CN107895213A - Forecasting Methodology, device and the electronic equipment of spending limit - Google Patents
Forecasting Methodology, device and the electronic equipment of spending limit Download PDFInfo
- Publication number
- CN107895213A CN107895213A CN201711269842.7A CN201711269842A CN107895213A CN 107895213 A CN107895213 A CN 107895213A CN 201711269842 A CN201711269842 A CN 201711269842A CN 107895213 A CN107895213 A CN 107895213A
- Authority
- CN
- China
- Prior art keywords
- shop
- user
- factor
- recommendation
- history
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
- G06Q30/0275—Auctions
-
- 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)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of Forecasting Methodology of spending limit, device and electronic equipment, and wherein method includes：Determine the history consumer record of user and the scene information related to the user；Based on the history consumer record and the scene information, it is defined as the shop that the user recommends；The store information of the history consumer record, the scene information and the shop of the recommendation is inputted into the mathematical modeling of training in advance；By user described in the mathematical model prediction in the spending limit in the shop of the recommendation.Technical scheme is by the way that the history consumer record of user, the scene information related to user and store information are input in the mathematical modeling of training in advance, spending limit of the user in the shop of recommendation is obtained by mathematical modeling, because the spending limit with reference to the information and store information related to user itself, therefore the consuming capacity of user can be more accurately predicted by the spending limit.
Description
Technical field
The application is related to Internet technical field, more particularly to a kind of Forecasting Methodology of spending limit, device and electronics are set
It is standby.
Background technology
With the deep development of Internet technology, a consumption habit by the shopping of electric business platform as users.
When user is done shopping by electric business platform, by browsing the retail shop registered in electric business platform, from user interface corresponding to retail shop
Select the commodity that its needs is bought.In the prior art, the order price for user in retail shop, it usually needs user is in retail shop
In choose the commodity that needs are bought, background server determines order price by way of placing an order, however, prior art is still not
User can be predicted in the spending limit of retail shop.
The content of the invention
In view of this, the application provides a kind of Forecasting Methodology of spending limit, device and electronic equipment, being capable of Accurate Prediction
Spending limit of the user in shop.
To achieve the above object, it is as follows to provide technical scheme by the application：
According to the first aspect of the application, it is proposed that a kind of Forecasting Methodology of consumption data, including：
Determine the history consumer record of user and the scene information related to the user；
Based on the history consumer record and the scene information, it is defined as the shop that the user recommends；
The store information of the history consumer record, the scene information and the shop of the recommendation is inputted to advance
In the mathematical modeling of training；
By user described in the mathematical model prediction in the spending limit in the shop of the recommendation.
According to the second aspect of the application, it is proposed that a kind of prediction meanss of spending limit, including：
First determining module, for the history consumer record for determining user and the scene information related to the user；
Second determining module, for the history consumer record and the scene determined based on first determining module
Information, it is defined as at least one shop that the user recommends；
Input module, for first determining module is determined the history consumer record, the scene information with
And the store information in the shop of the recommendation of the second determining module determination is inputted into the mathematical modeling of training in advance；
Prediction module, for by user described in the mathematical model prediction in the spending limit in the shop of the recommendation.
According to the third aspect of the application, it is proposed that a kind of computer-readable recording medium, the storage medium are stored with
Computer program, the computer program are used for the Forecasting Methodology for performing the spending limit that above-mentioned first aspect proposes.
Wherein, the processor, the Forecasting Methodology of the spending limit proposed for performing above-mentioned first aspect.
From above technical scheme, the application is by the way that the history consumer record of user, the scene related to user are believed
Breath and store information are inputted into the mathematical modeling of training in advance, pass through mathematical model prediction user disappearing in the shop of recommendation
Take amount, because the spending limit with reference to the information and store information related to user itself, therefore pass through the amount of consumption
Degree can more accurately predict the consuming capacity of user.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the exemplary embodiment of the application one.
Fig. 2 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the application further example embodiment.
Fig. 3 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the another exemplary embodiment of the application.
Fig. 4 is the structural representation of the electronic equipment shown in the exemplary embodiment of the application one.
Fig. 5 is the structural representation of the prediction meanss of the spending limit shown in the exemplary embodiment of the application one.
Fig. 6 is the structural representation of the prediction meanss of the spending limit shown in the application further example embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects be described in detail in claims, the application.
It is only merely for the purpose of description specific embodiment in term used in this application, and is not intended to be limiting the application.
" one kind " of singulative used in the application and appended claims, " described " and "the" are also intended to including majority
Form, unless context clearly shows that other implications.It is also understood that term "and/or" used herein refers to and wrapped
Containing the associated list items purpose of one or more, any or all may be combined.
It will be appreciated that though various information, but this may be described using term first, second, third, etc. in the application
A little information should not necessarily be limited by these terms.These terms are only used for same type of information being distinguished from each other out.For example, do not departing from
In the case of the application scope, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as
One information.Depending on linguistic context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determining ".
Fig. 1 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the exemplary embodiment of the application one；This implementation
Example can be applicable on the electronic equipments such as server, portable set, as shown in figure 1, comprising the following steps：
Step 101, the history consumer record of user and the scene information related to user are determined.
In one embodiment, the history consumer record of user may include：User is gone through by each under electric business platform
Payment Amount of the merchandise classification of history order, the time to be placed an order and each History Order etc..In one embodiment, may be used
To filter out the history consumer record of the user from the history consumer record of the mass users stored.
In one embodiment, the scene information related to user may include：It is geographical position that user is currently located, current
Date, current weather etc..In one embodiment, user can be positioned by electronic equipment to obtain what user was currently located
Geographical position, the weather in geographical position is currently located according to geographical position acquisition to user, can the system based on electronic equipment
Time determines the current date.
Step 102, based on history consumer record and scene information, it is defined as the shop that user recommends.
In one embodiment, the consumption average price of user can be determined based on history consumer record, is determined based on scene information
The address location of user.Based on consumption average price and geographical position, it is defined as the shop of user's recommendation, it is necessary to which explanation, recommends
Shop can be one, or two or more, the application are not limited to the quantity in the shop of recommendation.For example, user
Consumption average price be 100 yuan, current location be Chaoyang District, Beijing City Wangjing, then can be user recommend be located at Chaoyang District Wangjing simultaneously
And pre-capita consumption is in 100 or so ten shops, it may thereby be ensured that what the consumption level of user and the shop recommended provided
Excellent service standard matches.
Step 103, the store information of history consumer record, scene information and the shop of recommendation is inputted to training in advance
Mathematical modeling in.
In one embodiment, mathematical modeling can be that logistical regression (Logistic Regression, is referred to as
LR), gradient lifting decision tree (Gradient Boosting DecisionTree, referred to as GBDT), deep neural network
(Deep NeuralNetworks, referred to as DNN).
In one embodiment, the store information in the shop of recommendation may include：The public praise in shop point, means of distribution, shop disappear
Merchandise classification that expense person-time, shop visitor's unit price, history provide the user into single rate, shop etc..
Step 104, spending limit of the mathematical model prediction user in the shop of recommendation is passed through.
For example, for user ABC recommend 10 shop M1, M2 ..., M10, for shop M1, M2 ..., M10, by user
The store information of ABC history consumer record, the scene information related to during user's ABC current consumptions and shop M1 input to
In the mathematical modeling of training in advance, spending limits of the user ABC in shop M1 is obtained, it is similar, user ABC history is consumed
The store information of record, the scene information related to user ABC and shop M2 is inputted into the mathematical modeling of training in advance, is obtained
To user ABC shop M2 spending limit, for shop M3 ..., M10, pass through similar mode, you can obtain user in shop
Spread M1, M2 ..., the respective spending limits of M10.
In the present embodiment, by by the history consumer record of user, the scene information related to user and store information
Input is into the mathematical modeling of training in advance, by spending limit of the mathematical model prediction user in the shop of recommendation, due to disappearing
Expense amount with reference to the information and store information related to user itself, therefore can more accurately be predicted by spending limit
The consuming capacity of user.In addition, the shop of history consumer record, scene information and the shop of recommendation is handled by mathematical modeling
Information, easily mathematical modeling can be transplanted in the data services such as order ads strategy, orientation marketing, businessman's promotion, entered
And pushed away the spending limit that mathematical model prediction obtains as order ads strategy, orientation marketing, businessman's promotion, consumer personality
A reference factor in business such as recommend.
Fig. 2 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the application another exemplary embodiment；This reality
Example is applied on the basis of above-described embodiment, example is carried out exemplified by how being ranked up based on spending limit to the shop recommended
Property explanation, as shown in Fig. 2 comprising the following steps：
Step 201, for each shop in the shop of recommendation, the consumption data based on user in each shop,
Determine first revenue factor in each shop.
In one embodiment, for each shop in the shop of recommendation, disappeared based on history corresponding to each shop
Take number and history number of clicks, determine the conversion ratio in each shop, wherein, history consumption number of times can be each shop
Whole consumption number of times before being layered on current point in time, or going through in the preset time period before current point in time
History consumption number of times, for example, shop since the time point that electric business platform is registered, by the end of current point in time, shares 50 users
The history consumption number of times of 100 times are generated in the shop；History number of clicks can be each shop current point in time it
Preceding whole history numbers of clicks, or the history number of clicks in the preset time period before current point in time,
For example, shop since the time point that electric business platform is registered, by the end of current point in time, shares 50 users and produced in the shop
The history number of clicks of 200 times.In one embodiment, the ratio between history consumption number of times and history number of clicks can be passed through
Value, obtains the conversion ratio in each shop, for example, history consumption number of times are P, history number of clicks is Q, then shop conversion ratio
R=P/Q.
In one embodiment, each can be determined based on conversion ratio, user in the history spending limit in each shop
First revenue factor corresponding to shop；In one embodiment, conversion ratio can be multiplied with history spending limit or add and, obtain
To first revenue factor in shop.
Step 202, second revenue factor of the electric business platform with respect to each shop is determined.
In one embodiment, for each shop in the shop of recommendation, determine that each shop carries for electric business platform
The ad auction price of confession；Determine the ad click rate in each shop；Based on ad auction price and ad click rate, it is determined that
Electric business platform is with respect to the second revenue factor corresponding to each shop.In one embodiment, can be to ad auction price and wide
Clicking rate is accused to be multiplied or add and obtain the ad auction price that shop provides for electric business platform.
Step 203, the experience factor of the user in each shop is determined.
In one embodiment, the space length between each shop in the shop of user and recommendation is determined；It is determined that with
The experience factor corresponding to space length, the experience factor are the experience factor of the user in each shop.In one embodiment, may be used
With by searching distance-factor mapping table, determine space between each shop in the shop of user and recommendation away from
From, such as：Space length between user and shop is 5 kilometers, and the experience factor is 5 points, and space length is 3 kilometers, experience because
Son is 2.5 points, from there through distance-factor mapping table is searched, is searched from the mapping table corresponding with space length
The experience factor, and then can determine that the experience factor of the user in shop.
Step 204, second income in each relative shop of the first revenue factor based on each shop, electric business platform
The factor and user are in the experience factor in each shop, the shop sequence to recommendation.
In one embodiment, for each shop in the shop of recommendation, the first receipts corresponding to each shop are determined
The beneficial factor, electric business platform with respect to second revenue factor in each shop, user the experience factor in each shop weight
Coefficient；By weight coefficient to the of the first revenue factor corresponding to each shop, electric business platform with respect to each shop
The experience factor of two revenue factors, user in each shop is weighted, and obtains the score value in each shop；Based at least
One respective score value in shop, the shop of recommendation is sorted.
For example, for user ABC recommend 10 shop M1, M2 ..., M10, it is illustrative by taking the M1 of shop as an example,
Shop M1 the first revenue factor is a, and second revenue factor of the electric business platform with respect to shop M1 is b, body of the user in shop M1
It is c to test the factor, wherein, the weight coefficient of the first revenue factor is m1, and the weight coefficient of the second revenue factor is m2, experiences the factor
Weight coefficient be m3, then the above three factor is weighted by weight coefficient, the score value for obtaining shop M1 is：a*m1+
B*m2+c*m3, similarly, obtain the score value in remaining 9 shops.And then to this 10 shops according to score value it is descending or by
It is small to be ranked up to big order.
In the present embodiment, first revenue factor in shop is determined by spending limit of the user in each shop, based on
One revenue factor, the second revenue factor and the experience factor, realize the sequence to shop, due to passing through the first revenue factor, the
Two revenue factors and experience factor integration consider the factor of electric business platform, shop and user each side, therefore the present embodiment
In sequence to shop it is more reasonable.
Fig. 3 is the schematic flow sheet of the Forecasting Methodology of the spending limit shown in the another exemplary embodiment of the application；This reality
Example is applied on the basis of above-mentioned embodiment illustrated in fig. 1, it is illustrative exemplified by how training mathematical modeling, such as Fig. 3 institutes
Show, comprise the following steps：
Step 301, to each shop in the shop of the first setting quantity, second in the consumption of each shop is counted
Set the history consumer record of the user of quantity.
In one embodiment, the first setting quantity and the second setting quantity can be the quantity of magnanimity level.
Step 302, the history of the user of the store information in the shop of the setting of statistics first quantity and the second setting quantity
Scene information.
In one embodiment, the description of store information, history consumer record can be found in retouching for above-mentioned embodiment illustrated in fig. 1
State, will not be described in detail herein.Wherein, historic scenery information be user in history consumer record under it is single when scene information, for example,
User in history consumer record under it is single when where geographical position, the date at that time, weather at that time etc..
Step 303, the store information in the shop based on the first setting quantity, the history consumption of the user of the second setting quantity
Record, the historic scenery information of the user of the second setting quantity, train mathematical modeling.
In one embodiment, store information, the history consumer record of user and historic scenery information can be included
Specifying information spliced, be input to parallel in mathematical modeling, so as to realize the training to mathematical modeling.
In one embodiment, the data model can disappear to each user under each scene information to each shop
Expense amount is predicted.In one embodiment, the mathematical modeling can have been carried out self-defined for the output interval of spending limit
Mapping, so that it is guaranteed that the output interval of the mathematical modeling 0 between preset value, preset value can be according to the reality of electric business platform
Demand is set, and for example, 100.
For example, by user in history consumer record into monovalent lattice, consumption merchandise classification and consumption time, shop
Public praise point, means of distribution, shop consumption person-time, shop visitor's unit price, history into single rate, shop category, and user is under
The dispatching distance input between time, weather, temperature, place city, user and shop when single passes through sea into mathematical modeling
The history consumer record and the store information in magnanimity shop and the scene information of user of user is measured, mathematical modeling is carried out more
Secondary training.
In the present embodiment, by training mathematical modeling, mathematical modeling easily can be transplanted to order ads strategy, determined
Into business such as marketing, businessman's promotion, the portability of mathematical modeling is improved.
Corresponding with the embodiment of the Forecasting Methodology of foregoing spending limit, present invention also provides the prediction of spending limit dress
The embodiment put.
The embodiment of the prediction meanss of the application spending limit can be applied on an electronic device.Device embodiment can lead to
Software realization is crossed, can also be realized by way of hardware or software and hardware combining.Exemplified by implemented in software, as a logic
Device in meaning, it is to be referred to corresponding computer program in nonvolatile memory by the processor of electronic equipment where it
Order reads what operation in internal memory was formed.For hardware view, as shown in figure 4, the prediction meanss for the application spending limit
A kind of hardware structure diagram of place electronic equipment, except the processor shown in Fig. 4, internal memory, network interface and non-volatile deposit
Outside reservoir, the electronic equipment in embodiment where device can also include it generally according to the actual functional capability of the electronic equipment
His hardware, is repeated no more to this.
Wherein, processor, for performing the Forecasting Methodology of any spending limits of above-mentioned Fig. 1-3.
The application also provides a kind of computer-readable recording medium, and storage medium is stored with computer program, computer journey
Sequence is used for the Forecasting Methodology for performing any spending limits of above-mentioned Fig. 1-3.
Fig. 5 is the structural representation of the prediction meanss of the spending limit shown in the exemplary embodiment of the application one, such as Fig. 5 institutes
Show, the prediction meanss of spending limit may include：
First determining module 51, for the history consumer record for determining user and the scene information related to user；
Second determining module 52, for the history consumer record and scene information determined based on the first determining module 51, really
It is set to the shop of user's recommendation；
Input module 53, for determined based on the first determining module 51 history consumer record, scene information and second
The store information in the shop for the recommendation that determining module 52 determines is inputted into the mathematical modeling of training in advance；
Prediction module 54, for the shop of recommendation that is determined by mathematical model prediction user in the second determining module 52
Spending limit.
Fig. 6 is the structural representation of the prediction meanss of the consumption data shown in the application further example embodiment, such as Fig. 6
Shown, on the basis of above-mentioned embodiment illustrated in fig. 5, device may also include：
3rd determining module 55, for each shop in the shop for recommendation, based on user in each shop
Spending limit, determine first revenue factor in each shop；
4th determining module 56, for determining second revenue factor of the electric business platform with respect to each shop；
5th determining module 57, for determining the experience factor of the user in each shop；
Order module 58, the first revenue factor for each shop for being determined based on the 3rd determining module 55, the 4th
The electric business platform that determining module 56 determines determines with respect to second revenue factor in each shop and the 5th determining module 57
User is in the experience factor in each shop, the shop sequence to recommendation.
In one embodiment, order module 58 is particularly used in：
For each shop in the shop of recommendation, determine that the first revenue factor, electric business are put down corresponding to each shop
Platform with respect to second revenue factor in each shop, user the experience factor in each shop weight coefficient；
By weight coefficient to the of the first revenue factor corresponding to each shop, electric business platform with respect to each shop
The experience factor of two revenue factors, user in each shop is weighted, and obtains the score value in each shop；
Based on the respective score value in each shop, the shop of recommendation is sorted.
In one embodiment, the 3rd determining module 55 is particularly used in：
History consumption number of times and history number of clicks based on each shop, determine the conversion ratio in each shop；
Based on conversion ratio, user in the history spending limit in each shop, determine corresponding to each shop that first receives
The beneficial factor.
In one embodiment, the 4th determining module 56 is particularly used in：
It is the ad auction price that electric business platform provides to determine each shop；
Determine the ad click rate in each shop；
Based on ad auction price and ad click rate, determine electric business platform with respect to the second income corresponding to each shop
The factor.
In one embodiment, the 5th determining module 57 is particularly used in：
Determine the space length between user and each shop；
It is determined that corresponding with space length experience the factor, the experience factor is the experience factor of the user in each shop.
In one embodiment, the second determining module 52 may include：
First determining unit 521, for determining the consumption average price of user based on history consumer record；
Second determining unit 522, for determining the geographical position of user based on scene information；
3rd determining unit 523, for the consumption average price and the second determining unit determined based on the first determining unit 521
522 geographical position determined, it is defined as at least one shop of user's recommendation.
In one embodiment, device may also include：
First statistical module 59, for each shop in the shop to the first setting quantity, count in each shop
The history consumer record of the user of second setting quantity of paving consumption；
Second statistical module 60, store information and second for counting the first shop for setting quantity set quantity
The historic scenery information of user；
Training module 61, the history for the user of the second setting quantity obtained based on the second statistical module 59 statistics are disappeared
The store information and the second setting quantity in the shop for the first setting quantity that expense record, second statistical module 60 statistics obtain
The historic scenery information of user, train mathematical modeling.
The function of unit and the implementation process of effect specifically refer to and step are corresponded in the above method in said apparatus
Implementation process, it will not be repeated here.
For device embodiment, because it corresponds essentially to embodiment of the method, so related part is real referring to method
Apply the part explanation of example.Device embodiment described above is only schematical, wherein described be used as separating component
The unit of explanation can be or may not be physically separate, can be as the part that unit is shown or can also
It is not physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can be according to reality
Need to select some or all of module therein to realize the purpose of application scheme.Those of ordinary skill in the art are not paying
In the case of going out creative work, you can to understand and implement.
The preferred embodiment of the application is the foregoing is only, not limiting the application, all essences in the application
God any modification, equivalent substitution and improvements done etc., should be included within the scope of the application protection with principle.
Claims (10)
1. a kind of Forecasting Methodology of spending limit, it is characterised in that methods described includes：
Determine the history consumer record of user and the scene information related to the user；
Based on the history consumer record and the scene information, it is defined as the shop that the user recommends；
The store information of the history consumer record, the scene information and the shop of the recommendation is inputted to training in advance
Mathematical modeling in；
By user described in the mathematical model prediction in the spending limit in the shop of the recommendation.
2. according to the method for claim 1, it is characterised in that it is described by user described in the mathematical model prediction in institute
After the step of stating the spending limit in the shop of recommendation, methods described also includes：
For each shop in the shop of the recommendation, the spending limit based on the user in each shop,
It is determined that first revenue factor in each shop；
Determine second revenue factor in each relatively described shop of electric business platform；
Determine the experience factor of the user in each shop；
The first revenue factor based on each shop, second income in each relatively described shop of the electric business platform
The factor and the user are in the experience factor in each shop, the shop sequence to the recommendation.
3. according to the method for claim 2, it is characterised in that it is described based on first income in each shop because
Second revenue factor in sub, described each relatively described shop of electric business platform and the user are in each shop
The factor is experienced, the shop of the recommendation is sorted, including：
For each shop in the shop of the recommendation, it is determined that the first revenue factor, institute corresponding to each described shop
State second revenue factor in each relatively described shop of electric business platform, the user each shop the experience factor
Weight coefficient；
It is relatively described every to the first revenue factor, the electric business platform corresponding to each described shop by the weight coefficient
The experience factor of second revenue factor, the user in one shop in each shop is weighted, and is obtained described every
The score value in one shop；
Based on the respective score value in each shop, the shop of the recommendation is sorted.
4. according to the method for claim 2, it is characterised in that the disappearing in each shop based on the user
Take amount, it is determined that first revenue factor in each shop, including：
History consumption number of times and history number of clicks based on each shop, it is determined that the conversion in each shop
Rate；
Based on the conversion ratio, the user each shop history spending limit, it is determined that each described shop
Corresponding first revenue factor.
5. according to the method for claim 2, it is characterised in that each relatively described shop of the determination electric business platform
Second revenue factor, including：
It is determined that each described shop is the ad auction price that electric business platform provides；
It is determined that the ad click rate in each shop；
Based on the ad auction price and the ad click rate, each relatively described shop pair of the electric business platform is determined
The second revenue factor answered.
6. according to the method for claim 2, it is characterised in that the body for determining the user in each shop
The factor is tested, including：
Determine the space length between the user and each described shop；
It is determined that corresponding with the space length experience the factor, the experience factor is body of the user in each shop
Test the factor.
7. according to the method for claim 1, it is characterised in that described to be believed based on the history consumer record and the scene
Breath, it is defined as the shop that the user recommends, including：
The consumption average price of the user is determined based on the history consumer record；
The geographical position of the user is determined based on the scene information；
Based on the consumption average price and the geographical position, it is defined as at least one shop that the user recommends.
8. according to any described methods of claim 1-7, it is characterised in that methods described also includes：
To each shop in the shop of the first setting quantity, the second setting quantity in the consumption of each described shop is counted
User history consumer record；
Count the historic scenery of the store information in the shop of the first setting quantity and the user of the second setting quantity
Information；
The store information in the shop based on the described first setting quantity, the history of the described second user for setting quantity consume note
Record, the historic scenery information of the user of the second setting quantity, train the mathematical modeling.
9. a kind of prediction meanss of spending limit, it is characterised in that described device includes：
First determining module, for the history consumer record for determining user and the scene information related to the user；
Second determining module, the history consumer record and the scene for being determined based on first determining module are believed
Breath, it is defined as the shop that the user recommends；
Input module, for the history consumer record, the scene information and the institute for determining first determining module
The store information for stating the shop of the recommendation of the second determining module determination is inputted into the mathematical modeling of training in advance；
Prediction module, for the recommendation determined by user described in the mathematical model prediction in second determining module
Shop spending limit.
10. a kind of computer-readable recording medium, it is characterised in that the storage medium is stored with computer program, the meter
Calculation machine program is used for the Forecasting Methodology for performing any described spending limits of the claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711269842.7A CN107895213A (en) | 2017-12-05 | 2017-12-05 | Forecasting Methodology, device and the electronic equipment of spending limit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711269842.7A CN107895213A (en) | 2017-12-05 | 2017-12-05 | Forecasting Methodology, device and the electronic equipment of spending limit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107895213A true CN107895213A (en) | 2018-04-10 |
Family
ID=61807068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711269842.7A Pending CN107895213A (en) | 2017-12-05 | 2017-12-05 | Forecasting Methodology, device and the electronic equipment of spending limit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107895213A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108694625A (en) * | 2018-07-02 | 2018-10-23 | 阿里巴巴集团控股有限公司 | Equity preference predictor method, device and server |
| CN109214585A (en) * | 2018-09-25 | 2019-01-15 | 平安科技（深圳）有限公司 | Customer consumption prediction technique, device, electronic equipment and storage medium |
| CN109658125A (en) * | 2018-11-09 | 2019-04-19 | 口碑(上海)信息技术有限公司 | Benefit data provides and consumes the determination method and device of time peak period |
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN110060107A (en) * | 2019-04-25 | 2019-07-26 | 湖南餐效信息科技有限公司 | Business revenue evaluation method, business revenue estimating system, terminal and storage medium |
| CN110796513A (en) * | 2019-09-25 | 2020-02-14 | 北京三快在线科技有限公司 | Multitask learning method and device, electronic equipment and storage medium |
| CN111598677A (en) * | 2020-07-24 | 2020-08-28 | 北京淇瑀信息科技有限公司 | Resource quota determining method and device and electronic equipment |
| CN112348616A (en) * | 2020-05-29 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method and device for pushing information, electronic equipment and readable medium |
| CN112907278A (en) * | 2021-01-29 | 2021-06-04 | 广州华多网络科技有限公司 | Rights object allocation control method, device, equipment and medium |
| CN113065717A (en) * | 2021-04-22 | 2021-07-02 | 杭州同犀智能科技有限公司 | E-commerce data processing method, device, equipment and storage medium |
| CN113935787A (en) * | 2021-12-15 | 2022-01-14 | 山东柏源技术有限公司 | Financial information management system based on association rule mining algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140351008A1 (en) * | 2013-05-27 | 2014-11-27 | Hitachi, Ltd. | Calculating machine, prediction method, and prediction program |
| CN106383882A (en) * | 2016-09-13 | 2017-02-08 | 北京三快在线科技有限公司 | Information recommendation method and device and server |
| CN106919641A (en) * | 2017-01-12 | 2017-07-04 | 北京三快在线科技有限公司 | A kind of interest point search method and device, electronic equipment |
-
2017
- 2017-12-05 CN CN201711269842.7A patent/CN107895213A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140351008A1 (en) * | 2013-05-27 | 2014-11-27 | Hitachi, Ltd. | Calculating machine, prediction method, and prediction program |
| CN106383882A (en) * | 2016-09-13 | 2017-02-08 | 北京三快在线科技有限公司 | Information recommendation method and device and server |
| CN106919641A (en) * | 2017-01-12 | 2017-07-04 | 北京三快在线科技有限公司 | A kind of interest point search method and device, electronic equipment |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等（上海）信息科技股份有限公司 | A kind of dining room recommended method and system |
| CN108694625A (en) * | 2018-07-02 | 2018-10-23 | 阿里巴巴集团控股有限公司 | Equity preference predictor method, device and server |
| CN109214585B (en) * | 2018-09-25 | 2023-04-18 | 平安科技（深圳）有限公司 | User consumption prediction method and device, electronic equipment and storage medium |
| CN109214585A (en) * | 2018-09-25 | 2019-01-15 | 平安科技（深圳）有限公司 | Customer consumption prediction technique, device, electronic equipment and storage medium |
| CN109658125A (en) * | 2018-11-09 | 2019-04-19 | 口碑(上海)信息技术有限公司 | Benefit data provides and consumes the determination method and device of time peak period |
| CN109658125B (en) * | 2018-11-09 | 2020-12-25 | 口碑(上海)信息技术有限公司 | Method and device for providing preferential data and determining consumption sub-peak time period |
| CN110060107A (en) * | 2019-04-25 | 2019-07-26 | 湖南餐效信息科技有限公司 | Business revenue evaluation method, business revenue estimating system, terminal and storage medium |
| CN110796513A (en) * | 2019-09-25 | 2020-02-14 | 北京三快在线科技有限公司 | Multitask learning method and device, electronic equipment and storage medium |
| CN110796513B (en) * | 2019-09-25 | 2024-07-16 | 北京三快在线科技有限公司 | Multi-task learning method, device, electronic equipment and storage medium |
| CN112348616A (en) * | 2020-05-29 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Method and device for pushing information, electronic equipment and readable medium |
| CN111598677A (en) * | 2020-07-24 | 2020-08-28 | 北京淇瑀信息科技有限公司 | Resource quota determining method and device and electronic equipment |
| CN112907278B (en) * | 2021-01-29 | 2024-04-16 | 广州华多网络科技有限公司 | Rights object distribution control method and device, equipment and medium thereof |
| CN112907278A (en) * | 2021-01-29 | 2021-06-04 | 广州华多网络科技有限公司 | Rights object allocation control method, device, equipment and medium |
| CN113065717A (en) * | 2021-04-22 | 2021-07-02 | 杭州同犀智能科技有限公司 | E-commerce data processing method, device, equipment and storage medium |
| CN113935787A (en) * | 2021-12-15 | 2022-01-14 | 山东柏源技术有限公司 | Financial information management system based on association rule mining algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107895213A (en) | Forecasting Methodology, device and the electronic equipment of spending limit | |
| CN103823908B (en) | Content recommendation method and server based on user preference | |
| CN106803190A (en) | A kind of ad personalization supplying system and method | |
| CN106407210B (en) | A kind of methods of exhibiting and device of business object | |
| CN107368488A (en) | A kind of method for determining user behavior preference, the methods of exhibiting and device of recommendation information | |
| CN110428298A (en) | A kind of shop recommended method, device and equipment | |
| CN108205766A (en) | Information-pushing method, apparatus and system | |
| JP2009511991A5 (en) | ||
| CN107316234A (en) | Personalized commercial Forecasting Methodology and device | |
| KR102340463B1 (en) | Sample weight setting method and device, electronic device | |
| CN108829808A (en) | A kind of page personalized ordering method, apparatus and electronic equipment | |
| Prathapan et al. | Effectiveness of digital marketing: Tourism websites comparative analytics based on AIDA model | |
| CN108596695B (en) | Entity pushing method and system | |
| CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
| CN110163647A (en) | A kind of data processing method and device | |
| CN105283841B (en) | The object of applied customization recycles and recycling | |
| EP2126767A1 (en) | Intentionality matching | |
| CN103678518A (en) | Method and device for adjusting recommendation lists | |
| CN108446297A (en) | A kind of recommendation method and device, electronic equipment | |
| CN106156965A (en) | A kind of logistics service dispatching method and equipment | |
| CN106130756B (en) | A kind of method and device of prediction access content clicking rate | |
| CN107993088A (en) | A kind of Buying Cycle Forecasting Methodology and device, electronic equipment | |
| CN107481093A (en) | Personalized shop Forecasting Methodology and device | |
| CN104331818A (en) | Method and system capable of controlling differential pushing of merchant service information | |
| CN103843026B (en) | Information processor, information processing method |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1253263 Country of ref document: HK |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180410 |