CN117391585A - Warehouse information management method and system of industrial Internet - Google Patents
Warehouse information management method and system of industrial Internet Download PDFInfo
- Publication number
- CN117391585A CN117391585A CN202311439022.3A CN202311439022A CN117391585A CN 117391585 A CN117391585 A CN 117391585A CN 202311439022 A CN202311439022 A CN 202311439022A CN 117391585 A CN117391585 A CN 117391585A
- Authority
- CN
- China
- Prior art keywords
- information
- management
- model
- warehouse
- data
- 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.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 206
- 238000003860 storage Methods 0.000 claims abstract description 109
- 238000012549 training Methods 0.000 claims abstract description 92
- 238000000605 extraction Methods 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000004927 fusion Effects 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010048669 Terminal state Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a warehouse information management method and system of an industrial Internet, comprising the steps of obtaining warehouse information training data of the industrial Internet; inputting the storage information training data into a basic network model; based on the feature extraction layer, after at least one piece of storage information is randomly hidden from storage information training data in an iteration mode, a plurality of different data sequence features corresponding to each piece of storage information training data are obtained through feature extraction, and are input into the classification layer for classification processing, so that a plurality of corresponding classification results are obtained; respectively calculating loss values between every two of the two; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that loss values are minimized, model training is completed, and a storage information management model is obtained; the storage information management model is used for managing storage information. According to the invention, the automatic management of the warehouse information can be realized based on the network model, the management accuracy and efficiency are improved, the data do not need to be marked, and the cost is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a warehouse information management method and system of an industrial Internet.
Background
The industrial internet is used for realizing interconnection and intercommunication of equipment, systems, data and the like in the production and operation processes through the internet of things and the internet technology, and realizing information sharing and cooperative work.
In the industrial internet, warehouse information management is an important link, and relates to collection, processing and management of warehouse data. The traditional warehouse information management method is generally based on rules and experience, and has the problems of incomplete information collection, low efficiency, easy error and the like and poor accuracy. Or training the deep learning model by adopting the marking data so as to manage the information, and then the mode needs more time to mark the data, so that the cost is increased.
Disclosure of Invention
The invention mainly aims to provide a warehouse information management method and system of the industrial Internet, and aims to overcome the defects of poor accuracy and increased cost in the existing warehouse information management.
In order to achieve the above purpose, the present invention provides a warehouse information management method of the industrial internet, comprising the following steps:
acquiring warehouse information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
Inputting the warehouse information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
for each warehouse information training data, based on the feature extraction layer, carrying out feature extraction to obtain a plurality of different data sequence features corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode;
respectively inputting a plurality of different data sequence features into the classification layer for classification processing to obtain a plurality of corresponding classification results;
for a plurality of classification results, calculating loss values between every two of the classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received.
Further, the step of obtaining the warehouse information management model after the step of performing iterative adjustment on model parameters of the feature extraction layer and the classification layer to minimize the loss values and complete training of the basic network model comprises the following steps:
Receiving target storage information of the industrial Internet; the target warehouse information is new industrial internet warehouse information and comprises a plurality of data sequences of the warehouse information;
inputting the target warehouse information into the warehouse information management model;
based on the feature extraction layer, after randomly hiding one storage information from the target storage information each time and repeating for three times, carrying out feature extraction to obtain three different data sequence features corresponding to the target storage information;
inputting three different data sequence features into the classification layer respectively for classification processing to obtain three corresponding classification results;
judging whether the three classification results are the same, and if so, verifying that the warehouse information management model is effective.
Further, the step of obtaining the warehouse information management model by iteratively adjusting model parameters of the feature extraction layer and the classification layer to minimize the loss values so as to complete training of the basic network model further comprises:
acquiring a currently available management terminal; the available management terminal is equipment for managing storage information in the storage system;
Selecting a target terminal from the currently available management terminals;
and deploying the warehouse information management model to the target terminal.
Further, the step of selecting a target terminal from the currently available management terminals includes:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal;
according to the length of the update time from the current time, sequencing all currently available management terminals according to the length from large to small to obtain a management terminal sequence;
acquiring identification information of each currently available management terminal; the number of the identification information is N, the number of the currently available management terminals is M, and M is smaller than N;
randomly selecting a preset character combination from a database; the database stores a plurality of preset character combinations, and the number of characters of each preset character combination is N;
according to the sequence of the management terminals, carrying out character intersection calculation on the preset character combination and the identification information of the management terminals in sequence to obtain the number of characters, the number of the characters is the same as that of the preset character combination and the identification information of each management terminal; after performing a character intersection calculation with the identification information of the management terminal, when entering the character intersection calculation of the identification information of the next management terminal, deleting one character at the end of the preset character combination;
And obtaining the management terminal with the largest number of the same characters as the target terminal according to the number of the same characters of the preset character combination and the identification information of each management terminal.
Further, the step of deploying the warehouse information management model to the target terminal includes:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal;
judging whether the time length of the update time of each available management terminal from the current time exceeds a threshold value, if not, acquiring each corresponding management terminal as a first management terminal, and acquiring first model parameters of an original historical storage information management model on each first management terminal;
acquiring second model parameters of the storage information management model obtained through training;
carrying out fusion calculation on the second model parameters and each first model parameter to obtain fusion model parameters;
and transmitting the fusion model parameters to the target terminal, and updating model parameters of the historical warehouse information management model on the target terminal based on the fusion model parameters so as to realize deployment of the warehouse information management model.
Further, the step of transmitting the fusion model parameters to the target terminal includes:
acquiring identification information of each first management terminal and the number of the first management terminals;
selecting a preset number of characters from the identification information of each first management terminal to serve as first characters; wherein the preset number is determined by the number of the first management terminals;
randomly arranging and combining first characters selected from the identification information of each first management terminal, and taking the obtained combined character string as an encryption password;
encrypting the fusion model parameters based on the encryption password, transmitting the encrypted fusion model parameters to the target terminal, and simultaneously transmitting a data packet sequence; wherein, only one data packet in the data packet sequence stores the encryption password, one data packet stores a sequence number, and the other data packets are messy code data; the sequence number is the ranking of the data packet where the encryption password is located in the data packet sequence.
The invention also provides a warehouse information management system of the industrial Internet, which comprises:
the acquisition unit is used for acquiring storage information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
The input unit is used for inputting the storage information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
the feature extraction unit is used for extracting features of a plurality of different data sequences corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode based on the feature extraction layer aiming at each warehouse information training data;
the classification unit is used for inputting a plurality of different data sequence features into the classification layer respectively for classification processing to obtain a plurality of corresponding classification results;
the training unit is used for respectively calculating loss values between every two of the multiple classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received.
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 provides a warehouse information management method and a warehouse information management system of an industrial Internet, which comprise the steps of acquiring warehouse information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data; inputting the warehouse information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer; for each warehouse information training data, based on the feature extraction layer, carrying out feature extraction to obtain a plurality of different data sequence features corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode; respectively inputting a plurality of different data sequence features into the classification layer for classification processing to obtain a plurality of corresponding classification results; for a plurality of classification results, calculating loss values between every two of the classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received. According to the invention, the automatic management of the warehouse information can be realized based on the network model, the management accuracy and efficiency are improved, the data do not need to be marked, and the cost is reduced.
Drawings
FIG. 1 is a schematic diagram showing steps of a warehouse information management method of an industrial Internet according to an embodiment of the present invention;
FIG. 2 is a block diagram of a warehouse information management system of the industrial Internet according to an embodiment of the 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, there is provided a warehouse information management method of the industrial internet, including the steps of:
step S1, acquiring storage information training data of an industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
s2, inputting the storage information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
Step S3, for each warehouse information training data, based on the feature extraction layer, after at least one warehouse information is randomly hidden from the warehouse information training data in an iteration mode, feature extraction is carried out to obtain a plurality of different data sequence features corresponding to each warehouse information training data;
s4, inputting a plurality of different data sequence features into the classification layer respectively for classification processing to obtain a plurality of corresponding classification results;
step S5, respectively calculating loss values between every two of the classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received.
In the embodiment, the scheme is applied to management of warehouse information, can improve storage efficiency, optimize logistics and reduce operation cost, thereby remarkably improving the operation efficiency of the industrial Internet; and the data do not need to be marked, so that the cost is reduced.
Specifically, as described in the above step S1, warehouse information data of the industrial internet for training is acquired. These data are unlabeled, i.e., they are not manually classified or labeled in advance. Such data may come from sensors, devices, or other data sources. Each data sequence may contain a plurality of pieces of warehouse information, each of which may contain different features and attributes. For example, one warehouse information may include a warehouse number, a type of goods, a quantity of goods, etc.
The acquired warehouse information training data is input into the underlying network model as described in step S2 above. The underlying network model consists of two main parts: a feature extraction layer and a classification layer. The feature extraction layer is responsible for extracting important features from the input data, and the classification layer classifies the data according to the extracted features.
The feature extraction layer employs various machine learning and deep learning techniques to automatically learn useful features in the data. These techniques may include Convolutional Neural Networks (CNNs), recurrent Neural Networks (RNNs), or transformers, among others. By inputting the warehouse information training data into the feature extraction layer, the model can learn and extract useful features representing the data.
As described in step S3, for each warehouse information training data, an iterative operation is performed based on the feature extraction layer to obtain the data sequence features. In the iterative process, at least one piece of warehouse information is randomly selected from the warehouse information training data and hidden. This operation of randomly hiding the bin information is intended to increase the model's ability to understand the different features in the data. By iteratively hiding the warehouse information and extracting the characteristics, a plurality of different data sequence characteristics corresponding to the training data of each warehouse information can be obtained.
The data sequence features can capture the differences and similarities between warehouse information in the data, and provide richer information for subsequent classification and management. Then, the features are respectively input into a classification layer for classification processing, and a plurality of corresponding classification results are obtained. .
As described in step S4, a plurality of corresponding classification results are obtained by inputting a plurality of different data sequence features obtained previously into the classification layer for classification processing.
The classification layer is typically comprised of one or more classifiers for mapping the characteristics of the input data sequence to corresponding classes. Each classifier may perform a two-classification or multi-classification task for a particular class, classifying the input features into different classes. By classifying each data sequence feature, a plurality of classification results can be obtained, and the classification results correspond to different storage information where the input features are located. The classification results can be used for subsequent analysis and management, helping to better understand and process the warehouse information in the industrial internet.
As described in step S5 above, the loss values between the plurality of classification results are calculated and minimized by iteratively adjusting the model parameters. For the plurality of classification results obtained, the loss value may be calculated by comparing the differences between them. This may be achieved by using different evaluation indices and loss functions, such as cross entropy, mean square error, etc. The loss value reflects the accuracy and consistency of the model for different classification results. By iteratively adjusting the model parameters of the feature extraction layer and classification layer, one can try to minimize these loss values. The model parameters can be adjusted step by using optimization algorithms such as gradient descent, so that the model can be better adapted to training data and classification accuracy is improved.
Finally, the model parameters are adjusted through repeated iteration to minimize the loss value, the training of the basic network model is completed, and the warehouse information management model is obtained. The model can be used for classifying, identifying and managing the warehouse information of the industrial Internet when receiving the warehouse information, and improving the efficiency and accuracy of warehouse information management.
In the embodiment, the information management efficiency can be improved by managing the warehouse information based on the network model, so that the storage efficiency is improved, the logistics is optimized, the operation cost is reduced, and the operation efficiency of the industrial Internet is remarkably improved; and the data do not need to be marked, so that the cost is reduced.
In an embodiment, the step of obtaining the warehouse information management model after the step of performing iterative adjustment on model parameters of the feature extraction layer and the classification layer to minimize the loss values and complete training of the basic network model includes:
receiving target storage information of the industrial Internet; the target warehouse information is new industrial internet warehouse information and comprises a plurality of data sequences of the warehouse information;
inputting the target warehouse information into the warehouse information management model;
based on the feature extraction layer, after randomly hiding one storage information from the target storage information each time and repeating for three times, carrying out feature extraction to obtain three different data sequence features corresponding to the target storage information;
inputting three different data sequence features into the classification layer respectively for classification processing to obtain three corresponding classification results;
judging whether the three classification results are the same, and if so, verifying that the warehouse information management model is effective.
In this embodiment, the target warehouse information is new industrial internet warehouse information, which includes a plurality of data sequences of warehouse information. The target warehousing information may be real-time information from sensors, equipment, or other data sources. The information may include warehouse number, type of goods, quantity of goods, etc.
And inputting the received target warehouse information into a warehouse information management model trained before. The model comprises a trained feature extraction layer and a classification layer, which can process and classify input target warehouse information.
And processing the target warehouse information based on the feature extraction layer. This operation is repeated three times, randomly hiding one warehouse information from the target warehouse information each time, and extracting the characteristics. Thus, three different data sequence characteristics corresponding to the target warehouse information can be obtained.
And then, respectively inputting the obtained three different data sequence characteristics into a classification layer for classification processing. The classification layer judges the category to which the classification layer belongs according to the input characteristics and obtains a corresponding classification result. Because one warehouse information is hidden randomly and three feature extraction operations are performed, three classification results are obtained.
And judging whether the three classification results are the same or not. If they are the same, the model can accurately classify the target warehouse information through feature extraction and classification processing. The validity and the accuracy of the warehouse information management model are verified, and the model is proved to be capable of accurately managing the warehouse information in practical application.
Through the steps, the storage information of the new industrial Internet can be input into the trained storage information management model, and the classification accuracy of the model on the new data is verified. The intelligent storage information management can be realized by helping the industrial Internet, and the operation efficiency and accuracy are improved.
In an embodiment, the step of obtaining the warehouse information management model further includes:
acquiring a currently available management terminal; the available management terminal is equipment for managing storage information in the storage system; in a warehouse system, there are a plurality of devices for managing warehouse information, which are generally called management terminals. This step involves obtaining a list of currently available devices from the available management terminals.
Selecting a target terminal from the currently available management terminals; among the available management terminal lists, a target terminal is selected according to a specific selection policy or algorithm. The objective of selecting the target terminal is to deploy the warehouse information management model to a specific device for practical application.
And deploying the warehouse information management model to the target terminal. And deploying the storage information management model subjected to training and optimization to the selected target terminal. This enables the terminal to invoke the warehouse information management model according to the input warehouse information to perform warehouse information management.
In an embodiment, the step of selecting a target terminal from the currently available management terminals includes:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal; and acquiring a list of currently available management terminal devices from the warehousing system. These devices are used to manage and process logistic requests and storage requests. And acquiring the update time of the existing historical warehouse information management model on each currently available management terminal. These update times reflect the last training or update of the model on the terminal.
According to the length of the update time from the current time, sequencing all currently available management terminals according to the length from large to small to obtain a management terminal sequence; and sequencing the management terminals according to the sequence from big to small according to the time length of the historical model updating time and the current time on each management terminal. That is, the terminal having the longest update time from the current time is arranged at the first position.
Acquiring identification information of each currently available management terminal; the number of the identification information is N, the number of the currently available management terminals is M, and M is smaller than N; the identification information of each currently available management terminal is acquired for calculation and comparison in a subsequent step. The identification information may be a unique ID of the device or other information capable of uniquely identifying the terminal.
Randomly selecting a preset character combination from a database; the database stores a plurality of preset character combinations, and the number of characters of each preset character combination is N;
according to the sequence of the management terminals, carrying out character intersection calculation on the preset character combination and the identification information of the management terminals in sequence to obtain the number of characters, the number of the characters is the same as that of the preset character combination and the identification information of each management terminal; after performing a character intersection calculation with the identification information of the management terminal, when entering the character intersection calculation of the identification information of the next management terminal, deleting one character at the end of the preset character combination; the result of the intersection calculation is the number of identical characters, that is, the number of characters existing in both the preset character combination and the identification information of the management terminal. Meanwhile, after each time of character intersection calculation is carried out on the identification information of the management terminal, when character intersection calculation of the identification information of the next management terminal is carried out, one character at the end of the preset character combination needs to be deleted, so that the management terminal arranged in front has higher probability of increasing the number of the same characters when the character intersection calculation is carried out, and the priority of the management terminal is higher.
And obtaining the management terminal with the largest number of the same characters as the target terminal according to the number of the same characters of the preset character combination and the identification information of each management terminal.
In an embodiment, the step of deploying the warehouse information management model to the target terminal includes:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal; the update time reflects the last training or update of the model on the terminal.
Judging whether the time length of the update time of each available management terminal from the current time exceeds a threshold value, if not, acquiring each corresponding management terminal as a first management terminal, and acquiring first model parameters of an original historical storage information management model on each first management terminal; for each available management terminal, judging whether the duration of the update time and the current time exceeds a threshold value. If the threshold is not exceeded, the next step is continued. If the threshold is exceeded, the terminal is not selected as the first management terminal. And selecting the available management terminal which does not exceed the threshold value as a first management terminal, and acquiring first model parameters of an original historical warehouse information management model on the terminal for subsequent fusion calculation.
Acquiring second model parameters of the storage information management model obtained through training;
carrying out fusion calculation on the second model parameters and each first model parameter to obtain fusion model parameters; and carrying out fusion calculation on the first model parameter and the second model parameter to obtain a final fusion model parameter. The manner of fusion may employ weighted averaging, weighted summation, or other algorithms depending on the particular needs.
And transmitting the fusion model parameters to the target terminal, and updating model parameters of the historical warehouse information management model on the target terminal based on the fusion model parameters so as to realize deployment of the warehouse information management model. And transmitting the fusion model parameters to the selected target terminal, and updating the model parameters of the historical storage information management model on the target terminal based on the parameters. The target terminal can manage and predict the logistics request and the storage request by using the new model parameters.
Through the steps, the trained warehouse information management model can be deployed to the selected target terminal. By fusing the calculated model parameters, the target terminal can predict and manage the logistics demand and the storage demand more accurately and in real time. The deployment mode can select the most suitable terminal according to the actual demand and the terminal state, and the warehouse information management model is effectively applied to actual management.
In an embodiment, the step of transmitting the fusion model parameters to the target terminal includes:
acquiring identification information of each first management terminal and the number of the first management terminals;
selecting a preset number of characters from the identification information of each first management terminal to serve as first characters; wherein the preset number is determined by the number of the first management terminals; if the number of the first management terminals is less than three, the preset number is 4; the number of the first management terminals is three to five, the preset number is 2, and if the number of the first management terminals is greater than five, the preset number is 1.
Randomly arranging and combining first characters selected from the identification information of each first management terminal, and taking the obtained combined character string as an encryption password; and randomly arranging and combining the selected first characters to generate a new character string serving as an encryption password. Therefore, the passwords generated each time can be randomly and unpredictably ensured, and the security of the data is improved.
Encrypting the fusion model parameters based on the encryption password, transmitting the encrypted fusion model parameters to the target terminal, and simultaneously transmitting a data packet sequence; wherein, only one data packet in the data packet sequence stores the encryption password, one data packet stores a sequence number, and the other data packets are messy code data; the sequence number is the ranking of the data packet where the encryption password is located in the data packet sequence.
In this embodiment, the generated encryption password is used to encrypt the fusion model parameters, so as to ensure confidentiality and integrity of data in the transmission process. And sending the encrypted fusion model parameters to the target terminal so that the target terminal can receive and decrypt the parameters and update the stored information management model of the target terminal. And simultaneously transmitting a data packet sequence, wherein only one data packet stores the generated encryption password, the other data packet stores a sequence number, and the rest data packets are messy-code data. The sequence number in the transmitted sequence of data packets indicates the rank of the data packet in which the encryption password is located in the sequence of data packets. Through the steps, the fusion model parameters are encrypted and then sent to the target terminal, and a data packet sequence is sent to ensure safe transmission and reception of data. The target terminal can decrypt the data and update the storage information management model by using the received encrypted model parameters and the data packet sequence, so as to realize the deployment and update of the storage information management model. Such a step may protect the confidentiality of the data from unauthorized access and tampering.
The method comprises the steps that a preset number of characters are selected from identification information of each first management terminal to serve as first characters, and specifically comprises the following steps:
determining the preset number according to the number of the first management terminals;
inputting the preset number as an input parameter into a preset script for operation processing to obtain result information output by the preset script; wherein the result information is a character group; the character set is usually a character string composed of numbers and letters.
Rearranging the standard coding table according to the preset number to obtain a new coding table; the new encoding table has uniqueness after rearrangement, and data security is increased.
Decoding the character set based on a new encoding table to obtain a decoded character set; decoding is the inverse of encoding, and decoding and encoding are based on the new encoding table. The above-described decoded character set is a combination of digital characters, i.e., a string of numbers. For example, the decoding character set is 1394.
Obtaining a separation mode corresponding to the preset number based on the mapping relation of the number stored in the database and the separation mode; e.g., a 2-1-1 rule, the 1394 can be split into 13-9-4.
Performing character separation on the decoding character set based on the separation mode to obtain a plurality of separation character combinations; 13, 9, 4.
Analyzing each separation character combination to obtain corresponding numbers; sequentially selecting a preset number of characters from the identification information of each first management terminal; when the characters are selected, the characters at the corresponding arrangement positions in the identification information of the first management terminal are selected according to the numbers corresponding to the separation character combinations; for example, if the numbers corresponding to the separation character combinations are 13, 9, and 4, the characters located at the 13 th, 9 th, and 4 th positions are sequentially selected from the identification information of the first management terminal as the first characters.
Referring to fig. 2, in an embodiment of the present invention, there is further provided an industrial internet warehouse information management system, including:
the acquisition unit is used for acquiring storage information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
the input unit is used for inputting the storage information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
The feature extraction unit is used for extracting features of a plurality of different data sequences corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode based on the feature extraction layer aiming at each warehouse information training data;
the classification unit is used for inputting a plurality of different data sequence features into the classification layer respectively for classification processing to obtain a plurality of corresponding classification results;
the training unit is used for respectively calculating loss values between every two of the multiple classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received. In this embodiment, for specific implementation of each unit in the above embodiment of the apparatus, please refer to the description in the above embodiment of the method, and no further description is given here.
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 display screen, an input device, 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 to store the corresponding data in this embodiment. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the above-mentioned method.
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 also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above method. 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 and the system for managing the warehouse information of the industrial internet provided by the embodiment of the invention comprise the steps of obtaining the warehouse information training data of the industrial internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data; inputting the warehouse information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer; for each warehouse information training data, based on the feature extraction layer, carrying out feature extraction to obtain a plurality of different data sequence features corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode; respectively inputting a plurality of different data sequence features into the classification layer for classification processing to obtain a plurality of corresponding classification results; for a plurality of classification results, calculating loss values between every two of the classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received. According to the invention, the automatic management of the warehouse information can be realized based on the network model, the management accuracy and efficiency are improved, the data do not need to be marked, and the cost is reduced.
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 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, 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 (8)
1. The warehouse information management method of the industrial Internet is characterized by comprising the following steps of:
acquiring warehouse information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
Inputting the warehouse information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
for each warehouse information training data, based on the feature extraction layer, carrying out feature extraction to obtain a plurality of different data sequence features corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode;
respectively inputting a plurality of different data sequence features into the classification layer for classification processing to obtain a plurality of corresponding classification results;
for a plurality of classification results, calculating loss values between every two of the classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received.
2. The method for managing information of warehouse of industrial internet as set forth in claim 1, wherein the step of obtaining the information of warehouse management model by iteratively adjusting model parameters of the feature extraction layer and the classification layer to minimize the loss values to complete training of the basic network model comprises:
Receiving target storage information of the industrial Internet; the target warehouse information is new industrial internet warehouse information and comprises a plurality of data sequences of the warehouse information;
inputting the target warehouse information into the warehouse information management model;
based on the feature extraction layer, after randomly hiding one storage information from the target storage information each time and repeating for three times, carrying out feature extraction to obtain three different data sequence features corresponding to the target storage information;
inputting three different data sequence features into the classification layer respectively for classification processing to obtain three corresponding classification results;
judging whether the three classification results are the same, and if so, verifying that the warehouse information management model is effective.
3. The method for managing information of warehouse of industrial internet as set forth in claim 1, wherein the step of obtaining the information of warehouse management model by iteratively adjusting model parameters of the feature extraction layer and the classification layer to minimize the loss values to complete training of the basic network model further includes:
acquiring a currently available management terminal; the available management terminal is equipment for managing storage information in the storage system;
Selecting a target terminal from the currently available management terminals;
and deploying the warehouse information management model to the target terminal.
4. The method for managing warehouse information of the industrial internet as claimed in claim 3, wherein the step of selecting a target terminal from the currently available management terminals comprises:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal;
according to the length of the update time from the current time, sequencing all currently available management terminals according to the length from large to small to obtain a management terminal sequence;
acquiring identification information of each currently available management terminal; the number of the identification information is N, the number of the currently available management terminals is M, and M is smaller than N;
randomly selecting a preset character combination from a database; the database stores a plurality of preset character combinations, and the number of characters of each preset character combination is N;
according to the sequence of the management terminals, carrying out character intersection calculation on the preset character combination and the identification information of the management terminals in sequence to obtain the number of characters, the number of the characters is the same as that of the preset character combination and the identification information of each management terminal; after performing a character intersection calculation with the identification information of the management terminal, deleting one character at the end of the preset character combination when entering the character intersection calculation of the identification information of the next management terminal;
And obtaining the management terminal with the largest number of the same characters as the target terminal according to the number of the same characters of the preset character combination and the identification information of each management terminal.
5. The method for warehouse information management of the industrial internet as claimed in claim 3, wherein the deploying the warehouse information management model to the target terminal comprises:
acquiring the update time of an original historical warehouse information management model on each currently available management terminal;
judging whether the time length of the update time of each available management terminal from the current time exceeds a threshold value, if not, acquiring each corresponding management terminal as a first management terminal, and acquiring first model parameters of an original historical storage information management model on each first management terminal;
acquiring second model parameters of the storage information management model obtained through training;
carrying out fusion calculation on the second model parameters and each first model parameter to obtain fusion model parameters;
and transmitting the fusion model parameters to the target terminal, and updating model parameters of the historical warehouse information management model on the target terminal based on the fusion model parameters so as to realize deployment of the warehouse information management model.
6. The method of claim 5, wherein the step of transmitting the fusion model parameters to the target terminal comprises:
acquiring identification information of each first management terminal and the number of the first management terminals;
selecting a preset number of characters from the identification information of each first management terminal to serve as first characters; wherein the preset number is determined by the number of the first management terminals;
randomly arranging and combining first characters selected from the identification information of each first management terminal, and taking the obtained combined character string as an encryption password;
encrypting the fusion model parameters based on the encryption password, transmitting the encrypted fusion model parameters to the target terminal, and simultaneously transmitting a data packet sequence; wherein, only one data packet in the data packet sequence stores the encryption password, one data packet stores a sequence number, and the other data packets are messy code data; the sequence number is the ranking of the data packet where the encryption password is located in the data packet sequence.
7. The warehouse information management system of the industrial internet is characterized by comprising:
The acquisition unit is used for acquiring storage information training data of the industrial Internet; the storage information training data is a data sequence comprising a plurality of storage information, wherein the storage information training data is unlabeled data;
the input unit is used for inputting the storage information training data into a basic network model; the basic network model comprises a feature extraction layer and a classification layer;
the feature extraction unit is used for extracting features of a plurality of different data sequences corresponding to each warehouse information training data after at least one warehouse information is hidden from the warehouse information training data at random in an iteration mode based on the feature extraction layer aiming at each warehouse information training data;
the classification unit is used for inputting a plurality of different data sequence features into the classification layer respectively for classification processing to obtain a plurality of corresponding classification results;
the training unit is used for respectively calculating loss values between every two of the multiple classification results; the model parameters of the feature extraction layer and the classification layer are subjected to iterative adjustment, so that the loss values are minimized, training of a basic network model is completed, and a warehouse information management model is obtained; the storage information management model is used for managing storage information when the storage information of the industrial Internet is received.
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, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311439022.3A CN117391585A (en) | 2023-11-01 | 2023-11-01 | Warehouse information management method and system of industrial Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311439022.3A CN117391585A (en) | 2023-11-01 | 2023-11-01 | Warehouse information management method and system of industrial Internet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117391585A true CN117391585A (en) | 2024-01-12 |
Family
ID=89438973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311439022.3A Pending CN117391585A (en) | 2023-11-01 | 2023-11-01 | Warehouse information management method and system of industrial Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117391585A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117828572A (en) * | 2024-03-05 | 2024-04-05 | 深圳市正业玖坤信息技术有限公司 | Data security management method and device of industrial Internet of things and computer equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111831675A (en) * | 2020-07-07 | 2020-10-27 | 平安科技（深圳）有限公司 | Storage model training method and device, computer equipment and storage medium |
| CN113535964A (en) * | 2021-09-15 | 2021-10-22 | 深圳前海环融联易信息科技服务有限公司 | Enterprise classification model intelligent construction method, device, equipment and medium |
| CN113869398A (en) * | 2021-09-26 | 2021-12-31 | 平安科技（深圳）有限公司 | Unbalanced text classification method, device, equipment and storage medium |
| CN114328904A (en) * | 2021-09-07 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Content processing method, content processing device, computer equipment and storage medium |
-
2023
- 2023-11-01 CN CN202311439022.3A patent/CN117391585A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111831675A (en) * | 2020-07-07 | 2020-10-27 | 平安科技（深圳）有限公司 | Storage model training method and device, computer equipment and storage medium |
| CN114328904A (en) * | 2021-09-07 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Content processing method, content processing device, computer equipment and storage medium |
| CN113535964A (en) * | 2021-09-15 | 2021-10-22 | 深圳前海环融联易信息科技服务有限公司 | Enterprise classification model intelligent construction method, device, equipment and medium |
| CN113869398A (en) * | 2021-09-26 | 2021-12-31 | 平安科技（深圳）有限公司 | Unbalanced text classification method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117828572A (en) * | 2024-03-05 | 2024-04-05 | 深圳市正业玖坤信息技术有限公司 | Data security management method and device of industrial Internet of things and computer equipment |
| CN117828572B (en) * | 2024-03-05 | 2024-05-24 | 深圳市正业玖坤信息技术有限公司 | Data security management method and device of industrial Internet of things and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110730140B (en) | Deep learning flow classification method based on combination of space-time characteristics | |
| CN109509021B (en) | Behavior track-based anomaly identification method and device, server and storage medium | |
| CN111444952A (en) | Method and device for generating sample identification model, computer equipment and storage medium | |
| CN111131314B (en) | Network behavior detection method and device, computer equipment and storage medium | |
| CN117391585A (en) | Warehouse information management method and system of industrial Internet | |
| CN113139536B (en) | Text verification code identification method and equipment based on cross-domain meta learning and storage medium | |
| US11658989B1 (en) | Method and device for identifying unknown traffic data based dynamic network environment | |
| US11182468B1 (en) | Methods and systems for facilitating secure authentication of user based on known data | |
| CN109698798B (en) | Application identification method and device, server and storage medium | |
| CN113297393A (en) | Situation awareness and big data based information generation method and information security system | |
| CN111740946A (en) | Webshell message detection method and device | |
| CN114650176A (en) | Phishing website detection method and device, computer equipment and storage medium | |
| CN114168968A (en) | Vulnerability mining method based on Internet of things equipment fingerprints | |
| CN116541228B (en) | Touch response detection method and device for display and computer equipment | |
| CN117527369A (en) | Hash function-based android malicious attack monitoring method and system | |
| CN113904961B (en) | User behavior identification method, system, equipment and storage medium | |
| CN107220262A (en) | Information processing method and device | |
| CN113271319B (en) | Communication data encryption method and system based on block chain | |
| CN115690566A (en) | Deep sea animal new species identification method based on deep migration clustering learning | |
| CN114138709A (en) | Librarian room integrated management realized based on cloud archive integrated platform | |
| CN112817816A (en) | Embedded point processing method and device, computer equipment and storage medium | |
| CN112328779A (en) | Training sample construction method and device, terminal equipment and storage medium | |
| CN111131322A (en) | Network behavior detection method and device, computer equipment and storage medium | |
| Jain et al. | An Approach to Identify Vulnerable Features of Instant Messenger | |
| CN116258829B (en) | Method and device for constructing map and vision robot |
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 |