CN107358472A - Data processing method and device - Google Patents

Data processing method and device Download PDF

Info

Publication number
CN107358472A
CN107358472A CN201710587974.8A CN201710587974A CN107358472A CN 107358472 A CN107358472 A CN 107358472A CN 201710587974 A CN201710587974 A CN 201710587974A CN 107358472 A CN107358472 A CN 107358472A
Authority
CN
China
Prior art keywords
commodity
mrow
represent
order
halo effect
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
Application number
CN201710587974.8A
Other languages
Chinese (zh)
Inventor
李聚信
张蔷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Original Assignee
Beijing Jingdong Century Trading Co Ltd
Beijing Jingdong Shangke Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Jingdong Century Trading Co Ltd, Beijing Jingdong Shangke Information Technology Co Ltd filed Critical Beijing Jingdong Century Trading Co Ltd
Priority to CN201710587974.8A priority Critical patent/CN107358472A/en
Publication of CN107358472A publication Critical patent/CN107358472A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0203—Market surveys; Market polls

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of data processing method and device, it is related to field of information processing.Method therein includes：According to the History Order data of commodity, calculate commodity by proxy indicator, wherein, commodity represent that user buys the probability that other commodity substitute purchase commodity by proxy indicator；According to the follow-up order data of the system head single users of purchase commodity, the halo effect indexs of commodity is calculated, wherein, the halo effect index expression commodity of commodity attract the ability that user buys other commodity；According to the halo effect index by proxy indicator and commodity of the historic sales data of commodity, commodity, the effectiveness of commodity is calculated.It is achieved thereby that the quantization for commodity effectiveness, and then more objectively weigh the value of commodity.

Description

Data processing method and device
Technical field
The present invention relates to field of information processing, more particularly to a kind of data processing method and device.
Background technology
In retail trade, commodity are the bridges for connecting consumer and retailer.Which type of commodity is sold, determines zero The targeted user population of business is sold, determines the profitability of retailer, determine the rival of retailer, final decision zero Sell the development prospect of business.
With the fast development of ecommerce, the commodity that consumer can select are also more and more, in face of such magnanimity Commodity, retailer how the quantization for commodity effectiveness, in order to weigh the value of commodity, so as to select that there are certain values Commodity are particularly important.
In the prior art, pin personnel are adopted the commodity of suitable target market demand is selected from supply market, it is necessary to by right The observation of historical data, then by the judgement of business, the introducing of commodity is determined by the sequence and rule of some indexs, kept Or remove.
The content of the invention
Inventor study find, in the prior art by Concerned Industry index, competitor's platform scale, price sales volume, itself The data such as the sales situation of commodity can only make rough judgement to commodity effectiveness.By the sales volume of commodity, sales volume, gross profit and Cost etc. can not quantify the incremental value contribution after commodity introduce, can not accurately instruct industry as the index for weighing commodity Which commodity business personnel, which manage, is only reasonably.For selection, the true value of commodity is that commodity are brought after pickup Incremental value.The data such as the sale of commodity, price can only reflect the history performance of commodity, for new product and consumer need Ask to reflect well.These indexs of sales volume, sales volume can only reflect the current state of itself of commodity, fail to consider commodity with Relation between commodity, for example can play the role of to drive to the sale of other commodity when New Arrivals or substitute.
The technical problem that the present invention solves is how to realize the quantization for commodity effectiveness, so as to more objective Weigh the value of commodity.
One side according to embodiments of the present invention, there is provided a kind of data processing method, including：According to the history of commodity Order data, calculate commodity by proxy indicator, wherein, commodity are represented that user buys other commodity and replaced by proxy indicator Buy the probability for buying commodity on behalf；According to the follow-up order data of the system head single users of purchase commodity, the halo effects of commodity is calculated Index, wherein, the halo effect index expression commodity of commodity attract the ability that user buys other commodity；According to the history of commodity Sales data, the halo effect index by proxy indicator and commodity of commodity, calculate the effectiveness of commodity.
In one embodiment, according to the historic sales data of commodity, commodity by proxy indicator and the light of commodity Toroidal effect index, calculating the effectiveness of commodity includes：According to the irreplaceability index that commodity are calculated by proxy indicator of commodity； By the weighted sum of the sales volume of commodity and the profit of commodity, commodity can not be by the halo effect index of proxy indicator, commodity It is multiplied, the effectiveness of commodity is calculated.
In one embodiment, the effectiveness of commodity is calculated using equation below：
Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i's By proxy indicator,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weight of profit Value.
In one embodiment, according to the History Order data of commodity, being included by proxy indicator for commodity is calculated：According to History Order data of the user in continuous order pair, user are calculated in continuous order pair, from commodity replacing to another commodity For property consumption；By all users in all continuous orders pair, from commodity to the alternative consumption of other each commodity plus and, Make ratio with the sales volume of commodity, be calculated commodity by proxy indicator.
In one embodiment, the alternative consumption from commodity A to commodity B is calculated using equation below：
Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1ARepresent commodity A in the first order The amount of money, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, the first order and second Order is the continuous order of same user.
In one embodiment, using equation below calculating commodity A by proxy indicator：
Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
In one embodiment, according to the follow-up order data of the system head single users of purchase commodity, the light of commodity is calculated Toroidal effect index includes：It is first using the follow-up order amount of money for the system head single users for buying commodity, and the system of purchase commodity The follow-up order of single user calculates the halo effect values of commodity relative to the time of single commodity under first；Utilize the light of commodity Toroidal effect is worth, and the sales volume of commodity, calculates the halo effect index of commodity.
In one embodiment, the halo effect that commodity i is calculated using equation below is worth：
Wherein, hiRepresent commodity i halo effect value, the follow-up order of single commodity i user under Sale is represented first The amount of money, γ represent decay factor, t represent first under single commodity i user follow-up order relative under first single commodity i when Between.
In one embodiment, commodity i halo effect index is calculated using equation below：
Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
In one embodiment, this method also includes：Decision variable is established for each commodity；Define the constraint of decision variable Condition；The summation of the effectiveness of each commodity and the difference of cost is defined as decision objective；Selected by combined optimization method Product decision-making.
In one embodiment, the constraints of decision variable is defined using equation below：
Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the business currently managed Product quantity, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, and i.A represents commodity i attributes A Value, i.B represents commodity i attributes B value, and (a, b) represents all property value sets, Na,bRepresent that property value set (a, b) is right The minimum commodity amount answered.
Other side according to embodiments of the present invention, there is provided a kind of data processing equipment, including：By proxy indicator Computing unit, be configured as the History Order data according to commodity, calculate commodity by proxy indicator, wherein, the quilt of commodity Proxy indicator represents that user buys the probability that other commodity substitute purchase commodity；Halo effect indicator calculating unit, is configured For the follow-up order data of the system head single users according to purchase commodity, the halo effect indexs of commodity is calculated, wherein, commodity Halo effect index expression commodity attract the ability that user buys other commodity；Commodity effectiveness computing unit, is configured as basis The historic sales data of commodity, the halo effect index by proxy indicator and commodity of commodity, calculate the effectiveness of commodity.
In one embodiment, commodity effectiveness computing unit is configured as：Business is calculated by proxy indicator according to commodity The irreplaceability index of product；By the weighted sum of the sales volume of commodity and the profit of commodity, commodity can not by proxy indicator, The halo effect index of commodity is multiplied, and the effectiveness of commodity is calculated.
In one embodiment, the effectiveness of commodity is calculated using equation below：
Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i's By proxy indicator,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weight of profit Value.
In one embodiment, it is configured as by proxy indicator computing unit：According to user in continuous order pair History Order data, user are calculated in continuous order pair, from commodity to the alternative consumption of another commodity；All users are existed All continuous order centerings, from commodity to the alternative consumption of other each commodity plus and, make ratio with the sales volume of commodity, count Calculate obtain commodity by proxy indicator.
In one embodiment, it is configured as by proxy indicator computing unit：Using equation below calculate from commodity A to Commodity B alternative consumption：
Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1ARepresent commodity A in the first order The amount of money, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, the first order and second Order is the continuous order of same user.
In one embodiment, it is configured as by proxy indicator computing unit：Commodity A quilt is calculated using equation below Proxy indicator：
Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
In one embodiment, halo effect indicator calculating unit is configured as：It is alone using the system head for buying commodity The follow-up order amount of money at family, and the system head single users of purchase commodity follow-up order relative under first single commodity when Between, the halo effect for calculating commodity is worth；It is worth using the halo effect of commodity, and the sales volume of commodity, calculate commodity Halo effect index.
In one embodiment, halo effect indicator calculating unit is configured as：Commodity i light is calculated using equation below Toroidal effect is worth：
Wherein, hiRepresent commodity i halo effect value, the follow-up order of single commodity i user under Sale is represented first The amount of money, γ represent decay factor, t represent first under single commodity i user follow-up order relative under first single commodity i when Between.
In one embodiment, halo effect indicator calculating unit is configured as：Commodity i light is calculated using equation below Toroidal effect index：
Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
In one embodiment, the data processing equipment also includes selection decision package, is configured as：Built for each commodity Vertical decision variable；Define the constraints of decision variable；The summation of the effectiveness of each commodity and the difference of cost is defined as determining Plan target；Selection decision-making is carried out by combined optimization method.
In one embodiment, data selection decision package is configured as：The pact of decision variable is defined using equation below Beam condition：
Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the business currently managed Product quantity, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, and i.A represents commodity i attributes A Value, i.B represents commodity i attributes B value, and (a, b) represents all property value sets, Na,bRepresent that property value set (a, b) is right The minimum commodity amount answered.
Another aspect according to embodiments of the present invention, there is provided a kind of data processing equipment, including：Memory；And The processor of memory is coupled to, processor is configured as the instruction based on storage in memory, performed at foregoing data Reason method.
Another aspect according to embodiments of the present invention, there is provided a kind of computer-readable recording medium, it is computer-readable Storage medium is stored with computer instruction, and instruction realizes foregoing data processing method when being executed by processor.
Data processing method provided by the invention, the quantization for commodity effectiveness can be realized, so as to more objectively weigh Measure the value of commodity.
By referring to the drawings to the present invention exemplary embodiment detailed description, further feature of the invention and its Advantage will be made apparent from.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 shows the schematic flow sheet of one embodiment of data processing method of the present invention.
Fig. 2 shows the schematic flow sheet of another embodiment of data processing method of the present invention.
Fig. 3 shows the system structure diagram of one embodiment of selection Optimized model of the present invention.
Fig. 4 shows the structural representation of one embodiment of data processing equipment of the present invention.
Fig. 5 shows the structural representation of another embodiment of data processing equipment of the present invention.
Fig. 6 shows the structural representation of another embodiment of data processing equipment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Below Description only actually at least one exemplary embodiment is illustrative, is never used as to the present invention and its application or makes Any restrictions.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise Lower obtained all other embodiment, belongs to the scope of protection of the invention.
The data processing method that Fig. 1 introduces one embodiment of the invention is combined first.
Fig. 1 shows the schematic flow sheet of the data processing method of one embodiment of the invention.As shown in figure 1, the embodiment Data processing method include：
Step S102, according to the History Order data of commodity, calculate commodity by proxy indicator.Wherein, the quilt of commodity Proxy indicator represents that user buys the probability that other commodity substitute purchase commodity.
A kind of optional embodiment is, according to History Order data of the user in continuous order pair, to calculate user and exist Continuous order centering, from commodity to the alternative consumption of another commodity；By all users in all continuous orders pair, from commodity To other each commodity alternative consumption plus and, make ratio with the sales volume of commodity, be calculated commodity by alternative finger Mark.
Can be according to replacing in first latter two order of same user in the History Order data of commodity by proxy indicator Calculated for property consumption.For example, user have purchased commodity A in the first order, have purchased in next order (the second order) Commodity B, then consumption of the user in the first order on commodity A into the second order commodity B shift amount of money S (A, B), for Spending amount of the family on commodity A be multiplied by commodity B in order 2 sales volume accounting (i.e. in the second order commodity B for for For commodity A accounting).Equation below (1) can be utilized to calculate the alternative consumption from commodity A to commodity B：
Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1ARepresent commodity A in the first order The amount of money, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, the first order and second Order is the continuous order of same user.
It is then possible to which the alternative consumption that the History Order by each user is calculated takes together, commodity are calculated Between it is alternative.For example, using equation below (2) calculating commodity A by proxy indicator：
Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
Step S104, according to the follow-up order data of the system head single users of purchase commodity, calculate the halo effects of commodity Index.Wherein, the halo effect index expression commodity of commodity attract the ability that user buys other commodity.
A kind of optional embodiment is, using the follow-up order data amount of money for the system head single users for buying commodity, with And the follow-up order of the system head single users of purchase commodity calculates the halo effect of commodity relative to the time of single commodity under first Value；It is worth using the halo effect of commodity, and the sales volume of commodity, calculates the halo effect index of commodity.
For example, according to the follow-up order data of the system head single users of purchase commodity, for being placed an order first in same category And first single commodity bundle i containing commodity user, it is believed that commodity i brings the user, therefore the follow-up order amount of money of the user is pressed Certain proportion is shared on commodity i, and the halo effect as the commodity is worth, and is designated as hi.Equation below (3) can be utilized to calculate Commodity i halo effect value：
hi=∑New user∑OrderSale*e-γt (3)
Wherein, hiRepresent commodity i halo effect value；Sale be first under single commodity i user follow-up order gold Volume；γ represents decay factor, such as can be with value 0.5；The follow-up order of single commodity i user is relative to head under t is represented first Single commodity i time under secondary, can be in units of year
It is then possible to commodity i halo effect index is calculated using equation below：
Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
Step S106, according to the halo effect by proxy indicator and commodity of the historic sales data of commodity, commodity Index, calculate the effectiveness of commodity.
A kind of optional embodiment is, according to the irreplaceability index that commodity are calculated by proxy indicator of commodity； By the weighted sum of the sales volume of commodity and the profit of commodity, commodity can not be by the halo effect index of proxy indicator, commodity It is multiplied, the effectiveness of commodity is calculated.
For example, the effectiveness of commodity effectiveness function (5) calculating commodity can be utilized：
Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i's By proxy indicator,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weight of profit Value, α1And α2Value is nonnegative value.
In above-described embodiment, according to the History Order data of commodity, calculate commodity by proxy indicator；Buy commodity The follow-up order data of system head single users, calculate the halo effect index of commodity；Finally according to the historic sales data of commodity, The halo effect index by proxy indicator and commodity of commodity, calculate the effectiveness of commodity.It is achieved thereby that imitated for commodity Quantization, it can more objectively weigh the value of commodity.Meanwhile the commodity effectiveness that the present embodiment is calculated, Neng Gouliang The influence and the consumption demand of consumer that good reflection new product is stimulated consumption, while consider the relation between commodity and commodity, The effectiveness of objective, quantization commodity helps more comprehensively, accurately to understand the incremental value brought after commodity introduce, and then instructs Business personnel carries out the selection operation of commodity.
The data processing method of another embodiment of the present invention is introduced with reference to Fig. 2.
Fig. 2 shows the schematic flow sheet of the data processing method of another embodiment of the present invention.In the embodiment shown in Fig. 1 On the basis of, the data processing method of the present embodiment also includes：
Step S208, decision variable is established for each commodity.
For example, to each commodity i, decision variable X is establishedi, obtain a decision variable set.
Step S210, define the constraints of decision variable.
For example, commodity restocking, the number constraint condition of undercarriage can be defined, and consumer is for item property demand Covering constraint.Respectively as shown in formula (6), (7), (8)：
Σi∈SXi≤(1+ub)·N (6)
Σi∈SXi≥(1-Ib)·N (7)
Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the business currently managed Product quantity, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, span be generally (0, 1), such as ub and lb can be respectively set to 30%, 15%.I.A represents commodity i attributes A value, and i.B represents commodity i category Property B value, (a, b) represents all property value set, Na,bRepresent minimum commodity amount corresponding to property value set (a, b).
Step S212, the summation of the effectiveness of each commodity and the difference of cost is defined as decision objective.
For example, give weight parameter α in user1And α2On the basis of, the object definition of selection can be maximized total Effectiveness and minimum selection cost, i.e. object function is max ∑siU (i)-C (i), wherein CiFor commodity i selection cost.Wherein, Total utility is the integrated value of sales volume and profit, can be by setting different weight parameters, and the target for defining selection is to maximize Sales volume, maximize profit or maximize resultant effect.
Step S214, selection decision-making is carried out by combined optimization method.
For example, the operational research optimization method such as Combinatorial Optimization or integer programming can be selected to be solved, and return to selection knot Fruit.Solve XiValue, if Xi=1, then manage the commodity；If Xi=0, then the commodity are not managed.
In above-described embodiment, the value of utility of commodity is calculated first with commodity effectiveness function, is then based on commodity effectiveness Value establishes selection Optimized model.So as to propose a kind of optimal selection method of target, introducing, cost is minimum and meet client Maximum revenue is realized in the case of demand, so as to instruct businessman to carry out the upper undercarriage decision-making of commodity.
The system implementations of selection Optimized model are introduced with reference to Fig. 3.
Fig. 3 shows the system structure diagram of the selection Optimized model of one embodiment of the invention.As shown in figure 3, this is System can calculate the effectiveness of commodity, and the setting of the role based on commodity category and achievement growth side with commodity in use utility function To providing selection decision recommendation using selection Optimized model.
The system mainly includes four modules：Input data module, parameter module, nucleus module, subscriber interface module.
The data of input data module input can include item property data, transaction data, by proxy indicator and light Toroidal effect index.Wherein, item property data can include the information such as the brands of each commodity, the place of production, pattern, size, weight. Transaction data module can include commodity price, peel off advertisement with show position factor adjustment after sales volume data, sales volume, cost, Profit, etc. factor data.It can be calculated by proxy indicator and halo effect index according to method previously.
The data of parameter module input can include selection parameter and consumer demand structural parameters.Selection parameter refers to use Goal-setting of the family to category, including the weight of sales volume and profit, selection ratio (such as previously mentioned ub, lb) etc., typically It can be formulated according to category role and performance objectives.Consumer demand structure is the item property list sorted by importance degree, Reflection is priority of the item property to consumer's shopping decision-making.The front two attribute most paid close attention to such as milk category, consumer It is brand and the place of production (such as import or domestic) respectively, the sequence on attribute can wait by inquiry to draw.Consumer demand What structural parameters referred to can most meet property value set corresponding to the commodity of consumer demand.Accounted for always for example, we can choose All properties set is as parameter corresponding to the commodity of sales volume 95%.In order to meet consumer demand, in all combinations, Corresponding commodity amount is required to reach certain standard., can also be with maximum contention depending on the standard may be referred to market environment The commodity amount of opponent is as the benchmark compared.
Nucleus module includes utility computing module, optimal selection decision-making module and selection effect simulation module three parts.Effect The incremental value after commodity introduce is weighed by commodity effectiveness function with computing module.Optimal selection decision-making module can pass through one Combinatorial Optimization Model, calculate optimal selection suggestion so that sales volume and profit integration objective value are optimal.Commodity effectiveness value and choosing Product result can be output to user interface.Selection effect simulation module can simulate category level, brand from dimensions such as sales volume, profits Level, the selection effect of supplier's level.The upper undercarriage result that selection effect simulation module allows user to calculate model is done Freely adjust, and calculate the index such as sales volume, profit, effectiveness corresponding to new grouping of commodities automatically, and by brand, supply Packet index of business's dimension etc..
Subscriber interface module allows User Defined selection parameter and consumer demand structure, and can check under each classification Merchandising suggestion, and according to business need make the appropriate adjustments.
The data processing equipment of one embodiment of the invention is introduced with reference to Fig. 4.
Fig. 4 shows the structural representation of the data processing equipment of one embodiment of the invention.As shown in figure 4, the present embodiment Data processing equipment 40 include：
By proxy indicator computing unit 402, be configured as the History Order data according to commodity, calculate commodity by for For property index, wherein, commodity represent that user buys the probability that other commodity substitute purchase commodity by proxy indicator.
Halo effect indicator calculating unit 404, it is configured as the follow-up order of the system head single users according to purchase commodity Data, the halo effect index of commodity is calculated, wherein, the halo effect index expression commodity of commodity attract user to buy other business The ability of product.
Commodity effectiveness computing unit 406, be configured as the historic sales data according to commodity, commodity by proxy indicator And the halo effect index of commodity, calculate the effectiveness of commodity.
In above-described embodiment, according to the History Order data of commodity, calculate commodity by proxy indicator；According to purchase business The follow-up order data of the system head single users of product, calculate the halo effect index of commodity；Finally according to the historical sales of commodity Data, the halo effect index by proxy indicator and commodity of commodity, calculate the effectiveness of commodity.It is achieved thereby that for business The quantization of product effectiveness, it can more objectively weigh the value of commodity.Meanwhile the commodity effectiveness that the present embodiment is calculated, energy The influence and the consumption demand of consumer that enough good reflection new products are stimulated consumption, while consider the pass between commodity and commodity System, the effectiveness of objective, quantization commodity help more comprehensively, accurately to understand the incremental value brought after commodity introduce, and then Service guidance personnel carry out the selection operation of commodity.
In one embodiment, commodity effectiveness computing unit 406 is configured as：Calculated according to commodity by proxy indicator The irreplaceability index of commodity；By the weighted sum of the sales volume of commodity and the profit of commodity, commodity can not be by alternative finger Mark, the halo effect index of commodity are multiplied, and the effectiveness of commodity is calculated.
In one embodiment, commodity effectiveness computing unit 406 is configured as：The effect of commodity is calculated using equation below With：
Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i's By proxy indicator,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weight of profit Value.
In one embodiment, it is configured as by proxy indicator computing unit 402：According to user in continuous order pair History Order data, calculate user in continuous order pair, from commodity to the alternative consumption of another commodity；By all users In all continuous orders pair, from commodity to the alternative consumption of other each commodity plus and, make ratio with the sales volume of commodity, Be calculated commodity by proxy indicator.
In one embodiment, it is configured as by proxy indicator computing unit 402：Calculated using equation below from commodity A to commodity B alternative consumption：
Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1ARepresent commodity A in the first order The amount of money, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, the first order and second Order is the continuous order of same user；Using equation below calculating commodity A by proxy indicator：
Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
In one embodiment, halo effect indicator calculating unit 404 is configured as：It is first single using the system for buying commodity The follow-up order data amount of money of user, and the system head single users of purchase commodity follow-up order relative to single commodity under first Time, calculate commodity halo effect value；It is worth using the halo effect of commodity, and the sales volume of commodity, calculate business The halo effect index of product.
In one embodiment, halo effect indicator calculating unit 404 is configured as：Commodity i is calculated using equation below Halo effect value：
Wherein, hiRepresent commodity i halo effect value, Sale be first under single commodity i user follow-up order gold Volume, γ represent decay factor, t represent first under single commodity i user follow-up order relative under first single commodity i when Between；Commodity i halo effect index is calculated using equation below：
Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
In one embodiment, the device also includes selection decision package 408, is configured as：Establish and determine for each commodity Plan variable；Define the constraints of decision variable；The summation of the effectiveness of each commodity and the difference of cost is defined as decision-making mesh Mark；Selection decision-making is carried out by combined optimization method.
In one embodiment, selection decision package 408 is additionally configured to：The pact of decision variable is defined using equation below Beam condition：
Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the business currently managed Product quantity, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, and i.A represents commodity i attributes A Value, i.B represents commodity i attributes B value, and (a, b) represents all property value sets, Na,bRepresent that property value set (a, b) is right The minimum commodity amount answered.
In above-described embodiment, the value of utility of commodity is calculated first with commodity effectiveness function, is then based on commodity effectiveness Value establishes selection Optimized model.So as to propose a kind of optimal selection method of target, introducing, cost is minimum and meet client Maximum revenue is realized in the case of demand, so as to instruct businessman to carry out the upper undercarriage decision-making of commodity.
Fig. 5 shows the structural representation of another embodiment of data processing equipment of the present invention.As shown in figure 5, the reality Applying the data processing equipment 50 of example includes：Memory 510 and the processor 520 for being coupled to the memory 510, processor 520 It is configured as, based on the instruction being stored in memory 510, performing the data processing method in any one foregoing embodiment.
Wherein, memory 510 is such as can include system storage, fixed non-volatile memory medium.System stores Device is such as being stored with operating system, application program, Boot loader (Boot Loader) and other programs.
Fig. 6 shows the structural representation of another embodiment of data processing equipment of the present invention.As shown in fig. 6, the reality Applying the data processing equipment 60 of example includes：Memory 510 and processor 520, input/output interface 630, net can also be included Network interface 640, memory interface 650 etc..For example may be used between these interfaces 630,640,650 and memory 510 and processor 520 To be connected by bus 650.Wherein, input/output interface 630 is the input-output equipment such as display, mouse, keyboard, touch-screen Connecting interface is provided.Network interface 640 provides connecting interface for various networked devices.Memory interface 650 is that SD card, USB flash disk etc. are outer Put storage device and connecting interface is provided.
Present invention additionally comprises a kind of computer-readable recording medium, computer instruction is stored thereon with, the instruction is processed Device realizes the data processing method in any one foregoing embodiment when performing.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program Product.Therefore, the present invention can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware Apply the form of example.Moreover, the present invention can use the computer for wherein including computer usable program code in one or more The calculating implemented in non-transient storage medium (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.) can be used The form of machine program product.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided The processors of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one The step of function of being specified in individual square frame or multiple square frames.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.

Claims (24)

  1. A kind of 1. data processing method, it is characterised in that including：
    According to the History Order data of commodity, calculate the commodity by proxy indicator, wherein, the commodity it is alternative Index expression user buys other commodity and substitutes the probability for buying the commodity；
    According to the follow-up order data for the system head single users for buying the commodity, the halo effect index of the commodity is calculated, Wherein, commodity described in the halo effect index expression of the commodity attract the ability that user buys other commodity；
    Referred to according to the halo effect by proxy indicator and the commodity of the historic sales data of the commodity, the commodity Mark, calculate the effectiveness of the commodity.
  2. 2. data processing method as claimed in claim 1, it is characterised in that the historical sales number according to the commodity According to the halo effect index by proxy indicator and the commodity of, commodity, calculating the effectiveness of the commodity includes：
    According to the irreplaceability index that the commodity are calculated by proxy indicator of the commodity；
    By the weighted sum of the sales volume of the commodity and the profit of the commodity, the commodity can not be by proxy indicator, institute The halo effect index for stating commodity is multiplied, and the effectiveness of the commodity is calculated.
  3. 3. data processing method as claimed in claim 1, it is characterised in that
    The effectiveness of commodity is calculated using equation below：
    Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i by for For property index,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weighted value of profit.
  4. 4. data processing method as claimed in claim 1, it is characterised in that the History Order data according to commodity, meter Calculate being included by proxy indicator for the commodity：
    According to History Order data of the user in continuous order pair, the user is calculated in the continuous order pair, from institute State alternative consumption of the commodity to another commodity；
    By all users in all continuous orders pair, from the commodity to the alternative consumption of other each commodity plus and, Make ratio with the sales volume of the commodity, be calculated the commodity by proxy indicator.
  5. 5. data processing method as claimed in claim 4, it is characterised in that calculated using equation below from commodity A to commodity B Alternative consumption：
    <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>A</mi> <mo>,</mo> <mi>B</mi> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>Sale</mi> <mrow> <mn>1</mn> <mi>A</mi> </mrow> </msub> <mo>*</mo> <mfrac> <mrow> <msub> <mi>Sale</mi> <mrow> <mn>2</mn> <mi>B</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>Sale</mi> <mn>2</mn> </msub> </mrow> </mfrac> </mrow>
    Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1AThe amount of money of commodity A in the first order is represented, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, first order and described Two orders are the continuous order of same user.
  6. 6. data processing method as claimed in claim 5, it is characterised in that calculate being substituted for commodity A using equation below Property index：
    Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
  7. 7. data processing method as claimed in claim 1, it is characterised in that described first single according to the system for buying the commodity The follow-up order data of user, calculating the halo effect index of the commodity includes：
    It is alone using the follow-up order amount of money for the system head single users for buying the commodity, and the system head of the purchase commodity The follow-up order at family relative to the commodity that place an order first time, calculate the commodity halo effect value；
    It is worth using the halo effect of the commodity, and the sales volume of the commodity, the halo effect for calculating the commodity refer to Mark.
  8. 8. data processing method as claimed in claim 7, it is characterised in that
    The halo effect that commodity i is calculated using equation below is worth：
    Wherein, hiCommodity i halo effect value is represented, the follow-up order amount of money of single commodity i user under Sale expressions first, γ represent decay factor, t represent first under single commodity i user follow-up order relative to single commodity i under first time.
  9. 9. data processing method as claimed in claim 8, it is characterised in that
    Commodity i halo effect index is calculated using equation below：
    Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
  10. 10. data processing method as claimed in claim 1, it is characterised in that methods described also includes：
    Decision variable is established for each commodity；
    Define the constraints of decision variable；
    The summation of the effectiveness of each commodity and the difference of cost is defined as decision objective；
    Selection decision-making is carried out by combined optimization method.
  11. 11. data processing method as claimed in claim 10, it is characterised in that the pact of decision variable is defined using equation below Beam condition：
    <mrow> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <mi>S</mi> </mrow> </munder> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>&amp;le;</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>+</mo> <mi>u</mi> <mi>b</mi> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <mi>N</mi> </mrow>
    <mrow> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <mi>S</mi> </mrow> </munder> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>&amp;GreaterEqual;</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <mi>l</mi> <mi>b</mi> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <mi>N</mi> </mrow>
    Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the commodity number currently managed Amount, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, and i.A represents commodity i attributes A value, I.B represents commodity i attributes B value, and (a, b) represents all property value sets, Na,bRepresent corresponding to property value set (a, b) Minimum commodity amount.
  12. A kind of 12. data processing equipment, it is characterised in that including：
    By proxy indicator computing unit, the History Order data according to commodity are configured as, calculate being substituted for the commodity Property index, wherein, the commodity are represented that user buys other commodity and substitutes the probability for buying the commodity by proxy indicator；
    Halo effect indicator calculating unit, it is configured as the follow-up order numbers according to the system head single users for buying the commodity According to, the halo effect indexs of the commodity is calculated, wherein, commodity described in the halo effect index expression of the commodity attract user Buy the ability of other commodity；
    Commodity effectiveness computing unit, be configured as the historic sales data according to the commodity, the commodity by alternative finger It is marked with and the halo effect index of the commodity, calculates the effectiveness of the commodity.
  13. 13. data processing equipment as claimed in claim 12, it is characterised in that the commodity effectiveness computing unit is configured For：
    According to the irreplaceability index that the commodity are calculated by proxy indicator of the commodity；
    By the weighted sum of the sales volume of the commodity and the profit of the commodity, the commodity can not be by proxy indicator, institute The halo effect index for stating commodity is multiplied, and the effectiveness of the commodity is calculated.
  14. 14. data processing equipment as claimed in claim 12, it is characterised in that
    The effectiveness of commodity is calculated using equation below：
    Wherein, i represents goods number, SiRepresent commodity i sales volume, MiRepresent commodity i profit, βiRepresent commodity i by for For property index,Represent commodity i halo effect index, α1Represent the weighted value of sales volume, α2Represent the weighted value of profit.
  15. 15. data processing equipment as claimed in claim 12, it is characterised in that it is described by proxy indicator computing unit by with It is set to：
    According to History Order data of the user in continuous order pair, the user is calculated in the continuous order pair, from institute State alternative consumption of the commodity to another commodity；
    By all users in all continuous orders pair, from the commodity to the alternative consumption of other each commodity plus and, Make ratio with the sales volume of the commodity, be calculated the commodity by proxy indicator.
  16. 16. data processing equipment as claimed in claim 15, it is characterised in that it is described by proxy indicator computing unit by with It is set to：The alternative consumption from commodity A to commodity B is calculated using equation below：
    <mrow> <mi>S</mi> <mrow> <mo>(</mo> <mi>A</mi> <mo>,</mo> <mi>B</mi> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>Sale</mi> <mrow> <mn>1</mn> <mi>A</mi> </mrow> </msub> <mo>*</mo> <mfrac> <mrow> <msub> <mi>Sale</mi> <mrow> <mn>2</mn> <mi>B</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>Sale</mi> <mn>2</mn> </msub> </mrow> </mfrac> </mrow>
    Wherein, S (A, B) represents the alternative consumption from commodity A to commodity B, Sale1AThe amount of money of commodity A in the first order is represented, Sale2BRepresent the amount of money of commodity B in the second order, Sale2Represent the total amount of the second order, first order and described Two orders are the continuous order of same user.
  17. 17. data processing equipment as claimed in claim 16, it is characterised in that it is described by proxy indicator computing unit by with It is set to：Using equation below calculating commodity A by proxy indicator：
    Wherein, βARepresent that commodity A's represents another substitute goods, S by proxy indicator, TARepresent commodity A sales volume.
  18. 18. data processing equipment as claimed in claim 12, it is characterised in that the halo effect indicator calculating unit by with It is set to：
    It is first using the follow-up order amount of money according to the system head single users for buying the commodity, and the system of the purchase commodity The follow-up order of single user relative to the commodity that place an order first time, calculate the commodity halo effect value；
    It is worth using the halo effect of the commodity, and the sales volume of the commodity, the halo effect for calculating the commodity refer to Mark.
  19. 19. data processing equipment as claimed in claim 18, it is characterised in that the halo effect indicator calculating unit by with It is set to：
    The halo effect that commodity i is calculated using equation below is worth：
    Wherein, hiCommodity i halo effect value is represented, the follow-up order amount of money of single commodity i user under Sale expressions first, γ represent decay factor, t represent first under single commodity i user follow-up order relative to single commodity i under first time.
  20. 20. data processing equipment as claimed in claim 19, it is characterised in that the halo effect indicator calculating unit by with It is set to：
    Commodity i halo effect index is calculated using equation below：
    Wherein,Represent commodity i halo effect index, SiRepresent commodity i sales volume.
  21. 21. data processing equipment as claimed in claim 12, it is characterised in that the data processing equipment is also determined including selection Plan unit, is configured as：
    Decision variable is established for each commodity；
    Define the constraints of decision variable；
    The summation of the effectiveness of each commodity and the difference of cost is defined as decision objective；
    Selection decision-making is carried out by combined optimization method.
  22. 22. data processing equipment as claimed in claim 21, it is characterised in that the data selection decision package is configured For：The constraints of decision variable is defined using equation below：
    <mrow> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <mi>S</mi> </mrow> </munder> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>&amp;le;</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>+</mo> <mi>u</mi> <mi>b</mi> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <mi>N</mi> </mrow>
    <mrow> <munder> <mo>&amp;Sigma;</mo> <mrow> <mi>i</mi> <mo>&amp;Element;</mo> <mi>S</mi> </mrow> </munder> <msub> <mi>X</mi> <mi>i</mi> </msub> <mo>&amp;GreaterEqual;</mo> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <mi>l</mi> <mi>b</mi> <mo>)</mo> </mrow> <mo>&amp;CenterDot;</mo> <mi>N</mi> </mrow>
    Wherein, XiCommodity i decision variable is represented, S represents the commodity set currently managed, and N represents the commodity number currently managed Amount, ub represent the maximum ratio of new restocking commodity, and lb represents the maximum ratio of undercarriage commodity, and i.A represents commodity i attributes A value, I.B represents commodity i attributes B value, and (a, b) represents all property value sets, Na,Represent corresponding to property value set (a, b) most Low commodity amount.
  23. A kind of 23. data processing equipment, it is characterised in that including：
    Memory；And
    The processor of the memory is coupled to, the processor is configured as based on the instruction being stored in the memory, Perform the data processing method as described in any one of claim 1 to 11.
  24. 24. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium storage has computer to refer to The data processing method described in any one of claim 1 to 11 is realized in order, the instruction when being executed by processor.
CN201710587974.8A 2017-07-19 2017-07-19 Data processing method and device Pending CN107358472A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710587974.8A CN107358472A (en) 2017-07-19 2017-07-19 Data processing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710587974.8A CN107358472A (en) 2017-07-19 2017-07-19 Data processing method and device

Publications (1)

Publication Number Publication Date
CN107358472A true CN107358472A (en) 2017-11-17

Family

ID=60284389

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710587974.8A Pending CN107358472A (en) 2017-07-19 2017-07-19 Data processing method and device

Country Status (1)

Country Link
CN (1) CN107358472A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109903104A (en) * 2017-12-08 2019-06-18 北京京东尚科信息技术有限公司 Method and device for data analysis
CN109961307A (en) * 2017-12-25 2019-07-02 北京京东尚科信息技术有限公司 The appraisal procedure and device of object-oriented
CN110490682A (en) * 2018-05-15 2019-11-22 北京京东尚科信息技术有限公司 The method and apparatus for analyzing item property
CN110880119A (en) * 2018-09-05 2020-03-13 北京京东尚科信息技术有限公司 Data processing method and device
CN111292111A (en) * 2018-12-07 2020-06-16 阿里巴巴集团控股有限公司 Commodity information processing method and device and electronic equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203204918U (en) * 2013-02-05 2013-09-18 李春林 Supermarket variety optimization decision-making display board and simulation training sand table
CN105354736A (en) * 2015-11-24 2016-02-24 北京云镜元谱信息科技有限公司 Intelligent virtual shop system based on RFID technique and commodity selection algorithm
CN106408181A (en) * 2016-09-09 2017-02-15 广州速鸿信息科技有限公司 Smart store system and method based on big data analysis
CN106611366A (en) * 2015-10-26 2017-05-03 阿里巴巴集团控股有限公司 Method and device for automatically selecting article
CN106951516A (en) * 2017-03-18 2017-07-14 深圳市彬讯科技有限公司 A kind of finishing selection intelligent sorting method based on big data

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203204918U (en) * 2013-02-05 2013-09-18 李春林 Supermarket variety optimization decision-making display board and simulation training sand table
CN106611366A (en) * 2015-10-26 2017-05-03 阿里巴巴集团控股有限公司 Method and device for automatically selecting article
CN105354736A (en) * 2015-11-24 2016-02-24 北京云镜元谱信息科技有限公司 Intelligent virtual shop system based on RFID technique and commodity selection algorithm
CN106408181A (en) * 2016-09-09 2017-02-15 广州速鸿信息科技有限公司 Smart store system and method based on big data analysis
CN106951516A (en) * 2017-03-18 2017-07-14 深圳市彬讯科技有限公司 A kind of finishing selection intelligent sorting method based on big data

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109903104A (en) * 2017-12-08 2019-06-18 北京京东尚科信息技术有限公司 Method and device for data analysis
CN109961307A (en) * 2017-12-25 2019-07-02 北京京东尚科信息技术有限公司 The appraisal procedure and device of object-oriented
CN110490682A (en) * 2018-05-15 2019-11-22 北京京东尚科信息技术有限公司 The method and apparatus for analyzing item property
CN110490682B (en) * 2018-05-15 2024-02-09 北京京东尚科信息技术有限公司 Method and device for analyzing commodity attributes
CN110880119A (en) * 2018-09-05 2020-03-13 北京京东尚科信息技术有限公司 Data processing method and device
CN111292111A (en) * 2018-12-07 2020-06-16 阿里巴巴集团控股有限公司 Commodity information processing method and device and electronic equipment
CN111292111B (en) * 2018-12-07 2023-05-09 阿里巴巴集团控股有限公司 Commodity information processing method and device and electronic equipment

Similar Documents

Publication Publication Date Title
CN107358472A (en) Data processing method and device
AU2002353396B2 (en) Sales optimization
JP5337174B2 (en) Demand prediction device and program thereof
US20140188584A1 (en) Product pricing system on electronic commerce using the internet
WO2021077844A1 (en) Risk supervision method and system for commodity net price
CN109685651A (en) The credit risk monitoring method and device of current assets mortgage
JP5418326B2 (en) Price determining apparatus, price determining method, and computer program
CN109961368A (en) Data processing method and device based on machine learning
Jiang et al. Optimizing shipping-fee schedules to maximize e-tailer profits
CN112967108B (en) BP-ANN-based power retail package search ordering simulation system and method
JP7354363B2 (en) Provision device, method and program
JP2019091508A (en) Advice data generation system
WO2007136011A1 (en) Transaction estimation system and program
CN111768243A (en) Sales prediction method, prediction model construction method, device, equipment and medium
JP7150968B1 (en) Provision device, provision method and provision program
CN115147144A (en) Data processing method and electronic equipment
Quan et al. Effects of consumers’ strategic behavior and psychological satisfaction on the retailer’s pricing and inventory decisions
CN106462816A (en) Framework for assessing the sensitivity of productivity measures to exogenous factors and operational decisions
US20090132319A1 (en) Method for generating an asset loading plan
JP2007272325A (en) Sma management system and sma management method
US20030055761A1 (en) Investment and return simulation method and apparatus
JPH0973491A (en) Component inventory planning support system
Sana et al. An inventory model for stock with advertising sensitive demand
KR102381486B1 (en) System for managing online shopping mall syntagmatically
CN108932615A (en) A kind of digital asset method of commerce, system and computer readable storage medium

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20171117

RJ01 Rejection of invention patent application after publication