CN107818474A - A kind of method and apparatus for being used to dynamically adjust product price - Google Patents

A kind of method and apparatus for being used to dynamically adjust product price Download PDF

Info

Publication number
CN107818474A
CN107818474A CN201610822402.9A CN201610822402A CN107818474A CN 107818474 A CN107818474 A CN 107818474A CN 201610822402 A CN201610822402 A CN 201610822402A CN 107818474 A CN107818474 A CN 107818474A
Authority
CN
China
Prior art keywords
price
product
unit
cycle
dimension
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.)
Granted
Application number
CN201610822402.9A
Other languages
Chinese (zh)
Other versions
CN107818474B (en
Inventor
吕强
程恒奇
李夫收
金洪伟
刘心元
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.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and 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 Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201610822402.9A priority Critical patent/CN107818474B/en
Publication of CN107818474A publication Critical patent/CN107818474A/en
Application granted granted Critical
Publication of CN107818474B publication Critical patent/CN107818474B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0283Price estimation or determination

Abstract

The invention provides a kind of method and apparatus for being used to dynamically adjust product price, this method includes:When the present price end cycle of product, according to cycle data of the product in present price cycle and a upper price cycle, the mechanical periodicity information of the product was obtained;According to the mechanical periodicity information and the dimensional information of the product, it is determined that the multiple price units corresponding with next price cycle of the product;It is determined that the price of each price unit during next price cycle in the multiple price unit.According to the solution of the present invention, adjustment product price can be automated, considerably reduces artificial input, has saved human cost, and can realize that the differentiation of product is determined.

Description

A kind of method and apparatus for being used to dynamically adjust product price
Technical field
The present invention relates to field of computer technology, more particularly to a kind of method and dress for being used to dynamically adjust product price Put.
Background technology
In the prior art, the operator of product is typically based on manual analysis mode to realize the price of product or price adjustment, such as Each dimension of manual analysis product, current share data, price susceptibility (history ring is than data experience) etc., with based on analysis As a result price or price adjustment policymaking are made.However, the manual analysis mode needs to continue the specialized manpower of input, human cost is high, And mainly judged on the basis of historical statistical data based on experience, neither one standard reliably judges scheme so that Its analysis result can not accomplish very accurately, so as to realize preferably price adjustment effect.
The content of the invention
It is an object of the invention to provide a kind of method and apparatus for being used to dynamically adjust product price.
According to an aspect of the present invention, there is provided a kind of method for being used to dynamically adjust product price, wherein, this method bag Include:
When the present price end cycle of product, according to the product in present price cycle and a upper price cycle Cycle data, obtain the mechanical periodicity information of the product;
According to the mechanical periodicity information and the dimensional information of the product, it is determined that next price with the product Multiple price units corresponding to cycle phase;
It is determined that the price of each price unit during next price cycle in the multiple price unit.
According to another aspect of the present invention, a kind of device for being used to dynamically adjust product price is additionally provided, wherein, should Device includes:
For when the present price end cycle of product, according to the product in present price cycle and a upper price The cycle data in cycle, obtain the device of the mechanical periodicity information of the product;
For the dimensional information according to the mechanical periodicity information and the product, it is determined that next with the product Price cycle corresponding multiple price units device;
For determining the valency of each price unit during next price cycle in the multiple price unit The device of lattice.
According to a further aspect of the invention, a kind of equipment for being used to dynamically adjust product price, the equipment are additionally provided Including:
One or more processors,
Memory, one or more programs are stored with,
When one or more of programs are by one or more of computing devices so that one or more of places Manage the method for being used to dynamically adjust product price that device realizes the present invention.
Compared with prior art, the present invention has advantages below:Adjustment product price can be automated, is considerably reduced Artificial input, has saved human cost;When the present price end cycle of product, can according to product the present price cycle with The cycle data of a upper price cycle, and the dimensional information of product are relative with next price cycle of product to determine The multiple price units answered, so as to further determine that the price of each price unit in the plurality of price unit so that each The price unit of price cycle is dynamically determined, and by variable price unit, being capable of automatic identification influence Price Sensitive The key element of degree, the differentiation price of product is realized, lifts overall goals.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, of the invention is other Feature, objects and advantages will become more apparent upon:
Fig. 1 is the schematic flow sheet for being used to dynamically adjust the method for product price of one embodiment of the invention;
Fig. 2 is the dimension tree schematic diagram of the film ticket of an example of the present invention;
Fig. 3 is the schematic diagram that dimension tree shown in Fig. 2 is divided into multiple price units of an example of the present invention;
Fig. 4 is the schematic flow sheet for being used to dynamically adjust the method for product price of another embodiment of the present invention;
Fig. 5 is that the present invention determines that the price of each price unit is shown by taking film ticket as an example based on price cell queue It is intended to;
Fig. 6 is the structural representation for being used to dynamically adjust the device of product price of one embodiment of the invention;
Fig. 7 is the structural representation for being used to dynamically adjust the device of product price of another embodiment of the present invention;
Fig. 8 shows the signal for being used to dynamically adjust an implementation of the equipment of product price according to the present invention Figure.
Same or analogous reference represents same or analogous part in accompanying drawing.
Embodiment
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail The processing described as flow chart or method.Although operations are described as the processing of order by flow chart, therein to be permitted Multioperation can be implemented concurrently, concomitantly or simultaneously.In addition, the order of operations can be rearranged.When it The processing can be terminated when operation is completed, it is also possible to the additional step being not included in accompanying drawing.The processing It can correspond to method, function, code, subroutine, subprogram etc..
Alleged within a context " computer equipment ", also referred to as " computer ", referring to can be by running preset program or referring to Order performs the intelligent electronic device of the predetermined process process such as numerical computations and/or logical calculated, its can include processor with Memory, the programmed instruction to be prestored in memory by computing device perform predetermined process process, or by ASIC, The hardware such as FPGA, DSP perform predetermined process process, or are realized by said two devices combination.Computer equipment includes but unlimited In server, PC, notebook computer, tablet personal computer, smart mobile phone etc..
The computer equipment is for example including user equipment and the network equipment.Wherein, the user equipment includes but unlimited In PC, tablet personal computer, smart mobile phone, PDA etc.;The network equipment includes but is not limited to single network server, multiple nets Network server group into server group or based on cloud computing (Cloud Computing) by a large amount of computers or the webserver The cloud of composition, wherein, cloud computing is one kind of Distributed Calculation, and one be made up of the computer collection of a group loose couplings is super Virtual machine.Wherein, the computer equipment can isolated operation realize the present invention, also can access network and by with network In the interactive operations of other computer equipments realize the present invention.Wherein, the network residing for the computer equipment include but It is not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN, VPN etc..
It should be noted that the user equipment, the network equipment and network etc. are only for example, other are existing or from now on may be used The computer equipment that can occur such as is applicable to the present invention, should also be included within the scope of the present invention, and by reference It is incorporated herein.
The method (some of them illustrated by flow) discussed herein below can by hardware, software, firmware, in Between part, microcode, hardware description language or its any combination implement.When with software, firmware, middleware or microcode come real Shi Shi, to implement the program code of necessary task or code segment can be stored in machine or computer-readable medium (such as Storage medium) in.(one or more) processor can implement necessary task.
Concrete structure and function detail disclosed herein are only representational, and are for describing showing for the present invention The purpose of example property embodiment.But the present invention can be implemented by many alternative forms, and it is not interpreted as It is limited only by the embodiments set forth herein.
Although it should be appreciated that may have been used term " first ", " second " etc. herein to describe unit, But these units should not be limited by these terms.It is used for the purpose of using these terms by a unit and another unit Make a distinction.For example, in the case of the scope without departing substantially from exemplary embodiment, it is single that first module can be referred to as second Member, and similarly second unit can be referred to as first module.Term "and/or" used herein above include one of them or Any and all combination of more listed associated items.
Term used herein above is not intended to limit exemplary embodiment just for the sake of description specific embodiment.Unless Context clearly refers else, otherwise singulative used herein above "one", " one " also attempt to include plural number.Should also When understanding, term " comprising " and/or "comprising" used herein above provide stated feature, integer, step, operation, The presence of unit and/or component, and do not preclude the presence or addition of other one or more features, integer, step, operation, unit, Component and/or its combination.
It should further be mentioned that in some replaces realization modes, the function/action being previously mentioned can be according to different from attached The order indicated in figure occurs.For example, depending on involved function/action, the two width figures shown in succession actually may be used Substantially simultaneously to perform or can perform in a reverse order sometimes.
The present invention is described in further detail below in conjunction with the accompanying drawings.
Fig. 1 is the schematic flow sheet for being used to dynamically adjust the method for product price of one embodiment of the invention.According to this The method of embodiment includes step S1, step S2 and step S3.
In step sl, when the present price end cycle of product, computer equipment is working as present value according to the product The cycle data in lattice cycle and a upper price cycle, obtained the mechanical periodicity information of the product.
Wherein, a product corresponds to multiple continuous price cycles.It should be noted that product of the present invention is not A specific products (such as mobile phone of model " X ", the film ticket of certain film) is limited to, the product can be price cycle Identical product set (such as film ticket of multi-section film), therefore, the scheme of the present embodiment are applicable not only to dynamic and adjust certain The price of individual specific products, and suitable for adjusting the price of identical multiple product price cycle simultaneously.
It should be noted that preferably, the quantity of the price cycle of product is probably predetermined, or restricted bar Part, or it is unconfined;Also, the Cycle Length of each price cycle of product may be fixed or variable, such as may be used The Cycle Length of follow-up price cycle is adjusted flexibly.Preferably, the stop condition of the price cycle of product can be pre-set (as produced Pin Xia cities etc.), or the price cycle of manual termination's product.
Wherein, the cycle data includes product caused any data within a price cycle, such as the valency of product Lattice data, sales data etc..
Wherein, the mechanical periodicity information includes any for indicating product in present price cycle and a upper price week The information of mechanical periodicity situation between phase, rate change information, the sales volume change information of such as product, wherein, the valency Lattice change information is used for the price behavior for indicating product, and the sale change information is used for the sales volume change for indicating product Situation.It should be noted that during a price cycle, product may be corresponding with multiple prices, the film of such as one film Ticket may have different prices in different movie theatre difference plays.Preferably, the mechanical periodicity information of product can indicate product Change in each dimension, wherein, dimension refers to the various factors for influenceing the price of product, as influenceed the price of film ticket Factor includes but is not limited to:Movie name, movie theatre, city, price etc..
As a step S1 example, for a film shown, each price cycle of its film ticket Cycle Length is one day, and at the end of one day (namely present price end cycle), computer equipment is existed by comparing film ticket The cycle data on the same day and in the cycle data of upper one day, obtains the mechanical periodicity information of film ticket, the mechanical periodicity information refers to Show the price reduction of film ticket 5%, and sales volume adds 10%.
In step s 2, computer equipment is according to the mechanical periodicity information and the dimensional information of the product, it is determined that The multiple price units corresponding with next price cycle of the product.
Wherein, the dimensional information includes any information related to the price dimension of product, more as corresponding to product Association between dimension values that individual dimension, each dimension are included, dimension values etc..For example, dimension includes corresponding to film ticket:Shadow Institute, city, price;Wherein, movie theatre, which includes " star is beautiful " and " middle shadow ", city, includes " Shanghai ", " Beijing ", " Chengdu ", " price " Dimension includes 30,40,50, and the dimension values included by " price " dimension are the initial price of film ticket herein, such as the part in Shanghai Play is initially priced at 30, and another part play is initially priced at 40, then when the dimension values of " city " dimension are " Shanghai ", The dimension values of " price " dimension include 30 and 40 accordingly.
Wherein, the price unit represents the granularity for being fixed a price, namely the base unit of adjustment product price.Its In, a price unit can correspond to one or more dimension values, when a unit of fixing a price corresponds to multiple dimension values, the plurality of dimension Angle value can correspond at least one dimension.For example, one of product price unit meets that " city=Shanghai " (namely Shanghai is all Film play), another price unit of product meets " city=Beijing, movie name=Warcraft ", and (namely " Warcraft " in Beijing All film plays), equal sign front end that is above-mentioned or subsequently occurring is dimension, and equal sign rear end is dimension values.
As a kind of preferred scheme, the step S2 further comprises step S21-1, step S21-2 and step S21-3.
In step S21-1, computer equipment constructs the dimension tree of the product according to the dimensional information of product.
The schematic diagrames that is directed to dimension tree that film ticket construct of the Fig. 2 by an example of the present invention.Wherein, film ticket includes Following dimension:Movie theatre, city, price;Wherein, movie theatre includes " star beautiful " and " middle shadow ", city including " Shanghai ", " Beijing ", " into All ";Price includes 30,40,50.It should be noted that Fig. 2 exemplarily only shows the partial periodicity data of product.
It should be noted that if the dimensional information of product does not change, the dimension tree of product be it is constant, therefore, After the dimension tree of first time construction product, the dimension tree can be stored, then make it that in follow-up price cycle step need not be repeated Rapid S21-1's operates to construct the dimension tree of product;(dimension of such as product however, if the dimensional information of product changes Angle value is removed), the dimension tree of product should be reconfigured, therefore, in step S21-1, if the dimension previously constructed be present Tree, then can first judge whether the dimensional information of product changes, if if changing according to after change dimensional information construct The dimension tree of product, if not changing, directly obtain the dimension tree previously constructed.
In step S21-2, computer equipment calculates each dimension in dimension tree according to the mechanical periodicity information of product The corresponding price standard entropy of value.
Wherein, the price standard entropy represents the consistent implementations of the mechanical periodicity distribution of dimension values.
Preferably for a dimension values of product, computer equipment is based on equation below, according to the dimension in dimension tree The mechanical periodicity information of all nodes under value, calculates the price standard entropy H corresponding to the dimension values:
H=-rPP*ln (rPP)-rPN*ln (rPN)-rNP*ln (rNP)-rNN*ln (rNN)
Wherein, rPP=| PP |/SUM, rPN=| PN |/SUM, rNP=| NP |/SUM, rNN=| NN |/SUM, SUM=| PP |+| PN |+| NP |+| NN |, ln represents the natural logrithm using e as the truth of a matter.Wherein, table 1 gives PP, PN, NP, NN definition:
Table 1
Wherein, Δ cyclical sales amount represents the cyclical sales amount change of each node under the dimension values, Δ cycle price Represent the cycle price change of each node under the dimension values, upward arrow represents nonnegative value (namely on the occasion of or 0), downwards Arrow represent negative value.Can be the node of nonnegative value according to corresponding Δ cyclical sales amount and Δ cycle price based on table 1 According to corresponding Δ cyclical sales amount it is nonnegative value and Δ cycle price is that the node of negative value calculates PP is calculated According to corresponding Δ cyclical sales amount it is negative value and Δ cycle price is that NP, root is calculated in the node of nonnegative value to PN NN is calculated according to the node that corresponding Δ cyclical sales amount and Δ cycle price are negative value.
It should be noted that above-mentioned formula is only for example, rather than limitation of the present invention, it will be appreciated by those skilled in the art that Other can be used in calculating the implementation of the price standard entropy of each node in dimension tree, should also be included in the scope of the present invention It is interior.
In step S21-3, computer equipment is according to the price standard entropys of each dimension values being calculated, and based on mark Quasi- entropy minimum principle, the dimension tree is divided into the multiple price units corresponding with next price cycle of product.
Wherein, the standard entropy minimum principle refers to draw to perform based on the minimum dimension values of corresponding price standard entropy Divide operation.
As an example, Fig. 3 is that dimension tree shown in Fig. 2 is divided into multiple units of fixing a price by an example of the present invention Schematic diagram, first, the price standard entropy of each dimension values in computer equipment dimension tree according to Fig. 2, determine dimension values " on Price standard entropy corresponding to sea " is minimum, then dimension tree is divided into the tree comprising " Shanghai " and do not included by computer equipment The tree in " Shanghai ";Then, for including the tree in " Shanghai ", computer equipment determines the price standard entropy of dimension values " 30 " in the tree Minimum, then computer equipment the tree comprising " Shanghai " is further divided into the tree comprising " 30 " and tree not comprising " 30 ";It is right In the tree not comprising " Shanghai ", computer equipment determines that the price standard entropy of dimension values " 30 " is minimum, then computer equipment will not Tree comprising " Shanghai " is further divided into the tree comprising " 30 " and the tree not comprising " 30 ".In Fig. 3, " MIN=X " represents dimension Value X price standard entropy is minimum, and " NON-X " represents not including X, and X is dimension values, do not include as " NON- Shanghai " represents " on Sea ".
Specifically, computer equipment is according to the price standard entropy of each node being calculated, and minimum based on standard entropy Principle, the dimension tree is divided into the implementation bag of the multiple price units corresponding with next price cycle of product Include but be not limited to:
1) computer equipment is according to the price standard entropy, and is based on standard entropy minimum principle, and the dimension tree is divided For the predetermined quantity price unit corresponding with next price cycle of the product.
For example, predetermined quantity is 4, computer equipment is based on standard entropy minimum principle according to the price standard entropy, first Dimension tree is divided into Tree1 and Tree2;Then, computer equipment is according to the price standard entropy, and it is minimum to be based on standard entropy Principle, Tree1 is divided into Tree11 and Tree12, and Tree2 is divided into Tree21 and Tree22, and by Tree11, Tree12, Tree21, Tree22 are as the 4 price units corresponding with next price cycle of product.
In another example predetermined quantity 3, computer equipment is based on standard entropy minimum principle according to the price standard entropy, Dimension tree is first divided into Tree1 and Tree2;Then, computer equipment is selected based on pre-defined rule (such as number of nodes is more) Determine Tree1, and be based on standard entropy minimum principle, Tree1 is divided into Tree11 and Tree12, and by Tree11, Tree12, Tree2 is as the 3 price units corresponding with next price cycle of product.
2) computer equipment is according to the price standard entropy and predetermined support, and is based on standard entropy minimum principle, will The dimension tree is divided into the multiple price units corresponding with next price cycle of the product.
Wherein, the predetermined supports conditions supported to represent predetermined price unit and need to met, such as predetermined support indicate Sales volume is more than 1000 etc..
For example, price standard entropy of the computer equipment according to each dimension values of product, and standard entropy minimum principle is based on, Dimension tree is divided into two trees for meeting predetermined support;The each tree obtained for division, computer equipment is according to product Each dimension values price standard entropy, and be based on standard entropy minimum principle, the tree be further divided into meet predetermined support Two trees of degree;The like, support that the tree for meeting predetermined support can not be obtained.
It should be noted that when that dimension tree can not be divided into the price unit for meeting predetermined support, can be by entirely Dimension tree is as a price unit.
It should be noted that the above-mentioned implementation 1 of the step S21-3) and 2) can be combined.For example, computer Equipment is based on standard entropy minimum principle according to the price standard entropys of each dimension values of product, and dimension tree is divided into satisfaction Two trees of predetermined support;For the obtained each tree of division, computer equipment is according to the prices of each dimension values of product Standard entropy, and standard entropy minimum principle is based on, two trees that the tree is further divided into meeting predetermined support;Class successively Push away, until the tree for meeting predetermined support can not be obtained, or, pass through the tree of division operation acquisition predetermined quantity.
As step S2 another preferred scheme, the step S2 comprises the following steps:Computer equipment is according to The dimensional information of mechanical periodicity information and product, the multiple dimension collections corresponding with product are obtained, wherein, a dimension collection At least one mechanical periodicity situation for closing included each object is same or similar;Then, computer equipment is according to Multiple dimension collections, it is determined that the multiple price units corresponding with next price cycle of product.
Wherein, the mechanical periodicity situation includes but is not limited to price behavior, sales volume situation of change etc., can be based on The mechanical periodicity information of product obtains the mechanical periodicity situation of each dimension or dimension values of product.
Wherein, the object that the dimension collection includes can be the dimension or dimension values of product.Preferably, sale can be based on Amount increase or decrease, the increasing degree of sales volume or reduce amplitude, the raising or reduction of price, the increase rate of price or drop Low amplitude etc. is same or similar to judge the mechanical periodicity situation of which dimension or dimension values.For example, dimension values " Shanghai " are right The sales volume increasing degree answered is 15%, and sales volume increasing degree corresponding to dimension values " Beijing " is 12%, then it is believed that dimension The mechanical periodicity situation for being worth " Shanghai " and " Beijing " is close.
Wherein, computer equipment can by the various ways such as statistical analysis, cluster come according to the mechanical periodicity information with And the dimensional information of product, obtain the multiple dimension collections corresponding with product.
Wherein, computer equipment can determine a price unit based on one or more dimension collections.For example, computer Equipment can directly using a dimension collection as one price unit, or, when based on determined by a dimension collection price When unit can not meet predetermined support, the dimension collection is combined to determine that meets a predetermined branch with other dimension collections The price unit for degree of holding.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that any according to the mechanical periodicity information and the dimensional information of product, it is determined that with production Next price cycles of product corresponding multiple price units implementation, should be included in the scope of the present invention.
In step s3, computer equipment is determined during next price cycle in the multiple price unit The price of each price unit.
Specifically, computer equipment can be determined the multiple during next price cycle using a variety of implementations The price of each price unit in price unit.
Alternatively, for each price unit in the multiple price unit, the price unit is calculated Marginal benefit;According to the marginal benefit, it is determined that during next price cycle in the multiple price unit The price of each price unit.The alternative will be described in detail in subsequent embodiment.
Alternatively, it is corresponding according to the price unit for each price unit, computer equipment Mechanical periodicity situation, to improve or reduce the price of the price unit.
For example, in step s 2, computer equipment according to the sales volume change information and dimensional information of product, obtain with Next price cycle of product corresponding two price units:U1, U2, wherein, U1 cyclical sales amount increase, U2 week Phase sales volume is reduced;In step s3, computer equipment improves U1 price, and drop according to U1 and U2 mechanical periodicity situation Low U2 price.
It should be noted that the price range for improving or reducing can be fixed or adjustable, such as different cycle Situation of change corresponds to different price ranges.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that any determine during next price cycle in the multiple price unit Each price unit price implementation, should be included in the scope of the present invention.
It should be noted that terminating whenever a price cycle of product, computer equipment just performs the side of the present embodiment Case determines the price of multiple price units corresponding to next price cycle and each price unit.Need furtherly Bright, computer equipment can dynamically be adjusted after second price cycle of product terminates based on the scheme of the present embodiment Whole product price;Preferably, price of the product during its first price cycle is usually predetermined, product its Price during two price cycles can be to predefine or based on determined by the cycle data of first price cycle.
In the prior art, the operator of product is typically based on manual analysis mode to realize the price of product or price adjustment, such as Each dimension of manual analysis product, current share data, price susceptibility (history ring is than data experience) etc., with based on analysis As a result price or price adjustment policymaking are made.However, the manual analysis mode needs to continue the specialized manpower of input, human cost is high, And mainly judged on the basis of historical statistical data based on experience, neither one standard reliably judges scheme so that Its analysis result can not accomplish very accurately, it is poor to further result in effect.
Also exist based on machine learning the scheme fixed a price to single product at present, present invention discover that the program needs A large amount of historical datas are collected, and require long period, all products can not be applied to.
According to the scheme of the present embodiment, adjustment product price can be automated, considerably reduces artificial input, is saved Human cost;, can be according to product in present price cycle and a upper price cycle when the present price end cycle of product Cycle data, and the dimensional information of product, to determine the multiple price lists corresponding with next price cycle of product Member, so as to further determine that the price of each price unit in the plurality of price unit so that the price of each price cycle Unit is dynamically determined, and by variable price unit, being capable of automatic identification influences the key element of price sensitivity, reality The differentiation price of existing product, lifts overall goals;By cycle iterations, it can be good at the strategy of reply market/competing product, and Any product can be applied to.
Fig. 4 is the schematic flow sheet for being used to dynamically adjust the method for product price of another embodiment of the present invention.According to The method of the present embodiment includes step S1, step S2 and step S3, wherein, the step S3 further comprises step S31 and step Rapid S32.Wherein, the step S1 and step S2 are described in detail with reference to the embodiment shown in FIG. 1, will not be repeated here.
In step S31, for each price unit in multiple price units for determining in step s 2, computer is set The standby marginal benefit for calculating the price unit.
Wherein, computer equipment can calculate the marginal benefit of price unit based on below equation:
The marginal benefit of price unit=| Δ cyclical sales amount/Δ cycle price |
In step s 32, computer equipment is according to the marginal benefit being calculated, it is determined that during next price cycle The price of each price unit in the multiple price unit.
Specifically, computer equipment is according to the marginal benefit being calculated, it is determined that described during next price cycle The implementation of the price of each price unit in multiple price units includes but is not limited to:
1) computer equipment is according to the marginal benefit and preset limit information, it is determined that in next price cycle The price of each price unit in period the multiple price unit.
Wherein, the preset limit information includes any restricted information related to the sale of product set in advance, excellent Selection of land, the preset limit information include but is not limited to:Default budget information, default ROI (Return On Investment, Rate of return on investment) information.Wherein, the default budget information includes any limitation letter related to product budget (namely subsidy) Breath is such as the master budget of product input, is the budget of each input price cycle.Wherein, the default ROI information includes appointing What restricted information related to ROI, such as target ROI.
Preferably, computer equipment is ranked up according to the size of the marginal benefit to the multiple price unit, is obtained Must be fixed a price cell queue;Then, computer equipment is according to the preset limit information and predetermined subsidy rule, from the price The larger one end of marginal benefit obtains a price unit and increases subsidy with not putting back to successively in cell queue, and/or, from institute The other end for stating price unit obtains a price unit and reduces subsidy with not putting back to successively, so as to can determine that each price is single The price of member.
As an example, computer equipment is according to corresponding marginal benefit from big to small to identified multiple prices Unit is ranked up, and obtains cell queue of fixing a price as shown in Figure 5:Fix a price unit 1, price unit 2 ..., price unit n, Wherein, | △ draws a bill/△ subsidies | represent the marginal benefit of price unit.In step s 32, computer equipment performs following grasp Make:
If i) current ROI is more than target ROI, computer equipment does not obtain with not putting back to successively from the front end of price cell queue One price unit, and increase the subsidy of acquired price unit, until current ROI is less than target ROI, perform operation ii); If cell queue of fixing a price terminates for sky, operation.Wherein, after the subsidy of one price unit of increase, (△ always flows current RO1= Water+unit flowing water)/(△ always subsidizes+unit subsidy), wherein, the total flowing water of △ is the change of the overall amount of drawing a bill, and unit flowing water is should The amount of drawing a bill of price unit, △ always subsidies are the change integrally subsidized, and unit subsidy is the subsidy of the price unit.
Ii) if current ROI is less than target ROI, computer equipment does not obtain with not putting back to successively from the rear end of price cell queue A price unit is taken, and reduces the subsidy of acquired price unit, until current ROI is more than target ROI, performs operation i);If cell queue of fixing a price terminates for sky, operation.Wherein, after the subsidy of one price unit of reduction, (△ is total by current RO1= Flowing water-unit flowing water)/(△ always subsidizes-unit subsidy).
Then after operation terminates, for each price unit, computer equipment can be increased based on the price unit to add deduct Few subsidizes to determine the price of the price unit.
2) computer equipment does not obtain the absolute value highest of marginal benefit with not putting back to from the multiple price unit every time With minimum two prices units, and following operate is performed to this two price units:
The price of the minimum price unit of absolute value of marginal benefit corresponding in this two price units is reduced, and is carried The price of another price unit in high this two prices unit, wherein, the price numerical value reduced and institute's huff Numerical value is identical.
Preferably, reduced obtain two price units with not putting back to every time after or huff is different, such as the first time Reduce or huff is 10 yuan, second of reduction or huff are 5 yuan etc..
As an example, in step s 2, computer equipment determines corresponding with next price cycle of product Four price units:R1、R2、R3、R4.In step S31, the limit of aforementioned four price unit is calculated in computer equipment Income is respectively:T1, T2, T3, T4, and T1<T2<T3<T4.In step s 32, computer equipment is first from this four price units Obtain T1 and T4 (T1 marginal benefit is minimum, T4 marginal benefit highest) with not putting back to, and by T1 5 yuan of price reduction, will T4 price improves 5 yuan;Then, computer equipment takes remaining T2 and T3, and by T2 4 yuan of price reduction, by T3 price Improve 4 yuan.
It should be noted that in this implementation, if current only surplus price unit, can not change the price unit Price, or improve or reduce the price of the price unit based on pre-defined rule.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that it is any according to the marginal benefit, it is determined that the institute during next price cycle The implementation of the price of each price unit in multiple price units is stated, should be included in the scope of the present invention.
, can be according to the marginal benefit for each price unit being calculated, to determine according to the scheme of the present embodiment The price of each price unit during next price cycle of product;Further, it is possible to further combined with preset limit information, come It is determined that the price for unit of each fixing a price, to realize that target maximizes (such as flowing water maximum, return rate highest under conditions of restriction Deng).
Fig. 6 is the structural representation for being used to dynamically adjust the device of product price of one embodiment of the invention.This is used for The device (hereinafter referred to as " Dynamic Pricing device ") of dynamic adjustment product price includes first and obtains the determination dress of device 1, first Put the 2, second determining device 3.
First, which obtains device 1, is used for when the present price end cycle of product, according to the product in present price week The cycle data of phase and a upper price cycle, obtained the mechanical periodicity information of the product.
Wherein, a product corresponds to multiple continuous price cycles.It should be noted that product of the present invention is not A specific products (such as mobile phone of model " X ", the film ticket of certain film) is limited to, the product can be price cycle Identical product set (such as film ticket of multi-section film), therefore, the scheme of the present embodiment are applicable not only to dynamic and adjust certain The price of individual specific products, and suitable for adjusting the price of identical multiple product price cycle simultaneously.
It should be noted that preferably, the quantity of the price cycle of product is probably predetermined, or restricted bar Part, or it is unconfined;Also, the Cycle Length of each price cycle of product may be fixed or variable, such as may be used The Cycle Length of follow-up price cycle is adjusted flexibly.Preferably, the stop condition of the price cycle of product can be pre-set (as produced Pin Xia cities etc.), or the price cycle of manual termination's product.
Wherein, the cycle data includes product caused any data within a price cycle, such as the valency of product Lattice data, sales data etc..
Wherein, the mechanical periodicity information includes any for indicating product in present price cycle and a upper price week The information of mechanical periodicity situation between phase, rate change information, the sales volume change information of such as product, wherein, the valency Lattice change information is used for the price behavior for indicating product, and the sale change information is used for the sales volume change for indicating product Situation.It should be noted that during a price cycle, product may be corresponding with multiple prices, the film of such as one film Ticket may have different prices in different movie theatre difference plays.Preferably, the mechanical periodicity information of product can indicate product Change in each dimension, wherein, dimension refers to the various factors for influenceing the price of product, as influenceed the price of film ticket Factor includes but is not limited to:Movie name, movie theatre, city, price etc..
As an example, for a film shown, the Cycle Length of each price cycle of its film ticket For one day, at the end of one day (namely present price end cycle), first obtained device 1 by comparing film ticket on the day of Cycle data and in the cycle data of upper one day, obtains the mechanical periodicity information of film ticket, mechanical periodicity information instruction film The price reduction of ticket 5%, and sales volume adds 10%.
First determining device 2 according to the mechanical periodicity information and the dimensional information of the product, it is determined that with the production Next price cycles of product corresponding multiple price units.
Wherein, the dimensional information includes any information related to the price dimension of product, more as corresponding to product Association between dimension values that individual dimension, each dimension are included, dimension values etc..For example, dimension includes corresponding to film ticket:Shadow Institute, city, price;Wherein, movie theatre, which includes " star is beautiful " and " middle shadow ", city, includes " Shanghai ", " Beijing ", " Chengdu ", " price " Dimension includes 30,40,50, and the dimension values included by " price " dimension are the initial price of film ticket herein, such as the part in Shanghai Play is initially priced at 30, and another part play is initially priced at 40, then when the dimension values of " city " dimension are " Shanghai ", The dimension values of " price " dimension include 30 and 40 accordingly.
Wherein, the price unit represents the granularity for being fixed a price, namely the base unit of adjustment product price.Its In, a price unit can correspond to one or more dimension values, when a unit of fixing a price corresponds to multiple dimension values, the plurality of dimension Angle value can correspond at least one dimension.For example, one of product price unit meets that " city=Shanghai " (namely Shanghai is all Film play), another price unit of product meets " city=Beijing, movie name=Warcraft ", and (namely " Warcraft " in Beijing All film plays), equal sign front end that is above-mentioned or subsequently occurring is dimension, and equal sign rear end is dimension values.
As a kind of preferred scheme, first determining device 2 further comprises that constructing apparatus (not shown), first calculate Device (not shown), the first division device (not shown).
Constructing apparatus is used for the dimensional information according to product, constructs the dimension tree of the product.
The schematic diagrames that is directed to dimension tree that film ticket construct of the Fig. 2 by an example of the present invention.Wherein, film ticket includes Following dimension:Movie theatre, city, price;Wherein, movie theatre includes " star beautiful " and " middle shadow ", city including " Shanghai ", " Beijing ", " into All ";Price includes 30,40,50.It should be noted that Fig. 2 exemplarily only shows the partial periodicity data of product.
It should be noted that if the dimensional information of product does not change, the dimension tree of product be it is constant, therefore, After the dimension tree of first time construction product, the dimension tree can be stored, then is caused in follow-up price cycle without triggering construction dress Put and repeat operation to construct the dimension tree of product;(dimension of such as product however, if the dimensional information of product changes Angle value is removed), the dimension tree of product should be reconfigured, therefore, if the dimension tree previously constructed be present, constructing apparatus can be first Judge whether the dimensional information of product changes, if the dimension for constructing product if changing according to the dimensional information after change Tree, if not changing, directly obtain the dimension tree previously constructed.
First computing device is calculated and determined corresponding to each dimension values in dimension tree according to the mechanical periodicity information of product Valency standard entropy.
Wherein, the price standard entropy represents the consistent implementations of the mechanical periodicity distribution of dimension values.
Preferably for a dimension values of product, the first computing device is based on equation below, according to the dimension in dimension tree The mechanical periodicity information of all nodes under angle value, calculate the price standard entropy H corresponding to the dimension values:
H=-rPP*ln (rPP)-rPN*ln (rPN)-rNP*ln (rNP)-rNN*ln (rNN)
Wherein, rPP=| PP |/SUM, rPN=| PN |/SUM, rNP=| NP |/SUM, rNN=| NN |/SUM, SUM=| PP |+| PN |+| NP |+| NN |, ln represents the natural logrithm using e as the truth of a matter.PP, PN, NP, NN definition are shown in Table 1.
It should be noted that above-mentioned formula is only for example, rather than limitation of the present invention, it will be appreciated by those skilled in the art that Other can be used in calculating the implementation of the price standard entropy of each node in dimension tree, should also be included in the scope of the present invention It is interior.
First divides price standard entropy of the device according to each dimension values being calculated, and minimum former based on standard entropy Then, the dimension tree is divided into the multiple price units corresponding with next price cycle of product.
Wherein, the standard entropy minimum principle refers to draw to perform based on the minimum dimension values of corresponding price standard entropy Divide operation.
As an example, Fig. 3 is that dimension tree shown in Fig. 2 is divided into multiple units of fixing a price by an example of the present invention Schematic diagram, first, the price standard entropy of each dimension values, determines dimension values in first division device dimension tree according to Fig. 2 Price standard entropy corresponding to " Shanghai " is minimum, then dimension tree is divided into the tree that includes " Shanghai " and not by the first division device Include the tree in " Shanghai ";Then, for including the tree in " Shanghai ", the first division device determines the price of dimension values " 30 " in the tree Standard entropy is minimum, then the tree comprising " Shanghai " is further divided into the tree comprising " 30 " and not comprising " 30 " by the first division device Tree;For the tree not comprising " Shanghai ", the first division device determines that the price standard entropy of dimension values " 30 " is minimum, then first stroke The tree for not including " Shanghai " is further divided into the tree comprising " 30 " and the tree not comprising " 30 " by separating device.In Fig. 3, " MIN= X " represents that dimension values X price standard entropy is minimum, and " NON-X " represents not including X, and X is dimension values, and such as " NON- Shanghai " represents not Include in " Shanghai ".
Specifically, first price standard entropy of the device according to each node being calculated is divided, and based on standard entropy most Small principle, the dimension tree is divided into the implementation of the multiple price units corresponding with next price cycle of product Including but not limited to:
1) the first division device further comprises the second division device (not shown).Second division device is according to the price Standard entropy, and standard entropy minimum principle is based on, the dimension tree is divided into relative with next price cycle of the product The predetermined quantity price unit answered.
For example, predetermined quantity is 4, the second division device is based on standard entropy minimum principle according to the price standard entropy, Dimension tree is first divided into Tree1 and Tree2;Then, the second division device is according to the price standard entropy, and is based on standard entropy Minimum principle, Tree1 is divided into Tree11 and Tree12, and Tree2 is divided into Tree21 and Tree22, and will Tree11, Tree12, Tree21, Tree22 are as the 4 price units corresponding with next price cycle of product.
In another example predetermined quantity 3, the second division device is according to the price standard entropy, and it is minimum former to be based on standard entropy Then, dimension tree is first divided into Tree1 and Tree2;Then, (such as number of nodes is more based on pre-defined rule for the second division device Deng) selected Tree1, and be based on standard entropy minimum principle, Tree1 be divided into Tree11 and Tree12, and by Tree11, Tree12, Tree2 are as the 3 price units corresponding with next price cycle of product.
2) the first division device further comprises the 3rd division device (not shown).3rd division device is used for according to Price standard entropy and predetermined support, and standard entropy minimum principle is based on, the dimension tree is divided into and the product Next price cycle corresponding multiple price units.
Wherein, the predetermined supports conditions supported to represent predetermined price unit and need to met, such as predetermined support indicate Sales volume is more than 1000 etc..
For example, price standard entropy of the 3rd division device according to each dimension values of product, and it is minimum former based on standard entropy Then, dimension tree is divided into two trees for meeting predetermined support;For the obtained each tree of division, the 3rd division device according to The price standard entropy of each dimension values of product, and standard entropy minimum principle is based on, the tree is further divided into meeting to make a reservation for Two trees of support;The like, support that the tree for meeting predetermined support can not be obtained.
It should be noted that when that dimension tree can not be divided into the price unit for meeting predetermined support, can be by entirely Dimension tree is as a price unit.
It should be noted that the above-mentioned implementation 1 of the first division device) and 2) can be combined.For example, first Price standard entropy of the device according to each dimension values of product is divided, and is based on standard entropy minimum principle, dimension tree is divided into Meet two trees of predetermined support;The each tree obtained for division, first divides each dimension values of the device according to product Price standard entropy, and be based on standard entropy minimum principle, two trees that the tree is further divided into meeting predetermined support;According to It is secondary to analogize, until the tree for meeting predetermined support can not be obtained, or, pass through the tree of division operation acquisition predetermined quantity.
As another preferred scheme of the first determining device 2, first determining device 2 includes second and obtains device (not shown) and the 3rd determining device (not shown).Second, which obtains device, is used for according to the mechanical periodicity information and product Dimensional information, the multiple dimension collections corresponding with product are obtained, wherein, each object that a dimension collection is included is extremely A kind of few mechanical periodicity situation is same or similar;Then, the 3rd determining device is according to the multiple dimension collection, it is determined that with production Next price cycles of product corresponding multiple price units.
Wherein, the mechanical periodicity situation includes but is not limited to price behavior, sales volume situation of change etc., can be based on The mechanical periodicity information of product obtains the mechanical periodicity situation of each dimension or dimension values of product.
Wherein, the object that the dimension collection includes can be the dimension or dimension values of product.Preferably, sale can be based on Amount increase or decrease, the increasing degree of sales volume or reduce amplitude, the raising or reduction of price, the increase rate of price or drop Low amplitude etc. is same or similar to judge the mechanical periodicity situation of which dimension or dimension values.For example, dimension values " Shanghai " are right The sales volume increasing degree answered is 15%, and sales volume increasing degree corresponding to dimension values " Beijing " is 12%, then it is believed that dimension The mechanical periodicity situation for being worth " Shanghai " and " Beijing " is close.
Wherein, the second acquisition device can be by various ways such as statistical analysis, clusters come according to the mechanical periodicity information And the dimensional information of product, obtain the multiple dimension collections corresponding with product.
Wherein, the 3rd determining device can determine a price unit based on one or more dimension collections.For example, the 3rd Determining device can directly using a dimension collection as one price unit, or, when based on determined by a dimension collection When price unit can not meet predetermined support, the dimension collection is combined to determine that one meets in advance with other dimension collections Determine the price unit of support.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that any according to the mechanical periodicity information and the dimensional information of product, it is determined that with production Next price cycles of product corresponding multiple price units implementation, should be included in the scope of the present invention.
Second determining device 3 determines each price in the multiple price unit during next price cycle The price of unit.
Specifically, the second determining device 3 can be determined described during next price cycle using a variety of implementations The price of each price unit in multiple price units.
Alternatively, for each price unit in the multiple price unit, the price unit is calculated Marginal benefit;According to the marginal benefit, it is determined that during next price cycle in the multiple price unit The price of each price unit.The alternative will be described in detail in subsequent embodiment.
Alternatively, for each price unit, the second determining device 3 is according to the price unit pair The mechanical periodicity situation answered, to improve or reduce the price of the price unit.
For example, sales volume change information and dimensional information of first determining device 2 according to product, under acquisition and product One price cycle corresponding two price units:U1, U2, wherein, U1 cyclical sales amount increase, U2 cyclical sales amount Reduce;Second determining device 3 improves U1 price, and reduce U2 price according to U1 and U2 mechanical periodicity situation.
It should be noted that the price range for improving or reducing can be fixed or adjustable, such as different cycle Situation of change corresponds to different price ranges.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that any determine during next price cycle in the multiple price unit Each price unit price implementation, should be included in the scope of the present invention.
It should be noted that terminating whenever a price cycle of product, just trigger first and obtain the determination of device 1, first The determining device 3 of device 2 and second performs operation to determine multiple price units corresponding to next price cycle and each The price of price unit.It should be further stated that can be after second price cycle of product terminates, based on this implementation The scheme of example dynamically adjusts product price;Preferably, price of the product during its first price cycle is usually advance Determine, price of the product during its second price cycle can be the predetermined or week based on first price cycle Issue is determined by.
In the prior art, the operator of product is typically based on manual analysis mode to realize the price of product or price adjustment, such as Each dimension of manual analysis product, current share data, price susceptibility (history ring is than data experience) etc., with based on analysis As a result price or price adjustment policymaking are made.However, the manual analysis mode needs to continue the specialized manpower of input, human cost is high, And mainly judged on the basis of historical statistical data based on experience, neither one standard reliably judges scheme so that Its analysis result can not accomplish very accurately, it is poor to further result in effect.
Also exist based on machine learning the scheme fixed a price to single product at present, present invention discover that the program needs A large amount of historical datas are collected, and require long period, all products can not be applied to.
According to the scheme of the present embodiment, adjustment product price can be automated, considerably reduces artificial input, is saved Human cost;, can be according to product in present price cycle and a upper price cycle when the present price end cycle of product Cycle data, and the dimensional information of product, to determine the multiple price lists corresponding with next price cycle of product Member, so as to further determine that the price of each price unit in the plurality of price unit so that the price of each price cycle Unit is dynamically determined, and by variable price unit, being capable of automatic identification influences the key element of price sensitivity, reality The differentiation price of existing product, lifts overall goals;By cycle iterations, it can be good at the strategy of reply market/competing product, and Any product can be applied to.
Fig. 7 is the structural representation for being used to dynamically adjust the device of product price of another embodiment of the present invention.According to The Dynamic Pricing device of the present embodiment includes first and obtains device 1, the first determining device 2 and the second determining device 3, wherein, institute State the second determining device 3 and further comprise the second computing device 31 and the 4th determining device 32.Wherein, described first device is obtained 1 and first determining device 2 be described in detail with reference to the embodiment shown in FIG. 6, will not be repeated here.
For each price unit in multiple price units, the second computing device 31 calculates the limit receipts of the price unit Benefit.
Wherein, the second computing device 31 can calculate the marginal benefit of price unit based on below equation:
The marginal benefit of price unit=| Δ cyclical sales amount/Δ cycle price |
4th determining device 32 is used for according to the marginal benefit being calculated, it is determined that described during next price cycle The price of each price unit in multiple price units.
Specifically, the 4th determining device 32 is according to the marginal benefit being calculated, it is determined that during next price cycle The implementation of the price of each price unit in the multiple price unit includes but is not limited to:
1) the 4th determining device 32 further comprises the 5th determining device (not shown).5th determining device is used for according to institute Marginal benefit and preset limit information are stated, it is determined that every in the multiple price unit during next price cycle The price of individual price unit.
Wherein, the preset limit information includes any restricted information related to the sale of product set in advance, excellent Selection of land, the preset limit information include but is not limited to:Default budget information, default ROI (Return On Investment, Rate of return on investment) information.Wherein, the default budget information includes any limitation letter related to product budget (namely subsidy) Breath is such as the master budget of product input, is the budget of each input price cycle.Wherein, the default ROI information includes appointing What restricted information related to ROI, such as target ROI.
Preferably, the 5th determining device further comprises collator (not shown) and the first pricing device (not shown). Collator is used to be ranked up the multiple price unit according to the size of the marginal benefit, obtains price unit team Row;First pricing device is used for according to the preset limit information and predetermined subsidy rule, from the price cell queue The larger one end of marginal benefit obtains a price unit and increases subsidy with not putting back to successively, and/or, from the price unit The other end obtain a price unit with not putting back to successively and reduce subsidy, so as to can determine that the price of each unit of fixing a price.
As an example, collator is single to identified multiple prices from big to small according to corresponding marginal benefit Member is ranked up, and obtains cell queue of fixing a price as shown in Figure 5:Fix a price unit 1, price unit 2 ..., price unit n, its In, | △ draws a bill/△ subsidies | represent the marginal benefit of price unit.First pricing device performs following operate:
If i) current ROI is more than target ROI, the first pricing device does not obtain with not putting back to successively from the front end of price cell queue A price unit is taken, and the subsidy for the unit that must be fixed a price acquired in increase, until current ROI is less than target ROI, perform operation ii);If cell queue of fixing a price terminates for sky, operation.Wherein, after the subsidy of one price unit of increase, current RO1=(△ Total flowing water+unit flowing water)/(△ always subsidizes+unit subsidy), wherein, the total flowing water of △ is the change of the overall amount of drawing a bill, unit flowing water For the amount of drawing a bill of the price unit, △ always subsidies are the change integrally subsidized, and unit subsidy is the subsidy of the price unit.
Ii) if current ROI is less than target ROI, the first pricing device does not put back to ground successively from the rear end of price cell queue A price unit is obtained, and reduces the subsidy of acquired price unit, until current ROI is more than target ROI, performs operation i);If cell queue of fixing a price terminates for sky, operation.Wherein, after the subsidy of one price unit of reduction, (△ is total by current RO1= Flowing water-unit flowing water)/(△ always subsidizes-unit subsidy).
Then after operation terminates, for each price unit, the first pricing device can be based on the price unit increase or Reduction is subsidized to determine the price of the price unit.
2) the 4th determining device 32 further comprises the second pricing device (not shown).Second price unit is every time from described The absolute value highest and minimum two price units of marginal benefit are not obtained in multiple price units with not putting back to, and to this two Unit of fixing a price performs following operate:
The price of the minimum price unit of absolute value of marginal benefit corresponding in this two price units is reduced, and is carried The price of another price unit in high this two prices unit, wherein, the price numerical value reduced and institute's huff Numerical value is identical.
Preferably, reduced obtain two price units with not putting back to every time after or huff is different, such as the first time Reduce or huff is 10 yuan, second of reduction or huff are 5 yuan etc..
As an example, the first determining device 2 determines four prices corresponding with next price cycle of product Unit:R1、R2、R3、R4.Second computing device 31 be calculated aforementioned four price unit marginal benefit be respectively:T1、 T2, T3, T4, and T1<T2<T3<T4.Second pricing device first from this four price units do not obtain with not putting back to T1 and T4 (T1's Marginal benefit is minimum, T4 marginal benefit highest), and by T1 5 yuan of price reduction, T4 price is improved 5 yuan;Then, Two pricing devices take remaining T2 and T3, and by T2 4 yuan of price reduction, T3 price is improved into 4 yuan.
It should be noted that in this implementation, if current only surplus price unit, can not change the price unit Price, or improve or reduce the price of the price unit based on pre-defined rule.
It should be noted that the above-mentioned examples are merely illustrative of the technical solutions of the present invention, rather than the limit to the present invention System, it should be appreciated by those skilled in the art that it is any according to the marginal benefit, it is determined that the institute during next price cycle The implementation of the price of each price unit in multiple price units is stated, should be included in the scope of the present invention.
, can be according to the marginal benefit for each price unit being calculated, to determine according to the scheme of the present embodiment The price of each price unit during next price cycle of product;Further, it is possible to further combined with preset limit information, come It is determined that the price for unit of each fixing a price, to realize that target maximizes (such as flowing water maximum, return rate highest under conditions of restriction Deng).
Present invention also offers a kind of equipment for being used to dynamically adjust product price, the equipment includes:
One or more processors,
Memory, one or more programs are stored with,
When one or more of programs are by one or more of computing devices so that one or more of places Reason device realizes the above-mentioned method for being used to dynamically adjust product price.
Fig. 8 shows the signal for being used to dynamically adjust an implementation of the equipment of product price according to the present invention Figure.The equipment 400 includes memory 410 and processor 420.Memory 410 is stored with one or more programs, when one Or multiple programs, when being performed by processor 420, processor 420 realizes the above-mentioned method for being used to dynamically adjust product price.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling Change is included in the present invention.Any reference in claim should not be considered as to the involved claim of limitation.This Outside, it is clear that the word of " comprising " one is not excluded for other units or step, and odd number is not excluded for plural number.That is stated in system claims is multiple Unit or device can also be realized by a unit or device by software or hardware.The first, the second grade word is used for table Show title, and be not offered as any specific order.

Claims (21)

1. a kind of method for being used to dynamically adjust product price, wherein, this method includes:
When the present price end cycle of product, according to the product in present price cycle and the week of a upper price cycle Issue evidence, obtain the mechanical periodicity information of the product;
According to the mechanical periodicity information and the dimensional information of the product, it is determined that next price cycle with the product Corresponding multiple price units;
It is determined that the price of each price unit during next price cycle in the multiple price unit.
2. according to the method for claim 1, wherein, it is described according to the mechanical periodicity information and the dimension of the product Information, it is determined that the step of corresponding with next price cycle of the product multiple price units include:
According to the dimensional information of the product, the dimension tree of the product is constructed;
According to the mechanical periodicity information, the price standard entropy corresponding to each dimension values in the dimension tree is calculated;
According to the price standard entropy, and be based on standard entropy minimum principle, by the dimension tree be divided into under the product One price cycle corresponding multiple price units.
3. the method according to claim 11, wherein, it is described according to the price standard entropy and minimum former based on standard entropy Then, the step of dimension tree being divided into multiple price units corresponding with next price cycle of the product is wrapped Include:
According to the price standard entropy, and be based on standard entropy minimum principle, by the dimension tree be divided into under the product One price cycle it is corresponding predetermined quantity price unit.
4. the method according to claim 11, wherein, it is described according to the price standard entropy and minimum former based on standard entropy Then, the step of dimension tree being divided into multiple price units corresponding with next price cycle of the product is wrapped Include:
According to the price standard entropy and predetermined support, and standard entropy minimum principle is based on, the dimension tree is divided into The multiple price units corresponding with next price cycle of the product.
5. method according to claim 1, wherein, it is described to be believed according to the mechanical periodicity information and the dimension of the product Breath, it is determined that the step of corresponding with next price cycle of the product multiple price units include:
According to the mechanical periodicity information and the dimensional information of the product, the multiple dimensions corresponding with the product are obtained Set, wherein, at least one mechanical periodicity situation for each object that a dimension collection is included is same or similar;
According to the multiple dimension collection, it is determined that the multiple price units corresponding with next price cycle of the product.
6. method according to claim 1, wherein, the determination the multiple price during next price cycle is single The step of price of each price unit in member, includes:
For each price unit in the multiple price unit, the marginal benefit of the price unit is calculated;
According to the marginal benefit, it is determined that each price during next price cycle in the multiple price unit The price of unit.
7. method according to claim 6, wherein, it is described according to the marginal benefit, it is determined that in next price cycle The step of price of each price unit in period the multiple price unit, includes:
According to the marginal benefit and preset limit information, it is determined that the multiple price during next price cycle The price of each price unit in unit.
8. according to the method for claim 7, wherein, the preset limit information includes at least one of following:
- preset budget information;
- preset ROI information.
9. according to the method for claim 7, wherein, it is described according to the marginal benefit and preset limit information, it is determined that The step of price of each price unit during next price cycle in the multiple price unit, includes:
The multiple price unit is ranked up according to the size of the marginal benefit, obtains price cell queue;
According to the preset limit information and predetermined subsidy rule, marginal benefit is larger from the price cell queue one End obtains a price unit and increases subsidy with not putting back to successively, and/or, do not put successively from the other end of the price unit Ground is gone back to obtain a price unit and reduce subsidy.
10. method according to claim 6, wherein, it is described according to the marginal benefit, it is determined that in next price cycle The step of price of each price unit in period the multiple price unit, includes:
The absolute value highest and minimum two prices of marginal benefit are not obtained from the multiple price unit every time with not putting back to Unit, and following operate is performed to this two price units:
The price of the minimum price unit of absolute value of marginal benefit corresponding in this two price units is reduced, and improve should The price of another price unit in two price units, wherein, the price numerical value reduced and institute's huff numerical value It is identical.
11. a kind of device for being used to dynamically adjust product price, wherein, the device includes:
For when the present price end cycle of product, according to the product in present price cycle and a upper price cycle Cycle data, obtain the device of the mechanical periodicity information of the product;
For the dimensional information according to the mechanical periodicity information and the product, it is determined that next price with the product The device of multiple price units corresponding to cycle phase;
For determining the price of each price unit during next price cycle in the multiple price unit Device.
12. device according to claim 11, wherein, it is described to be used for according to the mechanical periodicity information and the product Dimensional information, it is determined that the device of the multiple price units corresponding with next price cycle of the product includes:
For the dimensional information according to the product, the device of the dimension tree of the product is constructed;
For according to the mechanical periodicity information, calculating the price standard entropy corresponding to each dimension values in the dimension tree Device;
For according to the price standard entropy, and standard entropy minimum principle is based on, the dimension tree is divided into and the product Next price cycle corresponding multiple price units device.
13. device according to claim 12, wherein, it is described to be used for according to the price standard entropy, and it is based on standard entropy Minimum principle, the dimension tree is divided into the dress of the multiple price units corresponding with next price cycle of the product Put including:
For according to the price standard entropy, and standard entropy minimum principle is based on, the dimension tree is divided into and the product Next price cycle it is corresponding predetermined quantity price unit device.
14. device according to claim 12, wherein, it is described to be used for according to the price standard entropy, and it is based on standard entropy Minimum principle, the dimension tree is divided into the dress of the multiple price units corresponding with next price cycle of the product Put including:
For according to the price standard entropy and predetermined support, and standard entropy minimum principle is based on, the dimension tree is drawn It is divided into the device of the multiple price units corresponding with next price cycle of the product.
15. device according to claim 11, wherein, the dimension being used for according to the mechanical periodicity information and the product Information is spent, it is determined that the device of the multiple price units corresponding with next price cycle of the product includes:
For the dimensional information according to the mechanical periodicity information and the product, obtain corresponding with the product multiple The device of dimension collection, wherein, at least one mechanical periodicity situation for each object that a dimension collection is included it is identical or Person is close;
For according to the multiple dimension collection, it is determined that the multiple price lists corresponding with next price cycle of the product The device of member.
16. device according to claim 11, wherein, it is described the multiple during next price cycle for determining The device of the price of each price unit in price unit includes:
For for each price unit in the multiple price unit, calculating the device of the marginal benefit of the price unit;
For according to the marginal benefit, it is determined that each in the multiple price unit during next price cycle The device of the price of price unit.
17. device according to claim 16, wherein, it is described to be used for according to the marginal benefit, it is determined that in next valency The device of the price of each price unit during the lattice cycle in the multiple price unit includes:
For according to the marginal benefit and preset limit information, it is determined that the multiple during next price cycle The device of the price of each price unit in price unit.
18. device according to claim 17, wherein, the preset limit information includes at least one of following:
- preset budget information;
- preset ROI information.
19. device according to claim 17, wherein, it is described to be used to be believed according to the marginal benefit and preset limit Cease, it is determined that the device bag of the price of each price unit during next price cycle in the multiple price unit Include:
The multiple price unit is ranked up for the size according to the marginal benefit, obtains the dress of price cell queue Put;
For according to the preset limit information and predetermined subsidy rule, marginal benefit to be larger from the price cell queue One end obtain a price with not putting back to successively unit and increase subsidy, and/or, from the other end of the unit of fixing a price successively Obtain a price unit with not putting back to and reduce the device of subsidy.
20. device according to claim 16, wherein, it is described to be used for according to the marginal benefit, it is determined that in next valency The device of the price of each price unit during the lattice cycle in the multiple price unit includes:
For every time from it is the multiple price unit in do not obtain with not putting back to marginal benefit absolute value highest and minimum two Price unit, and this two price units are performed with the devices of following operation:
The price of the minimum price unit of absolute value of marginal benefit corresponding in this two price units is reduced, and improve should The price of another price unit in two price units, wherein, the price numerical value reduced and institute's huff numerical value It is identical.
21. a kind of equipment, including:
One or more processors,
Memory, one or more programs are stored with,
When one or more of programs are by one or more of computing devices so that one or more of processors Realize the method as described in any in claim 1 to 10.
CN201610822402.9A 2016-09-13 2016-09-13 Method and device for dynamically adjusting product price Active CN107818474B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610822402.9A CN107818474B (en) 2016-09-13 2016-09-13 Method and device for dynamically adjusting product price

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610822402.9A CN107818474B (en) 2016-09-13 2016-09-13 Method and device for dynamically adjusting product price

Publications (2)

Publication Number Publication Date
CN107818474A true CN107818474A (en) 2018-03-20
CN107818474B CN107818474B (en) 2022-01-18

Family

ID=61601278

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610822402.9A Active CN107818474B (en) 2016-09-13 2016-09-13 Method and device for dynamically adjusting product price

Country Status (1)

Country Link
CN (1) CN107818474B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109191164A (en) * 2018-07-12 2019-01-11 北京猫眼文化传媒有限公司 A kind of film analysis method and device
CN109741097A (en) * 2018-12-26 2019-05-10 复旦大学 A kind of adaptive calculation of price method based on the service of goods period
CN109816459A (en) * 2019-03-21 2019-05-28 深圳市丰巢科技有限公司 A kind of dynamic price adjustment method, apparatus, terminal and storage medium
CN110782269A (en) * 2019-09-18 2020-02-11 北京你财富计算机科技有限公司 Sales promotion commodity price automatic updating method and device and electronic equipment
WO2020186819A1 (en) * 2019-02-01 2020-09-24 北京三快在线科技有限公司 Product data processing
CN112054912A (en) * 2020-08-31 2020-12-08 北京易捷思达科技发展有限公司 Resource charging system and method of OpenStack open source cloud platform

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1633660A (en) * 2000-10-02 2005-06-29 Sht株式会社 Sale method and system employing product price varying dependent upon valid date
CN101447059A (en) * 2008-12-25 2009-06-03 上海宝钢钢材贸易有限公司 Pricing device applicable to steel-trading and method thereof
US7546277B1 (en) * 1997-10-09 2009-06-09 Walker Digital, Llc Method and apparatus for dynamically managing vending machine inventory prices
CN102708509A (en) * 2012-05-22 2012-10-03 北京像素软件科技股份有限公司 Prop transaction handling method in network games
CN102737315A (en) * 2011-04-01 2012-10-17 腾讯科技(深圳)有限公司 Method and server for automatically triggering commodity attribute modification
CN102737316A (en) * 2011-04-01 2012-10-17 东方钢铁电子商务有限公司 Construction method of automatic pricing and multi-organization price adjustment model and apparatus thereof
CN103325061A (en) * 2012-11-02 2013-09-25 中国人民解放军国防科学技术大学 Community discovery method and system
CN105205701A (en) * 2015-09-22 2015-12-30 创点客(北京)科技有限公司 Network dynamic pricing method and system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7546277B1 (en) * 1997-10-09 2009-06-09 Walker Digital, Llc Method and apparatus for dynamically managing vending machine inventory prices
CN1633660A (en) * 2000-10-02 2005-06-29 Sht株式会社 Sale method and system employing product price varying dependent upon valid date
CN101447059A (en) * 2008-12-25 2009-06-03 上海宝钢钢材贸易有限公司 Pricing device applicable to steel-trading and method thereof
CN102737315A (en) * 2011-04-01 2012-10-17 腾讯科技(深圳)有限公司 Method and server for automatically triggering commodity attribute modification
CN102737316A (en) * 2011-04-01 2012-10-17 东方钢铁电子商务有限公司 Construction method of automatic pricing and multi-organization price adjustment model and apparatus thereof
CN102708509A (en) * 2012-05-22 2012-10-03 北京像素软件科技股份有限公司 Prop transaction handling method in network games
CN103325061A (en) * 2012-11-02 2013-09-25 中国人民解放军国防科学技术大学 Community discovery method and system
CN105205701A (en) * 2015-09-22 2015-12-30 创点客(北京)科技有限公司 Network dynamic pricing method and system

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109191164A (en) * 2018-07-12 2019-01-11 北京猫眼文化传媒有限公司 A kind of film analysis method and device
CN109741097A (en) * 2018-12-26 2019-05-10 复旦大学 A kind of adaptive calculation of price method based on the service of goods period
WO2020186819A1 (en) * 2019-02-01 2020-09-24 北京三快在线科技有限公司 Product data processing
CN109816459A (en) * 2019-03-21 2019-05-28 深圳市丰巢科技有限公司 A kind of dynamic price adjustment method, apparatus, terminal and storage medium
CN110782269A (en) * 2019-09-18 2020-02-11 北京你财富计算机科技有限公司 Sales promotion commodity price automatic updating method and device and electronic equipment
CN112054912A (en) * 2020-08-31 2020-12-08 北京易捷思达科技发展有限公司 Resource charging system and method of OpenStack open source cloud platform

Also Published As

Publication number Publication date
CN107818474B (en) 2022-01-18

Similar Documents

Publication Publication Date Title
CN107818474A (en) A kind of method and apparatus for being used to dynamically adjust product price
CN104424230B (en) A kind of cyber recommended method and device
CN108287864B (en) Interest group dividing method, device, medium and computing equipment
CN106204118A (en) A kind of method and apparatus found for commercial circle
CN104063361B (en) Report design method and Report Form Design system
CN106651392A (en) Intelligent business location selection method, apparatus and system
Fan et al. Paint mesh cutting
CN103399951B (en) Semi-supervised image reordering method with self-feedback characteristic based on heterogeneous diagram
CN108121737A (en) A kind of generation method, the device and system of business object attribute-bit
CN106570008A (en) Recommendation method and device
CN110033156A (en) A kind of determination method and device of business activity effect
CN109671020A (en) Image processing method, device, electronic equipment and computer storage medium
CN106446189A (en) Message-recommending method and system
CN107003834B (en) Pedestrian detection device and method
Wu et al. ClothGAN: generation of fashionable Dunhuang clothes using generative adversarial networks
CN106777086A (en) A kind of webpage buries dynamic management approach and device a little
CN105867951A (en) Data processing method and device as well as screen designer
CN105447765A (en) Distribution network feeder automatic mapping method
CN110120087A (en) The label for labelling method, apparatus and terminal device of three-dimensional sand table
US20110154254A1 (en) System and method for setting goals and modifying segment criteria counts
CN105808682A (en) Relational graph display method and apparatus
CN103136669A (en) Product display method and product display system based on product model base
CN109614577A (en) A kind of Burgers equation solution method and device
JP6068507B2 (en) Automatic demand parameter estimation
CN106777304B (en) Theme pushing method and device

Legal Events

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