CN113379344A - Intelligent logistics processing method and system based on cloud computing processing - Google Patents
Intelligent logistics processing method and system based on cloud computing processing Download PDFInfo
- Publication number
- CN113379344A CN113379344A CN202110585655.XA CN202110585655A CN113379344A CN 113379344 A CN113379344 A CN 113379344A CN 202110585655 A CN202110585655 A CN 202110585655A CN 113379344 A CN113379344 A CN 113379344A
- Authority
- CN
- China
- Prior art keywords
- data
- scale
- variable
- analysis
- decision
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 95
- 230000009466 transformation Effects 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000006243 chemical reaction Methods 0.000 claims abstract description 52
- 230000007246 mechanism Effects 0.000 claims abstract description 42
- 230000008569 process Effects 0.000 claims abstract description 41
- 238000007418 data mining Methods 0.000 claims abstract description 33
- 238000007405 data analysis Methods 0.000 claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 7
- 238000013499 data model Methods 0.000 claims description 35
- 238000005259 measurement Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005065 mining Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000007726 management method Methods 0.000 abstract description 7
- 238000002474 experimental method Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 33
- 238000011156 evaluation Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 7
- 238000010276 construction Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013341 scale-up Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 229910017052 cobalt Inorganic materials 0.000 description 1
- 239000010941 cobalt Substances 0.000 description 1
- GUTLYIVDDKVIGB-UHFFFAOYSA-N cobalt atom Chemical compound [Co] GUTLYIVDDKVIGB-UHFFFAOYSA-N 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
Images
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
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention requests to protect an intelligent logistics processing method and system based on cloud computing processing, basic service data scale is determined, variable scale data in a decision analysis process are analyzed, data mining is carried out based on variable scale data analysis, a data security platform is carried out by adopting a key generation method based on a block chain, and multi-objective service resource combination optimization is carried out based on cloud computing; a scale transformation mechanism is established by aiming at the problems of data structure determination, analysis level conversion and analysis result inspection faced by a decision analysis system constructed by applying a cross-industry data mining standard process, and a foundation is laid for realizing an automatic data analysis technology supporting a data mining process. Moreover, a variable-scale clustering analysis algorithm facing various data types is provided for the most common clustering analysis task in the application of the data mining technology, and the advantages and application values of scale transformation in the practical management problem are verified by the practical data experiment results of different decision analysis scenes.
Description
Technical Field
The invention belongs to the technical field of computer application, and particularly relates to an intelligent logistics processing method and system based on cloud computing processing.
Background
Under the digital economic background, in each decision-making link of an enterprise in production and operation activities, decision-making quality and decision-making efficiency can be improved by using data analysis results, and the establishment of a data mining system facing decision-making analysis becomes an urgent need of enterprises in different industries and different development stages. According to the life cycle of an enterprise during construction of a data mining system, a data mining technology gradually forms a normalized application process methodology in practical application, namely a cross-industry data mining standard process (CRISP-DMM)
The CRISP-DM standard process is used for building an enterprise decision analysis system and the subsequent operation process of the enterprise decision analysis system hinders engineering of the enterprise decision analysis system and intelligentization and automation of system operation, so that a plurality of data mining algorithms can only be used as an independent demand-driven data analysis tool, and the three links of data preparation, analysis model building and analysis result evaluation need to depend on subjective participation of analysts, and can be connected into a complete process of decision analysis.
Meanwhile, cloud manufacturing has produced profound influences on the manufacturing industry as a product of the integration of advanced technologies such as cloud computing, internet of things and artificial intelligence. Cloud manufacturing not only draws wide attention of academic circles, but also invests a large amount of funds to carry out research on the cloud manufacturing, governments and the industry, certain achievements are achieved in application levels of manufacturing service combination, workshop scheduling, resource allocation, logistics management and the like, and the theory and method research of the cloud manufacturing has important academic and application values. In the cloud manufacturing mode, manufacturing resources can be shared in a wider range, and the manufacturing cost can be reduced while the utilization rate of the manufacturing resources is improved. With the further deepening of the application development of the internet of things, the requirement on the safety of the internet of things is gradually improved, so that a new technology of the safety technology of the internet of things needs to be further sought in order to adapt to new internet environment and safety requirements, and the requirements on the safety and privacy of the internet of things are met.
Disclosure of Invention
In order to solve the problems of complexity and unsafety of current data analysis and processing, the invention firstly requests to protect an intelligent logistics processing method based on cloud computing processing, and is characterized by comprising the following steps:
determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three types of original service data, namely classified variable data, binary variable data and numerical variable data, and establishing a complete data structure foundation for variable-scale data analysis;
analyzing variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing automatic identification and conversion of a reasonable analysis level of service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
data mining is carried out based on variable-scale data analysis, a data security platform is built by adopting a key generation method based on a block chain, and multi-target service resource combination optimization is carried out based on cloud computing.
Specifically, the determining the scale of the basic service data, determining the scale structure of the basic service data according to the characteristics of three types of original service data, namely, the classified variable data, the binary variable data and the numerical variable data, and establishing a complete data structure basis for the analysis of the variable-scale data specifically includes:
establishing a multi-scale business data model facing to the spatial representation of the decision problem, and determining an observation scale and the scale thereof required by the decision problem;
constructing a multi-scale data model of a single observation ruler for each observation ruler;
integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model;
completing variable-scale clustering analysis, and determining an observation scale and a scale thereof required by a decision problem;
constructing a multi-scale data model of a single observation ruler for each observation ruler;
and integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model.
Further, analyzing the variable-scale data in the decision analysis process, simulating the thinking process when a manager performs decision analysis hierarchical conversion, aiming at improving the quality of the decision result, constructing a data scale conversion mechanism based on the data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing the automatic identification and conversion of the reasonable analysis hierarchy of the service data, and establishing an automatic decision analysis mechanism based on the data scale conversion, specifically comprising:
the variable scale clustering analysis method with multiple complex value classification variable data is used for defining the data repetition degree of a multi-scale data model and establishing the scale transformation rate measurement of classification variable data;
a classification variable data scale transformation mechanism is adopted, the mechanism optimizes the selection process of a scale transformation strategy by adding multiple complex value preprocessing links of classification variable data, and the calculation efficiency of a meta-clustering analysis algorithm is improved;
providing a classification variable data scale-variable clustering analysis algorithm according to a classification variable data scale transformation mechanism;
the variable scale clustering analysis method with binary variable data is to establish a multi-scale binary variable data model and define breadth scale transformation;
establishing a binary variable data scale transformation rate measurement according to a multi-scale binary variable data model, and providing a binary variable data scale transformation mechanism by combining a scale up-conversion mechanism, wherein the mechanism controls a breadth scale transformation process by using the binary variable data scale transformation rate;
and providing a binary variable data variable scale clustering analysis algorithm according to a binary variable data scale transformation mechanism.
Further, the data mining is performed based on variable scale data analysis, and the data security platform is built by adopting a block chain-based key generation method, specifically including:
carrying out variable-scale clustering analysis on classified variable data and binary variable data to obtain client types and various client preference characteristics and attention contents, and determining actual requirements formulated by enterprises;
and extracting the track data type of the requirement, and generating a key for the service data by adopting a block chain based on the data requirement of the track type to obtain the clustering safety tracking of the track scale.
The invention also requests to protect an intelligent logistics processing system based on cloud computing processing, which is characterized by comprising the following components:
the service scale determining module is used for determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three original service data types of classified variable data, binary variable data and numerical variable data, and establishing a complete data structure basis for variable scale data analysis;
the decision analysis module is used for analyzing the variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing the automatic identification and conversion of the reasonable analysis level of the service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
and the data mining safety module is used for mining data based on variable-scale data analysis and building a data safety platform by adopting a key generation method based on a block chain.
The invention establishes a scale transformation mechanism aiming at the problems of data structure determination, analysis level conversion and analysis result inspection in the construction of a decision analysis system by using a cross-industry data mining standard process (CRISP-DM), and lays a foundation for realizing an automatic data analysis technology supporting the whole application process of data mining. Moreover, a variable-scale clustering analysis algorithm facing various data types (including classification variable data, binary variable data and numerical variable data) is provided for the most common clustering analysis task in the application of the data mining technology, and the advantages and application values of scale transformation in practical management problems are verified by the practical data experiment results of different decision analysis scenes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a work flow chart of an intelligent logistics processing method based on cloud computing processing according to the present invention;
fig. 2 is a system block diagram of an intelligent logistics processing system based on cloud computing processing according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention firstly requests an intelligent logistics processing method based on cloud computing processing, which is characterized by comprising:
determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three types of original service data, namely classified variable data, binary variable data and numerical variable data, and establishing a complete data structure foundation for variable-scale data analysis;
analyzing variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing automatic identification and conversion of a reasonable analysis level of service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
data mining is carried out based on variable-scale data analysis, a data security platform is built by adopting a key generation method based on a block chain, and multi-target service resource combination optimization is carried out based on cloud computing.
Specifically, the determining the scale of the basic service data, determining the scale structure of the basic service data according to the characteristics of three types of original service data, namely, the classified variable data, the binary variable data and the numerical variable data, and establishing a complete data structure basis for the analysis of the variable-scale data specifically includes:
establishing a multi-scale business data model facing to the spatial representation of the decision problem, and determining an observation scale and the scale thereof required by the decision problem; determining the scale and scale value of all observation scales and each observation scale required in the decision analysis process according to the business knowledge and experience of decision-making personnel, generally taking the initial scale during business data acquisition as the basic scale of each observation scale, and respectively constructing a conceptual space model capable of describing the scale hierarchical structure relationship for each observation scale
Constructing a multi-scale data model of a single observation ruler for each observation ruler; and finding a concept space corresponding to each observation ruler in the initial service data, and gradually expanding the value taking result of the object under the basic scale to each scale level according to the scale value structure relationship in the concept space. If the enterprise selects the industry standard concept space model in the above stage, the scale and the scale value capable of reflecting the business characteristics of the enterprise in the industry standard concept space model are also selected before the object data is expanded.
Integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model; and integrating the independent multi-scale data of each observation ruler obtained in the above stage according to a uniform object sequence to form a complete multi-scale data model containing all the observation rulers required by the decision analysis process. For multi-scale data constructed according to an industry standard concept space model, as the industry general scale value sometimes exceeds the business range of an enterprise, the constructed multi-scale data may have redundant scales which cannot be combined with object values, and all the redundant scales need to be deleted to ensure the conversion efficiency of the subsequent decision analysis level.
Completing variable-scale clustering analysis, and determining an observation scale and a scale thereof required by a decision problem;
constructing a multi-scale data model of a single observation ruler for each observation ruler;
and integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model.
Further, analyzing the variable-scale data in the decision analysis process, simulating the thinking process when a manager performs decision analysis hierarchical conversion, aiming at improving the quality of the decision result, constructing a data scale conversion mechanism based on the data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing the automatic identification and conversion of the reasonable analysis hierarchy of the service data, and establishing an automatic decision analysis mechanism based on the data scale conversion, specifically comprising:
the variable scale clustering analysis method with multiple complex value classification variable data is used for defining the data repetition degree of a multi-scale data model and establishing the scale transformation rate measurement of classification variable data;
a classification variable data scale transformation mechanism is adopted, the mechanism optimizes the selection process of a scale transformation strategy by adding multiple complex value preprocessing links of classification variable data, and the calculation efficiency of a meta-clustering analysis algorithm is improved;
providing a classification variable data scale-variable clustering analysis algorithm according to a classification variable data scale transformation mechanism;
specifically, inputting a multi-scale classification variable data model DsScale transformation strategy type (aggressive or conservative scale transformation strategy), upper limit threshold mu of data repetition degree of the multi-scale data model; and (3) outputting: satisfied class and scale features SF, scale transformation path STP. Preprocessing of multi-repeated value data and identification of multi-scale data model DsIs a basic scale hierarchy data D0All the objects are repeated, and only one representative object is reserved for each repeated value. Basic scale hierarchical clustering, using meta-clustering analysis algorithm to pair D0To carry out the first stageAnd starting clustering, and evaluating the basic scale level clustering result by utilizing the granularity deviation GrD. And determining a satisfaction judgment threshold, identifying all satisfaction classes in the basic scale hierarchical clustering result, and taking the maximum granularity deviation of all the satisfaction classes as a satisfaction judgment threshold heart. If the satisfactory class cannot be found and the highest scale level is not reached, executing step scale transformation; otherwise, the operation is terminated. Initial satisfaction class result output and data update, adding repeated objects into the representative object class, outputting all satisfaction classes and scale characteristics SF of each class, and outputting all objects in each satisfaction class from DsIs deleted.
Scale transformation, calculating the scale transformation rate of classified variable data by using the upper limit threshold mu of the data repetition degree of the multi-scale data model, and updating the data DsAll objects in (1) that are not classified into a satisfactory class are subjected to an on-scale cobalt transformation. If an aggressive scale transformation strategy is adopted, selecting an observation ruler with the largest classification variable data scale transformation rate to implement scale-up drilling transformation, and obtaining transformed single-scale data D'; if a conservative scale transformation strategy is adopted, selecting an observation ruler with the minimum classification variable data scale transformation rate to implement scale-up drilling transformation, and obtaining transformed single-scale data D'; and if the scale transformation rates of all the observation scales are the same, selecting any one observation scale to implement scale transformation.
Preprocessing the data of the multiple repeated values, identifying all the repeated objects in D', and only reserving one representative object for each repeated value; performing scale level clustering after transformation, clustering D' by using a meta-clustering analysis algorithm, and evaluating a scale level clustering result after transformation by using a granularity deviation GrD; automatic recognition of satisfaction class, determining the threshold R if satisfaction0If the granularity deviation is smaller than or equal to R, all granularity deviations in the scale level clustering result after the transformation are identified0Is taken as a satisfactory class, and when the evaluation result of the particle size deviation of all classes is larger than R0Directly taking the equivalent class in the D' as a satisfactory class; otherwise, step satisfaction determination threshold determination is performed.
Output of satisfaction class result and data update, adding repeated objects to representative object class, and outputting all satisfaction classes and each classScale feature SF and convert all objects in each satisfaction class from DsDeleting; judging whether the scale transformation iteration process of the variable scale clustering analysis is terminated or not; if D issIf there still exist objects which are not classified into satisfactory classes, step scaling is performed, if D issAnd outputting the scale transformation path STP when the set is the empty set.
The variable scale clustering analysis method with binary variable data is to establish a multi-scale binary variable data model and define breadth scale transformation;
establishing a binary variable data scale transformation rate measurement according to a multi-scale binary variable data model, and providing a binary variable data scale transformation mechanism by combining a scale up-conversion mechanism, wherein the mechanism controls a breadth scale transformation process by using the binary variable data scale transformation rate;
and providing a binary variable data variable scale clustering analysis algorithm according to a binary variable data scale transformation mechanism.
Further, the data mining is performed based on variable scale data analysis, and the data security platform is built by adopting a block chain-based key generation method, specifically including:
carrying out variable-scale clustering analysis on classified variable data and binary variable data to obtain client types and various client preference characteristics and attention contents, and determining actual requirements formulated by enterprises;
and extracting the track data type of the requirement, and generating a key for the service data by adopting a block chain based on the data requirement of the track type to obtain the clustering safety tracking of the track scale.
Referring to fig. 2, the present invention further provides an intelligent logistics processing system based on cloud computing processing, which is characterized by comprising:
the service scale determining module is used for determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three original service data types of classified variable data, binary variable data and numerical variable data, and establishing a complete data structure basis for variable scale data analysis;
the decision analysis module is used for analyzing the variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing the automatic identification and conversion of the reasonable analysis level of the service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
and the data mining safety module is used for mining data based on variable-scale data analysis and building a data safety platform by adopting a key generation method based on a block chain. The intelligent contract of the intelligent key generation scheme based on the ECC algorithm is realized by multiple contracts, so that Gas consumption during contract calling is saved, the public key of the scheme is printed by a storage module of a secondary contract, and the private key is also stored in the key storage module. The user sends a key request to the block chain; 2) block chains: printing the public key and the encrypted private key in a transaction result; 3) an encryption and decryption module: the Internet of things node initiates a key request to the block chain, and the block chain system generates a key by means of the Internet of things key generation system and then stores the key in the key storage module. 1) Obtaining a public key: the public key is directly printed in the transaction result, and the node can inquire the transaction result through the block chain to obtain the public key. 2) Obtaining a private key: and after the node queries the transaction result to obtain a private key ciphertext M, the ciphertext M is decrypted by using the account private key to obtain the generated private key.
Key generation is divided into three modules: the device comprises a key management module, a key generation module and a key storage module. Wherein, the key management module: 1) the information of the node responsible for acquiring the trigger transaction comprises a node address and a public key of a node account, and is stored in a key storage module as an owner of a generated key pair and the generated key; 2) the public key is output to the whole network; 3) responsible for distributing the private key. A key generation module: and the key pair related to the account is generated according to the information transmitted by the management module and the data of the intelligent contract. A key storage module: and the system is responsible for correspondingly storing the information of the owner of the key and the key.
The information stored in the key storage module includes: a transaction trigger wallet address, a trigger account public key, a generated smart key pair. The transaction trigger wallet address is the owner of the token-generated smart key pair; the trigger account public key is a public key of the blockchain account, is a cryptography technology based on the blockchain and is related to the safety of the account; the generated smart key pair is a pair of a public key and a private key.
In the Internet of things based on the block chain, when a node needs a secret key, a transaction is sent to an intelligent secret key generation contract to generate a secret key pair, wherein the public key encrypts a data text into a ciphertext, and the private key is responsible for decrypting the ciphertext to obtain the text. The smart key generation steps are as follows:
1. the node A triggers contract preset conditions or sends transactions to contracts;
2. acquiring node A information including a node A wallet address and a node A account public key by a main contract;
3. calling a secondary contract according to the acquired parameters and the secondary contract address;
4. the secondary contract generates a key pair according to the improved ECC algorithm;
5. the public key is output to the whole network, and the private key is distributed to a key owner and is defaulted as a node for triggering transaction;
6. contract clearing node information and a key pair;
7. the node B obtains the public key by looking at the transaction result.
The invention establishes a scale transformation mechanism aiming at the problems of data structure determination, analysis level conversion and analysis result inspection in the construction of a decision analysis system by using a cross-industry data mining standard process (CRISP-DM), and lays a foundation for realizing an automatic data analysis technology supporting the whole application process of data mining. Moreover, a variable-scale clustering analysis algorithm facing various data types (including classification variable data, binary variable data and numerical variable data) is provided for the most common clustering analysis task in the application of the data mining technology, and the advantages and application values of scale transformation in practical management problems are verified by the practical data experiment results of different decision analysis scenes.
Specifically, the cloud computing-based multi-target service resource combination optimization includes: task decomposition, service operation and matching, service combination evaluation, loss function optimization and better combined service execution path.
Task decomposition means that in the cloud manufacturing process, tasks issued by manufacturing demand users through a cloud manufacturing platform can be according to the tasks
The functional attributes are divided into a number of manufacturing subtasks. And these subtasks may be matched by corresponding candidate manufacturing services. Suppose the manufacturing demand task is MTask ═ MT1,MT2,MT3,MT4...,MTn) Where n is the total number of manufacturing tasks currently received. The corresponding subtasks for each of its manufacturing requirement tasks may be represented as:
where m is the ith manufacturing requirement task MTiThe total number of manufacturing subtasks into which it is divided.Is MTiThe mth manufacturing subtask of (1). Each manufacturing subtask corresponds to a respective set of candidate services. To accurately match each manufacturing subtask to a suitable service, a search and match of candidate services is required. Suppose the ith manufacturing requirement task MTiM candidate services ofThen each correspondingA candidate service consists of k specific services, which are represented by:
Each subtask of a manufacturing requirement matches a corresponding candidate service, a process referred to as service composition. In the process of service composition, it is necessary to not only perform simple search and matching from the candidate service set, but also consider whether the selected service can satisfy the QoS index of the user (for example, whether the total price of the selected service is within the user's acceptance range, whether the production speed of the actual production plant of the selected service can satisfy the user's expectation in time, whether the selected service can satisfy the quality standard, and the like). Therefore, in order to find a better service composition execution path, the evaluation of the service composition becomes more important. Generally, the evaluation of a service composition mainly involves the evaluation of service functions, the evaluation of service quality, and the evaluation of service effectiveness.
The QoS vector for each manufacturing sub-service is represented asWherein q istTo representThe tth QoS index of (2). In order to calculate the QoS index of the overall manufacturing task, the QoS parameter values are first normalized, i.e. scaled to a true value between 0 and 1, and the specific calculation method is as follows:
wherein q ist,maxAnd q ist,minRespectively cloud manufacturing sub-servicesThe maximum and minimum values of the t-th QoS index,
The scaled QoS value is then compared with a preference weight value ωtMultiplying and summing to obtain:
wherein, ω istIs a group of preference weights related to QoS indexes, and determines the influence of each QoS index;
finally, the formula (3) is substituted for the formula (4) to obtain the QoS value of the whole manufacturing task;
after a set of service combination evaluation results are obtained, the mocsccm introduces a Back Propagation (BP) concept in the field of neural networks to perform real-time feedback adjustment on the system. The back propagation is to compare the results of the obtained set of service combination evaluations with the real evaluations of the users, calculate the loss value (loss) between the two by using a Loss Function (LF), and feed the loss value back to the system for adjustment. The loss function can be expressed as:
wherein, yiAndreal-time rating values and predictive service combined rating values, respectively. Equation (5) represents the average error margin of the predicted QoS estimation value, and the loss function does not need to consider the direction of the error, and ranges from 0 to ∞.
The present invention is not limited to the above preferred embodiments, but rather, any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. An intelligent logistics processing method based on cloud computing processing is characterized by comprising the following steps:
determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three types of original service data, namely classified variable data, binary variable data and numerical variable data, and establishing a complete data structure foundation for variable-scale data analysis; analyzing variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing automatic identification and conversion of a reasonable analysis level of service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
data mining is carried out based on variable-scale data analysis, a data security platform is built by adopting a key generation method based on a block chain, and multi-target service resource combination optimization is carried out based on cloud computing.
2. The intelligent logistics processing method based on cloud computing processing as claimed in claim 1, wherein said determining a scale of basic service data, determining a scale structure of basic service data for characteristics of three types of original service data, namely, classified variable data, binary variable data, and numerical variable data, and establishing a complete data structure basis for variable scale data analysis specifically comprises:
establishing a multi-scale business data model facing to the spatial representation of the decision problem, and determining an observation scale and the scale thereof required by the decision problem; constructing a multi-scale data model of a single observation ruler for each observation ruler;
integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model;
completing variable-scale clustering analysis, and determining an observation scale and a scale thereof required by a decision problem;
constructing a multi-scale data model of a single observation ruler for each observation ruler;
and integrating the multi-scale data models of all the single observation scales to form a final multi-scale data model.
3. The intelligent logistics processing method based on cloud computing processing as claimed in claim 1, wherein the analysis of the scale-variable data in the decision analysis process simulates a thinking process of a manager in the decision analysis level conversion, and the data scale conversion mechanism based on the data mining result is constructed with the goal of improving the quality of the decision result, and the automatic identification and conversion of the reasonable analysis level of the business data are realized by considering the influence of different original business data types on the data scale conversion mode, and the automatic decision analysis mechanism based on the data scale conversion is established, which specifically comprises:
the variable scale clustering analysis method with multiple complex value classification variable data is used for defining the data repetition degree of a multi-scale data model and establishing the scale transformation rate measurement of classification variable data;
a classification variable data scale transformation mechanism is adopted, the mechanism optimizes the selection process of a scale transformation strategy by adding multiple complex value preprocessing links of classification variable data, and the calculation efficiency of a meta-clustering analysis algorithm is improved;
providing a classification variable data scale-variable clustering analysis algorithm according to a classification variable data scale transformation mechanism;
the variable scale clustering analysis method with binary variable data is to establish a multi-scale binary variable data model and define breadth scale transformation;
establishing a binary variable data scale transformation rate measurement according to a multi-scale binary variable data model, and providing a binary variable data scale transformation mechanism by combining a scale up-conversion mechanism, wherein the mechanism controls a breadth scale transformation process by using the binary variable data scale transformation rate;
and providing a binary variable data variable scale clustering analysis algorithm according to a binary variable data scale transformation mechanism.
4. The intelligent logistics processing method based on cloud computing processing of claim 1, wherein the data mining is performed based on variable-scale data analysis, and the data security platform building is performed by adopting a block chain-based key generation method, specifically comprising:
carrying out variable-scale clustering analysis on classified variable data and binary variable data to obtain client types and various client preference characteristics and attention contents, and determining actual requirements formulated by enterprises;
and extracting the track data type of the requirement, and generating a key for the service data by adopting a block chain based on the data requirement of the track type to obtain the clustering safety tracking of the track scale.
5. An intelligent logistics processing system based on cloud computing processing, comprising:
the service scale determining module is used for determining the scale of basic service data, determining the scale structure of the basic service data aiming at the characteristics of three original service data types of classified variable data, binary variable data and numerical variable data, and establishing a complete data structure basis for variable scale data analysis;
the decision analysis module is used for analyzing the variable-scale data in the decision analysis process, simulating the thinking process of a manager during decision analysis level conversion, aiming at improving the quality of a decision result, constructing a data scale conversion mechanism based on a data mining result, considering the influence of different original service data types on a data scale conversion mode, realizing the automatic identification and conversion of the reasonable analysis level of the service data, and establishing an automatic decision analysis mechanism based on data scale conversion;
and the data mining safety module is used for mining data based on variable-scale data analysis, building a data safety platform by adopting a key generation method based on a block chain, and performing multi-target service resource combination optimization based on cloud computing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110585655.XA CN113379344A (en) | 2021-05-27 | 2021-05-27 | Intelligent logistics processing method and system based on cloud computing processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110585655.XA CN113379344A (en) | 2021-05-27 | 2021-05-27 | Intelligent logistics processing method and system based on cloud computing processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113379344A true CN113379344A (en) | 2021-09-10 |
Family
ID=77572167
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110585655.XA Pending CN113379344A (en) | 2021-05-27 | 2021-05-27 | Intelligent logistics processing method and system based on cloud computing processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113379344A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115374316A (en) * | 2022-10-24 | 2022-11-22 | 北京科技大学 | Intelligent variable-scale data analysis method and system supported by real-time decision |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109583796A (en) * | 2019-01-08 | 2019-04-05 | 河南省灵山信息科技有限公司 | A kind of data digging system and method for Logistics Park OA operation analysis |
CN110458558A (en) * | 2019-07-04 | 2019-11-15 | 重庆金融资产交易所有限责任公司 | Data encryption method, device and computer equipment based on block chain |
CN110689433A (en) * | 2019-09-26 | 2020-01-14 | 上海克而瑞信息技术有限公司 | Resource management information service system, method and device based on alliance chain |
CN110717716A (en) * | 2019-10-10 | 2020-01-21 | 安徽九州通智能科技有限公司 | Cloud logistics platform and construction method |
-
2021
- 2021-05-27 CN CN202110585655.XA patent/CN113379344A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109583796A (en) * | 2019-01-08 | 2019-04-05 | 河南省灵山信息科技有限公司 | A kind of data digging system and method for Logistics Park OA operation analysis |
CN110458558A (en) * | 2019-07-04 | 2019-11-15 | 重庆金融资产交易所有限责任公司 | Data encryption method, device and computer equipment based on block chain |
CN110689433A (en) * | 2019-09-26 | 2020-01-14 | 上海克而瑞信息技术有限公司 | Resource management information service system, method and device based on alliance chain |
CN110717716A (en) * | 2019-10-10 | 2020-01-21 | 安徽九州通智能科技有限公司 | Cloud logistics platform and construction method |
Non-Patent Citations (1)
Title |
---|
王艾: "面向决策支持的变尺度聚类分析技术", 中国博士学位论文全文数据库信息科技辑, no. 2, 15 February 2021 (2021-02-15), pages 1 - 171 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115374316A (en) * | 2022-10-24 | 2022-11-22 | 北京科技大学 | Intelligent variable-scale data analysis method and system supported by real-time decision |
CN115374316B (en) * | 2022-10-24 | 2023-01-03 | 北京科技大学 | Intelligent variable-scale data analysis method and system supported by real-time decision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pamučar et al. | Selection of a location for the development of multimodal logistics center: Application of single-valued neutrosophic MABAC model | |
Pang et al. | An integrated fuzzy synthetic evaluation approach for supplier selection based on analytic network process | |
CN108647914B (en) | Production scheduling method and device, computer equipment and storage medium | |
WO2021130771A1 (en) | System and method of machine learning based deviation prediction and interconnected-metrics derivation for action recommendations | |
Ramadass et al. | Evaluation of cloud vendors from probabilistic linguistic information with unknown/partial weight values | |
Huang et al. | A study of distributionally robust multistage stochastic optimization | |
KR20220115357A (en) | A method and apparatus for generating future demand forecast data based on attention mechanism | |
Hamrouni et al. | Optimal team recruitment strategies for collaborative mobile crowdsourcing systems | |
CN115563859A (en) | Power load prediction method, device and medium based on layered federal learning | |
Ghadimi et al. | Reinforcement learning via parametric cost function approximation for multistage stochastic programming | |
Tian et al. | A dynamic job-shop scheduling model based on deep learning. | |
CN115309647A (en) | Federal learning-based software defect prediction privacy protection method | |
CN113379344A (en) | Intelligent logistics processing method and system based on cloud computing processing | |
Skulimowski | A foresight support system to manage knowledge on information society evolution | |
Gómez-Marín et al. | Integrating multi-agent system and microsimulation for dynamic modeling of urban freight transport | |
Al-Zarrad et al. | A new model to improve project time-cost trade-off in uncertain environments | |
CN116703553A (en) | Financial anti-fraud risk monitoring method, system and readable storage medium | |
CN113379345A (en) | Intelligent logistics processing method and system based on trajectory tracking | |
CN113779116B (en) | Object ordering method, related equipment and medium | |
Lakhno et al. | Multi-criterial optimization composition of cyber security circuits based on genetic algorithm | |
Zolotareva et al. | New approach to risk controlling in information security | |
Deyi et al. | Stochastic programming for the optimization of transportation-inventory strategy | |
Zhang et al. | Research on high-efficiency resource allocation of multi-edge devices based on cloud manufacturing mode | |
Alves et al. | Linear Programming and Genetic Algorithm for Generation Maintenance Scheduling and Hydrothermal Dispatch considering Uncertainties in Multicriteira Decision Making | |
RU2542925C1 (en) | Method of self-organisation of distributed multiprocessor system |
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 |