements in the second value set; wherein, during comparison, only elements at the same position are compared;
acquiring the number of elements in the target hash table which are the same as the number of elements in the second value set; acquiring a second numerical value set with the most identical elements as a target numerical value set;
and obtaining the product classification corresponding to the target numerical value set, and taking the product classification as the classification of the products detected by the industrial robot.
2. The data processing method based on the industrial internet of things according to claim 1, wherein the step of training a preset deep learning model based on the device parameter data to obtain a corresponding classification model comprises the following steps:
acquiring characteristic information of the equipment parameter data and acquiring a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
forming a training pair by the type characteristic and the numerical characteristic of the equipment parameter data and the classification label of the industrial robot, and inputting the training pair into an initial first deep learning model for training to obtain a first weight parameter of the first deep learning model;
matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and updating the first weight parameter of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
3. The data processing method based on the industrial internet of things according to claim 2, wherein the step of performing an aggregation calculation on the first weight parameter and each second weight parameter to obtain a corresponding aggregation value includes:
communication negotiation is carried out together with each robot management device, and a trusted third party terminal is determined from a third party database; wherein, a plurality of trusted third party terminals are stored in the third party database;
generating a random interference parameter and adding a mark to the interference parameter; combining the interference parameter with the first weight parameter to obtain a combined weight parameter, and sending the combined weight parameter to the third-party terminal;
transmitting the second weight parameters to the third party terminal based on each robot management device;
performing mark recognition on the combining weight parameters based on the third-party terminal, and removing interference parameters corresponding to the marks from the combining weight parameters when the marks are recognized to obtain the first weight parameters; fusion calculation is carried out on the first weight parameter and the second weight parameter, and a corresponding fusion value is obtained;
and combining the fusion value and the interference parameter based on the third party terminal to obtain the aggregation value.
4. The method for processing data based on industrial internet of things according to claim 3, wherein the step of updating the first weight parameter of the first deep learning model based on the aggregate value comprises:
receiving the aggregate value fed back by the third party terminal;
performing mark recognition on the aggregation value; if the mark is identified, deleting the interference parameter corresponding to the mark from the aggregation value to obtain the fusion value;
and updating the first weight parameter of the first deep learning model to the fusion value.
5. A data processing method based on industrial internet of things according to claim 3, wherein the step of negotiating with each of the robot management devices and determining a trusted third party terminal from a third party database comprises:
sequentially acquiring the credibility of each credible third-party terminal in the third-party database, and sorting the credibility to select a pre-selected third-party terminal in the first three of the arrangement;
sequentially sending the information of the selected preselected third party terminal to each robot management device to obtain feedback of each robot management device; wherein the feedback includes trusted and untrusted;
and if the feedback of each robot management device is credible, taking the corresponding preselected third party terminal as a third party terminal determined through negotiation.
6. Data processing device based on industry thing networking, characterized by comprising:
the connecting unit is used for connecting the industrial robot through an internet protocol and accessing an industrial Internet of things system;
an acquisition unit for acquiring data on the industrial robot; wherein the data comprises device parameter data and product detection data; the product detection data are data corresponding to products detected by the industrial robot;
the classification unit is used for classifying and summarizing the product detection data according to a preset mode and classifying the products detected by the industrial robot according to a summarizing result;
the training unit is used for training a preset deep learning model based on the equipment parameter data to obtain a corresponding classification model; the classification model is used for classifying the industrial robot;
the classifying unit is specifically configured to:
selecting a plurality of specified data from the product detection data; sorting the specified data according to a preset sorting to obtain a data sequence; wherein the specified data is specified core data;
acquiring the value of each appointed data in the data sequence, and characterizing the value of the appointed data as a corresponding first numerical value set;
acquiring a second stored value set in a preset cloud database; the cloud database is stored with a plurality of second value sets, elements in the second value sets are values obtained by product parameters based on preset hash function operation, and each second value set corresponds to one product classification;
mapping elements in the first numerical value set to a target hash table based on a plurality of preset hash functions; the elements in the target hash table are hash values corresponding to all elements in the first numerical value set; each hash function only carries out hash mapping on one element at a corresponding position in the first numerical value set;
comparing the elements in the target hash table with the elements in the second value set; wherein, during comparison, only elements at the same position are compared;
acquiring the number of elements in the target hash table which are the same as the number of elements in the second value set; acquiring a second numerical value set with the most identical elements as a target numerical value set;
and obtaining the product classification corresponding to the target numerical value set, and taking the product classification as the classification of the products detected by the industrial robot.
7. The data processing device based on industrial internet of things according to claim 6, wherein the training unit is specifically configured to:
acquiring characteristic information of the equipment parameter data and acquiring a classification label of the industrial robot; wherein the characteristic information comprises type characteristics and numerical characteristics of the equipment parameter data;
forming a training pair by the type characteristic and the numerical characteristic of the equipment parameter data and the classification label of the industrial robot, and inputting the training pair into an initial first deep learning model for training to obtain a first weight parameter of the first deep learning model;
matching a plurality of corresponding robot management devices according to the type characteristics and the numerical characteristics of the device parameter data; wherein, each robot management device stores training data; and each training data comprises corresponding type characteristics and numerical characteristics;
training a second deep learning model preset on each robot management device based on training data on each robot management device to obtain second weight parameters of each second deep learning model;
performing aggregation calculation on the first weight parameters and the second weight parameters to obtain corresponding aggregation values;
and updating the first weight parameter of the first deep learning model based on the aggregation value to obtain an updated network model serving as the classification model.
8. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 5.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310462733.6A CN116186595B (en) | 2023-04-26 | 2023-04-26 | Data processing method and device based on industrial Internet of things and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310462733.6A CN116186595B (en) | 2023-04-26 | 2023-04-26 | Data processing method and device based on industrial Internet of things and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116186595A CN116186595A (en) | 2023-05-30 |
| CN116186595B true CN116186595B (en) | 2023-08-18 |
Family
ID=86433052
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310462733.6A Active CN116186595B (en) | 2023-04-26 | 2023-04-26 | Data processing method and device based on industrial Internet of things and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116186595B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107205016A (en) * | 2017-04-18 | 2017-09-26 | 中国科学院计算技术研究所 | The search method of internet of things equipment |
| CN115390570A (en) * | 2022-10-26 | 2022-11-25 | 深圳市思傲拓科技有限公司 | Swimming pool robot management and control system and method based on artificial intelligence |
| CN115786889A (en) * | 2023-02-13 | 2023-03-14 | 广州志橙半导体有限公司 | Data acquisition method and device of CVD (chemical vapor deposition) equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180284758A1 (en) * | 2016-05-09 | 2018-10-04 | StrongForce IoT Portfolio 2016, LLC | Methods and systems for industrial internet of things data collection for equipment analysis in an upstream oil and gas environment |
-
2023
- 2023-04-26 CN CN202310462733.6A patent/CN116186595B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107205016A (en) * | 2017-04-18 | 2017-09-26 | 中国科学院计算技术研究所 | The search method of internet of things equipment |
| CN115390570A (en) * | 2022-10-26 | 2022-11-25 | 深圳市思傲拓科技有限公司 | Swimming pool robot management and control system and method based on artificial intelligence |
| CN115786889A (en) * | 2023-02-13 | 2023-03-14 | 广州志橙半导体有限公司 | Data acquisition method and device of CVD (chemical vapor deposition) equipment |
Non-Patent Citations (1)
| Title |
|---|
| 计算机算法模型的新型辅助服务市场架构体系;李彦宾 等;信息技术(第12期);第136-142页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116186595A (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021027317A1 (en) | Relationship network-based attribute information processing method and device, computer apparatus, and storage medium | |
| CN103944813B (en) | A kind of gateway and method for realizing General adaptive function | |
| WO2019232964A1 (en) | Risk management data processing method and apparatus, computer device, and storage medium | |
| CN111931076B (en) | Method and device for carrying out relationship recommendation based on authorized directed graph and computer equipment | |
| WO2020125463A1 (en) | Report generation method and apparatus, computer device, and computer readable storage medium | |
| WO2019144549A1 (en) | Vulnerability testing method and device, computer equipment, and storage medium | |
| US11489676B2 (en) | Blockchain internet-of-things system and related method | |
| US11250166B2 (en) | Fingerprint-based configuration typing and classification | |
| CN113535825A (en) | Cloud computing intelligence-based data information wind control processing method and system | |
| CN111652615A (en) | Safety identification method based on block chain big data and artificial intelligence cloud service platform | |
| CN111666399A (en) | Intelligent question and answer method and device based on knowledge graph and computer equipment | |
| EP3972315A1 (en) | Network device identification | |
| AU2020437435A1 (en) | Adversarial image generation method, apparatus, device, and readable storage medium | |
| US20220006814A1 (en) | System, method, and computer program for automatically classifying user accounts in a computer network using keys from an identity management system | |
| CN113157863A (en) | Question and answer data processing method and device, computer equipment and storage medium | |
| US20220222952A1 (en) | Domain-specific human-model collaborative annotation tool | |
| JP2023012311A (en) | Information processing device, information processing method and program | |
| CN116186595B (en) | Data processing method and device based on industrial Internet of things and computer equipment | |
| AU2021104400A4 (en) | An intelligent system for detecting behavioral cyber attack on industrial iot using ai federated learning algorithm | |
| CN112839055B (en) | Network application identification method and device for TLS encrypted traffic and electronic equipment | |
| CN111026972B (en) | Subscription data pushing method, device, equipment and storage medium in Internet of things | |
| CN111680645B (en) | Garbage classification treatment method and device | |
| CN114584522B (en) | Identification method, system, medium and terminal of Internet of things equipment | |
| Hyun-Seong et al. | Design of automatic identification gateway system for different iot devices and services | |
| CN114373090A (en) | Model lightweight method, device, electronic equipment and computer readable storage 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 |