CN116976955B - Global order management system and method thereof - Google Patents
Global order management system and method thereof Download PDFInfo
- Publication number
- CN116976955B CN116976955B CN202311226930.4A CN202311226930A CN116976955B CN 116976955 B CN116976955 B CN 116976955B CN 202311226930 A CN202311226930 A CN 202311226930A CN 116976955 B CN116976955 B CN 116976955B
- Authority
- CN
- China
- Prior art keywords
- commodity
- sales
- dealer
- information
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 11
- 238000012795 verification Methods 0.000 claims abstract description 24
- 238000007726 management method Methods 0.000 claims abstract description 22
- 230000035945 sensitivity Effects 0.000 claims description 38
- 238000012886 linear function Methods 0.000 claims description 28
- 238000013507 mapping Methods 0.000 claims description 28
- 238000013475 authorization Methods 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 16
- 230000001737 promoting effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000012797 qualification Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000013068 supply chain management Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (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 relates to a global order management system and a global order management method, and belongs to the technical field of internet service. The sales volume prediction method comprises an order acquisition module, an order classification module, a sales volume prediction module and an order checking module, wherein sales volume prediction results of sales promotion commodities are obtained by acquiring order information and predicting sales volume of sales promotion commodities according to a sales promotion sales volume prediction model, dealer qualification is analyzed, order volume verification results are output according to dealer qualification, reference is provided for dealer order volume, supply chain balance is favorably controlled, enterprises are helped to master dealer operation conditions through order management, and decision support is provided for dealer order verification.
Description
Technical Field
The invention belongs to the technical field of Internet service, and particularly relates to a global order management system and a global order management method.
Background
With the deep development of the internet, the level of supply chain management is continuously improved, and the demands of various large enterprises and electronic commerce platforms on order management systems are greatly increased. The order management system of each platform has huge order data, the manual interference affects the order management efficiency, the information between enterprises and dealers is opaque, the enterprises do not know the operation condition of the dealers, the dealers cannot control the order quantity, no mode exists at present, the data support can be objectively provided for the enterprises, the enterprises can grasp the operation condition of the dealers through order management, the balance of supply chains is controlled, and decision support is provided for the order verification of the dealers.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a global order management system and a global order management method, which are used for obtaining order information, predicting sales volume of sales promotion commodities according to a sales promotion sales volume prediction model to obtain a prediction result of sales promotion commodities, analyzing dealer qualification and outputting an order volume verification result according to dealer qualification, providing reference for the dealer order volume, facilitating control of supply chain balance, helping enterprises grasp dealer operation conditions through order management, and providing decision support for dealer order verification.
The aim of the invention can be achieved by the following technical scheme:
a global order management method, comprising the steps of:
s1: acquiring order information, wherein the order information comprises dealer information and order demand information;
s2: the related promotion database calculates the order demand information to obtain a mapping order, and the mapping order is classified through a normalized linear function to obtain promotion type commodities and non-promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
s3: invoking historical sales data in the sales database to train a sales volume prediction model, and processing the sales volume prediction result of the sales type commodity by sales sensitivity commodity classification and semantic similarity commodity classification to output the sales volume prediction result of the sales type commodity;
s4: verifying a sales authorization range of a dealer and dealer credit information according to the dealer information and the commodity name, and outputting order quantity verification information, wherein the dealer information comprises a dealer name and a dealer address;
s5: calculating dealer stock limit according to the dealer sales authorization range and the dealer credit information, wherein the calculation formula is as follows:d is annual demand of a dealer, s is ordering cost, c is holding cost, and an ordering quantity verification result of the ordering quantity verification information is output;
preferably, the specific implementation method of step S2 includes:
s201: obtaining the mapping order through the associated promotion database according to the commodity name;
s202: calculating the Euclidean distance of the mapping order corresponding to the normalized linear function, and extracting a maximum Euclidean distance and a minimum Euclidean distance, wherein the difference between the maximum Euclidean distance and the minimum Euclidean distance is the information distance of the corresponding normalized linear function;
s203: according to the formula:calculating the information distance adjacent to the normalized linear function to obtain an adjacent information distance, wherein Y j For the adjacent information distance d i Information distance, d, representing the ith said normalized linear function k The information distance of the kth normalized linear function is represented, i and k represent two adjacent positive integers, and D (·) is a preset calculation function;
s204: judging the adjacent information distance, when Yj is more than 0 and less than 1, the normalized linear function corresponds to the mapping order to be the sales promotion commodity, when Y j When the value is more than 1, the normalized linear function corresponds to the mapping order and is the non-promotion commodity;
preferably, the normalized linear function is:wherein g h =g h-1 +V h And g 1 =v 1 ,g h For the offset, V h H is a positive integer, Q represents a weight vector corresponding to the mapping order, Q is a preset parameter, and x is the mapping order;
preferably, the step S3 specifically includes:
the sales promotion commodities comprise non-first sales promotion commodities and first sales promotion commodities, the non-first sales promotion commodities are classified by the sales promotion sensitivity commodity classification to obtain non-first sales promotion commodity classes, and the first sales promotion commodities are classified by the semantic similarity commodity classification to obtain first sales promotion commodity classes;
inputting commodity categories into the sales promotion quantity prediction model to obtain sales promotion quantity prediction results of the sales promotion commodities, wherein the commodity categories are a set of non-first sales promotion commodities and first sales promotion commodities.
Preferably, the promotion sensitivity commodity classification specifically includes:
calculating the sales promotion sensitivity value of the non-first sales promotion commodity, wherein the calculation formula is as follows:wherein i is commodity, j is sales promotion number, and h i A total number of times r of participation in the promotional program for the non-first promotional item ij For sales, pr ij Prse as a percentage of price reduction i Is the promotion sensitivity value;
arranging the sales promotion sensitive values from small to large, and equally dividing the non-first sales promotion commodities into n parts according to the sorting result;
recording the maximum value of the promotion sensitivity values in the first n-1 non-first promotion commodities, storing a variable Zoe _D, setting the value in Zoe _D as the upper limit and the lower limit of a promotion sensitivity range corresponding to the non-first promotion commodity, wherein the n non-first promotion commodities correspond to m promotion sensitivity value fields, specifically (0, zoe_D1], (Zoe _D1, zoe _D2], (Zoe _D (n-2), zoe _D (n-1) ], (Zoe _D (n-1), +_n), and m=n;
and comparing the sales promotion sensitivity value of the non-first sales promotion commodity with the sales promotion sensitivity value field according to the sales promotion sensitivity value field to obtain the non-first sales promotion commodity.
Preferably, the semantic similarity commodity classification specifically includes:
preprocessing the commodity name of the first promoted commodity by using a Jieba word segmentation method to obtain a commodity word set;
processing the commodity word set into a vector set through word2vec, wherein the vector set is the set of the first promoted commodity;
calculating the semantic similarity between the vector set and the promoted commodity in the promoted database, wherein the calculation formula is as follows:wherein (1)>For the vector set, +.>For a set of promotional items in said promotional database, < > j->For the semantic similarity;
when the semantic similarity is greater than or equal to 0.85, the first promotion commodity is the first promotion commodity class.
Preferably, the step S4 specifically includes:
determining the sales authorization range of the dealer according to the dealer name and the dealer address, judging whether the commodity name accords with the sales authority of the dealer, if so, carrying effective identification information of dealer authorization by the commodity name, and if not, returning unauthorized commodity information;
and checking the credit information of the dealer by carrying the commodity name with the dealer authorized effective identification information, obtaining historical arrearage information of the dealer according to the dealer name, judging the total amount information and the dealer credit limit, if yes, returning the information exceeding the dealer credit limit information, and if not, outputting the order checking information.
Preferably, the step S5 specifically includes calculating a dealer stock limit, where the calculation formula is:and d is the annual demand of the dealer, s is the ordering cost, c is the holding cost, whether the commodity demand exceeds the inventory limit of the dealer is judged, if yes, the order quantity verification information is output as an invalid order, and if not, the order quantity verification information is output as a valid order.
A global order management system, comprising:
the order acquisition module is used for acquiring order information, wherein the order information comprises dealer information and order demand information;
the order classification module is used for correlating the sales promotion database to calculate the order demand information to obtain a mapping order, classifying the mapping order through a normalized linear function to obtain sales promotion type commodities and non-sales promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
the sales volume prediction module is used for calling the historical sales volume prediction model trained by the sales volume data in the sales volume database, and processing the sales volume prediction results of the sales volume type commodities through sales volume sensitivity commodity classification and semantic similarity commodity classification;
the order checking module is used for verifying the sales authorization range of the dealer and the credit information of the dealer according to the dealer information and the commodity name, outputting the order quantity checking information, and calculating the inventory limit of the dealer according to the sales authorization range of the dealer and the credit information of the dealer and outputting the order quantity checking result of the order quantity checking information.
The beneficial effects of the invention are as follows:
1. according to the invention, order demand information is calculated through the associated sales promotion database to obtain a mapping order, sales promotion type commodities and non-sales promotion type commodities are obtained through normalization linear function classification according to the mapping order, sales promotion type commodities are processed through sales promotion sensitivity commodity classification and semantic similarity commodity classification to output sales promotion type commodity sales volume prediction results, the prediction results can provide reference for sales dealer ordering volume, and loss caused by goods backlog and repeated ordering is avoided;
2. according to the invention, the dealer authorization range and the dealer credit information are verified through dealer information and commodity names, order quantity verification information is output, dealer inventory limit is calculated according to the order quantity verification information, whether commodity demand exceeds the dealer inventory limit is judged, an order quantity verification result is output, supply chain balance is controlled, supply chain incompatibility caused by malicious stock storage of the dealer is avoided, enterprises are helped to grasp dealer operation conditions through order management, and decision support is provided for dealer order verification.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
FIG. 1 is a schematic flow chart of the method of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention for achieving the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects according to the invention with reference to the attached drawings and the preferred embodiment.
Referring to fig. 1, a global order management system and method thereof includes:
s1: acquiring order information, wherein the order information comprises dealer information and order demand information;
s2: processing order demand information according to a sales promotion database through a classification function to obtain sales promotion type commodities and non-sales promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
s3: invoking historical sales data in a sales database to train a sales volume prediction model, and processing sales volume prediction results of sales type commodities of the sales type through sales sensitivity commodity classification and semantic similarity commodity classification;
s4: verifying a sales authorization range of a dealer and credit information of the dealer according to dealer information and commodity names, and outputting order quantity verification information, wherein the dealer information comprises dealer names and dealer addresses;
s5: calculating dealer stock limit according to dealer sales authorization range and dealer credit information, wherein the calculation formula is thatWherein d is the annual demand of the dealer, s is the ordering cost, c is the holding cost, and the ordering quantity verification result of the ordering quantity verification information is output.
Step S1 involves an order acquisition module, wherein order information refers to an order request submitted by a dealer, and corresponding to the generated order information, the order information comprises dealer name, dealer address, commodity name, commodity demand and total information.
Step S2 relates to an order classification module, according to a promotion database, the order demand information is processed through a classification function to obtain promotion type commodities and non-promotion type commodities, the promotion database contains historical promotion data and recent promotion data, the historical promotion data is promotion commodity sales data after the promotion is finished, the promotion commodity sales data comprises promotion commodity names, promotion commodity sales and promotion commodity discounts, and the recent promotion data is promotion commodity data in the promotion process, wherein the promotion commodity names and promotion commodity discounts are included.
Obtaining a mapping order through the associated promotion database according to the commodity name, and utilizing a formulaCalculating to obtain normalized linear function f h (x) Calculating the Euclidean distance of the normalized linear function corresponding to the mapping order, extracting the maximum Euclidean distance and the minimum Euclidean distance, wherein the difference between the maximum Euclidean distance and the minimum Euclidean distance is the information distance of the normalized linear function, and using a formula->Calculating the information distance of the adjacent normalized linear function to obtain the adjacent information distance Y j When 0 is<Y j <1, the normalized linear function corresponds to the mapping order being the promotional class commodity, when Y j >1, the normalized linear function corresponds to the mapping order being the non-promotional class commodity.
And S3, a sales volume prediction module predicts sales volume of the sales-class commodities to obtain sales volume prediction results of the sales-class commodities through a sales volume prediction model, wherein the sales volume prediction model is trained by historical sales data in a sales database. The sales promotion commodities comprise non-first sales promotion commodities and first sales promotion commodities, the non-first sales promotion commodities are classified by sales promotion sensitivity commodity classification to obtain non-first sales promotion commodity classes, and the first sales promotion commodities are classified by semantic similarity commodity classification to obtain first sales promotion commodity classes.
Calculating sales promotion sensitivity values of non-first sales promotion commodities by using the formula:obtaining sales promotion sensitivity value Prse of non-first sales promotion commodity i Arranging promotion sensitivity values from small to large, equally dividing non-first promotion commodities into n parts according to a sequencing result, recording the maximum value of promotion sensitivity values in the first n-1 non-first promotion commodities, storing a variable Zoe _D, setting the value in Zoe _D as the upper limit and the lower limit of a promotion sensitivity range corresponding to the non-first promotion commodities, and setting n non-first promotion commodities to correspond to m promotion sensitivity value fields, namely (0, zoe_D1)],(Zoe_D1,Zoe_D2],...,(Zoe_D(n-2),Zoe_D(n-1)](Zoe _d (n-1), +_j), where m=n; and comparing the sales promotion sensitivity value of the non-first sales promotion commodity with the sales promotion sensitivity value field according to the sales promotion sensitivity value field to obtain the non-first sales promotion commodity.
The method comprises the steps of firstly preprocessing commodity names of first-time promoted commodities through a Jieba word segmentation method to obtain commodity word sets, wherein the preprocessing comprises the steps of processing the commodity word sets into vector sets through word2vec by deleting punctuation marks, blank spaces and stop words, and the vector sets are the first-time promoted commodity sets, and words and vectors in the commodity word sets and the vector sets are in one-to-one correspondence; calculating the semantic similarity between the vector set and the promoted commodity in the promoted database, and utilizing a formulaCalculating the semantic similarity of vector sets and promotional items in a promotional database>The larger the value of (2) is, the higher the semantic similarity of the two commodities is, and when the semantic similarity is more than or equal to 0.85, the first promotion commodity is judged to be the first promotion commodity class.
Inputting the commodity category into a sales promotion quantity prediction model to obtain a sales promotion quantity prediction result, wherein the commodity category is a set of non-first sales promotion commodity and first sales promotion commodity.
Step S4 and step S5 involve an order checking module verifying the dealer sales authorization range and the dealer credit information based on the dealer information and the commodity name, and calculating an order verification result of dealer inventory restriction output order verification information based on the dealer sales authorization range and the dealer credit information. In step S4, the sales authorization range of the dealer is determined according to the dealer name and the dealer address, and whether the commodity name accords with the sales authority of the dealer is judged, if yes, the commodity name carries the valid identification information of the dealer authorization, and if no, the unauthorized commodity information is returned. And carrying the commodity name with the dealer authorized effective identification information to the dealer for checking the dealer credit, obtaining the historical arrearage information of the dealer according to the dealer name, judging whether the sum of the total amount information and the historical arrearage information of the dealer exceeds the dealer credit line, if so, returning the information exceeding the dealer credit line, otherwise, outputting the order checking information. In step S5, dealer inventory limits are calculated using the formula asD is the annual demand of the dealer, s is the ordering cost, c is the holding cost, the inventory limit Inli of the dealer is calculated, whether the commodity demand exceeds the inventory limit of the dealer is judged, if yes, the order quantity verification information is output as an invalid order, and if not, the order quantity verification information is output as a valid order.
A global order management system, comprising:
the order acquisition module is used for acquiring order information, wherein the order information comprises dealer information and order demand information;
the order classification module is used for calculating the order demand information according to the related promotion database to obtain a mapping order, classifying the mapping order through a normalized linear function to obtain promotion type commodities and non-promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
the sales volume prediction module is used for calling historical sales data in the sales database to train a sales volume prediction model, and processing sales volume prediction results of sales type commodities by sales sensitivity commodity classification and semantic similarity commodity classification;
the order checking module is used for verifying the sales authorization range of the dealer and the credit information of the dealer according to the dealer information and the commodity name, outputting the order quantity checking information, and calculating the order quantity checking result of the dealer inventory limit output order quantity checking information according to the sales authorization range of the dealer and the credit information of the dealer.
The working principle of the invention is as follows:
the order information is acquired through an order acquisition module, order demand information in the order information is processed through an order classification module to obtain sales promotion type commodities and non-sales promotion type commodities, sales promotion type commodities are predicted, and sales promotion type commodities are processed through sales promotion sensitivity commodity classification and semantic similarity commodity classification to output sales promotion type commodity sales prediction results. And finally, verifying the sales authorization range of the dealer and the credit information of the dealer through an order checking module, and calculating an order quantity checking result of the dealer inventory limit output order quantity checking information according to the sales authorization range of the dealer and the credit information of the dealer.
Program code embodied in a system in an embodiment of the invention may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (3)
1. A global order management method, comprising the steps of:
s1: acquiring order information, wherein the order information comprises dealer information and order demand information;
s2: the related promotion database calculates the order demand information to obtain a mapping order, and the mapping order is classified through a normalized linear function to obtain promotion type commodities and non-promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
s3: invoking historical sales data in the sales database to train a sales volume prediction model, and processing the sales volume prediction result of the sales type commodity by sales sensitivity commodity classification and semantic similarity commodity classification to output the sales volume prediction result of the sales type commodity;
s4: verifying a sales authorization range of a dealer and dealer credit information according to the dealer information and the commodity name, and outputting order quantity verification information, wherein the dealer information comprises a dealer name and a dealer address;
s5: calculating dealer stock limit according to the dealer sales authorization range and the dealer credit information, wherein the calculation formula is as follows:wherein d is the annual demand of the dealer, s is the ordering cost, c is the holding cost, inli is the inventory limit of the dealer, whether the commodity demand exceeds the inventory limit of the dealer is judged, if yes, the order quantity verification information is output as an invalid order, and if not, the order quantity verification information is output as a valid order;
the step S2 specifically includes the following steps:
s201: obtaining the mapping order through the associated promotion database according to the commodity name;
s202: calculating the Euclidean distance of the mapping order corresponding to the normalized linear function, and extracting a maximum Euclidean distance and a minimum Euclidean distance, wherein the difference between the maximum Euclidean distance and the minimum Euclidean distance is the information distance of the corresponding normalized linear function;
s203: according to the formulaCalculating the information distance adjacent to the normalized linear function to obtain an adjacent information distance, wherein Y j For the adjacent information distance d i Information distance, d, representing the ith said normalized linear function k The information distance of the kth normalized linear function is represented, i and k represent two adjacent positive integers, and D (·) is a preset calculation function;
s204: judging the adjacent information distance, wherein when 0< Yj <1, the normalized linear function corresponds to the mapping order and is the sales promotion commodity, and when Yj >1, the normalized linear function corresponds to the mapping order and is the non-sales promotion commodity;
the normalized linear function is:wherein g h =g h-1 +v h And g 1 =v 1 ,g h As the amount of the offset to be used,v h h is a positive integer, Q represents a weight vector corresponding to the mapping order, Q is a preset parameter, and x is the mapping order;
the step S3 specifically includes:
the sales promotion commodities comprise non-first sales promotion commodities and first sales promotion commodities, the non-first sales promotion commodities are classified by the sales promotion sensitivity commodity classification to obtain non-first sales promotion commodity classes, and the first sales promotion commodities are classified by the semantic similarity commodity classification to obtain first sales promotion commodity classes;
inputting commodity categories into the sales promotion quantity prediction model to obtain sales promotion quantity prediction results of the sales promotion commodities, wherein the commodity categories are a set of non-first sales promotion commodities and first sales promotion commodities;
the sales promotion sensitivity commodity classification specifically comprises:
calculating the sales promotion sensitivity value of the non-first sales promotion commodity, wherein the calculation formula is as follows:wherein i is commodity, j is sales promotion number, and h i A total number of times r of participation in the promotional program for the non-first promotional item ij For sales, pr ij Prse as a percentage of price reduction i Is the promotion sensitivity value;
arranging the sales promotion sensitive values from small to large, and equally dividing the non-first sales promotion commodities into n parts according to the sorting result;
recording the maximum value of the promotion sensitivity values in the first n-1 non-first promotion commodities, storing a variable Zoe _D, setting the value in Zoe _D as the upper limit and the lower limit of a promotion sensitivity range corresponding to the non-first promotion commodity, wherein the n non-first promotion commodities correspond to m promotion sensitivity value fields, specifically (0, zoe_D1], (Zoe _D1, zoe _D2], (Zoe _D (n-2), zoe _D (n-1) ], (Zoe _D (n-1), +_n), and m=n;
comparing the sales promotion sensitivity value of the non-first sales promotion commodity with the sales promotion sensitivity value field according to the sales promotion sensitivity value field to obtain the non-first sales promotion commodity class;
the semantic similarity commodity classification specifically comprises the following steps:
preprocessing the commodity name of the first promoted commodity by using a Jieba word segmentation method to obtain a commodity word set;
processing the commodity word set into a vector set through word2vec, wherein the vector set is the set of the first promoted commodity;
calculating the semantic similarity between the vector set and the promoted commodity in the promoted database, wherein the calculation formula is as follows:wherein (1)>For the vector set, +.>For a set of promotional items in said promotional database, < > j->For the semantic similarity;
when the semantic similarity is greater than or equal to 0.85, the first promotion commodity is the first promotion commodity class.
2. The global order management method according to claim 1, wherein the step S4 specifically comprises:
determining the sales authorization range of the dealer according to the dealer name and the dealer address, judging whether the commodity name accords with the sales authority of the dealer, if so, carrying effective identification information of dealer authorization by the commodity name, and if not, returning unauthorized commodity information;
and checking the credit information of the dealer by carrying the commodity name with the dealer authorized effective identification information, obtaining historical arrearage information of the dealer according to the dealer name, judging the total amount information and the dealer credit limit, if yes, returning the information exceeding the dealer credit limit information, and if not, outputting the order checking information.
3. A global order management system employing the global order management method of claim 1, comprising:
the order acquisition module is used for acquiring order information, wherein the order information comprises dealer information and order demand information;
the order classification module is used for correlating the sales promotion database to calculate the order demand information to obtain a mapping order, classifying the mapping order through a normalized linear function to obtain sales promotion type commodities and non-sales promotion type commodities, wherein the order demand information comprises commodity names, commodity demand and total information;
the sales volume prediction module is used for calling the historical sales volume prediction model trained by the sales volume data in the sales volume database, and processing the sales volume prediction results of the sales volume type commodities through sales volume sensitivity commodity classification and semantic similarity commodity classification;
the order checking module is used for verifying the sales authorization range of the dealer and the credit information of the dealer according to the dealer information and the commodity name, outputting the order quantity checking information, and calculating the inventory limit of the dealer according to the sales authorization range of the dealer and the credit information of the dealer and outputting the order quantity checking result of the order quantity checking information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311226930.4A CN116976955B (en) | 2023-09-22 | 2023-09-22 | Global order management system and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311226930.4A CN116976955B (en) | 2023-09-22 | 2023-09-22 | Global order management system and method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116976955A CN116976955A (en) | 2023-10-31 |
CN116976955B true CN116976955B (en) | 2023-12-26 |
Family
ID=88483492
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311226930.4A Active CN116976955B (en) | 2023-09-22 | 2023-09-22 | Global order management system and method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116976955B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013182415A (en) * | 2012-03-01 | 2013-09-12 | Toshiba Tec Corp | Demand prediction device and program |
CN104217355A (en) * | 2014-09-11 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Method and device for predicting sales volume of promotion items |
EP2960848A1 (en) * | 2014-06-27 | 2015-12-30 | Toshiba TEC Kabushiki Kaisha | Demand prediction apparatus and demand prediction method by the same |
CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
CN112330358A (en) * | 2020-10-22 | 2021-02-05 | 北京明略昭辉科技有限公司 | Method and apparatus for product sales prediction, storage medium, and electronic device |
CN112734494A (en) * | 2021-01-18 | 2021-04-30 | 深圳市轱辘车联数据技术有限公司 | Sales prediction method and device, terminal equipment and readable storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140200992A1 (en) * | 2013-01-14 | 2014-07-17 | Oracle International Corporation | Retail product lagged promotional effect prediction system |
-
2023
- 2023-09-22 CN CN202311226930.4A patent/CN116976955B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013182415A (en) * | 2012-03-01 | 2013-09-12 | Toshiba Tec Corp | Demand prediction device and program |
EP2960848A1 (en) * | 2014-06-27 | 2015-12-30 | Toshiba TEC Kabushiki Kaisha | Demand prediction apparatus and demand prediction method by the same |
CN104217355A (en) * | 2014-09-11 | 2014-12-17 | 北京京东尚科信息技术有限公司 | Method and device for predicting sales volume of promotion items |
CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
CN112330358A (en) * | 2020-10-22 | 2021-02-05 | 北京明略昭辉科技有限公司 | Method and apparatus for product sales prediction, storage medium, and electronic device |
CN112734494A (en) * | 2021-01-18 | 2021-04-30 | 深圳市轱辘车联数据技术有限公司 | Sales prediction method and device, terminal equipment and readable storage medium |
Non-Patent Citations (1)
Title |
---|
基于FTRL和XGBoost组合算法的电商销量预测***;钟小勇;;信息记录材料(01);第1-3页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116976955A (en) | 2023-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113255815B (en) | User behavior abnormity analysis method, device, equipment and storage medium | |
RU2487394C2 (en) | Methods and systems for implementing approximate string matching within database | |
CN109739844B (en) | Data classification method based on attenuation weight | |
CN107818344A (en) | The method and system that user behavior is classified and predicted | |
CN107704512A (en) | Financial product based on social data recommends method, electronic installation and medium | |
CN110704730A (en) | Product data pushing method and system based on big data and computer equipment | |
CN109740642A (en) | Invoice category recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
CN110688536A (en) | Label prediction method, device, equipment and storage medium | |
CN112581252A (en) | Address fuzzy matching method and system fusing multidimensional similarity and rule set | |
CN113706291A (en) | Fraud risk prediction method, device, equipment and storage medium | |
CN112950347A (en) | Resource data processing optimization method and device, storage medium and terminal | |
CN114742432A (en) | Market procurement trade wind control management method and management system thereof | |
CN112861056A (en) | Enterprise website construction information display and release system and method | |
CN115374354A (en) | Scientific and technological service recommendation method, device, equipment and medium based on machine learning | |
CN113628043B (en) | Complaint validity judging method, device, equipment and medium based on data classification | |
CN116976955B (en) | Global order management system and method thereof | |
CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
CN112148880A (en) | Customer service dialogue corpus clustering method, system, equipment and storage medium | |
CN115713399B (en) | User credit evaluation system combined with third-party data source | |
CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
CN107424026A (en) | Businessman's reputation evaluation method and device | |
CN114840660A (en) | Service recommendation model training method, device, equipment and storage medium | |
CN115511187A (en) | Asset recovery prediction method, device, equipment, medium and computer program product | |
CN114297235A (en) | Risk address identification method and system and electronic equipment | |
CN114792007A (en) | Code detection method, device, equipment, storage medium and computer program product |
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 |