CN112990968A - Lubrication dividing system and method - Google Patents
Lubrication dividing system and method Download PDFInfo
- Publication number
- CN112990968A CN112990968A CN202110266421.9A CN202110266421A CN112990968A CN 112990968 A CN112990968 A CN 112990968A CN 202110266421 A CN202110266421 A CN 202110266421A CN 112990968 A CN112990968 A CN 112990968A
- Authority
- CN
- China
- Prior art keywords
- proportion
- lubrication
- order
- recommended
- calculation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005461 lubrication Methods 0.000 title claims abstract description 146
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 222
- 230000003020 moisturizing effect Effects 0.000 claims abstract description 61
- 230000004069 differentiation Effects 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 91
- 238000013528 artificial neural network Methods 0.000 claims description 36
- 238000007726 management method Methods 0.000 claims description 20
- 238000005516 engineering process Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 238000009736 wetting Methods 0.000 claims description 4
- 238000002156 mixing Methods 0.000 description 7
- 239000000047 product Substances 0.000 description 7
- 238000012512 characterization method Methods 0.000 description 2
- 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
- 238000012545 processing Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0222—During e-commerce, i.e. online transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
- G06Q20/102—Bill distribution or payments
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0213—Consumer transaction fees
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0214—Referral reward systems
-
- 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
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a separating and moistening system and a method, wherein the system comprises an order management module, a separating and moistening module and a judging module, wherein the order management module is used for acquiring order information and judging whether the order has red packet subsidies and belongs to recommended purchase or not; the distribution proportion calculation module is used for respectively inputting the order information into the return packet distribution proportion calculation model and/or the sales volume distribution proportion calculation model and/or the recommended distribution proportion calculation model to obtain the return packet distribution proportion and/or the sales volume distribution proportion and/or the recommended distribution proportion; the weight distribution module is used for acquiring a first calculation weight, a second calculation weight and a third calculation weight corresponding to the return red packet lubrication ratio, the sales quantity lubrication ratio and the recommended lubrication ratio; the order separately-moistening determining module is used for obtaining order separately-moistening according to the multiple separately-moistening proportions and the multiple calculating weights; and the payment clearing module is used for distributing the transaction funds according to the order differentiation. The method and the device solve the problem that various information influencing the transaction profit cannot be truly associated in a related moisturizing mode, and the client stickiness is influenced.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a lubrication division system and a lubrication division method.
Background
In the mobile internet era, with the rapid development of electronic commerce technology, a network platform has become an important tool for daily consumption of people. The merchant stores can also sell commodities through the network platform, and the problem of network sales differentiation exists between the merchant stores and the network platform. I.e. the network platform will perform a certain percentage of decimation. Currently, the network sales distribution of the related art generally sets a fixed distribution ratio according to the types of the products sold by the stores, for example, for the product a, the distribution of the platform is 6%, for the product B, the distribution of the platform is 8%, and so on.
When the inventor implements the existing online sales moisturizing method, the inventor finds that the moisturizing method in the related art is relatively mechanical, and various information influencing the profit of the transaction, such as information of different regions, different time periods, whether a red envelope subsidy exists, whether a recommendation exists and the like, cannot be really related, and all of the information can influence the profit of the transaction. For example, trading profits are different between economically developed areas and economically laggard areas, such as trading profits during discounted activities and at regular times; further, for example, the profit of the transaction is different between the one with the red envelope patch and the one without the red envelope patch. The existing lubrication dividing system does not take the influence information into consideration, and the proportion of lubrication dividing cannot be adjusted in time according to the information, so that the viscosity of a client is influenced.
Disclosure of Invention
The main purpose of the present application is to provide a moisturizing system and method, which solve the problem that in the prior art, a moisturizing manner is relatively mechanical, and cannot truly correlate various information that affects the profit of a transaction, so that the moisturizing proportion cannot be timely adjusted according to the information, and the stickiness of a client is affected.
To achieve the above object, according to a first aspect of the present application, a dispensing system is provided.
The system comprises:
the order management module is used for acquiring order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not;
the distribution proportion calculation module is used for respectively inputting the order information into a return packet distribution proportion calculation model and/or a sales distribution proportion calculation model and/or a recommended distribution proportion calculation model to obtain a return packet distribution proportion and/or a sales distribution proportion and/or a recommended distribution proportion corresponding to the order information;
the weight distribution module is used for acquiring a first calculation weight corresponding to the return packet lubrication ratio corresponding to the order information and/or a second calculation weight corresponding to the sales volume lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio;
the order moistening determination module is used for weighting and summing the return red packet moistening proportion and/or the sales quantity moistening proportion and/or the recommended moistening proportion according to the first calculation weight and/or the second calculation weight and/or the third calculation weight to obtain order moistening;
and the payment clearing module is used for distributing the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order differentiation determined by the order differentiation determining module.
Optionally, the system further includes a model training module, configured to train the collected training samples based on a big data technology to obtain a red return packet lubrication ratio calculation model, a sales volume lubrication ratio calculation model, and a recommended lubrication ratio calculation model, where the training samples include orders corresponding to different platforms, different commodity types, different regions, and different purchase periods, and corresponding red return packet lubrication ratios and/or sales volume lubrication ratios and/or recommended lubrication ratios.
Optionally, the model training module includes:
the first training unit is used for taking commodity type information, area information and purchase period information corresponding to an order including the proportion of the red return packet in a training sample as the input of the deep neural network, and taking the corresponding proportion of the red return packet as the output of the deep neural network to train the model to obtain a computation model of the proportion of the red return packet;
the second training unit is used for taking the commodity type information, the area information and the purchasing period information corresponding to the order comprising the sales volume moistening proportion in the training sample as the input of the deep neural network, and taking the corresponding return red packet moistening proportion as the output of the deep neural network to train the model to obtain a sales volume moistening proportion calculation model;
and the third training unit is used for taking the commodity type information, the area information and the purchase period information corresponding to the order including the recommended moisturizing proportion in the training sample as the input of the deep neural network, and taking the corresponding red return packet moisturizing proportion as the output of the deep neural network to train the model to obtain the recommended moisturizing proportion calculation model.
Optionally, the weight assignment module includes:
an acquisition unit for acquiring the area and/or purchase period to which the store belongs and the scale of the store in the order information;
and the weight distribution unit is used for acquiring a first calculation weight corresponding to the returned red packet lubrication ratio and/or a second calculation weight corresponding to the sales quantity lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio corresponding to the order information from the weight distribution table according to the region and/or the purchase time period of the store and the scale of the store, and performing corresponding distribution.
Optionally, the system further includes a model dynamic update module, configured to dynamically adjust the model according to the continuously updated sample to the return red packet lubrication ratio calculation model, the sales volume lubrication ratio calculation model, and the recommended lubrication ratio calculation model.
In order to achieve the above object, according to a second aspect of the present application, there is provided a dispensing method. The method is applied to the moistening system, and comprises the following steps:
the order management module acquires order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not;
according to whether a red envelope subsidy exists or not and whether the red envelope subsidy belongs to recommended purchase or not, the rewarding proportion calculation module respectively inputs order information acquired from the order management module into a red return envelope rewarding proportion calculation model and/or a sales volume rewarding proportion calculation model and/or a recommended rewarding proportion calculation model to obtain a red return envelope rewarding proportion and/or a sales volume rewarding proportion and/or a recommended rewarding proportion corresponding to the order information;
the weight distribution module acquires a first calculation weight corresponding to the returned red packet lubrication proportion and/or a second calculation weight corresponding to the sales volume lubrication proportion and/or a third calculation weight corresponding to the recommended lubrication proportion corresponding to the order information from the weight distribution table;
the order partial-moistening determining module carries out weighted summation on the returned red packet partial-moistening proportion and/or the sales volume partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial-moistening;
and the payment liquidation module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order moisture determined by the order moisture determination module.
Optionally, the method further includes:
the model training module trains collected training samples in advance based on a big data technology to obtain a red return packet lubrication proportion calculation model, a sales volume lubrication proportion calculation model and a recommended lubrication proportion calculation model, wherein the training samples comprise orders corresponding to different platforms, different commodity types, different regions and different purchase periods and corresponding red return packet lubrication proportions and/or sales volume lubrication proportions and/or recommended lubrication proportions.
Optionally, the model training module trains the collected training samples in advance based on a big data technology to obtain a red return packet lubrication ratio calculation model, a sales volume lubrication ratio calculation model, and a recommended lubrication ratio calculation model, and includes:
a first training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order including a proportion of the returned red packet in a training sample as the input of a deep neural network, and takes the corresponding proportion of the returned red packet as the output of the deep neural network to train the model to obtain a calculation model of the proportion of the returned red packet;
a second training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order comprising the sales quantity lubrication ratio in a training sample as the input of a deep neural network, and takes the corresponding return red packet lubrication ratio as the output of the deep neural network to train the model to obtain a sales quantity lubrication ratio calculation model;
and a third training unit in the model training module takes the commodity type information, the area information and the purchase period information corresponding to the order including the recommended moistening proportion in the training sample as the input of the deep neural network, and takes the corresponding returned red packet moistening proportion as the output of the deep neural network to train the model so as to obtain the recommended moistening proportion calculation model.
In order to achieve the above object, according to a third aspect of the present application, there is provided a computer-readable storage medium storing computer instructions for causing the computer to execute the lubrication method of any one of the second aspects.
In order to achieve the above object, according to a fourth aspect of the present application, there is provided an electronic apparatus comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the method of the second aspect.
In the embodiment of the application, the moisturizing system and the moisturizing method comprise an order management module, a moisturizing proportion calculation module, a weight distribution module, an order moisturizing determination module and a payment clearing module. The specific way of achieving the partial lubrication based on the modules is as follows: the order management module acquires order information, wherein the order information comprises a commodity type, a region to which a shop belongs and a purchase time period, and judges whether an order corresponding to the order information has a red envelope subsidy or not and belongs to recommended purchase or not; the grading proportion calculation module respectively inputs the order information acquired from the order management module into a return red packet grading proportion calculation model and/or a sales volume grading proportion calculation model and/or a recommended grading proportion calculation model according to whether the red packet subsidy exists or not and whether the red packet subsidy belongs to recommended purchase or not, so as to obtain a return red packet grading proportion and/or a sales volume grading proportion and/or a recommended grading proportion corresponding to the order information; the weight distribution module acquires a first calculation weight corresponding to the returned red packet lubrication proportion and/or a second calculation weight corresponding to the sales volume lubrication proportion and/or a third calculation weight corresponding to the recommended lubrication proportion corresponding to the order information from the weight distribution table; the order partial-moistening determining module carries out weighted summation on the returned red packet partial-moistening proportion and/or the sales volume partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial-moistening; and the payment liquidation module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order moisture determined by the order moisture determination module. It can be seen that in the embodiment of the application, when determining the platform and the shop, whether the factors influencing the profit of the transaction, such as whether the subsidy of the red envelope exists, whether the subsidy exists, and the sales volume, are considered, and each factor has a corresponding distribution proportion, and then according to the actually corresponding influence factor of each order, the corresponding distribution proportion is selected to perform weighting calculation to finally obtain the platform corresponding to each order and the distribution proportion corresponding to the shop. In addition, the three types of the moisturizing proportions are also changed according to different types of commodities, areas where stores belong and purchasing periods, namely, other influence factors influencing the profit of the transaction are fully considered. In addition, the moisturizing proportion in the embodiment of the application is calculated for each order, and is more reasonable compared with the prior art that the same moisturizing proportion is set only according to the same commodity type. In summary, the embodiment of the application fully considers various information influencing profit trading, and adjusts the lubrication proportion of each order based on the various information influencing profit trading, so that the rationality of lubrication is ensured to a certain extent, and the viscosity of customers is further improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
fig. 1 is a block diagram of a component lubrication system according to an embodiment of the present application;
FIG. 2 is a block diagram of another embodiment of a sub-lubricating system according to the present application;
fig. 3 is a flowchart of a method for distributing moisture according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present application, there is provided a distribution system, as shown in fig. 1, which is applied in a network sales platform, the system including:
the order management module 11 is configured to obtain order information, where the order information includes a commodity type, a region where a store belongs, and a purchase time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not;
the reason why the calculation of the differentiated order is carried out according to the order is that different orders are completed under different prompting conditions or influence factors may be different, for example, some orders are consumed after being recommended by a platform, which belongs to the recommended purchase, namely whether the order is recommended to be a factor influencing the profit of the transaction. For another example, some orders are consumed only by red packages returned by the platform, which belongs to the purchase with red package subsidies, i.e. whether the red package subsidies become a factor influencing the profit of the transaction.
The order information includes a commodity type, a region where the shop belongs, and a purchase time period, and the three kinds of information are exemplarily described, for example, the commodity type may be food, electronic products, home textiles, medicines, and the like; the delivery places of the local value stores belonging to the stores can be different cities, different provinces and the like; the purchase period may be divided into: normal consumption period and discount consumption period, or may be classified into source-abundant period and source-deficient period, etc. The above description is only exemplary, and the actual classification may be adapted, and is not exhaustive here.
In addition, the actual order information includes information other than the type of the product, the area of the store, and the purchase time period, such as whether there is a red envelope subsidy, whether it is a recommended purchase, and the like, which can also be obtained from the order information. Whether the red envelope subsidy exists or not and whether the recommended purchase belongs to can be identified through corresponding labels, for example, the identification with the red envelope subsidy is 1, the identification without the red envelope subsidy is 0, for example, the identification belonging to the recommended purchase is 1, and the identification not belonging to the recommended purchase is 0. In addition, the label can be judged to be added by the following method: and when the order is detected to be the order placed after the platform recommended purchase link, adding the recommended purchase identifier, otherwise, adding the recommended purchase identifier which does not belong. When the order is detected to be paid through the red packet, the red packet subsidy identification can be added, otherwise, the red packet subsidy identification is added.
The blending proportion calculation module 12 is configured to input the order information into a return package blending proportion calculation model and/or a sales volume blending proportion calculation model and/or a recommended blending proportion calculation model respectively to obtain a return package blending proportion and/or a sales volume blending proportion and/or a recommended blending proportion corresponding to the order information;
here, the type of the product, the region of the store, and the purchase period in the order information are input to the return red envelope running proportion calculation model and/or the sales volume running proportion calculation model and/or the recommended running proportion calculation model, respectively. Specifically, if the order does not have a red envelope subsidy and does not belong to recommended purchase, the order only needs to be input into the sales volume running proportion calculation model, if the order has a red envelope subsidy and does not belong to recommended purchase, the order needs to be input into the sales volume running proportion calculation model and the red envelope return running proportion calculation model respectively, if the order does not have a red envelope subsidy and belongs to recommended purchase, the order needs to be input into the sales volume running proportion calculation model and the recommended running proportion calculation model respectively, and if the order has a red envelope subsidy and belongs to recommended purchase, the order needs to be input into the sales volume running proportion calculation model, the red envelope return running proportion calculation model and the red envelope return running proportion calculation model respectively. The return packet lubrication proportion is input into the return packet lubrication proportion calculation model to obtain a return packet lubrication proportion, the sales volume lubrication proportion is input into the sales volume lubrication proportion calculation model to obtain a sales volume lubrication proportion, and the recommended lubrication proportion is input into the recommended lubrication proportion calculation model to obtain a recommended lubrication proportion.
The sales volume and rewarding proportion calculation model, the rewarding and rewarding proportion calculation model and the rewarding and rewarding proportion calculation model are obtained by training collected training samples based on a big data technology. The training samples comprise orders corresponding to different platforms, different commodity types, different regions and different purchasing time periods, and corresponding returned red packet lubrication ratios and/or sales volume lubrication ratios and/or recommended lubrication ratios. It should be noted here that the channel for obtaining the training samples is not limited, but the training samples must be samples that meet the standard market specification in the percentage of the run. Such as selecting a large e-commerce platform on the market today from which to obtain training samples. Each sample does not necessarily have the concepts of the proportion of the returned red packet, the proportion of the sold amount and the recommended proportion of the recommended packet, under the condition, the sample needs to be preprocessed, for example, for the condition that whether a sample order has a red packet subsidy or not and belongs to recommended purchase or not, the sample order is calculated according to the uniform proportion of the recommended packet, if the sample order has the red packet subsidy but does not belong to the recommended purchase, the uniform proportion of the recommended packet is respectively used as the proportion of the returned red packet, the proportion of the sold amount and the proportion of the unrevealed packet of the sample; if the sample order belongs to recommended purchase but has no red envelope subsidy, the unified moistening proportion is respectively used as the recommended moistening proportion and the sales quantity moistening proportion of the sample, and the red envelope moistening proportion is not returned; and if the sample order has the red envelope subsidy and also belongs to the recommended purchase, respectively taking the unified moistening proportion as the red envelope returning moistening proportion, the sales quantity moistening proportion and the recommended moistening proportion of the sample. It should be noted that the sales volume distribution ratio mainly refers to a distribution ratio calculated according to the sales amount of the product, and the distribution ratio is usually determined based on the sales volume, and the sales volume is also a factor that is always present, and therefore, whether or not the distribution ratio is analyzed and explained is not distinguished.
The type of goods in each sample, the area where the shop belongs, and the purchase period need to be characterized before training, for example, each type of goods is represented by n-bit codes, the area of each shop is represented by m-bit codes, and each purchase period is represented by k-bit codes. The specific characterization method is not limited, and the specific values of n, m, and k are not limited. Correspondingly, before the order information is respectively input into the return red packet lubrication proportion calculation model and/or the sales volume lubrication proportion calculation model and/or the recommended lubrication proportion calculation model and input into the models, the characterization processing in the same way is also required.
The weight distribution module 13 is configured to obtain a first calculation weight corresponding to the return packet lubrication ratio corresponding to the order information and/or a second calculation weight corresponding to the sales volume lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio;
each of the moisturizing proportions corresponds to a calculation weight, in this embodiment, different calculation weights are set for each of the moisturizing proportions corresponding to different areas to which the stores belong, different purchase periods corresponding to orders, and different store scales, that is, each of the moisturizing proportions is determined by multiple factors including the area to which the stores belong, the purchase period, and the store scale, these calculation weights may be set in advance and stored in the database (specifically, in the weight distribution table), for example, the database may record "shenzhen, double 11, large stores, the first calculation weight b1, the second calculation weight b2, and the third calculation weight b 3". The scale of the store can be obtained from basic information of the store.
The order moistening determination module 14 is configured to perform weighted summation on the return packet moistening ratio and/or the sales quantity moistening ratio and/or the recommended moistening ratio according to the first calculation weight and/or the second calculation weight and/or the third calculation weight to obtain order moistening;
the specific weighted sum formula is as follows:
the order is divided into a first calculation weight multiplied by the proportion of returned red packet divided, a second calculation weight multiplied by the proportion of sales amount divided, a third calculation weight multiplied by the proportion of recommended divided
In the calculation formula of the order-based running, if the return red envelope running ratio does not exist, the term "second calculation weight × sales volume running ratio" does not exist, and if the recommended running ratio does not exist, the term "third calculation weight × recommended running ratio" does not exist.
And the payment sorting module 15 is used for distributing the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order amortization determined by the order amortization determining module.
And allocating the transaction funds corresponding to the order according to the order diversity determined by the order diversity determination module. In this embodiment, the description will be given by taking the order amortization as the amortization ratio of the platform as an example, and the fund number obtained by multiplying the transaction resource by the order amortization ratio is allocated to the platform commission account, and the remaining fund number is allocated to the store fund account.
The following steps are described with reference to the structure of the system, and specifically include: the order management module 11 acquires order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not; according to whether a red envelope subsidy exists or not and whether the order belongs to recommended purchase or not, the moisturizing proportion calculation module 12 respectively inputs the order information acquired from the order management module 11 into a red return envelope moisturizing proportion calculation model and/or a sales volume moisturizing proportion calculation model and/or a recommended moisturizing proportion calculation model to obtain a red return envelope moisturizing proportion and/or a sales volume moisturizing proportion and/or a recommended moisturizing proportion corresponding to the order information; the weight distribution module 13 obtains a first calculation weight corresponding to the returned red packet lubrication ratio and/or a second calculation weight corresponding to the sales quantity lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio corresponding to the order information from the weight distribution table; the order moistening determination module 14 performs weighted summation on the returned red packet moistening proportion and/or the sales quantity moistening proportion and/or the recommended moistening proportion obtained by the moistening proportion calculation module 12 according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distribution module 13 to obtain order moistening; the payment liquidation module 15 distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order liquidation determined by the order liquidation determination module 14.
From the above description, it can be seen that the moisturizing system in the embodiment of the present application includes an order management module, a moisturizing proportion calculation module, a weight distribution module, an order moisturizing determination module, and a payment clearing module. The specific way of achieving the partial lubrication based on the modules is as follows: the order management module acquires order information, wherein the order information comprises a commodity type, a region to which a shop belongs and a purchase time period, and judges whether an order corresponding to the order information has a red envelope subsidy or not and belongs to recommended purchase or not; the grading proportion calculation module respectively inputs the order information acquired from the order management module into a return red packet grading proportion calculation model and/or a sales volume grading proportion calculation model and/or a recommended grading proportion calculation model according to whether the red packet subsidy exists or not and whether the red packet subsidy belongs to recommended purchase or not, so as to obtain a return red packet grading proportion and/or a sales volume grading proportion and/or a recommended grading proportion corresponding to the order information; the weight distribution module acquires a first calculation weight corresponding to the returned red packet lubrication proportion and/or a second calculation weight corresponding to the sales volume lubrication proportion and/or a third calculation weight corresponding to the recommended lubrication proportion corresponding to the order information from the weight distribution table; the order partial-moistening determining module carries out weighted summation on the returned red packet partial-moistening proportion and/or the sales volume partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial-moistening; and the payment liquidation module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order moisture determined by the order moisture determination module. It can be seen that in the embodiment of the application, when determining the platform and the shop, whether the factors influencing the profit of the transaction, such as whether the subsidy of the red envelope exists, whether the subsidy exists, and the sales volume, are considered, and each factor has a corresponding distribution proportion, and then according to the actually corresponding influence factor of each order, the corresponding distribution proportion is selected to perform weighting calculation to finally obtain the platform corresponding to each order and the distribution proportion corresponding to the shop. In addition, the three types of the moisturizing proportions are also changed according to different types of commodities, areas where stores belong and purchasing periods, namely, other influence factors influencing the profit of the transaction are fully considered. In addition, the moisturizing proportion in the embodiment of the application is calculated for each order, and is more reasonable compared with the prior art that the same moisturizing proportion is set only according to the same commodity type. In summary, the embodiment of the application fully considers various information influencing profit trading, and adjusts the lubrication proportion of each order based on the various information influencing profit trading, so that the rationality of lubrication is ensured to a certain extent, and the viscosity of customers is further improved.
Further, as a supplement or refinement to the above embodiment, as shown in fig. 2, the moisturizing system in the above embodiment further includes a model training module 16, configured to train the collected training samples based on a big data technology to obtain a red return package moisturizing proportion calculation model, a sales volume moisturizing proportion calculation model, and a recommended moisturizing proportion calculation model, where the training samples include orders corresponding to different platforms, different commodity types, different regions, different purchase periods, and corresponding red return package moisturizing proportions and/or sales volume moisturizing proportions and/or recommended moisturizing proportions.
Specifically, as shown in fig. 2, the model training module 16 includes:
the first training unit 161 is configured to use commodity type information, region information, and purchase period information corresponding to an order including a proportion of the bonus package in a training sample as input of the deep neural network, and use the corresponding proportion of the bonus package as output of the deep neural network to perform model training to obtain a model of calculating the proportion of the bonus package;
the second training unit 162 is configured to use commodity type information, region information, and purchase period information corresponding to an order including a sales quantity lubrication ratio in a training sample as input of the deep neural network, and use a corresponding return red packet lubrication ratio as output of the deep neural network to perform model training to obtain a sales quantity lubrication ratio calculation model;
and the third training unit 163 is configured to use the commodity type information, the region information, and the purchase period information corresponding to the order including the recommended moisturizing ratio in the training sample as inputs of the deep neural network, and use the corresponding red-return packet moisturizing ratio as an output of the deep neural network to perform model training to obtain a recommended moisturizing ratio calculation model.
It should be noted that, in the embodiment of the present application, the training samples are subjected to grouping training, and orders containing the proportion of the returned red packet are taken as a group to be trained to obtain a calculation model of the proportion of the returned red packet; taking the orders containing the sales volume partial proportion as a group to train to obtain a sales volume partial proportion calculation model; and taking the orders containing the recommended lubrication proportion as a group to train so as to obtain a recommended lubrication proportion calculation model. The same order may be divided into multiple groups for training at the same time, which is determined according to actual conditions.
In addition, for selection of the deep neural network model, a mainstream network model such as CNN, DBN, DNM, DNN, or the like may be selected. When training, the existing model training tool can be used, and the trained model can be obtained by setting parameters (training end conditions, model accuracy and the like) and input and output of model training.
Further, as shown in fig. 2, the weight assignment module 13 includes:
an acquisition unit 131 configured to acquire an area and/or a purchase period to which the store belongs and a scale of the store in the order information;
the weight distribution unit 132 is configured to obtain a first calculation weight corresponding to the returned red packet moisturizing ratio and/or a second calculation weight corresponding to the sales moisturizing ratio and/or a third calculation weight corresponding to the recommended moisturizing ratio corresponding to the order information from the weight distribution table according to the region and/or the purchase time period to which the store belongs and the scale of the store, and perform corresponding distribution.
Specifically, the first weight and/or the second weight and/or the third weight corresponding to the region and/or the purchase period of the store and the size of the store are found by searching or matching in the database (specifically, in the weight distribution table). What weights are needed to obtain what weights when a query or match is made.
Further, as shown in fig. 2, the system further includes a model dynamic update module 16, configured to perform dynamic adjustment on the model according to the continuously updated sample to the returned red packet lubrication proportion calculation model, the sales volume lubrication proportion calculation model, and the recommended lubrication proportion calculation model.
The training samples can be continuously updated, and the model can be dynamically adjusted on the basis of the updated samples on the basis of the return red packet lubrication proportion calculation model, the sales volume lubrication proportion calculation model and the recommendation lubrication proportion calculation model. Specifically, the timing of the adjustment may be set, for example, every quarter, every other year, or when the new data accumulation exceeds a preset amount.
Further, an embodiment of the present application provides a sub-wetting method, as shown in fig. 3, where the method is applied in the above sub-wetting system, and the method includes the following steps:
s201, an order management module acquires order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; and judging whether the order corresponding to the order information has red envelope subsidies and belongs to recommended purchase.
S202, according to whether the red packet subsidy exists or not and whether the red packet subsidy belongs to recommended purchase or not, the moisturizing proportion calculation module respectively inputs the order information acquired from the order management module into the red packet returning moisturizing proportion calculation model and/or the sales volume moisturizing proportion calculation model and/or the recommended moisturizing proportion calculation model to obtain the red packet returning moisturizing proportion and/or the sales volume moisturizing proportion and/or the recommended moisturizing proportion corresponding to the order information.
S203, the weight distribution module obtains a first calculation weight corresponding to the red return packet lubrication ratio corresponding to the order information and/or a second calculation weight corresponding to the sales quantity lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio from the weight distribution table.
And S204, the order partial-moistening determining module performs weighted summation on the returned red packet partial-moistening proportion and/or the sales quantity partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial moistening.
S205, the payment sorting module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order sorting determined by the order sorting determining module.
As can be seen from the above description, the moisturizing method in the embodiment of the present application includes an order management module, a moisturizing proportion calculation module, a weight distribution module, an order moisturizing determination module, and a payment clearing module. The specific way of achieving the partial lubrication based on the modules is as follows: the order management module acquires order information, wherein the order information comprises a commodity type, a region to which a shop belongs and a purchase time period, and judges whether an order corresponding to the order information has a red envelope subsidy or not and belongs to recommended purchase or not; the grading proportion calculation module respectively inputs the order information acquired from the order management module into a return red packet grading proportion calculation model and/or a sales volume grading proportion calculation model and/or a recommended grading proportion calculation model according to whether the red packet subsidy exists or not and whether the red packet subsidy belongs to recommended purchase or not, so as to obtain a return red packet grading proportion and/or a sales volume grading proportion and/or a recommended grading proportion corresponding to the order information; the weight distribution module acquires a first calculation weight corresponding to the returned red packet lubrication proportion and/or a second calculation weight corresponding to the sales volume lubrication proportion and/or a third calculation weight corresponding to the recommended lubrication proportion corresponding to the order information from the weight distribution table; the order partial-moistening determining module carries out weighted summation on the returned red packet partial-moistening proportion and/or the sales volume partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial-moistening; and the payment liquidation module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order moisture determined by the order moisture determination module. It can be seen that in the embodiment of the application, when determining the platform and the shop, whether the factors influencing the profit of the transaction, such as whether the subsidy of the red envelope exists, whether the subsidy exists, and the sales volume, are considered, and each factor has a corresponding distribution proportion, and then according to the actually corresponding influence factor of each order, the corresponding distribution proportion is selected to perform weighting calculation to finally obtain the platform corresponding to each order and the distribution proportion corresponding to the shop. In addition, the three types of the moisturizing proportions are also changed according to different types of commodities, areas where stores belong and purchasing periods, namely, other influence factors influencing the profit of the transaction are fully considered. In addition, the moisturizing proportion in the embodiment of the application is calculated for each order, and is more reasonable compared with the prior art that the same moisturizing proportion is set only according to the same commodity type. In summary, the embodiment of the application fully considers various information influencing profit trading, and adjusts the lubrication proportion of each order based on the various information influencing profit trading, so that the rationality of lubrication is ensured to a certain extent, and the viscosity of customers is further improved.
Further, in addition to or as a refinement of the above method embodiment, the method further comprises:
the model training module trains collected training samples in advance based on a big data technology to obtain a red return packet lubrication proportion calculation model, a sales volume lubrication proportion calculation model and a recommended lubrication proportion calculation model, wherein the training samples comprise orders corresponding to different platforms, different commodity types, different regions and different purchase periods and corresponding red return packet lubrication proportions and/or sales volume lubrication proportions and/or recommended lubrication proportions.
The model training module is used for training collected training samples in advance based on big data technology to obtain a red return packet lubrication proportion calculation model, a sales volume lubrication proportion calculation model and a recommended lubrication proportion calculation model, and comprises the following steps:
a first training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order including a proportion of the returned red packet in a training sample as the input of a deep neural network, and takes the corresponding proportion of the returned red packet as the output of the deep neural network to train the model to obtain a calculation model of the proportion of the returned red packet;
a second training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order comprising the sales quantity lubrication ratio in a training sample as the input of a deep neural network, and takes the corresponding return red packet lubrication ratio as the output of the deep neural network to train the model to obtain a sales quantity lubrication ratio calculation model;
and a third training unit in the model training module takes the commodity type information, the area information and the purchase period information corresponding to the order including the recommended moistening proportion in the training sample as the input of the deep neural network, and takes the corresponding returned red packet moistening proportion as the output of the deep neural network to train the model so as to obtain the recommended moistening proportion calculation model.
Further, "obtaining a first calculation weight corresponding to the returned red packet running proportion and/or a second calculation weight corresponding to the sales volume running proportion and/or a third calculation weight corresponding to the recommended running proportion corresponding to the order information" specifically includes: acquiring the area and/or purchase time period of the shop in the order information and the scale of the shop; and acquiring a first calculation weight corresponding to the returned red packet lubrication ratio and/or a second calculation weight corresponding to the sales quantity lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio corresponding to the order information from the distribution table according to the region and/or the purchase period of the store and the scale of the store, and performing corresponding distribution.
Furthermore, the model can be dynamically adjusted according to the continuously updated samples on the basis of the returned red packet lubrication proportion calculation model, the sales volume lubrication proportion calculation model and the recommended lubrication proportion calculation model.
It should be noted that the implementation of the correlation between the different embodiments may be mutually referenced, that the steps illustrated in the flow chart of the figure may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flow chart, in some cases the steps illustrated or described may be performed in an order different than here.
According to an embodiment of the present application, there is further provided a computer-readable storage medium storing computer instructions for causing the computer to execute the method of the foregoing method embodiment.
According to an embodiment of the present application, there is also provided an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the method of the above method embodiments.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A system for dispensing moisture, the system comprising:
the order management module is used for acquiring order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not;
the distribution proportion calculation module is used for respectively inputting the order information into a return packet distribution proportion calculation model and/or a sales distribution proportion calculation model and/or a recommended distribution proportion calculation model to obtain a return packet distribution proportion and/or a sales distribution proportion and/or a recommended distribution proportion corresponding to the order information;
the weight distribution module is used for acquiring a first calculation weight corresponding to the return packet lubrication ratio corresponding to the order information and/or a second calculation weight corresponding to the sales volume lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio;
the order moistening determination module is used for weighting and summing the return red packet moistening proportion and/or the sales quantity moistening proportion and/or the recommended moistening proportion according to the first calculation weight and/or the second calculation weight and/or the third calculation weight to obtain order moistening;
and the payment clearing module is used for distributing the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order differentiation determined by the order differentiation determining module.
2. The lubrication system according to claim 1, further comprising a model training module, configured to train collected training samples based on a big data technology to obtain a red return package lubrication proportion calculation model, a sales volume lubrication proportion calculation model, and a recommended lubrication proportion calculation model, where the training samples include orders corresponding to different platforms, different commodity types, different regions, and different purchase periods, and corresponding red return package lubrication proportions and/or sales volume lubrication proportions and/or recommended lubrication proportions.
3. The lubrication system according to claim 2, wherein the model training module comprises:
the first training unit is used for taking commodity type information, area information and purchase period information corresponding to an order including the proportion of the red return packet in a training sample as the input of the deep neural network, and taking the corresponding proportion of the red return packet as the output of the deep neural network to train the model to obtain a computation model of the proportion of the red return packet;
the second training unit is used for taking the commodity type information, the area information and the purchasing period information corresponding to the order comprising the sales volume moistening proportion in the training sample as the input of the deep neural network, and taking the corresponding return red packet moistening proportion as the output of the deep neural network to train the model to obtain a sales volume moistening proportion calculation model;
and the third training unit is used for taking the commodity type information, the area information and the purchase period information corresponding to the order including the recommended moisturizing proportion in the training sample as the input of the deep neural network, and taking the corresponding red return packet moisturizing proportion as the output of the deep neural network to train the model to obtain the recommended moisturizing proportion calculation model.
4. The lubrication system according to claim 1, wherein the weight assignment module comprises:
an acquisition unit for acquiring the area and/or purchase period to which the store belongs and the scale of the store in the order information;
and the weight distribution unit is used for acquiring a first calculation weight corresponding to the returned red packet lubrication ratio and/or a second calculation weight corresponding to the sales quantity lubrication ratio and/or a third calculation weight corresponding to the recommended lubrication ratio corresponding to the order information from the weight distribution table according to the region and/or the purchase time period of the store and the scale of the store, and performing corresponding distribution.
5. The partial lubrication system according to claim 1, further comprising a model dynamic update module for performing dynamic adjustment of the model according to the continuously updated samples on the returned red packet partial lubrication proportion calculation model, the sales volume partial lubrication proportion calculation model and the recommended partial lubrication proportion calculation model.
6. A sub-wetting method is applied to the sub-wetting system, and comprises the following steps:
the order management module acquires order information, wherein the order information comprises a commodity type, a region where a shop belongs and a purchasing time period; judging whether the order corresponding to the order information has red envelope subsidies and is recommended to purchase or not;
according to whether a red envelope subsidy exists or not and whether the red envelope subsidy belongs to recommended purchase or not, the rewarding proportion calculation module respectively inputs order information acquired from the order management module into a red return envelope rewarding proportion calculation model and/or a sales volume rewarding proportion calculation model and/or a recommended rewarding proportion calculation model to obtain a red return envelope rewarding proportion and/or a sales volume rewarding proportion and/or a recommended rewarding proportion corresponding to the order information;
the weight distribution module acquires a first calculation weight corresponding to the returned red packet lubrication proportion and/or a second calculation weight corresponding to the sales volume lubrication proportion and/or a third calculation weight corresponding to the recommended lubrication proportion corresponding to the order information from the weight distribution table;
the order partial-moistening determining module carries out weighted summation on the returned red packet partial-moistening proportion and/or the sales volume partial-moistening proportion and/or the recommended partial-moistening proportion obtained by the partial-moistening proportion calculating module according to the first calculation weight and/or the second calculation weight and/or the third calculation weight obtained by the weight distributing module to obtain order partial-moistening;
and the payment liquidation module distributes the transaction funds into the fund account corresponding to the shop and the platform commission account corresponding to the system according to the order moisture determined by the order moisture determination module.
7. The method of claim 6, further comprising:
the model training module trains collected training samples in advance based on a big data technology to obtain a red return packet lubrication proportion calculation model, a sales volume lubrication proportion calculation model and a recommended lubrication proportion calculation model, wherein the training samples comprise orders corresponding to different platforms, different commodity types, different regions and different purchase periods and corresponding red return packet lubrication proportions and/or sales volume lubrication proportions and/or recommended lubrication proportions.
8. The method according to claim 7, wherein the model training module trains the collected training samples in advance based on big data technology to obtain a returned red packet lubrication proportion calculation model, a sales volume lubrication proportion calculation model and a recommended lubrication proportion calculation model, and comprises:
a first training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order including a proportion of the returned red packet in a training sample as the input of a deep neural network, and takes the corresponding proportion of the returned red packet as the output of the deep neural network to train the model to obtain a calculation model of the proportion of the returned red packet;
a second training unit in the model training module takes commodity type information, area information and purchase period information corresponding to an order comprising the sales quantity lubrication ratio in a training sample as the input of a deep neural network, and takes the corresponding return red packet lubrication ratio as the output of the deep neural network to train the model to obtain a sales quantity lubrication ratio calculation model;
and a third training unit in the model training module takes the commodity type information, the area information and the purchase period information corresponding to the order including the recommended moistening proportion in the training sample as the input of the deep neural network, and takes the corresponding returned red packet moistening proportion as the output of the deep neural network to train the model so as to obtain the recommended moistening proportion calculation model.
9. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 6 to 8.
10. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to cause the at least one processor to perform the method of any one of claims 6 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110266421.9A CN112990968A (en) | 2021-03-11 | 2021-03-11 | Lubrication dividing system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110266421.9A CN112990968A (en) | 2021-03-11 | 2021-03-11 | Lubrication dividing system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990968A true CN112990968A (en) | 2021-06-18 |
Family
ID=76336389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110266421.9A Pending CN112990968A (en) | 2021-03-11 | 2021-03-11 | Lubrication dividing system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990968A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724003A (en) * | 2021-08-27 | 2021-11-30 | 猪八戒股份有限公司 | Order transaction data based moisturizing method, electronic device and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157084A (en) * | 2015-01-15 | 2016-11-23 | 鸿宇电子商务股份有限公司 | There is networked shopping system and the implementation thereof of the mechanism of sharing in the benefit |
| CN106803201A (en) * | 2017-01-22 | 2017-06-06 | 杭州纳戒科技有限公司 | Instant method and system of sharing in the benefit |
| CN106934656A (en) * | 2017-03-06 | 2017-07-07 | 横琴国际知识产权交易中心有限公司 | A kind of electric business plateform system and method for sharing in the benefit |
| CN108205777A (en) * | 2017-11-27 | 2018-06-26 | 吴树贤 | It is a kind of to be sold system of sharing in the benefit |
| CN111882375A (en) * | 2020-06-15 | 2020-11-03 | 浙江吉利控股集团有限公司 | Method, system, equipment and medium for separating and moistening travel of special vehicle |
-
2021
- 2021-03-11 CN CN202110266421.9A patent/CN112990968A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106157084A (en) * | 2015-01-15 | 2016-11-23 | 鸿宇电子商务股份有限公司 | There is networked shopping system and the implementation thereof of the mechanism of sharing in the benefit |
| CN106803201A (en) * | 2017-01-22 | 2017-06-06 | 杭州纳戒科技有限公司 | Instant method and system of sharing in the benefit |
| CN106934656A (en) * | 2017-03-06 | 2017-07-07 | 横琴国际知识产权交易中心有限公司 | A kind of electric business plateform system and method for sharing in the benefit |
| CN108205777A (en) * | 2017-11-27 | 2018-06-26 | 吴树贤 | It is a kind of to be sold system of sharing in the benefit |
| CN111882375A (en) * | 2020-06-15 | 2020-11-03 | 浙江吉利控股集团有限公司 | Method, system, equipment and medium for separating and moistening travel of special vehicle |
Non-Patent Citations (1)
| Title |
|---|
| 雎岚;涂志勇;: "条件利润佣金模型及对我国保险经纪业务佣金支付模式的启示", 经济科学, no. 01, pages 95 - 105 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113724003A (en) * | 2021-08-27 | 2021-11-30 | 猪八戒股份有限公司 | Order transaction data based moisturizing method, electronic device and readable storage medium |
| CN113724003B (en) * | 2021-08-27 | 2023-12-08 | 猪八戒股份有限公司 | Order transaction data-based moistening method, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389431B (en) | Method and device for distributing coupons, electronic equipment and readable storage medium | |
| Kumar et al. | Customer relationship management: A databased approach | |
| Mostard et al. | Forecasting demand for single-period products: A case study in the apparel industry | |
| CN111445134B (en) | Commodity sales prediction method, commodity sales prediction apparatus, computer device, and storage medium | |
| CN103578010A (en) | Method and device generating flow quality comparison parameters and advertisement billing method | |
| CN107798607A (en) | Asset Allocation strategy acquisition methods, device, computer equipment and storage medium | |
| WO2011109781A4 (en) | Payment method decision engine | |
| TWI652639B (en) | Recommended system and method of product promotion combination | |
| CN102156932A (en) | Prediction method and device for secondary purchase intention of customers | |
| US20140229233A1 (en) | Consumer spending forecast system and method | |
| JP2013012168A (en) | Sales promoting plan support system and its program | |
| JP2018139036A (en) | Analysis device | |
| CN106920119A (en) | The evaluation method and device of a kind of user's value | |
| CN108428153A (en) | Strategy adjusting method, server and the Developing Tactics system of presell commodity | |
| WO2017119952A1 (en) | Consumer decision tree generation system | |
| CN109213936A (en) | product search method and device | |
| CN107358472A (en) | Data processing method and device | |
| Kleinsorge et al. | Evaluating logistics decisions | |
| CN111091409B (en) | Client tag determination method and device and server | |
| CN112200526A (en) | Order output method and device, computer equipment and computer readable storage medium | |
| CN111445133A (en) | Material management method and device, computer equipment and storage medium | |
| Shi | A theoretical analysis of endogenous and exogenous switching costs | |
| CN112990968A (en) | Lubrication dividing system and method | |
| CN111768216A (en) | Order price adjustment method, device, server and storage medium | |
| CN111507779A (en) | Method and device for grading commodities |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231013 Address after: Room 1001, 4th Floor, Incubation Building, Hainan Ecological Software Park, Old Town High-tech Industry Demonstration Zone, Chengmai County, Hainan Province, 571900 Applicant after: Hainan Zouzhong Hongbao Technology Co.,Ltd. Address before: 100089 room 248, courtyard 17-27, 164 Beiqing Road, Haidian District, Beijing Applicant before: Beijing swish Technology Co.,Ltd. |