CN114549090B - Data processing system for performing quarterly data accounting according to wholesale orders - Google Patents

Data processing system for performing quarterly data accounting according to wholesale orders Download PDF

Info

Publication number
CN114549090B
CN114549090B CN202210436673.6A CN202210436673A CN114549090B CN 114549090 B CN114549090 B CN 114549090B CN 202210436673 A CN202210436673 A CN 202210436673A CN 114549090 B CN114549090 B CN 114549090B
Authority
CN
China
Prior art keywords
module
data
data information
wholesale
classification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210436673.6A
Other languages
Chinese (zh)
Other versions
CN114549090A (en
Inventor
黄正芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Mingluofeng Technology Co ltd
Original Assignee
Shenzhen Mingluofeng Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Mingluofeng Technology Co ltd filed Critical Shenzhen Mingluofeng Technology Co ltd
Priority to CN202210436673.6A priority Critical patent/CN114549090B/en
Publication of CN114549090A publication Critical patent/CN114549090A/en
Application granted granted Critical
Publication of CN114549090B publication Critical patent/CN114549090B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38—Information transfer, e.g. on bus
    • G06F13/40—Bus structure
    • G06F13/4004—Coupling between buses
    • G06F13/4022—Coupling between buses using switching circuits, e.g. switching matrix, connection or expansion network
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38—Information transfer, e.g. on bus
    • G06F13/40—Bus structure
    • G06F13/4063—Device-to-bus coupling
    • G06F13/4068—Electrical coupling
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/14—Multichannel or multilink protocols

Abstract

The invention discloses a data processing system for performing quarterly data accounting according to a wholesale order, which comprises a wholesale order information module, a classification calculation module, an association analysis module, a main control module, a multi-channel transmission module and an upper management module, wherein the classification calculation module is used for performing classification calculation on the quarterly data according to the wholesale order; the main control module is respectively connected with the classification calculation module, the multi-channel transmission module, the correlation analysis module and the wholesale order information module, the output end of the classification calculation module is connected with the input end of the correlation analysis module, and the output end of the multi-channel transmission module is connected with the input end of the upper management module. The invention adopts the classification algorithm of the improved clustering analysis algorithm model module to realize the classification and calculation of different order data information, and manages and calculates the wholesale order data information according to wholesale batch, season, quantity, amount, style or cargo type and data information through the association analysis module so as to realize seasonal data accounting output and greatly improve the data accounting capability.

Description

Data processing system for performing quarterly data accounting according to wholesale orders
Technical Field
The present invention relates to the field of electronic digital data processing, and more particularly to a data processing system for quarterly data accounting from wholesale orders.
Background
The wholesale and retail industries. The 'commodity sales amount' replaces 'social consumer product retail amount' to serve as a value quantity index for reflecting wholesale and retail industry development conditions, the problems of cross repetition and poor representativeness among social consumer product retail amount index industries are solved, and the quality of accounting data is improved. The quarterly GDP is consistent with the annual GDP in the basic concept and caliber range. Compared with the annual GDP, the source and the calculation method of the quarterly GDP accounting data are different, and the quarterly GDP accounting data is far inferior to the annual GDP accounting data, so that the quarterly GDP accounting data depends on related indexes for calculation.
When quarterly data accounting is carried out, various forms such as the number and the type of wholesale orders are generally adopted, but the wholesale orders are various in types, and are easily influenced by external data information due to different types, so that the accuracy of a data core is difficult to improve when quarterly data accounting is carried out.
Disclosure of Invention
Aiming at the technical defects, the invention discloses a data processing system for performing seasonal data accounting according to wholesale orders, which adopts a classification algorithm of an improved clustering analysis algorithm model module to realize classification and calculation of data information of different orders, and manages and calculates the wholesale order data information according to wholesale batches, seasons, quantities, amounts, styles or cargo types and the data information through a correlation analysis module so as to realize output of the seasonal data accounting and greatly improve the data accounting capability.
In order to achieve the technical effects, the invention adopts the following technical scheme:
a data processing system for quarterly data accounting according to wholesale orders, comprising:
the wholesale order information module is used for providing order data information which at least comprises wholesale batches, seasons, quantities, money amounts, styles or cargo types;
a classification calculation module; the classification calculation module is an improved clustering analysis algorithm model module, and the improved clustering analysis algorithm model module comprises an input module, a data processing module, a classification judgment module, a classification identification module and an output module, wherein the output end of the input module is connected with the input end of the data processing module, the output end of the data processing module is connected with the input end of the classification judgment module, the output end of the classification judgment module is connected with the input end of the classification identification module, and the output end of the classification identification module is connected with the input end of the output module; the data processing module is a big data dimension reduction processing module for converting complex data information into simple data information, the classification judging module is a module for performing classification judgment based on the similarity of wholesale order data information, and the classification identification module is used for realizing wholesale order data information identification based on a similarity threshold value;
a correlation analysis module; the system is used for managing and calculating wholesale order data information according to wholesale batch, season, quantity, amount, style or cargo type and data information to realize quarterly data accounting output, the correlation analysis module comprises a correlation interface module, a matrix scale measurement module, a first matrix construction module, a second matrix construction module and a calculation output module, wherein the matrix scale module is used for constructing a data model by respectively constructing the wholesale order data information according to the wholesale batch, season, quantity, amount, style or cargo type and quarterly data accounting data information in a matrix mode, the matrix scale measurement module is used for measuring the data information constructed by the matrix scale module, the first matrix construction module is used for constructing the order data information, and the second matrix construction module is used for constructing the quarterly data accounting data information influencing the order data information, the correlation calculation module is used for correlating data information constructed by a first matrix construction module with data information constructed by a second matrix construction module, wherein the output end of the correlation interface module is connected with the input end of the matrix scale module, the output end of the matrix scale module is respectively connected with the input ends of the first matrix construction module and the second matrix construction module, the output ends of the first matrix construction module and the second matrix construction module are connected with the input end of the correlation calculation module, the output end of the correlation calculation module is connected with the input end of the calculation output module, and the output end of the matrix scale measurement module is connected with the input end of the matrix scale module;
a main control module; the main control module is used for controlling different modules to be in working states based on an STC12C4A60S single chip microcomputer,
a multi-channel delivery module; the system is used for realizing the interaction of different channels of wholesale order data information so as to synchronously realize the synchronous operation of various data channels and improve the data information interaction capacity; the multi-channel transmission module at least comprises an RS232 communication channel interface, an RS485 communication channel interface, a carrier communication channel interface, a TCP/IP communication channel interface, an RS422 communication channel interface, an Ethernet communication channel interface, a CAN communication channel interface, a USB communication channel interface, a WIFI communication channel interface, a ZigBee communication channel interface, a Bluetooth communication channel interface or an optical fiber communication channel interface; the multi-channel transmission module comprises a channel control module, a channel interface connected with the channel control module, a channel protocol module, a route optimization module and a channel output module; wherein the route optimization module is an AD HOC network-based module;
an upper management module; the data information receiving module is used for receiving the data information transmitted by the multi-channel transmission module so as to realize the receiving, application and analysis of the data information which is managed according to wholesale batches, seasons, quantities, money amounts, styles or goods types and the data information;
the main control module is respectively connected with the classification calculation module, the multi-channel transmission module, the association analysis module and the wholesale order information module, the output end of the classification calculation module is connected with the input end of the association analysis module, and the output end of the multi-channel transmission module is connected with the input end of the upper management module.
As a further technical scheme of the invention, the method for realizing classification by the classification calculation module comprises the following steps:
step one, inputting data information, and converting complex data information into a big data dimension reduction processing module of simple data information through the data processing module;
inputting n goods wholesale order multidimensional data sample sets as { x1，x2，…xnIn which x1，x2，…xnThe information data set of wholesale order goods randomly selects N condensation points from the set, and the composition set of the condensation points is
｛z1，z2，…zN｝；z1，z2，…zNRespectively representing wholesale batches, seasons, quantities, amounts, styles or types of goods; then, realizing the dimensionality reduction processing of the data information in a low variance filtering mode;
step two, classifying and judging the wholesale order data information similarity through the classification judging module;
calculating the distance between any goods wholesale order multi-dimensional data sample point and a condensation point:
Figure 675522DEST_PATH_IMAGE001
（1）
the formula (1) represents data information for describing a certain wholesale order
Figure 284358DEST_PATH_IMAGE002
And setting condensation points
Figure 129954DEST_PATH_IMAGE003
The shortest distance between, let w benIn the presence of NmMultidimensional data sample and setting of wholesale order of each goods
Figure 140636DEST_PATH_IMAGE004
A threshold value of (d);
thirdly, identifying the wholesale order data information by applying a similarity threshold through the classification identification module;
by means of a correlation function
Figure 311854DEST_PATH_IMAGE005
The sum gives the condensation point zNIs expressed as
Figure 407986DEST_PATH_IMAGE006
（2）
In formula (2)
Figure 290229DEST_PATH_IMAGE005
And the correlation function is represented, and the correlation expression of the data information of the wholesale order is represented and recorded as:
Figure 155417DEST_PATH_IMAGE007
（3）
in the formula (3)
Figure 497537DEST_PATH_IMAGE008
Expressed as an expression of a random matrix X,
Figure 80965DEST_PATH_IMAGE009
an information matrix representing the wholesale order of the goods,
Figure 268363DEST_PATH_IMAGE010
a data information matrix for expressing the quarterly data accounting of the information affecting the goods wholesale order;Mrepresenting D in the correlation function1The lateral dimensions of the matrix are such that,Nrepresenting D in the correlation function2Transverse dimension of the matrix, T denotes D1And D2The longitudinal dimension of (a);
suppose x and
Figure 253637DEST_PATH_IMAGE003
the maximum distance between is Y:
Figure 235500DEST_PATH_IMAGE011
（4）
by using
Figure 306224DEST_PATH_IMAGE012
Represents the classification distance if
Figure 61428DEST_PATH_IMAGE002
And
Figure 901208DEST_PATH_IMAGE003
the maximum distance between is greater than the classification distance, indicating wmThe points are not suitable as condensation points, so that the points are divided into two condensation points in the clustering interval, and the two condensation points are expressed by the following formula:
Figure 319551DEST_PATH_IMAGE013
（5）
in the formula (5)
Figure 611992DEST_PATH_IMAGE014
For describing constants greater than 0, if
Figure 406773DEST_PATH_IMAGE002
And
Figure 101059DEST_PATH_IMAGE003
the maximum distance between is less than the classification distance, wmThe dots are suitable as condensation points if
Figure 690303DEST_PATH_IMAGE002
And
Figure 735620DEST_PATH_IMAGE003
the maximum distance between is not less than the classification distance, indicates wmIf the points are not suitable as condensation points, returning to the step (2) for iterative calculation; up to
Figure 301468DEST_PATH_IMAGE002
And
Figure 850261DEST_PATH_IMAGE003
until the maximum distance between them is less than the classification distance;
step four, outputting the data information classified by the classification calculation module;
when in use
Figure 938303DEST_PATH_IMAGE015
And
Figure 408598DEST_PATH_IMAGE003
when the minimum distance therebetween is L, the expression for L is:
Figure 607499DEST_PATH_IMAGE016
（6）
by using
Figure 948481DEST_PATH_IMAGE017
Representing the merging distance, if the minimum distance L is less than the merging distance, the classification result wmAnd wnHave similarity therebetween, then
Figure 207424DEST_PATH_IMAGE018
Dot sum
Figure 899437DEST_PATH_IMAGE003
Point of agglomeration of dots
Figure 636449DEST_PATH_IMAGE019
Taking as follows:
Figure 159834DEST_PATH_IMAGE020
（7）
and (4) if the minimum distance L is larger than the merging distance, re-performing the step (4).
As a further technical scheme of the invention, the method for realizing the accounting correlation output of the wholesale order data information and the quarterly data through the correlation analysis module comprises the following steps:
step 1, receiving data information output by a classification calculation module through an associated interface module;
step 2, establishing wholesale order data information through a matrix scale module;
step 3, measuring matrix information of the matrix scale module through the matrix scale measuring module;
step 4, constructing order data information through a first matrix construction module, and constructing quarterly data accounting data information influencing the order data information through a second matrix construction module;
step 5, outputting a correlation function through a correlation calculation module to perform data information correlation on the order data information constructed by the first matrix construction module and the order data information with the influence constructed by the second matrix construction module,
in the context of the constructed relevance function,
Figure 25896DEST_PATH_IMAGE021
wherein:
Figure 1943DEST_PATH_IMAGE023
（8）
in the formula (8), the reaction mixture is,
Figure 480329DEST_PATH_IMAGE024
in (1)
Figure 123800DEST_PATH_IMAGE025
The method comprises the steps of representing the Tth price in the Mth category in goods wholesale order information, wherein T represents the data number of the goods wholesale order information;
Figure 396649DEST_PATH_IMAGE027
（9）
Figure 125571DEST_PATH_IMAGE010
in
Figure 204385DEST_PATH_IMAGE028
RepresentFactors influencing cargo wholesale order information to carry out seasonal data accounting, wherein N represents a Tth data parameter in an Mth category of seasonal data accounting influencing factors;
step 6, outputting a data calculation result through a calculation output module when
Figure 640046DEST_PATH_IMAGE029
When the value is less than 0, the factors influencing the wholesale order information of the goods are ignored; when in use
Figure 146113DEST_PATH_IMAGE030
When the number is between 0 and 1, the information factor influencing the goods wholesale order exists; when in use
Figure 798549DEST_PATH_IMAGE005
When the number is more than 1, the information factors influencing the goods wholesale order are more.
Positive and advantageous effects
The invention realizes the classification and calculation of different order data information by adopting the classification algorithm of the improved clustering analysis algorithm model module, and manages and calculates the wholesale order data information according to wholesale batches, seasons, quantities, amounts, styles or goods types and the data information by the association analysis module so as to realize seasonal data accounting output and greatly improve the data accounting capability. When data interaction is carried out, a multi-channel transmission module is also adopted; the system is used for realizing interaction of different channels of wholesale order data information so as to synchronously realize synchronous operation of various data channels and improve data information interaction capacity; the multi-channel transmission module at least comprises an RS232 communication channel interface, an RS485 communication channel interface, a carrier communication channel interface, a TCP/IP communication channel interface, an RS422 communication channel interface, an Ethernet communication channel interface, a CAN communication channel interface, a USB communication channel interface, a WIFI communication channel interface, a ZigBee communication channel interface, a Bluetooth communication channel interface or an optical fiber communication channel interface; the multi-channel transmission module comprises a channel control module, a channel interface connected with the channel control module, a channel protocol module, a route optimization module and a channel output module; wherein the route optimization module is an AD HOC network-based module; the data interaction capability is improved.
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, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without inventive exercise, wherein:
FIG. 1 is a system architecture diagram of the present invention;
FIG. 2 is a schematic diagram of a classification calculation module according to the present invention;
FIG. 3 is a schematic structural diagram of an association analysis module according to the present invention;
FIG. 4 is a schematic structural diagram of a multi-channel delivery module according to the present invention;
FIG. 5 is a diagram of an embodiment of the multi-channel delivery module optimizing channels according to the present invention;
FIG. 6 is a schematic diagram of a method of operation of the system of the present invention;
FIG. 7 is a flow chart illustrating a matrix association method according to the present invention;
FIG. 8 is a schematic diagram of an embodiment of a matrix association method according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, and it should be understood that the embodiments described herein are merely for the purpose of illustrating and explaining the present invention and are not intended to limit the present invention.
As shown in fig. 1, a data processing system for quarterly data accounting according to a wholesale order, includes:
the wholesale order information module is used for providing order data information which at least comprises wholesale batches, seasons, quantities, money amounts, styles or cargo types;
a classification calculation module; the classification calculation module is an improved clustering analysis algorithm model module, and the improved clustering analysis algorithm model module comprises an input module, a data processing module, a classification judgment module, a classification identification module and an output module, wherein the output end of the input module is connected with the input end of the data processing module, the output end of the data processing module is connected with the input end of the classification judgment module, the output end of the classification judgment module is connected with the input end of the classification identification module, and the output end of the classification identification module is connected with the input end of the output module; the data processing module is a big data dimension reduction processing module for converting complex data information into simple data information, the classification judging module is a module for performing classification judgment based on the similarity of wholesale order data information, and the classification identification module is used for realizing wholesale order data information identification based on a similarity threshold value;
a correlation analysis module; the system is used for managing and calculating wholesale order data information according to wholesale batch, season, quantity, amount, style or cargo type and data information to realize quarterly data accounting output, the correlation analysis module comprises a correlation interface module, a matrix scale measurement module, a first matrix construction module, a second matrix construction module and a calculation output module, wherein the matrix scale module is used for constructing a data model by respectively constructing the wholesale order data information according to the wholesale batch, season, quantity, amount, style or cargo type and quarterly data accounting data information in a matrix mode, the matrix scale measurement module is used for measuring the data information constructed by the matrix scale module, the first matrix construction module is used for constructing the order data information, and the second matrix construction module is used for constructing the quarterly data accounting data information influencing the order data information, the correlation calculation module is used for correlating data information constructed by a first matrix construction module with data information constructed by a second matrix construction module, wherein the output end of the correlation interface module is connected with the input end of the matrix scale module, the output end of the matrix scale module is respectively connected with the input ends of the first matrix construction module and the second matrix construction module, the output ends of the first matrix construction module and the second matrix construction module are connected with the input end of the correlation calculation module, the output end of the correlation calculation module is connected with the input end of the calculation output module, and the output end of the matrix scale measurement module is connected with the input end of the matrix scale module;
a main control module; the main control module is used for controlling different modules to be in working states based on an STC12C4A60S single chip microcomputer,
in the embodiment, a dual-control mode of ARM + DSP technology can be adopted, the operation state of the invention is controlled by an STC12C4A60S single chip microcomputer, the main control chip is completed by an STM32 controller, and structurally, data information transmission is realized by connecting a ZigBee coordination module and a WIFI communication module, wherein the STM32 controller is also provided with a cortex-M3 CPU based on ARM32 bits, and the module realizes calculation and application of the data information of the invention. In a specific design, a DMA controller with 12 channels, a D/A converter with 16 channels and a D/A converter with 12 bits and 3 types are arranged on the controller. Can realize the fast switch who detects data through this kind of mode, in addition, ARM Cortex application processor still adopts 16/32 RISC microprocessing, still is provided with SDIO interface, SD card interface, serial ports, net gape, USB interface etc. at the data interface department of this module, sets up through this kind of mode, can realize the interaction of multiple different communication mode. In order to improve the data calculation capacity, the system is also provided with a DSP processing module, the processing module is provided with an expansion circuit, an A/D conversion module, a display module, a D/A conversion module and the like, the DSP module is used as a calculation adapter in a hardware framework, when an ARM controller works, the high-precision calculation of data information input is realized, and the rapid calculation and processing of the system can be realized through the design of the DSP module.
A multi-channel delivery module; the system is used for realizing the interaction of different channels of wholesale order data information so as to synchronously realize the synchronous operation of various data channels and improve the data information interaction capacity; the multi-channel transmission module at least comprises an RS232 communication channel interface, an RS485 communication channel interface, a carrier communication channel interface, a TCP/IP communication channel interface, an RS422 communication channel interface, an Ethernet communication channel interface, a CAN communication channel interface, a USB communication channel interface, a WIFI communication channel interface, a ZigBee communication channel interface, a Bluetooth communication channel interface or an optical fiber communication channel interface; the multi-channel transmission module comprises a channel control module, a channel interface connected with the channel control module, a channel protocol module, a route optimization module and a channel output module; wherein the route optimization module is an AD HOC network-based module;
and applying an AODV (Ad HOC On-Demand Distance Vector Routing) Routing protocol, considering the attribute and the Routing metric of the data packet in the Routing of the AD HOC network, and determining the shortest transmission path for the source node of the wireless network by using the Routing protocol through forwarding a Routing request and Routing response. In order to improve the service quality of a wireless network, the research uses a cross-layer optimization technology to enable different functional modules in the AD HOC network to be in information intercommunication and interconnection with other modules, so that the network information redundancy is reduced, and a port is newly established to enable non-adjacent modules in the network to be in interaction. In specific application, a multi-parameter composite routing protocol can be provided, and the communication capacity of the wireless network is improved. The multi-parameters comprise energy, load and node quality of the network node, wherein the energy mainly refers to initial energy of the node, minimum used energy of the node and current energy, the load mainly refers to the size and use condition of a transmission buffer area, and the node quality comprises the speed and distance of the mobile node. In order to prolong the service time of the wireless AD HOC network, the network nodes need to save energy when in use, and the network nodes are responsible for forwarding data for other nodes and participating in other routing control. Energy-saving strategies are coordinated into each level in the network, and the nodes are managed based on balanced energy consumption, so that the situation that the scale of the wireless network is reduced due to the fact that the nodes with lower energy are used is avoided.
An upper management module; the system comprises a multi-channel transmission module, a data information receiving module, a data information analyzing module and a data information analyzing module, wherein the data information is used for receiving data information transmitted by the multi-channel transmission module so as to realize the receiving, application and analysis of the data information managed according to wholesale batches, seasons, quantities, money amounts, styles or cargo types and the data information;
the main control module is respectively connected with the classification calculation module, the multi-channel transmission module, the association analysis module and the wholesale order information module, the output end of the classification calculation module is connected with the input end of the association analysis module, and the output end of the multi-channel transmission module is connected with the input end of the upper management module.
In the above embodiment, the method for implementing classification by the classification calculation module includes the following steps:
step one, inputting data information, and converting complex data information into a big data dimension reduction processing module of simple data information through the data processing module;
inputting n goods wholesale order multidimensional data sample sets as { x1，x2，…xnIn which x1，x2，…xnThe information data set of wholesale order goods randomly selects N condensation points from the set, and the combination set of the condensation points is
｛z1，z2，…zN｝；z1，z2，…zNRespectively representing wholesale batches, seasons, quantities, amounts, styles or types of goods; then, realizing data information dimensionality reduction processing in a low variance filtering mode;
in a specific embodiment, the data column is deleted when the variance is too small (below a predetermined threshold), i.e., when the data in the data column varies little, much like the ratio of missing values. Of particular note are: the variance is range dependent, so the data is regularized before the method is applied. In other embodiments, a proportional approach to missing values may also be employed.
Step two, classifying and judging the wholesale order data information similarity through the classification judging module;
calculating the distance between any goods wholesale order multi-dimensional data sample point and a condensation point:
Figure 681055DEST_PATH_IMAGE031
（1）
formula (1) representsFor describing data information of a certain wholesale order
Figure 971222DEST_PATH_IMAGE002
And setting condensation points
Figure 913770DEST_PATH_IMAGE003
The shortest distance between, let w benIn the presence of NmMultidimensional data sample and setting of wholesale orders of individual goods
Figure 289388DEST_PATH_IMAGE004
A threshold value of (d);
when the threshold is set, the threshold may be set according to the accounting scale, for example, when there are many wholesale orders, the threshold may be set to be larger to match with the actual analysis. When there are fewer wholesale orders, a bit smaller may be set.
Thirdly, identifying the wholesale order data information by applying a similarity threshold through the classification identification module;
the condensation point is obtained by the summation of the correlation functions D (L)
Figure 710005DEST_PATH_IMAGE003
Is expressed as
Figure 182574DEST_PATH_IMAGE032
（2）
In formula (2)
Figure 968128DEST_PATH_IMAGE029
And the correlation function is represented, and the correlation expression of the data information of the wholesale order is represented and recorded as:
Figure 893358DEST_PATH_IMAGE033
（3）
in the formula (3)
Figure 553885DEST_PATH_IMAGE034
Expressed as an expression of a random matrix X,
Figure 880961DEST_PATH_IMAGE009
an information matrix representing the wholesale orders for the goods,
Figure 102995DEST_PATH_IMAGE010
a data information matrix for expressing information affecting the goods wholesale order to carry out seasonal data accounting;Mrepresenting D in the correlation function1The lateral dimensions of the matrix are such that,Nrepresenting D in the correlation function2Transverse dimension of the matrix, T denotes D1And D2The longitudinal dimension of (a);
suppose that
Figure 515521DEST_PATH_IMAGE002
And
Figure 215624DEST_PATH_IMAGE003
the maximum distance between is Y:
Figure 397207DEST_PATH_IMAGE035
（4）
by using
Figure 790142DEST_PATH_IMAGE012
Represents the classification distance if
Figure 689965DEST_PATH_IMAGE002
And
Figure 256075DEST_PATH_IMAGE003
the maximum distance between is greater than the classification distance, indicating wmThe points are not suitable as condensation points, so that the points are divided into two condensation points in the clustering interval, and the two condensation points are expressed by the following formula:
Figure 728383DEST_PATH_IMAGE036
（5）
in the formula (5)
Figure 354536DEST_PATH_IMAGE014
For describing constants greater than 0, if
Figure 679338DEST_PATH_IMAGE002
And
Figure 783561DEST_PATH_IMAGE003
the maximum distance between is less than the classification distance, indicates wmThe dots are suitable as condensation points if
Figure 877418DEST_PATH_IMAGE002
And
Figure 674473DEST_PATH_IMAGE003
the maximum distance between is not less than the classification distance, indicates wmIf the points are not suitable as condensation points, returning to the step (2) for iterative calculation; up to x and
Figure 220992DEST_PATH_IMAGE003
until the maximum distance between them is less than the classification distance;
step four, outputting the data information classified by the classification calculation module;
when the temperature is higher than the set temperature
Figure 394485DEST_PATH_IMAGE015
And
Figure 841384DEST_PATH_IMAGE003
with the minimum distance between is L, the expression for L is:
Figure 809340DEST_PATH_IMAGE037
（6）
by using
Figure 843155DEST_PATH_IMAGE017
Representing the merging distance, if the minimum distance L is less than the merging distance, the classification result wmAnd wnHave similarity therebetween, then
Figure 289180DEST_PATH_IMAGE015
Dot sum
Figure 357630DEST_PATH_IMAGE003
Condensation point of dots
Figure 496487DEST_PATH_IMAGE019
Note as:
Figure 79916DEST_PATH_IMAGE038
（7）
and (4) if the minimum distance L is larger than the merging distance, re-performing the step (4).
In summary, the order data information can be effectively processed by the method.
In the above embodiment, the method for implementing the wholesale order data information and quarterly data accounting correlation output through the correlation analysis module includes:
step 1, receiving data information output by a classification calculation module through an associated interface module;
step 2, establishing wholesale order data information through a matrix scale module;
step 3, measuring matrix information of the matrix scale module through the matrix scale measuring module;
step 4, constructing order data information through a first matrix construction module, and constructing quarterly data accounting data information influencing the order data information through a second matrix construction module;
step 5, outputting a correlation function through a correlation calculation module to perform data information correlation on the order data information constructed by the first matrix construction module and the order data information with the influence constructed by the second matrix construction module,
in the context of the constructed relevance function,
Figure 267314DEST_PATH_IMAGE039
wherein:
Figure 252588DEST_PATH_IMAGE041
（8）
in the formula (8), the reaction mixture is,
Figure 22002DEST_PATH_IMAGE042
in (1)
Figure 92727DEST_PATH_IMAGE025
The price T in the Mth category in the goods wholesale order information is represented, and the T represents the data number of the goods wholesale order information;
Figure 83816DEST_PATH_IMAGE044
（9）
Figure 923596DEST_PATH_IMAGE045
in (1)
Figure 341939DEST_PATH_IMAGE046
Expressing factors influencing cargo wholesale order information to carry out seasonal data accounting, wherein N expresses a Tth data parameter in an Mth category of seasonal data accounting influencing factors;
by constructing the matrix construction, the goods wholesale order information { P1, P2, P3 … … PM } and the quarterly data accounting influence factor data set { Q1, Q2, Q3 … … QN } can be linked, and the specific influence quantity can be calculated through the matrix calculation.
Step 6, outputting a data calculation result through a calculation output module when
Figure 634380DEST_PATH_IMAGE005
When the value is less than 0, the factors influencing the wholesale order information of the goods are ignored; when in use
Figure 491478DEST_PATH_IMAGE047
When the number is between 0 and 1, the information factor influencing the goods wholesale order exists;when in use
Figure 123448DEST_PATH_IMAGE029
When the number is more than 1, the information factors influencing the goods wholesale order are more.
In one embodiment, it is assumed that the data information of the wholesale orders of 1-12 months is extracted from certain database information, and the order types are clothes, daily necessities, electric appliances, furniture, drinks, snacks, staple foods, semi-finished products, cleaning supplies, teaching supplies, office supplies and meat respectively, and this way is only a specific implementation way and is not limited to all goods order types, and this way only extracts part of the information.
Data samples are reported in table 1.
TABLE 1 sample data record Table
Figure 775009DEST_PATH_IMAGE049
By substituting the data information of Table 1 into equation (3), then
Figure 256543DEST_PATH_IMAGE051
Converting into:
Figure 651753DEST_PATH_IMAGE053
at the same time will
Figure 138229DEST_PATH_IMAGE055
Converting into:
Figure 226271DEST_PATH_IMAGE057
(ii) a Then by formula (3)
Figure 430987DEST_PATH_IMAGE058
Performing data calculation, calculating
Figure 364308DEST_PATH_IMAGE059
Is evaluated according to the above criteria, and will be calculated in month 1, when
Figure 970870DEST_PATH_IMAGE047
Less than 0 indicates that the clothing is not subject to a large seasonal factor and may occur in the south, for example, in spring in four seasons of the year in Yunnan. Such as when the 3 months of the week are counted,
Figure 229813DEST_PATH_IMAGE047
when the value is between 0 and 1, the influence of the use occasion of the electric appliance is shown, for example, the power consumption is different in office and household occasions, and the influence is easily caused when the data information is checked when the electric appliance is applied due to the different use occasions. For example, in the month of 11 when
Figure 718563DEST_PATH_IMAGE047
When the number of the articles is more than 1, the office articles are greatly influenced by the office field, the office occasions are different, and the articles consumed by the office articles are different, so that through the embodiment, the method and the device can intuitively express that different wholesale orders are influenced by external influence factors, and further influence the data accounting result.
Although specific embodiments of the invention have been described herein, it will be understood by those skilled in the art that these embodiments are merely illustrative and that various omissions, substitutions and changes in the form and details of the methods and systems described may be made by those skilled in the art without departing from the spirit and scope of the invention. For example, it is within the scope of the present invention to combine the steps of the above-described methods to perform substantially the same function in substantially the same way to achieve substantially the same result. Accordingly, the scope of the invention is to be limited only by the following claims.

Claims (4)

1. A data processing system for quarterly data accounting according to wholesale orders, characterized by: the method comprises the following steps:
the wholesale order information module is used for providing order data information at least comprising wholesale batches, seasons, quantities, money amounts, styles or goods types;
a classification calculation module; the system is used for classifying the wholesale order data information according to wholesale batches, seasons, quantities, amounts, styles or cargo types;
the classification calculation module is an improved clustering analysis algorithm model module, the improved clustering analysis algorithm model module comprises an input module, a data processing module, a classification judgment module, a classification identification module and an output module, wherein the output end of the input module is connected with the input end of the data processing module, the output end of the data processing module is connected with the input end of the classification judgment module, the output end of the classification judgment module is connected with the input end of the classification identification module, and the output end of the classification identification module is connected with the input end of the output module; the data processing module is a big data dimension reduction processing module which converts complex data information into simple data information, the classification judging module is a module which performs classification judgment based on the similarity of wholesale order data information, and the classification identifying module is a module which realizes wholesale order data information identification based on a similarity threshold; a correlation analysis module; is used for managing and calculating the wholesale order data information according to wholesale batches, seasons, quantities, amounts, styles or goods types and the data information so as to realize seasonal data accounting output,
a main control module; used for controlling different modules to be in working states, the main control module is a singlechip which is based on STC12C4A60S and is used for controlling different modules to be in working states,
a multi-channel delivery module; the system is used for realizing the interaction of different channels of wholesale order data information so as to synchronously realize the synchronous operation of various data channels and improve the data information interaction capacity;
an upper management module; the system comprises a multi-channel transmission module, a data information receiving module, a data information analyzing module and a data information analyzing module, wherein the data information is used for receiving data information transmitted by the multi-channel transmission module so as to realize the receiving, application and analysis of the data information managed according to wholesale batches, seasons, quantities, money amounts, styles or cargo types and the data information;
the main control module is respectively connected with the classification calculation module, the multi-channel transmission module, the association analysis module and the wholesale order information module, the output end of the classification calculation module is connected with the input end of the association analysis module, and the output end of the multi-channel transmission module is connected with the input end of the upper management module;
the correlation analysis module comprises a correlation interface module, a matrix scale measuring module, a first matrix construction module, a second matrix construction module, a correlation calculation module and a calculation output module, wherein the matrix scale module is used for constructing a data model by matrix the wholesale order data information according to wholesale batch, season, quantity, amount, style or cargo type and quarter data accounting data information, the matrix scale measuring module is used for measuring the data information constructed by the matrix scale module, the first matrix construction module is used for constructing the order data information, the second matrix construction module is used for constructing the quarter data accounting data information influencing the order data information, the correlation calculation module is used for correlating the data information constructed by the first matrix construction module with the data information constructed by the second matrix construction module, and the output end of the correlation interface module is connected with the input end of the matrix scale module, the output end of the matrix scale module is respectively connected with the input ends of the first matrix building module and the second matrix building module, the output ends of the first matrix building module and the second matrix building module are connected with the input end of the correlation calculation module, the output end of the correlation calculation module is connected with the input end of the calculation output module, and the output end of the matrix scale measurement module is connected with the input end of the matrix scale module.
2. The data processing system for quarterly data accounting according to a wholesale order of claim 1, wherein: the multi-channel transmission module at least comprises an RS232 communication channel interface, an RS485 communication channel interface, a carrier communication channel interface, a TCP/IP communication channel interface, an RS422 communication channel interface, an Ethernet communication channel interface, a CAN communication channel interface, a USB communication channel interface, a WIFI communication channel interface, a ZigBee communication channel interface, a Bluetooth communication channel interface or an optical fiber communication channel interface; the multi-channel transmission module comprises a channel control module, a channel interface connected with the channel control module, a channel protocol module, a route optimization module and a channel output module; wherein the route optimization module is an AD HOC network based module.
3. The data processing system for quarterly data accounting according to a wholesale order of claim 1, wherein: the method for realizing classification by the classification calculation module comprises the following steps:
step one, inputting data information, and converting complex data information into a big data dimension reduction processing module of simple data information through the data processing module;
inputting n goods wholesale order multidimensional data sample sets as { x1，x2，…xnIn which x is1，x2，…xnThe information data set of wholesale order goods randomly selects N condensation points from the set, and the composition set of the condensation points is
｛z1，z2，…zN｝；z1，z2，…zNRespectively representing wholesale batches, seasons, quantities, amounts, styles or types of goods; then, realizing the dimensionality reduction processing of the data information in a low variance filtering mode;
step two, classifying and judging the wholesale order data information similarity through the classification judging module;
calculating the distance between any goods wholesale order multi-dimensional data sample point and a condensation point:
Figure 939907DEST_PATH_IMAGE001
（1）
equation (1) represents data information x for describing a certain wholesale order and setting a condensation point
Figure 60310DEST_PATH_IMAGE002
The shortest distance between, let w benIn the presence of NmMultidimensional data sample and setting of wholesale order of each goods
Figure 308889DEST_PATH_IMAGE003
A threshold value of (d);
thirdly, identifying the wholesale order data information by applying a similarity threshold through the classification identification module;
the condensation point is obtained by the summation of the correlation functions D (L)
Figure 172940DEST_PATH_IMAGE004
Is expressed as
Figure 456153DEST_PATH_IMAGE005
（2）
In formula (2)
Figure 980413DEST_PATH_IMAGE006
And the correlation expression which represents the correlation function and represents the data information of the wholesale order is recorded as:
Figure 981867DEST_PATH_IMAGE007
（3）
in the formula (3)
Figure 649609DEST_PATH_IMAGE008
Expressed as an expression of a random matrix X,
Figure 521750DEST_PATH_IMAGE009
an information matrix representing the wholesale order of the goods,
Figure 983956DEST_PATH_IMAGE010
a data information matrix for expressing information affecting the goods wholesale order to carry out seasonal data accounting; Min the representation of the correlation function
Figure 207126DEST_PATH_IMAGE011
The lateral dimension of the matrix is such that,Nin expressing the correlation function
Figure 412980DEST_PATH_IMAGE012
The lateral dimension of the matrix is such that,t represents D1And D2The longitudinal dimension of (a);
suppose x and
Figure 405207DEST_PATH_IMAGE004
the maximum distance between is Y:
Figure 536848DEST_PATH_IMAGE013
（4）
by d1Represents the classification distance if x and
Figure 247315DEST_PATH_IMAGE002
the maximum distance between is greater than the classification distance, indicating wmThe points are not suitable as condensation points, so that the points are divided into two condensation points in the clustering interval, and the two condensation points are expressed by the following formula:
Figure 991281DEST_PATH_IMAGE014
（5）
in the formula (5)
Figure 103593DEST_PATH_IMAGE015
For describing constants greater than 0, if x and
Figure 642022DEST_PATH_IMAGE002
the maximum distance between is less than the classification distance, wmThe points are suitable as condensation points if x and
Figure 839785DEST_PATH_IMAGE002
the maximum distance between is not less than the classification distance, indicates wmIf the points are not suitable as condensation points, returning to the step (2) for iterative calculation; up to x and
Figure 387441DEST_PATH_IMAGE002
the maximum distance therebetween is smaller than the classification distanceUntil the mixture is separated;
step four, outputting the data information classified by the classification calculation module;
when z ismAnd
Figure 852795DEST_PATH_IMAGE002
with the minimum distance between is L, the expression for L is:
Figure 827704DEST_PATH_IMAGE016
（6）
by d2Representing the merging distance, if the minimum distance L is less than the merging distance, the classification result wmAnd wnHave similarity between them, then zmDot sum
Figure 247184DEST_PATH_IMAGE002
Point of coagulation zmnNote as:
Figure 332952DEST_PATH_IMAGE017
（7）
and (4) if the minimum distance L is larger than the merging distance, re-performing the step (4).
4. The data processing system for quarterly data accounting according to a wholesale order of claim 1, wherein: the method for realizing the accounting correlation output of the wholesale order data information and the quarterly data through the correlation analysis module comprises the following steps:
step 1, receiving data information output by a classification calculation module through an associated interface module;
step 2, establishing wholesale order data information through a matrix scale module;
step 3, measuring matrix information of the matrix scale module through the matrix scale measuring module;
step 4, constructing order data information through a first matrix construction module, and constructing seasonal data accounting data information influencing the order data information through a second matrix construction module;
step 5, outputting a correlation function through a correlation calculation module to perform data information correlation on the order data information constructed by the first matrix construction module and the order data information influenced by the order data information constructed by the second matrix construction module,
in the context of the constructed relevance function,
Figure 154278DEST_PATH_IMAGE018
wherein:
Figure 565667DEST_PATH_IMAGE019
（8）
in the formula (8), D1In (1)
Figure 472443DEST_PATH_IMAGE020
The price T in the Mth category in the goods wholesale order information is represented, and the T represents the data number of the goods wholesale order information;
Figure 594858DEST_PATH_IMAGE021
（9）
D2in (1)
Figure 536269DEST_PATH_IMAGE022
Expressing factors influencing cargo wholesale order information to carry out seasonal data accounting, wherein N expresses a Tth data parameter in an Mth category of seasonal data accounting influencing factors;
step 6, outputting a data calculation result through a calculation output module when
Figure 118560DEST_PATH_IMAGE023
When the value is less than 0, the factors influencing the wholesale order information of the goods are ignored; when in use
Figure 512632DEST_PATH_IMAGE024
When the number is between 0 and 1, the information factor influencing the goods wholesale order exists; when the temperature is higher than the set temperature
Figure 205782DEST_PATH_IMAGE025
And if the quantity is larger than 1, the information factors influencing the goods wholesale order are more.
CN202210436673.6A 2022-04-25 2022-04-25 Data processing system for performing quarterly data accounting according to wholesale orders Active CN114549090B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210436673.6A CN114549090B (en) 2022-04-25 2022-04-25 Data processing system for performing quarterly data accounting according to wholesale orders

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210436673.6A CN114549090B (en) 2022-04-25 2022-04-25 Data processing system for performing quarterly data accounting according to wholesale orders

Publications (2)

Publication Number Publication Date
CN114549090A CN114549090A (en) 2022-05-27
CN114549090B true CN114549090B (en) 2022-07-19

Family

ID=81666764

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210436673.6A Active CN114549090B (en) 2022-04-25 2022-04-25 Data processing system for performing quarterly data accounting according to wholesale orders

Country Status (1)

Country Link
CN (1) CN114549090B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1619447A (en) * 2003-07-30 2005-05-25 费舍-柔斯芒特系统股份有限公司 Process control system utilising economic models
EP2821953A1 (en) * 2013-07-01 2015-01-07 Konchitchki, Yaniv Methods and systems for forecasting economic movements
CN107123020A (en) * 2017-03-31 2017-09-01 上海银澎信息科技有限公司 Method and apparatus for the order processing of supply chain
CN109559215A (en) * 2018-10-16 2019-04-02 深圳壹账通智能科技有限公司 Business datum accounting method, device, equipment and computer readable storage medium
CN110309578A (en) * 2019-06-27 2019-10-08 郑州铁路职业技术学院 A kind of economic data fitting system and method based on computer digital animation
CN111242165A (en) * 2019-12-30 2020-06-05 北京顺达同行科技有限公司 Merchant clustering method and device, computer equipment and storage medium
CN111523011A (en) * 2020-04-16 2020-08-11 武汉有牛科技有限公司 Cold and hot wallet intelligent label system based on block chain technology distributed graph calculation engine
CN111860692A (en) * 2020-07-31 2020-10-30 国网重庆市电力公司电力科学研究院 Abnormal data detection method based on K-media in Internet of things environment
CN111949795A (en) * 2020-08-14 2020-11-17 中国工商银行股份有限公司 Work order automatic classification method and device
CN114049185A (en) * 2021-11-01 2022-02-15 金蝶智慧科技(深圳)有限公司 Cost accounting method and device, computer equipment and storage medium

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104090882B (en) * 2013-11-14 2016-06-01 深圳市腾讯计算机系统有限公司 A kind of quick clustering method of advertisement order and system, server
CA2989505A1 (en) * 2017-12-19 2018-09-17 Adam Gant A method and system for valuation of a pool of real estate assets

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1619447A (en) * 2003-07-30 2005-05-25 费舍-柔斯芒特系统股份有限公司 Process control system utilising economic models
EP2821953A1 (en) * 2013-07-01 2015-01-07 Konchitchki, Yaniv Methods and systems for forecasting economic movements
CN107123020A (en) * 2017-03-31 2017-09-01 上海银澎信息科技有限公司 Method and apparatus for the order processing of supply chain
CN109559215A (en) * 2018-10-16 2019-04-02 深圳壹账通智能科技有限公司 Business datum accounting method, device, equipment and computer readable storage medium
CN110309578A (en) * 2019-06-27 2019-10-08 郑州铁路职业技术学院 A kind of economic data fitting system and method based on computer digital animation
CN111242165A (en) * 2019-12-30 2020-06-05 北京顺达同行科技有限公司 Merchant clustering method and device, computer equipment and storage medium
CN111523011A (en) * 2020-04-16 2020-08-11 武汉有牛科技有限公司 Cold and hot wallet intelligent label system based on block chain technology distributed graph calculation engine
CN111860692A (en) * 2020-07-31 2020-10-30 国网重庆市电力公司电力科学研究院 Abnormal data detection method based on K-media in Internet of things environment
CN111949795A (en) * 2020-08-14 2020-11-17 中国工商银行股份有限公司 Work order automatic classification method and device
CN114049185A (en) * 2021-11-01 2022-02-15 金蝶智慧科技(深圳)有限公司 Cost accounting method and device, computer equipment and storage medium

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
A Map Spectrum-Based Spatiotemporal Clustering Method for GDP Variation Pattern Analysis Using Nighttime Light Images of the Wuhan Urban Agglomeration;Penglin Zhang，et al;《ISPRS Int. J. Geo-Inf.》;20171231;第6卷(第160期);1-13 *
基于聚类算法的订单分批策略研究;秦馨等;《制造业自动化》;20210122;第43卷(第1期);134-137 *
基因表达数据聚类中模糊核算法的改进;周霆等;《江南大学学报》;20060430;第5卷(第2期);162-165,170 *
大批量定制下的客户订单聚类分析;徐宣国等;《中国机械工程》;20120731;第23卷(第14期);1678-1681 *

Also Published As

Publication number Publication date
CN114549090A (en) 2022-05-27

Similar Documents

Publication Publication Date Title
CN106021337A (en) A big data analysis-based intelligent recommendation method and system
Feng et al. Relation-aware dynamic attributed graph attention network for stocks recommendation
CN109710835B (en) Heterogeneous information network recommendation method with time weight
CN111949887B (en) Article recommendation method, apparatus and computer readable storage medium
CN105184600A (en) Rule and operation-based electronic business platform price engine implementing method
Yao Optimisation of one-stop delivery scheduling in online shopping based on the physical Internet
CN115860880B (en) Personalized commodity recommendation method and system based on multi-layer heterogeneous graph convolution model
CN114462623B (en) Data analysis method, system and platform based on edge calculation
CN102043863A (en) Method for Web service clustering
CN110097302A (en) The method and apparatus for distributing order
CN207300384U (en) A kind of sorting scale with communication function
CN108628882A (en) Method and system for prejudging problem
CN113298546A (en) Sales prediction method and device, and commodity processing method and device
CN114549090B (en) Data processing system for performing quarterly data accounting according to wholesale orders
Xue et al. Intelligent mining on purchase information and recommendation system for e-commerce
CN114723535A (en) Supply chain and knowledge graph-based item recommendation method, equipment and medium
CN111461826B (en) Information pushing method and device, storage medium and electronic device
Ding et al. Edge computing for terminal query based on iot
CN107103488B (en) Cigarette consumption studying and judging method based on collaborative filtering algorithm and clustering algorithm
CN111695035B (en) Recommendation system and multi-algorithm fusion recommendation processing flow
CN104462088B (en) For the matched method of mass text
CN106021514A (en) Goods customization system based on big data processing
CN207133857U (en) Intelligent inventory management system
Wen et al. Parallel naïve Bayes regression model-based collaborative filtering recommendation algorithm and its realisation on Hadoop for big data
LU et al. “New Retail”: Innovating the Development Model of China's Fresh E-commerce

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant