CN116957709B - Manifest transaction management system and method based on digital cloud platform - Google Patents
Manifest transaction management system and method based on digital cloud platform Download PDFInfo
- Publication number
- CN116957709B CN116957709B CN202310654700.1A CN202310654700A CN116957709B CN 116957709 B CN116957709 B CN 116957709B CN 202310654700 A CN202310654700 A CN 202310654700A CN 116957709 B CN116957709 B CN 116957709B
- Authority
- CN
- China
- Prior art keywords
- product
- dealer
- value
- products
- evaluation
- 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 43
- 238000012216 screening Methods 0.000 claims abstract description 38
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000010276 construction Methods 0.000 claims abstract description 17
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims description 110
- 238000007726 management method Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000003993 interaction Effects 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 208000034804 Product quality issues Diseases 0.000 claims 2
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of electronic commerce, in particular to a manifest transaction management system and method based on a digital cloud platform, wherein the system comprises a scheme screening module, a comprehensive influence degree analysis module, a preferred evaluation model construction module and an associated optimal scheme selection module, wherein the comprehensive influence degree analysis module is used for screening associated products of a product A based on an analysis result of the scheme screening module, combining comprehensive influence degree values of all the associated products to construct a product pushing model.
Description
Technical Field
The invention relates to the field of electronic commerce, in particular to a manifest transaction management system and method based on a digital cloud platform.
Background
The cloud computing industry of China has great potential, and China has most network users and perfect network infrastructure in the world, so that the China has the application scene of the largest and most burst requests in the world, and meanwhile, the China has remarkable innovation capability in the aspects of mobile network, industry digitization, electronic games, network trade and the like;
Electronic commerce refers to online transactions, namely, commodity buying and selling is performed on an internet platform, the occurrence of electronic commerce brings the most direct circulation channel for each commodity, a dealer can directly send the commodity to a customer and can obtain the demand information with optimal value from the customer, but the customer still has a plurality of problems when selecting the commodity, such as:
1) How to quickly select the optimal commodity;
2) How to reasonably screen related commodities;
3) How to optimally select the associated merchandise.
Disclosure of Invention
The invention aims to provide a manifest transaction management system and method based on a digital cloud platform, which are used for solving the problems in the background technology, and the invention provides the following technical scheme:
a manifest transaction management method based on a digital cloud platform, the method comprising the steps of:
S1, acquiring dealer information associated with a product A, generating a comprehensive evaluation value by combining data fed back by a dealer associated user corresponding to the product A in historical data, and generating an influence element weight ratio according to customer requirements;
S2, combining the analysis result in the S1, combining the historical data to screen the related products of the product A, analyzing the comprehensive influence degree value between the product A and the related products, and constructing a product pushing model;
S3, acquiring a product pushing model in the S2, taking corresponding client demand time in the product A as time limit, setting the associated product pushing priority sequence of the product A, and constructing a product preference evaluation model;
S4, setting an optimal scheme for the push priority sequence of the product B according to the generated weight ratio of the audio elements by combining the product preference evaluation model.
Further, the method of S1 includes the following steps:
Step 1001, record the dealer set associated with product a as set a *,
A*＝{A1,A2,A3,...,An}，
Wherein A n represents the nth dealer associated with product A, where n represents the total number of dealers associated with product A;
Step 1002, counting information data fed back by each dealer associated user using the product A, and recording first evaluation values of the products A corresponding to different dealers as
Wherein α 1、α2 and α 3 represent weight values preset for the database, H n represents the number of returns caused by the product quality problem when the nth dealer associated user uses the product a, T n represents the number of returns caused by the product transportation time problem when the nth dealer associated user uses the product a, ε represents the number of returns caused by the special cause, and Z n represents the total number of products shipped from the nth dealer a;
step 1003, repeat step 1002 to obtain the first evaluation value corresponding to the different products of the nth dealer, and calculate the comprehensive evaluation value of the nth dealer, which is denoted as R n,
Where a is a database preset constant,Representing a first evaluation value corresponding to the ith product in the nth dealer,Representing the average value of the accumulated first evaluation values corresponding to different products of the nth dealer, wherein R n reflects the discrete degree, namely, the larger the R n calculation result is, the worse the product quality of the corresponding dealer is;
Step 1004, repeating the steps 1002-1003 to obtain comprehensive evaluation values of different distributors, sequencing the calculation results according to the order from big to small, and combining the requirement confirmation scheme of the current user on the product A;
Step 1005, obtaining the position of the scheme confirmed by the current user in the sequence, cutting off the position as a cutting point, performing difference operation on the influencing elements in the first evaluation value corresponding to the scheme confirmed by the current user and the influencing elements in the first evaluation value of the products corresponding to each dealer, and recording the result as a plurality of sets P, wherein the number of dealers included in the segment before the cutting point is d-1,
P＝{(q0,w0,e0),(q1,w1,e1),(q2,w2,e2),...,(qd,wd,ed)},
Wherein (q d,wd,ed) represents a difference operation result of the influencing element in the first evaluation value corresponding to the scheme confirmed by the current user and the influencing element in the first evaluation value corresponding to the product of the d-th dealer, q d represents a difference operation result of the product quality problem in the first evaluation value corresponding to the scheme confirmed by the current user and the product quality problem in the first evaluation value corresponding to the product of the d-th dealer, w d represents a difference operation result of the product transportation time problem in the first evaluation value corresponding to the scheme confirmed by the current user and the product transportation time problem in the first evaluation value corresponding to the product of the d-th dealer, e d represents a difference operation result of the product special reason problem in the first evaluation value corresponding to the first evaluation value and the product special reason problem in the first evaluation value corresponding to the product of the d-th dealer,
Matching is carried out through database preset weight ratio adjustment data to obtain an influence element weight ratio group which accords with the current user, the influence element weight ratio is sequentially multiplied with each element in the data set P, the influence element weight ratio group with all multiplication results being greater than or equal to 0 is screened, the screened influence element weight ratio group multiplication operations are summed, the influence element weight ratio corresponding to the sum minimum value is used as the influence element weight ratio corresponding to the requirement of the current user, and the influence element weight ratio is recorded as/>The influence elements represent product quality problems, product transportation time problems and special reasons, and if all preset weight ratio adjustment data in the database do not accord with the weight ratio of the influence element of the current user, the original preset weight value is reserved.
According to the invention, the information data fed back by the related users of the product A are counted by acquiring the related dealer set of the product A, the first evaluation is carried out according to the fed back information data, the comprehensive evaluation value corresponding to each dealer is calculated by analyzing the first evaluation values of different products of different dealers, and the new influence element weight ratio is generated according to the comprehensive evaluation value corresponding to each dealer and the current user requirement, so that data reference is provided for the subsequent adjustment of the push sequence of the product B by the current user.
Further, the method of S2 includes the following steps:
Step 2001, obtaining a product set associated with the existence of the product A through historical data, which is marked as a set B *,
B*＝{B1,B2,B3,...,Bm}，
Wherein B m represents the mth product associated with product a, wherein the associated product comprises one or more dealer leaves the factory;
Step 2002, analyzing the product comprehensive influence degree value related to the existence of the mth product A, constructing a product pushing model by combining the analysis result, marking as Y m,
Wherein the method comprises the steps ofIndicating the degree of similarity between the mth product associated with the presence of product A and product A, Z m indicating the total number of mth products associated with the presence of product A selected by other users in the history while selecting product A, and Z B indicating the total number of products associated with the presence of product A selected by other users in the history while selecting product A,/>Representing an mth interaction influence value between the product and the product A which are related to the existence of the product A, wherein the mth interaction influence value between the product and the product A which are related to the existence of the product A is queried through a preset form, beta 1、β2 and beta 3 are weight values, the weight values are preset constants for a database, and the similarity degree between the product and the product A which are related to the existence of the product A can be obtained through a Jaccard similarity coefficient;
Step 2003, repeating step 2002 to obtain comprehensive influence degree values corresponding to different products related to the product A, sorting the comprehensive influence degree values corresponding to the different products from large to small, and taking the sorting result as a pushing sequence of the products related to the product A.
According to the invention, products related to the product A are obtained, the comprehensive influence degree of the related products and the product A is analyzed, a product pushing model is constructed according to the analysis result, the sorting is carried out according to the value of the comprehensive influence degree, the sorted result is used as a pushing sequence, the limiting conditions are set for the follow-up, and the product B meeting the current user requirements is screened by combining the product pushing model to provide data reference.
Further, the method of S3 includes the following steps:
Step 3001, obtaining the expected time from the dealer to the current user destination of the product A in the product A delivery optimal scheme in step 1004, and recording as T A;
Step 3002, obtaining the pushing sequence of the products related to the product A in step 2003, extracting the product B according to the current user demand, and marking the dealer related to the product B as a set C,
C＝{C1,C2,C3,...,Cf}，
Wherein C f represents a product B associated with the product a and shipped from the f-th dealer;
step 3003, obtaining related user satisfaction evaluation values of products B shipped by different dealers through historical data, constructing a product preference evaluation value model by combining the related user satisfaction evaluation values, marking as Y B,
Wherein the method comprises the steps ofRepresenting the total value of up to standard of the related user satisfaction evaluation value of the product B delivered by the f th dealer in the historical data,/>Representing total value of all satisfaction evaluation of associated users of product B shipped by f-th dealer in historical data,/>Representing the time required for the product B shipped from the f-th dealer to the current user destination in the historical data,/>The selling price of product B shipped from the f-th dealer is indicated.
According to the invention, the related user satisfaction evaluation values of the products B delivered by different distributors are obtained through historical data, and a product preference evaluation value model is constructed by combining the related user satisfaction evaluation values, so that data reference is provided for the follow-up screening of the optimal scheme of the products meeting the requirements of the current users.
Further, the method of S4 includes the following steps:
Step 4001, repeating steps 3002-3003 to obtain a preferred evaluation value model corresponding to the dealer associated with the product B;
Step 4002, obtain the analysis result of step 4001, rank the preferred evaluation values corresponding to the distributors associated with the product B from big to small, take T A as the time limit, reject the distributors corresponding to the time limit exceeding in the sequence, obtain the updated sequence, record as set C *,
Wherein the method comprises the steps ofRepresenting that the product A is related to the product B after the sequence update, and the product B leaves the g-th dealer, wherein g is less than or equal to f;
Step 4003, repeat step 1002, calculate the first evaluation value of product B corresponding to different dealers, record as
H g represents the number of returns caused by the product quality problem when the g-th dealer associated user uses the product B, T g represents the number of returns caused by the product transportation time problem when the g-th dealer associated user uses the product B, E B represents the number of returns caused by the special reason, and Z g represents the total number of products shipped from the g-th dealer to the product B;
Step 4004, repeat step 1003 to calculate the comprehensive evaluation value of each dealer, and arrange the comprehensive evaluation values in order from large to small according to the calculation result, and take the arranged sequence as the pushing sequence of the associated product.
According to the invention, through setting time limit, non-conforming elements in the product preference evaluation value model are removed, the product preference evaluation values corresponding to the removed results are ordered according to the order from large to small, the comprehensive evaluation values of all distributors are calculated for the second time by combining with the new influence factor weight ratio generated by the current user demand, and the pushing sequence of the related products is adjusted.
A manifest transaction management system based on a digital cloud platform, the system comprising the following modules:
Scheme screening module: the scheme screening module is used for acquiring dealer information associated with the product A and screening an optimal scheme by combining the requirement of a current user on the product A;
The comprehensive influence degree analysis module is used for: the comprehensive influence degree analysis module is used for screening related products of the product A based on the analysis result of the scheme screening module and constructing a product pushing model by combining the comprehensive influence degree values of the related products;
The preferred assessment model construction module: the optimal assessment model construction module is used for screening a product B meeting the current user requirements according to the current user requirements based on the limiting condition of the optimal scheme of the product A and combining a product pushing model to construct a product optimal assessment value model;
And (5) a correlation optimal scheme selection module: the association optimal scheme selection module is used for combining the analysis result of the optimization evaluation model construction module to screen an optimal scheme of the product B required by the current user.
Further, the scheme screening module includes a data acquisition unit, a first evaluation unit, and a scheme screening unit:
The data acquisition unit is used for acquiring an associated dealer set of the product A and counting information data fed back by the associated users of the dealers when using the product A;
The first evaluation unit is used for calculating first evaluation values of the products A corresponding to different dealers by combining the analysis results of the data acquisition unit;
The scheme screening unit is used for screening the best dealer leaving the factory of the product A by combining the calculation result of the first evaluation unit.
Further, the comprehensive influence degree analysis module comprises an associated product acquisition unit and a product pushing model construction unit:
the associated product acquisition unit is used for obtaining a product associated with the product A through combination of historical data analysis;
The product pushing model building unit is used for analyzing the comprehensive influence degree value between the related product and the product A and building a product pushing model according to the analysis result.
Further, the preferred evaluation model construction module includes an associated data screening unit and a preferred evaluation model construction unit:
the association data screening unit is used for acquiring an analysis result of the product pushing model construction unit, and screening the conforming products and distributors of the corresponding products according to the current user requirements;
the optimal selection evaluation model construction unit is used for acquiring the related user satisfaction evaluation values of the products B delivered by different dealers through historical data according to the analysis result of the related data screening unit, and constructing a product optimal selection evaluation value model by combining the related user satisfaction evaluation values.
Further, the associated optimal solution selection module includes a limit value analysis unit and an optimal solution acquisition unit:
the limit value analysis unit is used for setting a time limit value and screening a product B meeting the current user requirement by combining the time limit value;
The optimal scheme obtaining unit is used for screening an optimal scheme corresponding to the product B according to the current user requirement.
According to the invention, the user manifest information is analyzed, the product information in the manifest information is extracted, the associated products are pushed by combining with the user product information, and comprehensive evaluation is carried out on each associated product according to the purchase intention of the user, so that the optimal selection scheme meeting the user is obtained, the product screening efficiency required by the user is improved, and the rate of the interaction between the associated products is further improved.
Drawings
FIG. 1 is a flow diagram of a method for managing a manifest transaction based on a digital cloud platform of the present invention;
fig. 2 is a schematic block diagram of a manifest transaction management system based on a digital cloud platform according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1: referring to fig. 1, in this embodiment:
The manifest transaction management method based on the digital cloud platform is realized, and comprises the following steps:
S1, acquiring dealer information associated with a product A, generating a comprehensive evaluation value by combining data fed back by a dealer associated user corresponding to the product A in historical data, and generating an influence element weight ratio according to customer requirements;
The method of S1 comprises the following steps:
Step 1001, record the dealer set associated with product a as set a *,
A*＝{A1,A2,A3,...,An}，
Wherein A n represents the nth dealer associated with product A, where n represents the total number of dealers associated with product A;
Step 1002, counting information data fed back by each dealer associated user using the product A, and recording first evaluation values of the products A corresponding to different dealers as
Wherein α 1、α2 and α 3 represent weight values preset for the database, H n represents the number of returns caused by the product quality problem when the nth dealer associated user uses the product a, T n represents the number of returns caused by the product transportation time problem when the nth dealer associated user uses the product a, ε represents the number of returns caused by the special cause, and Z n represents the total number of products shipped from the nth dealer a;
step 1003, repeat step 1002 to obtain the first evaluation value corresponding to the different products of the nth dealer, and calculate the comprehensive evaluation value of the nth dealer, which is denoted as R n,
Where a is a database preset constant,Representing a first evaluation value corresponding to the ith product in the nth dealer,Representing the average value of the accumulated first evaluation values corresponding to different products of the nth dealer, wherein R n reflects the discrete degree, namely, the larger the R n calculation result is, the worse the product quality of the corresponding dealer is;
Step 1004, repeating the steps 1002-1003 to obtain comprehensive evaluation values of different distributors, sequencing the calculation results according to the order from big to small, and combining the requirement confirmation scheme of the current user on the product A;
Step 1005, obtaining the position of the scheme confirmed by the current user in the sequence, cutting off the position as a cutting point, performing difference operation on the influencing elements in the first evaluation value corresponding to the scheme confirmed by the current user and the influencing elements in the first evaluation value of the products corresponding to each dealer, and recording the result as a plurality of sets P, wherein the number of dealers included in the segment before the cutting point is d-1,
P＝{(q0,w0,e0),(q1,w1,e1),(q2,w2,e2),...,(qd,wd,ed)},
Wherein (q d,wd,ed) represents a difference operation result of the influencing element in the first evaluation value corresponding to the scheme confirmed by the current user and the influencing element in the first evaluation value corresponding to the product of the d-th dealer, q d represents a difference operation result of the product quality problem in the first evaluation value corresponding to the scheme confirmed by the current user and the product quality problem in the first evaluation value corresponding to the product of the d-th dealer, w d represents a difference operation result of the product transportation time problem in the first evaluation value corresponding to the scheme confirmed by the current user and the product transportation time problem in the first evaluation value corresponding to the product of the d-th dealer, e d represents a difference operation result of the product special reason problem in the first evaluation value corresponding to the first evaluation value and the product special reason problem in the first evaluation value corresponding to the product of the d-th dealer,
Matching is carried out through database preset weight ratio adjustment data to obtain an influence element weight ratio group which accords with the current user, the influence element weight ratio is sequentially multiplied with each element in the data set P, the influence element weight ratio group with all multiplication results being greater than or equal to 0 is screened, the screened influence element weight ratio group multiplication operations are summed, the influence element weight ratio corresponding to the sum minimum value is used as the influence element weight ratio corresponding to the requirement of the current user, and the influence element weight ratio is recorded as/>Wherein the influencing elements represent product quality problems, product transit time problems and special reasons.
S2, combining the analysis result in the S1, combining the historical data to screen the related products of the product A, analyzing the comprehensive influence degree value between the product A and the related products, and constructing a product pushing model;
the method of S2 comprises the following steps:
Step 2001, obtaining a product set associated with the existence of the product A through historical data, which is marked as a set B *,
B*＝{B1,B2,B3,...,Bm}，
Wherein B m represents the mth product associated with product a, wherein the associated product comprises one or more dealer leaves the factory;
Step 2002, analyzing the product comprehensive influence degree value related to the existence of the mth product A, constructing a product pushing model by combining the analysis result, marking as Y m,
Wherein the method comprises the steps ofIndicating the degree of similarity between the mth product associated with the presence of product A and product A, Z m indicating the total number of mth products associated with the presence of product A selected by other users in the history while selecting product A, and Z B indicating the total number of products associated with the presence of product A selected by other users in the history while selecting product A,/>Representing an mth interaction influence value between the product and the product A which are related with the product A, wherein the mth interaction influence value between the product and the product A which are related with the product A is queried through a preset form, beta 1、β2 and beta 3 are weight values, and the weight values are preset constants for a database;
Step 2003, repeating step 2002 to obtain comprehensive influence degree values corresponding to different products related to the product A, sorting the comprehensive influence degree values corresponding to the different products from large to small, and taking the sorting result as a pushing sequence of the products related to the product A.
S3, acquiring a product pushing model in the S2, taking corresponding client demand time in the product A as time limit, setting the associated product pushing priority sequence of the product A, and constructing a product preference evaluation model;
the method of S3 comprises the following steps:
Step 3001, obtaining the expected time from the dealer to the current user destination of the product A in the product A delivery optimal scheme in step 1004, and recording as T A;
Step 3002, obtaining the pushing sequence of the products related to the product A in step 2003, extracting the product B according to the current user demand, and marking the dealer related to the product B as a set C,
C＝{C1,C2,C3,...,Cf}，
Wherein C f represents a product B associated with the product a and shipped from the f-th dealer;
step 3003, obtaining related user satisfaction evaluation values of products B shipped by different dealers through historical data, constructing a product preference evaluation value model by combining the related user satisfaction evaluation values, marking as Y B,
Wherein the method comprises the steps ofRepresenting the total value of up to standard of the related user satisfaction evaluation value of the product B delivered by the f th dealer in the historical data,/>Representing total value of all satisfaction evaluation of associated users of product B shipped by f-th dealer in historical data,/>Representing the time required for the product B shipped from the f-th dealer to the current user destination in the historical data,/>The selling price of product B shipped from the f-th dealer is indicated.
S4, setting an optimal scheme for the push priority sequence of the product B according to the generated weight ratio of the audio elements by combining the product preference evaluation model.
The method of S4 comprises the following steps:
Step 4001, repeating steps 3002-3003 to obtain a preferred evaluation value model corresponding to the dealer associated with the product B;
Step 4002, obtain the analysis result of step 4001, rank the preferred evaluation values corresponding to the distributors associated with the product B from big to small, take T A as the time limit, reject the distributors corresponding to the time limit exceeding in the sequence, obtain the updated sequence, record as set C *,
Wherein the method comprises the steps ofRepresenting that the product A is related to the product B after the sequence update, and the product B leaves the g-th dealer, wherein g is less than or equal to f;
Step 4003, repeat step 1002, calculate the first evaluation value of product B corresponding to different dealers, record as
H g represents the number of returns caused by the product quality problem when the g-th dealer associated user uses the product B, T g represents the number of returns caused by the product transportation time problem when the g-th dealer associated user uses the product B, E B represents the number of returns caused by the special reason, and Z g represents the total number of products shipped from the g-th dealer to the product B;
Step 4004, repeat step 1003 to calculate the comprehensive evaluation value of each dealer, and arrange the comprehensive evaluation values in order from large to small according to the calculation result, and take the arranged sequence as the pushing sequence of the associated product.
In this embodiment:
A digital cloud platform-based manifest transaction management system (as shown in fig. 2) is disclosed for implementing specific solution content of the method.
Example 2: cutting according to the scheme confirmed by the current user to obtain an array sequence
{(q0,w0,e0),(q1,w1,e1),(q2,w2,e2)}, Wherein the current user-validated solution correspondence array is (q 2,w2,e2),
Calculating the difference between the influence elements in the first evaluation value corresponding to the scheme confirmed by the current user and the influence elements in the first evaluation value of the products corresponding to each dealer, and recording the result as a plurality of sets P
p＝{[(q2-q0),(w2-w0),(e2-e0)],[(q2-q1),(w2-w1),(e2-e1)]},
Wherein the database preset weight adjustment ratio is (beta 1,γ1,δ1)、(β2,γ2,δ2) and (beta 3,γ3,δ3),
By computing the weight-to-adjust ratio that filters the coincidence dataset P,
Determine P11＝β1*(q2-q0)+γ1*(w2-w0)+δ1*(e2-e0) whether the result of the operation is less than 0,
Determine P21＝β2*(q2-q0)+γ2*(w2-w0)+δ2*(e2-e0) whether the result of the operation is less than 0,
Determine P12＝β1*(q2-q1)+γ1*(w2-w1)+δ1*(e2-e1) whether the result of the operation is less than 0,
Determine P22＝β2*(q2-q1)+γ2*(w2-w1)+δ2*(e2-e1) whether the result of the operation is less than 0,
Determine P31＝β3*(q2-q0)+γ3*(w2-w0)+δ3*(e2-e0) whether the result of the operation is less than 0,
Determine P32＝β3*(q2-q1)+γ3*(w2-w1)+δ3*(e2-e1) whether the result of the operation is less than 0,
If P 31 is less than 0, the rest operation results are all greater than or equal to 0, taking (beta 3,γ3,δ3) as the weight ratio of the influence element of the current user, further analyzing the accumulated values of the data set elements corresponding to (beta 1,γ1,δ1) and (beta 2,γ2,δ2) respectively to obtain the weight ratio of the influence element of the current user, namely calculating min [ (P 11+P12),(P21+P22) ],
When min [ (P 11+P12),(P21+P22)]＝(P11+P12), taking (beta 1,γ1,δ1) as the weight ratio of the influence element of the current user,
When min [ (P 11+P12),(P21+P22)]＝(P21+P22), the (beta 2,γ2,δ2) is taken as the weight ratio of the influence element of the current user.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method for managing manifest transactions based on a digital cloud platform, the method comprising the steps of:
S1, acquiring dealer information associated with a product A, generating a comprehensive evaluation value by combining data fed back by a dealer associated user corresponding to the product A in historical data, and generating an influence element weight ratio according to customer requirements;
S2, combining the analysis result in the S1, combining the historical data to screen the related products of the product A, analyzing the comprehensive influence degree value between the product A and the related products, and constructing a product pushing model;
S3, acquiring a product pushing model in the S2, taking corresponding client demand time in the product A as time limit, setting the associated product pushing priority sequence of the product A, and constructing a product preference evaluation model;
s4, setting an optimal scheme for the push priority sequence of the product B according to the generated weight ratio of the audio elements by combining a product preference evaluation model;
The method of S1 comprises the following steps:
step 1001, record the dealer set associated with product A as a set ，
，
Wherein the method comprises the steps ofRepresenting an nth dealer associated with the product a, wherein n represents a total number of dealers associated with the product a;
Step 1002, counting information data fed back by each dealer associated user using the product A, and recording first evaluation values of the products A corresponding to different dealers as ，
，
Wherein the method comprises the steps of、/>And/>Representing a weight value, wherein the weight value is a database preset value,/>Representing the number of returns due to product quality issues when the nth dealer associated user is using product A,/>Representing the number of returns due to product transit time issues when the nth dealer associated user is using product A,/>Representing the number of returns due to a particular cause,/>Indicating the total number of products A shipped from the nth dealer;
Step 1003, repeating step 1002 to obtain first evaluation values corresponding to different products of the nth dealer, and calculating an nth dealer comprehensive evaluation value, which is recorded as ，
，
Where a is a database preset constant,Representing a first evaluation value corresponding to the ith product in the nth dealer,/>Representing the average value of the accumulated first evaluation values corresponding to different products of the nth dealer; step 1004, repeating the steps 1002-1003 to obtain comprehensive evaluation values of different distributors, sequencing the calculation results according to the order from big to small, and combining the requirement confirmation scheme of the current user on the product A;
Step 1005, obtaining the position of the current user-confirmed scheme in the sequence, cutting off the position as a cutting point, performing difference value operation on the influencing elements in the first evaluation values corresponding to the current user-confirmed scheme and the influencing elements in the first evaluation values of the products corresponding to the distributors, and recording the result as a plurality of sets Wherein the number of dealers included in the segment before the cut point is d-1,
，
Wherein the method comprises the steps ofAnd (3) representing a difference value operation result of the influence element in the first evaluation value corresponding to the scheme confirmed by the current user and the influence element in the first evaluation value of the product corresponding to the d dealer,/>Representing the difference operation result of the product quality problem in the first evaluation value corresponding to the scheme confirmed by the current user and the product quality problem in the first evaluation value corresponding to the product of the d dealer,/>Difference operation result of product transportation time problem in first evaluation value corresponding to current user-confirmed scheme and product transportation time problem in first evaluation value corresponding to product of d-th dealer,/>The current user-confirmed scheme corresponds to the difference operation result of the product-specific cause problem in the first evaluation value and the product-specific cause problem in the first evaluation value of the product corresponding to the d-th dealer,
Matching is carried out through database preset weight ratio adjustment data, an influence element weight ratio group which accords with the current user is obtained, and the influence element weight ratio is sequentially matched with a data setPerforming product operation on each element in the list, screening the influence element weight ratio groups with all product operation results being greater than or equal to 0, summing the screened influence element weight ratio group product operation, taking the influence element weight ratio corresponding to the sum minimum value as the influence element weight ratio corresponding to the current user requirement, and marking as、/>/>Wherein the influencing elements represent product quality problems, product transit time problems, and special reasons.
2. The method for managing manifest transaction based on the digital cloud platform according to claim 1, wherein the method of S2 comprises the following steps:
step 2001, obtaining a product set associated with the existence of the product A through historical data, and recording the product set as a set ，
，
Wherein the method comprises the steps ofRepresenting the mth product associated with product a;
step 2002, analyzing the m-th product comprehensive influence degree value related to the existence of the product A, and constructing a product pushing model by combining the analysis result, wherein the product pushing model is recorded as ,
，
Wherein the method comprises the steps ofRepresenting the degree of similarity between the mth product associated with the presence of product A and product A,/>Representing the total number of m-th products associated with the product A in the history while other users select the product A,/>In the representation is the total number of products related to the existence of the product A, which is selected by other users in the record at the same time of selecting the product A,/>Representing an mth interaction impact value between the product and the product A associated with the product A existence, wherein the mth interaction impact value between the product and the product A associated with the product A existence is queried through a preset form,/>、/>/>The weight value is a weight value, and a constant is preset for the database;
Step 2003, repeating step 2002 to obtain comprehensive influence degree values corresponding to different products related to the product A, sorting the comprehensive influence degree values corresponding to the different products from large to small, and taking the sorting result as a pushing sequence of the products related to the product A.
3. The method for managing manifest transaction based on the digital cloud platform according to claim 2, wherein the method of S3 comprises the following steps:
step 3001, obtaining the expected time from the dealer to the current user destination of the product A in the optimal delivery scheme of the product A in step 1004, and recording as ；
Step 3002, obtaining the pushing sequence of the products related to the product A in step 2003, extracting the product B according to the current user demand, and marking the dealer related to the product B as a set C,
，
Wherein the method comprises the steps ofRepresenting a product B associated with the product a and shipped from the f-th dealer;
Step 3003, obtaining related user satisfaction evaluation values of products B shipped from different dealers through historical data, and constructing a product preference evaluation value model by combining the related user satisfaction evaluation values, and recording as ，
，
Wherein the method comprises the steps ofIndicating that the related user satisfaction evaluation value of the product B delivered by the f-th dealer in the historical data reaches the standard total value,Representing total value of all satisfaction evaluation of associated users of product B shipped by f-th dealer in historical data,/>Representing the time required for the product B shipped from the f-th dealer to the current user destination in the historical data,/>The selling price of product B shipped from the f-th dealer is indicated.
4. A method for managing a manifest transaction based on a digital cloud platform according to claim 3, wherein the method of S4 comprises the steps of:
Step 4001, repeating steps 3002-3003 to obtain a preferred evaluation value model corresponding to the dealer associated with the product B;
step 4002, obtain the analysis result of step 4001, rank the preferred evaluation values corresponding to the dealers associated with the product B from large to small to As a time limit, removing distributors corresponding to the time limit exceeding in the sequence to obtain an updated sequence, and marking the updated sequence as a set/>，
，
Wherein the method comprises the steps ofRepresenting that the product A is related to the product B after the sequence update, and the product B leaves the g-th dealer, wherein g is less than or equal to f;
Step 4003, repeat step 1002, calculate the first evaluation value of product B corresponding to different dealers, record as ，
，
Representing the number of returns due to product quality issues when the g-th dealer associated user is using product B,/>Representing the number of returns due to product transit time issues for the g-th dealer associated user when using product B,/>Representing the number of returns of product B due to a particular cause,/>Indicating the total number of products B shipped by the g-th dealer;
Step 4004, repeat step 1003 to calculate the comprehensive evaluation value of each dealer, and arrange the comprehensive evaluation values in order from large to small according to the calculation result, and take the arranged sequence as the pushing sequence of the associated product.
5. A digital cloud platform-based manifest transaction management system, the system applying the implementation of the digital cloud platform-based manifest transaction management method according to any one of claims 1 to 4, characterized in that the system comprises the following modules:
Scheme screening module: the scheme screening module is used for acquiring dealer information associated with the product A and screening an optimal scheme by combining the requirement of a current user on the product A;
The comprehensive influence degree analysis module is used for: the comprehensive influence degree analysis module is used for screening related products of the product A based on the analysis result of the scheme screening module and constructing a product pushing model by combining the comprehensive influence degree values of the related products;
The preferred assessment model construction module: the optimal assessment model construction module is used for screening a product B meeting the current user requirements according to the current user requirements based on the limiting condition of the optimal scheme of the product A and combining a product pushing model to construct a product optimal assessment value model;
And (5) a correlation optimal scheme selection module: the association optimal scheme selection module is used for combining the analysis result of the optimization evaluation model construction module to screen an optimal scheme of the product B required by the current user.
6. The manifest transaction management system based on the digital cloud platform of claim 5, wherein the schema screening module comprises a data acquisition unit, a first evaluation unit and a schema screening unit:
The data acquisition unit is used for acquiring an associated dealer set of the product A and counting information data fed back by the associated users of the dealers when using the product A;
The first evaluation unit is used for calculating first evaluation values of the products A corresponding to different dealers by combining the analysis results of the data acquisition unit;
The scheme screening unit is used for screening the best dealer leaving the factory of the product A by combining the calculation result of the first evaluation unit.
7. The manifest transaction management system based on the digital cloud platform according to claim 6, wherein the comprehensive influence degree analysis module comprises an associated product acquisition unit and a product push model construction unit:
the associated product acquisition unit is used for obtaining a product associated with the product A through combination of historical data analysis;
The product pushing model building unit is used for analyzing the comprehensive influence degree value between the related product and the product A and building a product pushing model according to the analysis result.
8. The manifest transaction management system based on the digital cloud platform according to claim 7, wherein the preferred assessment model construction module comprises an associated data screening unit and a preferred assessment model construction unit:
the association data screening unit is used for acquiring an analysis result of the product pushing model construction unit, and screening the conforming products and distributors of the corresponding products according to the current user requirements;
the optimal selection evaluation model construction unit is used for acquiring the related user satisfaction evaluation values of the products B delivered by different dealers through historical data according to the analysis result of the related data screening unit, and constructing a product optimal selection evaluation value model by combining the related user satisfaction evaluation values.
9. The manifest transaction management system based on the digital cloud platform according to claim 8, wherein the associated optimal solution selection module comprises a limit value analysis unit and an optimal solution acquisition unit:
the limit value analysis unit is used for setting a time limit value and screening a product B meeting the current user requirement by combining the time limit value;
The optimal scheme obtaining unit is used for screening an optimal scheme corresponding to the product B according to the current user requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310654700.1A CN116957709B (en) | 2023-06-05 | 2023-06-05 | Manifest transaction management system and method based on digital cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310654700.1A CN116957709B (en) | 2023-06-05 | 2023-06-05 | Manifest transaction management system and method based on digital cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116957709A CN116957709A (en) | 2023-10-27 |
| CN116957709B true CN116957709B (en) | 2024-04-23 |
Family
ID=88448260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310654700.1A Active CN116957709B (en) | 2023-06-05 | 2023-06-05 | Manifest transaction management system and method based on digital cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116957709B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102037A (en) * | 2020-09-16 | 2020-12-18 | 汤涛 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
| JP2021068435A (en) * | 2019-10-17 | 2021-04-30 | 株式会社日立製作所 | Supplier evaluation device and supplier evaluation method |
| CN113298576A (en) * | 2021-06-22 | 2021-08-24 | 仟言科技(佛山)有限公司 | Internet marketing planning system and method |
| CN113780799A (en) * | 2021-09-07 | 2021-12-10 | 北京卓思天成数据咨询股份有限公司 | Identification and evaluation method and device for commodity dealer service weakness |
| CN115423575A (en) * | 2022-11-03 | 2022-12-02 | 孩子王儿童用品股份有限公司 | Digital analysis management system and method based on Internet |
-
2023
- 2023-06-05 CN CN202310654700.1A patent/CN116957709B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2021068435A (en) * | 2019-10-17 | 2021-04-30 | 株式会社日立製作所 | Supplier evaluation device and supplier evaluation method |
| CN112102037A (en) * | 2020-09-16 | 2020-12-18 | 汤涛 | Live E-commerce platform commodity content intelligent pushing management system based on big data |
| CN113298576A (en) * | 2021-06-22 | 2021-08-24 | 仟言科技(佛山)有限公司 | Internet marketing planning system and method |
| CN113780799A (en) * | 2021-09-07 | 2021-12-10 | 北京卓思天成数据咨询股份有限公司 | Identification and evaluation method and device for commodity dealer service weakness |
| CN115423575A (en) * | 2022-11-03 | 2022-12-02 | 孩子王儿童用品股份有限公司 | Digital analysis management system and method based on Internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116957709A (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108389073A (en) | Automatic calculating method and system, the electronic equipment and storage medium of commodity price | |
| CN109961357B (en) | User data processing method and device, electronic equipment and storage medium | |
| CN109711955B (en) | Poor evaluation early warning method and system based on current order and blacklist base establishment method | |
| CA2471294A1 (en) | Sales optimization | |
| CN113159881B (en) | Data clustering and B2B platform customer preference obtaining method and system | |
| CN116433052B (en) | Intelligent bidding information acquisition data analysis and evaluation system | |
| CN110674391A (en) | Product data pushing method and system based on big data and computer equipment | |
| CN116308684B (en) | Online shopping platform store information pushing method and system | |
| CN108268519B (en) | Method and device for recommending network object | |
| CN114723492A (en) | Enterprise portrait generation method and equipment | |
| CN114493361A (en) | Effectiveness evaluation method and device for commodity recommendation algorithm | |
| CN111104614A (en) | Method for generating recall information for tourist destination recommendation system | |
| CN112738536B (en) | Data matching method based on social live E-commerce distribution | |
| CN116957709B (en) | Manifest transaction management system and method based on digital cloud platform | |
| TWI747290B (en) | Customer grouping service customized marketing method and system | |
| CN111859188B (en) | Restaurant recommendation method and system based on hierarchical analysis of large-scale matrix | |
| CN116739654A (en) | Information acquisition device and system | |
| CN116452299A (en) | Intelligent recommendation system and method for electronic commerce | |
| CN115510329A (en) | Brand marketing software management method based on cloud computing big data | |
| CN111899049B (en) | Advertisement putting method, device and equipment | |
| CN107845019B (en) | Order generation method and network sales platform | |
| CN111709819A (en) | Point-and-shoot-net property right transaction recommendation system and recommendation method based on graph neural network | |
| US20040083161A1 (en) | Electronic bidding proxy system | |
| CN112650862A (en) | Method and device for constructing interest network, electronic equipment and computer storage medium | |
| JP2001022851A (en) | Method and system for scoring |
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 |