CN107437200A - Information determines method and device - Google Patents
Information determines method and device Download PDFInfo
- Publication number
- CN107437200A CN107437200A CN201710508208.8A CN201710508208A CN107437200A CN 107437200 A CN107437200 A CN 107437200A CN 201710508208 A CN201710508208 A CN 201710508208A CN 107437200 A CN107437200 A CN 107437200A
- Authority
- CN
- China
- Prior art keywords
- attribute
- preference
- type attribute
- user
- order
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of information and determines method and device.Wherein, method includes the steps:The History Order record of same user is obtained, includes History Order in the History Order record;According to the type attribute belonging to the order contents item included in the History Order, the order contents item that type attribute is first kind attribute is extracted from History Order record;The time difference according to type attribute for lower single time gap reference time of the order contents item of the first kind attribute, calculate preference of the user to the first kind attribute.The embodiment of the present invention can accurately determine out the actual preference of user.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of information to determine method and device.
Background technology
By carrying out statistics calculating to various consumer behavior data, the order data of electric business platform user colony, to draw
Preference of the user to some " things ".Here " things " can be a kind of commodity or class I goods.Such as
Taking out platform, commodity here can be a course (tomato scrambled eggs) or a style of cooking (Sichuan cuisine) or
One taste (pungent) etc..
In existing scheme, typically according to user on electric business platform for some things historical trading number it is more
It is few to determine preference of the user to the things, such as:More for the historical trading number of a certain things, user is to the things
Preference it is bigger.It can be seen that in the prior art determine user it is excessively simple to the method for the preference of a certain things, and with reality
Border preference deviation is larger.
The content of the invention
This existing scheme judges the purchase preference of user according only to the number of the historical trading number of user.Essence
On, the preference of user can occur to change over time, that is to say, that user is directed to the historical trading of some things
It often can not also represent user's current slot preference things;User for some things historical trading number less also without
Method represents user's current slot not preference things.Can not be accurate it can be seen that determining that method is using preference of the prior art
Really determine the currently practical preference of user.
Then, in one embodiment of the invention, there is provided a kind of information determines method.This method includes:Obtain same
The History Order record of one user, the History Order include History Order in recording;Included according in the History Order
Order contents item belonging to type attribute, from History Order record extract type attribute and being ordered for first kind attribute
Single content item;According to type attribute for the first kind attribute order contents item lower single time gap reference time when
Difference, calculate preference of the user to the first kind attribute.
Alternatively, type attribute is that the quantity of the order contents item of the first kind attribute is two or more;
The time difference according to lower single time gap reference time of the type attribute for the order contents item of the first kind attribute, meter
Preference of the user to the first kind attribute is calculated, including:Based on type attribute in the order of the first kind attribute
Hold the time difference of reference time described in lower single time gap of item, calculated using the time difference and preference influence value in the computation rule of inverse ratio
Type attribute is preference influence value corresponding to each order contents item in the order contents item of the first kind attribute;By type category
Property summed for preference influence value corresponding to each order contents item in the order contents item of the first kind attribute, obtain total
With;Numerical value conversion is carried out to the summation, to obtain the numerical value in default closed interval, using the numerical value as described in
Preference of the user to the first kind attribute.
Alternatively, numerical value conversion is carried out to the summation, to obtain the numerical value in default closed interval, including:
Input using the summation as arctan function, a number in the range of the arctan function codomain is calculated
Value.
Alternatively, described information determines that method may also include:Based on default point of system, the preference is modified to obtain
The span required to the default point of system.
Alternatively, methods described, may also include:According to the type belonging to the order contents item included in the History Order
Attribute, the order contents item that type attribute is Second Type attribute is extracted from History Order record;According to type attribute
For the time difference of lower single time gap reference time of the order contents item of the Second Type attribute, user is calculated to described second
The preference of type attribute;Compare the user to the preference of the first kind attribute and the user to second class
The preference of type attribute;According to the comparative result, for the user recommend respective type attribute service provider information and/
Or service content information.
In another embodiment of the invention, there is provided a kind of information determining means.The device includes:Acquisition module, use
Include History Order in the History Order record for obtaining same user, the History Order record;Extraction module, for root
According to the type attribute belonging to the order contents item in the History Order, extraction type attribute is from History Order record
The order contents item of first kind attribute;Computing module, for according to type attribute for the first kind attribute order in
Hold the time difference of lower single time gap reference time of item, calculate preference of the user to the first kind attribute.
In another embodiment of the present invention, there is provided a kind of electronic equipment.The electronic equipment includes processor and storage
Device, the memory are used to store one or more computer instruction, and one or more computer instruction is by the processing
Device can realize that above- mentioned information determines the step in method when performing.
In another embodiment of the present invention, there is provided a kind of computer-readable storage medium for being stored with computer program
Matter, it can realize that above- mentioned information determines the step in method when the computer program is computer-executed.
Technical scheme provided in an embodiment of the present invention, recorded according to the History Order of user and obtain the user to same
Lower single time of the multiple order contents item of type attribute, further according to lower single time of multiple order contents item, to determine the use
Preference of the family to the type attribute.It can be seen that this programme also introduces time factor this feature when calculating user preference and spending,
The preference being calculated possesses preferably ageing, can accurately reflect the actual preference of user's current slot, solve existing
Judge the problem of user preference degree error is big only in accordance with single factors with the presence of in technology.
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 this hairs
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet that the information that one embodiment of the invention provides determines method;
Fig. 2 is the schematic flow sheet that the information that another embodiment of the present invention provides determines method;
Fig. 3 is the structured flowchart for the information determining means that one embodiment of the invention provides;
Fig. 4 is the structured flowchart for the information determining means that another embodiment of the present invention provides;
Fig. 5 is the structured flowchart for the electronic equipment that one embodiment of the invention provides.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described.
In some flows described in the specification, claims and above-mentioned accompanying drawing of the present invention, contain according to spy
Multiple operations that fixed order occurs, these operations can not be performed or performed parallel according to the order that it occurs herein.
The sequence number of operation such as 101,102 etc., it is only used for distinguishing each different operation, it is suitable that sequence number does not represent any execution in itself
Sequence.In addition, these flows can include more or less operations, and these operations can in order be performed or held parallel
OK.It should be noted that the description such as herein " first ", " second ", be for distinguishing different message, equipment, module etc.,
Sequencing is not represented, it is different types also not limit " first " and " second ".
The design philosophy of the present invention is introduced first:Due to user for some things preference such as when anaplasia
To change and change, that is to say, that influence of the trading activity of user over time to the current preference of user is more and more weaker,
And influence of the nearest trading activity of user to preference is stronger.Therefore, calculate user preference spend when, it is necessary to the time of introducing because
This sub characteristic, to improve the calculating accuracy of user preference degree.
Based on above-mentioned invention thought, the embodiments of the invention provide be implemented as follows.Below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described.Obviously, described embodiment is only
Only it is part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those skilled in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Fig. 1 is the schematic flow sheet that the information that one embodiment of the invention provides determines method.As shown in figure 1, this method bag
Include:
101st, the History Order record of same user is obtained, includes History Order in the History Order record.
102nd, the type attribute according to belonging to the order contents item included in the History Order, remember from the History Order
The order contents item that type attribute is first kind attribute is extracted in record.
103rd, lower single time gap reference time according to type attribute for the order contents item of the first kind attribute
The time difference, calculate user to the preference of the first kind attribute.
In above-mentioned steps 101, include at least one History Order in History Order record, in a History Order
Include at least one order contents item.When user place an order purchase commodity in electric business platform, placing an order for user can be directed to
Behavior carries out record and forms an order record information, the i.e. corresponding order record information of an order, an order record
Information includes one or more order contents items and lower single time.Wherein, an order contents item include trade name,
The affiliated businessman of commodity.Optionally, the type attribute determined according to each order contents item is may also include in order record information.
For different electric business platforms, type attribute would also vary from.Such as:For clothes website dress ornament according to dress ornament style
(such as:National wind, American-European wind, academic attitude) classified, then just include dress ornament style in type attribute;According to dress ornament material
(such as:Cotton, silk, polyester fiber etc.) classified, then just include dress ornament material in type attribute.For taking out platform
On dish according to the style of cooking (such as:Guangdong dishes, Sichuan cuisine, Hunan cuisine) classified, then, just include the style of cooking in type attribute;According to
Taste (acid, sweet tea, hardship, peppery, salty fresh) is classified, then, just include taste in type attribute;According to name of the dish (such as tomato
Egg, fry cooking shredded potato with sweet sour sauce quickly) classified, then, just include name of the dish in type attribute.
If the order record information unification of all users on electric business platform is stored in a daily record, order record is preserved
User identity information is correspondingly preserved during information, such as:ID or login name.Remember when needing the History Order for obtaining a certain user
During record, then order record letter corresponding with the user identity information can be obtained from the daily record according to user identity information
Breath, that is, get the History Order record of the user.
If electric business platform descends single user individually to establish a daily record for each, and is uniquely marked with user identity information
Know corresponding daily record, the order record information of each user is correspondingly stored in the day using the user identity information of each user as mark
In will.When needing to obtain the History Order record of a certain user, then can be found according to user identity information with the user
Identification information is the daily record of mark, and the order record information of the user is obtained from the daily record, that is, gets the user
History Order record.
In above-mentioned steps 102, after the History Order for getting the user records, if in History Order record not
Type attribute corresponding to each order contents item is recorded, then can be obtained by obtaining type label corresponding to each order contents item
Type attribute corresponding to each order contents item.I.e. directly using type label corresponding to individual order contents item as each order contents item
Type attribute.Under normal circumstances, electric business platform can be that each commodity on platform mark at least one type label.For example,
Spicy hot pot, platform can mark at least one type label for it in advance, such as:The type labels such as peppery, Sichuan cuisine.If History Order
Record has type attribute corresponding to each order contents item in record, then can directly obtain type corresponding to each order contents item
Attribute.
According to the type attribute belonging to the order contents item included in the History Order, from History Order record
Extract the order contents item that type attribute is first kind attribute.
Due to the preference of user be can over time and send change, namely user lower single act over time
The passage preference program current on user influence more and more weaker, can be institute according to type attribute in above-mentioned steps 103 therefore
The time difference of lower single time gap reference time of the order contents item of first kind attribute is stated, calculates user to the first kind
The preference of attribute.Wherein, reference time can be current day or the initial time in current week (for example, when the day before yesterday is 2017 6
The moon 26, then reference time is 0 minute June 26 day 0 point in 2017;Current week is the 25th week 2017, then reference time is the 25th
0 minute 0 point of week), or it is current time.
In a kind of achievable scheme, in advance for influence value corresponding to different time difference section settings, the time difference is bigger,
Corresponding influence value is smaller.Lower single time gap reference according to type attribute for the order contents item of the first kind attribute
The time difference of time, influence value corresponding to the time difference section of the time difference place is obtained, using the influence value as the order contents
Preference influence value corresponding to., will if type attribute is that the quantity of the order contents item of the first kind attribute is one
Preference of the preference influence value as the user to the first kind attribute.If type attribute is the first kind
The quantity of the order contents item of attribute is two or more, then by type attribute in the order of the first kind attribute
Preference influence value corresponding to each order contents items of Rong Xiangzhong is summed, and obtains final preference.
In another achievable scheme, based on type attribute under the order contents item of the first kind attribute
The time difference of reference time described in single time gap, type attribute is calculated in the computation rule of inverse ratio using the time difference and preference influence value
Preference influence value corresponding to each order contents item in order contents item for the first kind attribute.It is described by type attribute
Preference influence value corresponding to each order contents item is summed in the order contents item of first kind attribute, obtains the user couple
The preference of the first kind attribute.It should be noted that if type attribute is the order contents of the first kind attribute
Quantity be one, then directly using preference influence value corresponding to an order contents item as the user to described first
The preference of type attribute.In actual applications, can be by setting a monotonic decreasing function to realize duration and preference influence value
In the computation rule of inverse ratio.
Technical scheme provided in an embodiment of the present invention, recorded according to the History Order of user and obtain the user to same
Lower single time of the multiple order contents item of type attribute, further according to lower single time of multiple order contents item, to determine the use
Preference of the family to the type attribute.It can be seen that this programme also introduces time factor this feature when calculating user preference and spending,
The preference being calculated possesses preferably ageing, can accurately reflect the actual preference of user's current slot, solve existing
Judge the problem of user preference degree error is big only in accordance with single factors with the presence of in technology.
In above-described embodiment or following each embodiments, methods described, it may also include:Included according in the History Order
Order contents item belonging to type attribute, from History Order record extract type attribute and being ordered for Second Type attribute
Single content item;According to type attribute for the Second Type attribute order contents item lower single time gap reference time when
Difference, calculate preference of the user to the Second Type attribute;Compare preference of the user to the first kind attribute
Preference with the user to the Second Type attribute;According to the comparative result, recommend respective type for the user
The service provider information and/or service content information of attribute.
Wherein, the service provider information refers to the related Business Information of the type attribute;The service content
Information refers to the related merchandise news of the type attribute.Preference that can be according to above-mentioned calculating user to first kind attribute
Method calculate user to the preference of Second Type attribute.If user is more than the user couple to the preference of Second Type attribute
The preference of first kind attribute, then recommend Business Information and/or merchandise news corresponding to Second Type attribute to the user.
If the History Order content item of user corresponds to two or more type attribute, the user is calculated to its history
The preference of all types attribute corresponding to order contents item, preference is recommended to exceed at least one of predetermined threshold value for the user
Type attribute related service provider information and/or service content information.
Fig. 2 is the schematic flow sheet that the information that further embodiment of this invention provides determines method.In the present embodiment, type
Attribute is that the quantity of the order contents item of the first kind attribute is two or more.As shown in Fig. 2 this method bag
Include:
201st, the History Order record of same user is obtained, includes History Order in the History Order record.
202nd, the type attribute according to belonging to the order contents item included in the History Order, remember from the History Order
The order contents item that type attribute is first kind attribute is extracted in record.
203rd, it is reference described in lower single time gap of the order contents item of the first kind attribute based on type attribute
The time difference of time, the time difference is used to calculate type attribute in the computation rule of inverse ratio as the first kind attribute with preference influence value
Order contents item in preference influence value corresponding to each order contents item.
204th, it is preference corresponding to each order contents item in the order contents item of the first kind attribute by type attribute
Influence value is summed, and obtains summation.
205th, numerical value conversion is carried out to the summation, to obtain the numerical value in default closed interval, by the number
It is worth the preference as the user to the first kind attribute.
Above-mentioned steps 201-202 can be found in corresponding contents in above-described embodiment, will not be repeated here.
In above-mentioned steps 203, by setting a monotonic decreasing function time difference can be realized with preference influence value in inverse ratio
Computation rule.Optionally, the present embodiment is realized using following power functions (1):
F (x)=xa(a<0) (1)
Wherein, x is the time difference, and f (x) is preference influence value, and x ∈ (0 ,+∞), f (x) ∈ (0 ,+∞), a are constant and be less than
Zero, a value can be adjusted according to the demand of practical business product, and the present invention is not especially limited to this.
Preference influences according to corresponding to above-mentioned power function (1) can calculate each order contents item in multiple order contents items
Value.In above-mentioned steps 204, it can be summed by following summing functions (2):
Wherein, n be user correspond to the type attribute lower single number, xiIt is lower single time gap that ith places an order
The time difference of the current time, a are above-mentioned constant.
Due to above-mentioned summing function y ∈ (0 ,+∞), in other words, the user preference degree finally drawn is an infinite area
Between (0 ,+∞), this is unfavorable for practical application, therefore, can be by the above-mentioned user being calculated in the step 205 of the present embodiment
Preference is transformed into a default closed interval.
In an achievable scheme, numerical value conversion is carried out to the summation, to obtain one in default closed interval
Numerical value, specifically, the input using the summation as arctan function, be calculated one and be in the arctan function value
Numerical value in the range of domain, using preference of the numerical value as the user to the type attribute.
The arctan function is:
Wherein, n be user correspond to the type attribute lower single number, xiIt is lower single time gap that ith places an order
The time difference of the current time, and g (x) ∈ [0, pi/2) (i.e. the codomain scope of arctan function (3)).Thus by above-mentioned calculating
Obtained user preference degree is transformed into the range of the arctan function codomain.
In the various embodiments described above or following each embodiments, methods described also includes:Based on default point of system, by the preference
Degree is modified to obtain the span that the default point of system requires.In actual applications, can be by correcting user preference degree
Calculation formula realize.
Due to above-mentioned g (x) codomain scope for [0, pi/2), then revised user preference degree calculation formula (4) is:
Wherein, n be user correspond to the type attribute lower single number, xiIt is lower single time gap that ith places an order
The time difference of the current time, a are constant and are modifying factor less than zero, b.B value determines according to default point of system, if default
Divide and be made as hundred-mark system, then b=100, if default point is made as ten point system, b=10.
Technical scheme provided in an embodiment of the present invention, recorded according to the History Order of user and obtain the user to same
Lower single time of the multiple order contents item of type attribute, further according to lower single time of multiple order contents item, to determine the use
Preference of the family to the type attribute.It can be seen that this programme also introduces time factor this feature when calculating user preference and spending,
The preference being calculated possesses preferably ageing, can accurately reflect the actual preference of user's current slot, solve existing
Judge the problem of user preference degree error is big only in accordance with single factors with the presence of in technology.
Below to take out platform, described in detail exemplified by calculating user's taste preference degree:
Taste type is first set, is peppery, sweet tea respectively, acid, salty fresh etc., taking out platform every dish product has its taste class
Type, preference of the user for taste is calculated according to the take-away order data of user, default point is made as hundred-mark system.
Basic data is extracted from the History Order record of user first, content is as shown in table 1 below:
Table 1
If calculating ID 1 to the preference of peppery taste, the P in above-mentioned tables of data and K are updated to above-mentioned user
Can be calculated in preference calculation formula (4) span [0,100) preference:
It should be noted that:The executive agent that above-described embodiment provides each step of method may each be same equipment,
Or this method is also by distinct device as executive agent.For example the executive agent of step 101 to step 103 can be equipment
A;Again for example, step 101 and 102 executive agent can be device A, and the executive agent of step 103 can be equipment B;Etc..
Fig. 3 is the structured flowchart for the information determining means that one embodiment of the invention provides.As shown in figure 3, the device includes:
Acquisition module 301, extraction module 302 and computing module 303.Wherein, acquisition module 301, for obtaining going through for same user
History order record, the History Order include History Order in recording.Extraction module 302, for according to the History Order
In type attribute belonging to the order contents item that includes, it is first kind category to extract type attribute from History Order record
The order contents item of property.Computing module 303, for according to type attribute for the first kind attribute order contents item under
The time difference of single time gap reference time, calculate preference of the user to the first kind attribute.
The technical scheme that the present embodiment provides, recorded according to the History Order of user and obtain the user to same type
Lower single time of the multiple order contents item of attribute, further according to lower single time of multiple order contents item, to determine the user couple
The preference of the type attribute.It can be seen that this programme also introduces time factor this feature when calculating user preference and spending, calculate
Obtained preference possess preferably it is ageing, the actual preference of user's current slot can be accurately reflected, solve existing skill
Judge that user preference degree has the problem of error is big only in accordance with single factors in art.
Further, type attribute be the quantity of the order contents item of the first kind attribute be two or two with
On.As shown in figure 4, above-mentioned computing module 303 can use following structure to realize.The computing module 303, including:Calculate single
Member 401, for based on type attribute for the first kind attribute order contents item lower single time gap described in reference when
Between the time difference, use the time difference and preference influence value to calculate type attribute in the computation rule of inverse ratio as the first kind attribute
Preference influence value corresponding to each order contents item in order contents item.Sum unit 402, for being described first by type attribute
Preference influence value corresponding to each order contents item is summed in the order contents item of type attribute, obtains summation.Converting unit
403, for carrying out numerical value conversion to the summation, to obtain the numerical value in default closed interval, the numerical value is made
Preference for the user to the first kind attribute.
Further, above-mentioned converting unit 403 can be specifically used for:Input using the summation as arctan function,
The numerical value in the range of the arctan function codomain is calculated.
Further, described device may also include correcting module.Correcting module is used for based on default point of system, by the preference
Degree is modified to obtain the span that the default point of system requires.
Further, described device, comparison module, recommending module be may also include.The extraction module 302, for basis
The type attribute belonging to order contents item included in the History Order, type attribute is extracted from History Order record
For the order contents item of Second Type attribute.The computing module 303, for being the Second Type attribute according to type attribute
Order contents item lower single time gap reference time the time difference, calculate user to the preference of the Second Type attribute.
Comparison module, for the user to the preference of the first kind attribute and the user to the Second Type category
The preference of property.Recommending module, for according to the comparative result, the service for recommending respective type attribute for the user to provide
Square information and/or service content information.
Need exist for explanation be:The information determining means that above-described embodiment provides can be realized in above-mentioned each method embodiment
The principle of the technical scheme of description, above-mentioned each module or unit specific implementation can be found in corresponding interior in above-mentioned each method embodiment
Hold, here is omitted.
One embodiment of the invention also provides a kind of electronic equipment.As shown in figure 5, the electronic equipment includes the He of processor 501
Memory 502, the memory 502, which is used to store, supports processor 501 to perform the information determination side that the various embodiments described above provide
The program of method, the processor 501 are configurable for performing the program stored in the memory 502.
Described program includes one or more computer instruction, wherein, described in the one or more computer instruction confession
Processor 501, which calls, to be performed.One or more computer instruction can realize that above- mentioned information is true when being performed by processor 501
Determine the step in method.
Memory 502 is used as a kind of non-volatile computer readable storage medium storing program for executing, available for storage non-volatile software journey
Sequence, non-volatile computer executable program and module, the program as corresponding to the information in the embodiment of the present invention determines method
Instruction/module (for example, acquisition module 301, extraction module 302 and computing module 303 shown in accompanying drawing 3).Processor 501 passes through
Operation is stored in non-volatile software program, instruction and module in memory 502, so as to perform the various work(of electronic equipment
It can apply and data processing, that is, realize that the information of above method embodiment determines method.
The processor 501 is used for:The History Order record of same user is obtained, is included in the History Order record
History Order;According to the type attribute belonging to the order contents item included in the History Order, recorded from the History Order
Middle extraction type attribute is the order contents item of first kind attribute;According to the order that type attribute is the first kind attribute
The time difference of lower single time gap reference time of content item, calculate preference of the user to the first kind attribute.
Processor 501 can perform the method that the embodiment of the present invention is provided, possess the corresponding functional module of execution method and
Beneficial effect, not ins and outs of detailed description in the present embodiment, reference can be made to the method that the embodiment of the present application is provided.
A kind of computer-readable recording medium for being stored with computer program that the embodiment of the present invention also provides, the calculating
Machine program can realize that the information that the various embodiments described above provide determines the step in method when being computer-executed.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can
To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list
Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs
In some or all of module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that:It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic;
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
The invention discloses A1, a kind of information to determine method, including:
The History Order record of same user is obtained, includes History Order in the History Order record;
According to the type attribute belonging to the order contents item included in the History Order, from History Order record
Extract the order contents item that type attribute is first kind attribute;
According to type attribute for the first kind attribute order contents item lower single time gap reference time when
Difference, calculate preference of the user to the first kind attribute.
A2, the method as described in A1, type attribute are that the quantity of the order contents item of the first kind attribute is two
Or two or more;And
Lower single time gap reference time according to type attribute for the order contents item of the first kind attribute
The time difference, calculate user to the preference of the first kind attribute, including:
It is reference time described in lower single time gap of the order contents item of the first kind attribute based on type attribute
The time difference, use the time difference and preference influence value to calculate type attribute ordering for the first kind attribute in the computation rule of inverse ratio
Preference influence value corresponding to each order contents item in single content item;
Type attribute is influenceed for preference corresponding to each order contents item in the order contents item of the first kind attribute
Value is summed, and obtains summation;
Numerical value conversion is carried out to the summation, to obtain the numerical value in default closed interval, the numerical value made
Preference for the user to the first kind attribute.
A3, the method as described in A2, numerical value conversion is carried out to the summation, to obtain one in default closed interval
Numerical value, including:
Input using the summation as arctan function, it is calculated one and is in the arctan function codomain scope
Interior numerical value.
A4, the method as any one of A1 to A3, in addition to:
Based on default point of system, the preference is modified to obtain the span that the default point of system requires.
A5, the method as any one of A1 to A3, in addition to:
According to the type attribute belonging to the order contents item included in the History Order, from History Order record
Extract the order contents item that type attribute is Second Type attribute;
According to type attribute for the Second Type attribute order contents item lower single time gap reference time when
Difference, calculate preference of the user to the Second Type attribute;
Compare the user to the preference of the first kind attribute and the user to the Second Type attribute
Preference;
According to the comparative result, recommend service provider information and/or the service of respective type attribute for the user
Content information.
The invention also discloses B6, a kind of information determining means, including:
Acquisition module, the History Order for obtaining same user record, and include history in the History Order record
Order;
Extraction module, for the type attribute according to belonging to the order contents item included in the History Order, from described
The order contents item that type attribute is first kind attribute is extracted in History Order record;
Computing module, for lower single time gap according to type attribute for the order contents item of the first kind attribute
The time difference of reference time, calculate preference of the user to the first kind attribute.
B7, the device as described in B6, type attribute are that the quantity of the order contents item of the first kind attribute is two
Or two or more;And
The computing module, including:
Computing unit, for lower single time gap based on type attribute for the order contents item of the first kind attribute
The time difference of the reference time, the time difference is used to calculate type attribute in the computation rule of inverse ratio as described first with preference influence value
Preference influence value corresponding to each order contents item in the order contents item of type attribute;
Sum unit, for type attribute is right for each order contents item in the order contents item of the first kind attribute
The preference influence value answered is summed, and obtains summation;
Converting unit, for carrying out numerical value conversion to the summation, to obtain the numerical value in default closed interval,
Using preference of the numerical value as the user to the first kind attribute.
B8, the device as described in B7, the converting unit are specifically used for:
Input using the summation as arctan function, it is calculated one and is in the arctan function codomain scope
Interior numerical value.
B9, the device as any one of B6 to B8, in addition to:
Correcting module, for based on default point of system, the preference being modified and required with obtaining the default point of system
Span.
B10, the device as any one of B6 to B8, in addition to:
The extraction module, for the type attribute according to belonging to the order contents item included in the History Order, from
The order contents item that type attribute is Second Type attribute is extracted in the History Order record;
The computing module, for lower single time according to type attribute for the order contents item of the Second Type attribute
Apart from the time difference of reference time, preference of the user to the Second Type attribute is calculated;
Comparison module, for the user to the preference of the first kind attribute and the user to described the
The preference of two type attributes;
Recommending module, for being the service provider that the user recommends respective type attribute according to the comparative result
Information and/or service content information.
The invention also discloses C11, a kind of electronic equipment, including memory and processor;The memory is used to store
One or more computer instruction, one or more computer instruction can be realized above-mentioned during the computing device
Any one of A1-A5 described informations determine the step in method.
The invention also discloses D12, a kind of computer-readable recording medium for being stored with computer program, the computer
Program can realize that any one of above-mentioned A1-A5 described information determines the step in method when being computer-executed.
Claims (10)
1. a kind of information determines method, it is characterised in that including:
The History Order record of same user is obtained, includes History Order in the History Order record;
According to the type attribute belonging to the order contents item included in the History Order, extracted from History Order record
Type attribute is the order contents item of first kind attribute;
The time difference according to type attribute for lower single time gap reference time of the order contents item of the first kind attribute, meter
Calculate preference of the user to the first kind attribute.
2. according to the method for claim 1, it is characterised in that
Type attribute is that the quantity of the order contents item of the first kind attribute is two or more;And
It is described according to type attribute for the first kind attribute order contents item lower single time gap reference time when
Difference, preference of the user to the first kind attribute is calculated, including:
Based on type attribute for the first kind attribute order contents item lower single time gap described in reference time when
Difference, the time difference is used to calculate type attribute in the computation rule of inverse ratio as in the order of the first kind attribute with preference influence value
Preference influence value corresponding to each order contents items of Rong Xiangzhong;
Type attribute is entered for preference influence value corresponding to each order contents item in the order contents item of the first kind attribute
Row summation, obtains summation;
Numerical value conversion is carried out to the summation, to obtain the numerical value in default closed interval, using the numerical value as institute
State preference of the user to the first kind attribute.
3. according to the method for claim 2, it is characterised in that numerical value conversion is carried out to the summation, to obtain at one
Numerical value in default closed interval, including:
Input using the summation as arctan function, one is calculated in the range of the arctan function codomain
Numerical value.
4. according to the method in any one of claims 1 to 3, it is characterised in that also include:
Based on default point of system, the preference is modified to obtain the span that the default point of system requires.
5. according to the method in any one of claims 1 to 3, it is characterised in that also include:
According to the type attribute belonging to the order contents item included in the History Order, extracted from History Order record
Type attribute is the order contents item of Second Type attribute;
The time difference according to type attribute for lower single time gap reference time of the order contents item of the Second Type attribute, meter
Calculate preference of the user to the Second Type attribute;
Compare preference of the user to the preference of the first kind attribute with the user to the Second Type attribute
Degree;
According to the comparative result, for the service provider information and/or service content of user recommendation respective type attribute
Information.
A kind of 6. information determining means, it is characterised in that including:
Acquisition module, the History Order for obtaining same user record, and include History Order in the History Order record;
Extraction module, for the type attribute according to belonging to the order contents item included in the History Order, from the history
The order contents item that type attribute is first kind attribute is extracted in order record;
Computing module, for lower single time gap reference according to type attribute for the order contents item of the first kind attribute
The time difference of time, calculate preference of the user to the first kind attribute.
7. device according to claim 6, it is characterised in that
Type attribute is that the quantity of the order contents item of the first kind attribute is two or more;And
The computing module, including:
Computing unit, for described in lower single time gap based on the order contents item that type attribute is the first kind attribute
The time difference of reference time, the time difference is used to calculate type attribute in the computation rule of inverse ratio as the first kind with preference influence value
Preference influence value corresponding to each order contents item in the order contents item of attribute;
Sum unit, for by type attribute in the order contents item of the first kind attribute corresponding to each order contents item
Preference influence value is summed, and obtains summation;
Converting unit, for carrying out numerical value conversion to the summation, to obtain the numerical value in default closed interval, by institute
State preference of the numerical value as the user to the first kind attribute.
8. device according to claim 7, it is characterised in that the converting unit is specifically used for:
Input using the summation as arctan function, one is calculated in the range of the arctan function codomain
Numerical value.
9. the device according to any one of claim 6 to 8, it is characterised in that also include:
Correcting module, for dividing system based on default, the preference is modified to obtain taking for the default point of system requirement
It is worth scope.
10. the device according to any one of claim 6 to 8, it is characterised in that also include:
The extraction module, for the type attribute according to belonging to the order contents item included in the History Order, from described
The order contents item that type attribute is Second Type attribute is extracted in History Order record;
The computing module, for lower single time gap according to type attribute for the order contents item of the Second Type attribute
The time difference of reference time, calculate preference of the user to the Second Type attribute;
Comparison module, for the user to the preference of the first kind attribute and the user to second class
The preference of type attribute;
Recommending module, for being the service provider information that the user recommends respective type attribute according to the comparative result
And/or service content information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710508208.8A CN107437200A (en) | 2017-06-28 | 2017-06-28 | Information determines method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710508208.8A CN107437200A (en) | 2017-06-28 | 2017-06-28 | Information determines method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107437200A true CN107437200A (en) | 2017-12-05 |
Family
ID=60459614
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710508208.8A Pending CN107437200A (en) | 2017-06-28 | 2017-06-28 | Information determines method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107437200A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109377023A (en) * | 2018-09-28 | 2019-02-22 | 北京三快在线科技有限公司 | Distribution method, device and the electronic equipment of order |
JP2021513166A (en) * | 2018-02-09 | 2021-05-20 | オカド・イノベーション・リミテッド | Customer personalization control units, systems, and methods |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140087175A (en) * | 2012-12-28 | 2014-07-09 | 한국기술교육대학교 산학협력단 | Apparatus and method for recommending friend |
CN105740480A (en) * | 2016-03-29 | 2016-07-06 | 上海携程商务有限公司 | Air ticket recommending method and system |
CN105824929A (en) * | 2016-03-17 | 2016-08-03 | 上海交通大学 | Air ticket personalized recommendation method and system based on social relationship |
-
2017
- 2017-06-28 CN CN201710508208.8A patent/CN107437200A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20140087175A (en) * | 2012-12-28 | 2014-07-09 | 한국기술교육대학교 산학협력단 | Apparatus and method for recommending friend |
CN105824929A (en) * | 2016-03-17 | 2016-08-03 | 上海交通大学 | Air ticket personalized recommendation method and system based on social relationship |
CN105740480A (en) * | 2016-03-29 | 2016-07-06 | 上海携程商务有限公司 | Air ticket recommending method and system |
Non-Patent Citations (1)
Title |
---|
李文哲: "基于时效性的优先新品的推荐方法", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2021513166A (en) * | 2018-02-09 | 2021-05-20 | オカド・イノベーション・リミテッド | Customer personalization control units, systems, and methods |
US11468502B2 (en) | 2018-02-09 | 2022-10-11 | Ocado Innovation Limited | Customer personalised control unit, system and method |
JP7203855B2 (en) | 2018-02-09 | 2023-01-13 | オカド・イノベーション・リミテッド | Customer Personalized Control Unit, System and Method |
CN109377023A (en) * | 2018-09-28 | 2019-02-22 | 北京三快在线科技有限公司 | Distribution method, device and the electronic equipment of order |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107835231B (en) | Feedback information processing method and terminal equipment | |
CN104866484B (en) | A kind of data processing method and device | |
CN108320213A (en) | Electric business Method of Commodity Recommendation and electric business Platform Server | |
WO2018136747A1 (en) | Systems, apparatuses, and methods for extracting inventory from unstructured electronic messages | |
EP2779058A1 (en) | Recommendations based upon explicit user similarity | |
CN107092647B (en) | Method and device for providing resource combination | |
CN107092616B (en) | Object sorting method and device | |
US20130275270A1 (en) | Method, web server and web browser of providing information | |
CN105184600A (en) | Rule and operation-based electronic business platform price engine implementing method | |
US8352301B1 (en) | Sales opportunity notification and tracking system and related methods | |
CN110163705A (en) | Method and apparatus for pushed information | |
CN108596705A (en) | A kind of commodity suitable for e-commerce recommend method and system with information classification | |
CN107562613A (en) | Program testing method, apparatus and system | |
Yusoff | The effects of real exchange rate on trade balance and domestic output: A case of Malaysia | |
EP2524345A1 (en) | Attribute aggregation for standard product unit | |
WO2018142753A1 (en) | Information processing device, method, and program that use deep learning | |
CN107679945A (en) | Method for establishing consumer objects recommended models and associated method and device | |
Jayaswal et al. | Price and lead time differentiation, capacity strategy and market competition | |
CN110033324A (en) | Data processing method, device, electronic equipment and computer readable storage medium | |
CN107437200A (en) | Information determines method and device | |
Chiappini | Do overseas investments create or replace trade? New insights from a macro-sectoral study on Japan | |
CN108229758A (en) | Service providing method, device, electronic equipment and computer readable storage medium | |
CN109993566A (en) | A kind of method and apparatus for predicting product objective data | |
CN107292643A (en) | Automatic price adjustment method and its system of readjusting prices automatically based on the network market | |
CN107633422A (en) | A kind of market prediction method and device based on user behavior |
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: 20171205 |
|
RJ01 | Rejection of invention patent application after publication |