CN107767227A - Method of Commodity Recommendation, the commercial product recommending system of online shopping mall - Google Patents
Method of Commodity Recommendation, the commercial product recommending system of online shopping mall Download PDFInfo
- Publication number
- CN107767227A CN107767227A CN201711048948.4A CN201711048948A CN107767227A CN 107767227 A CN107767227 A CN 107767227A CN 201711048948 A CN201711048948 A CN 201711048948A CN 107767227 A CN107767227 A CN 107767227A
- Authority
- CN
- China
- Prior art keywords
- commodity
- shopping mall
- online shopping
- fraction
- information
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a kind of Method of Commodity Recommendation of online shopping mall, the commercial product recommending system of online shopping mall.Wherein, the Method of Commodity Recommendation of online shopping mall includes:Obtain the data message and store product information for logging in any account number of online shopping mall;Commodity in online shopping mall are scored according to data message and store product information, to obtain commodity fraction;Commercial product recommending order is determined according to commodity fraction.Method of Commodity Recommendation provided by the invention is analyzed according to the data of user's various dimensions, considers many-sided dimension of user's concern, and the commodity of recommendation more meet user's request, more practicality, science.
Description
Technical field
The present invention relates to online shopping mall's technical field, in particular to a kind of Method of Commodity Recommendation of online shopping mall, net
The commercial product recommending system in upper store.
Background technology
Existing store commercial product recommending is not fine enough, is mainly based upon number of clicks and carries out commercial product recommending, user is to a certain
Commodity are clicked on and checked often, and when user is again turned on webpage, the display order of the commodity is with regard to forward, but such a recommendation method
It is few to analyze the dimension considered, it is impossible to which the commodity that really reflection user really actually wants to, inadequate system, the commodity of actual recommendation can
Can not be that user really wants.
Therefore, how to realize that the commodity order of online shopping mall's recommendation more meets user's request and turns into urgent problem to be solved.
The content of the invention
It is contemplated that at least solves one of technical problem present in prior art or correlation technique.
Therefore, one side of the invention is to propose a kind of Method of Commodity Recommendation of online shopping mall.
The second aspect of the invention is to propose a kind of commercial product recommending system of online shopping mall.
In view of this, according to an aspect of the present invention, it is proposed that a kind of Method of Commodity Recommendation of online shopping mall, including:
Obtain the data message and store product information for logging in any account number of online shopping mall;According to data message and store product information pair
Commodity are scored in online shopping mall, to obtain commodity fraction;Commercial product recommending order is determined according to commodity fraction.
The Method of Commodity Recommendation of online shopping mall provided by the invention, when a certain user logs in online shopping mall, acquisition user's account
Number information, then obtain the data message of account, data message reflects user in the operation information of online shopping mall, feedback information
Deng, while product information in market is obtained, such as certain product population, according to the data message of acquisition and store product information pair
Commodity are scored in online shopping mall, obtain the fraction of all commodity, because the scoring process is to store based on each user
What the data such as middle different operation information and feedback information were carried out, so after scoring of the different users to commodity in store
Divide difference, commercial product recommending order is determined according to commodity fraction, the higher commodity of score, recommendation order is more forward, realizes for not
With the personalized customization of user, recommendation method of the invention is not limited only to number of clicks to the dimension of considering of commodity, includes user
Operation information and feedback information etc. is a variety of considers dimension, in addition, the recommendation method of the present invention is to commodity product(s) data in store
Correlation, the commercial product recommending order difference for different total quantitys can be achieved so that on the one hand the commodity of recommendation more meet user needs
Ask, be on the other hand more conducive to the O&M operation in store, more practicality, science.
According to the Method of Commodity Recommendation of the above-mentioned online shopping mall of the present invention, there can also be following technical characteristic:
In the above-mentioned technical solutions, it is preferable that before obtaining the data message for logging in online shopping mall, in addition to:According to business
The species of product determines the default dimensions of species commodity;The corresponding relation of the default dimensions of storage and species commodity.
In the technical scheme, before each user logs in online shopping mall, commodity are determined previously according to the species of commodity
Default dimensions, the default dimensions of variety classes commodity are different, store the dimensions and commodity of every kind of commodity
Corresponding relation so that user carries out operation or the feedback information of default dimension for all commodity, and then carries out commodity scoring.
In any of the above-described technical scheme, it is preferable that according to the data message and store product information to described online
Commodity are scored in store, to obtain commodity fraction, are specifically included:Any account number is obtained to any commodity in online shopping mall
The evaluation information of default dimensions;According to preset rules, the evaluation information of default dimensions is converted into respective dimensions
Fraction;Obtain the store product information of any commodity;According to preset rules, the store product information of any commodity is converted into phase
Answer the fraction of dimension;The weight of the fraction of each respective dimensions and respective dimensions is subjected to product, to obtain the business of any commodity
Product fraction.
In the technical scheme, after user logs in online shopping mall, commodity in store are operated, number of operations can be with
Evaluation information is converted into, carrying out feedback to feedback dimension switchs to evaluation information, obtains user account number and commodity in online shopping mall are commented
Valency information, according to store default rule, these evaluation informations are converted into the score of the dimension, then point of each dimension
The weight of number and the dimension carries out product, and the weight setting of dimension that is important with respect to user or more paying close attention to is higher, less heavy
Will or the dimension weight less paid close attention to set lower, the store product information of any commodity is then obtained again, further according to appointing
The store product information of one commodity obtains the score of respective dimensions, finally gives the total score of commodity, the commodity as the commodity
Fraction.In this way, the different evaluation informational influence commodity fraction of different user, different user concern dimension is not all to set the dimension
Weighted, so the recommendation order that final each user sees is different, more meet the demand of each user, it is personalized fixed to realize
System;In addition, commodity final score is also related to product information in store, the commodity preferential recommendation more favourable to store O&M.
In any of the above-described technical scheme, it is preferable that obtain default dimension of any account number to any commodity in online shopping mall
Before the evaluation information of degree, in addition to:Judge whether to receive the evaluation information of any account number;When receiving evaluation information,
Any account number obtain in online shopping mall the step of the evaluation information of the default dimension of any commodity;It is any not receiving
During the evaluation information of account number, the institute drawn according to other account numbers in addition to any account number to the evaluation information of any commodity is obtained
There is commodity fraction, using the average value of all commodity fractions as commodity fraction.
In the technical scheme, obtain any account number to the evaluation information of the default dimension of any commodity in online shopping mall it
Before, it is first determined whether receive user account number carried out evaluation information to a certain commodity, if user carried out evaluation, then
Evaluation information of the user account number to commodity is chosen, commodity fraction is confirmed based on user account number personal evaluation information, if do not had
Have and received evaluation information of the user account number to a certain commodity, then obtain other use evaluated in addition to the user account number
The commodity fraction that family account number is drawn to the evaluation information of this commodity, using the commodity fraction average of all user account numbers as this business
Product to should user account number commodity fraction.
In any of the above-described technical scheme, it is preferable that default dimensions comprise at least:Commodity price, return of goods number, point
Hit number, purchase number, commercial quality, item property, the total volume of commodities.
In the technical scheme, the more than number of clicks of default dimensions of restriction, in addition to commodity price, the return of goods
Number, purchase number, commercial quality, item property.Number of clicks, purchase number are more, and fraction is higher;Commodity price is higher, point
Number is lower;Commercial quality is higher, and fraction is higher, item property more meets user's request, and fraction is higher;The total volume of commodities is more, point
Number is higher.
According to the second aspect of the invention, it is proposed that a kind of commercial product recommending system of online shopping mall, including:First obtains
Unit, the data message and store product information of any account number of online shopping mall are logged in for obtaining;Score unit, for according to number
It is believed that breath and store product information score commodity in online shopping mall, to obtain commodity fraction;Recommendation unit, for basis
Commodity fraction determines commercial product recommending order.
The commercial product recommending system of online shopping mall provided by the invention, when a certain user logs in online shopping mall, first obtains list
Member obtains the information of user account number, then obtains the data message of account, and data message reflects operation of the user in online shopping mall
Information, feedback information etc., while obtain product information in market, such as certain product population, judge paper member is according to the number of acquisition
It is believed that breath and store product information score commodity in online shopping mall, the fraction of all commodity is obtained, because this scored
Journey is that the data such as operation information and feedback information different in store are carried out based on each user, so different users couple
Score in store after the scoring of commodity is different, and recommendation unit determines commercial product recommending sequentially according to commodity fraction, and score is higher
Commodity, recommendation order is more forward, realizes the personalized customization for different user, and recommendation method of the invention is considered to commodity
Dimension is not limited only to number of clicks, and operation information and feedback information comprising user etc. are a variety of to consider dimension, in addition, the present invention
Recommendation method is related to commodity product(s) data in store, and the commercial product recommending order difference for different total quantitys can be achieved so that
On the one hand the commodity of recommendation more meet user's request, be on the other hand more conducive to the O&M operation in store, more practicality, science
Property.
According to the commercial product recommending system of the above-mentioned online shopping mall of the present invention, there can also be following technical characteristic:
In the above-mentioned technical solutions, it is preferable that determining unit, for determining the default of species commodity according to the species of commodity
Dimensions;Memory cell, for storing the corresponding relation of default dimensions and species commodity.
In the technical scheme, before each user logs in online shopping mall, species of the determining unit previously according to commodity
The default dimensions of commodity are determined, the default dimensions of variety classes commodity are different, and memory cell stores every kind of commodity
The corresponding relation of dimensions and commodity so that user carries out operation or the feedback information of default dimension for all commodity, enters
And carry out commodity scoring.
In any of the above-described technical scheme, it is preferable that scoring unit, specifically include:Second acquisition unit, appoint for obtaining
Evaluation information of one account number to the default dimensions of any commodity in online shopping mall;First conversion unit, for according to default
Rule, the evaluation information of default dimensions is converted into the fraction of respective dimensions;3rd acquiring unit, for obtaining any business
The store product information of product;Second conversion unit, for according to preset rules, the store product information of any commodity to be converted into
The fraction of respective dimensions;Computing unit, for the weight of the fraction of each respective dimensions and respective dimensions to be carried out into product, to obtain
Take the commodity fraction of any commodity.
In the technical scheme, after user logs in online shopping mall, commodity in store are operated, number of operations can be with
Evaluation information is converted into, feedback is carried out to feedback dimension and switchs to evaluation information, second acquisition unit obtains user account number to online
These evaluation informations are converted into the dimension by information on commodity comment on store, the first conversion unit according to store default rule
Score, then computing unit the weight of the fraction of each dimension and the dimension is carried out product, it is important with respect to user or more
The weight of the dimension of concern set it is higher, dimension weight that is less important or less paying close attention to set it is lower, then the 3rd
Acquiring unit obtains the store product information of any commodity, store product information of second conversion unit further according to any commodity again
The score of respective dimensions is obtained, finally gives the total score of commodity, the commodity fraction as the commodity.In this way, different user
Different evaluation informational influence commodity fraction, different user concern dimension are not all to set the dimension weighted, so final every
The recommendation order that individual user sees is different, more meets the demand of each user, realizes personalized customization;In addition, commodity finally divide
Number commodity preferential recommendation also related to product information in store, more favourable to store O&M.
In any of the above-described technical scheme, it is preferable that judging unit, for judging whether to receive the evaluation of any account number
Information;Second acquisition unit, specifically for when receiving evaluation information, carrying out obtaining any account number to any in online shopping mall
The step of evaluation information of the default dimension of commodity;Averaging unit, for when not receiving the evaluation information of any account number, obtaining
All commodity fractions drawn according to other account numbers in addition to any account number to the evaluation information of any commodity are taken, by all business
The average value of product fraction is as commodity fraction.
In the technical scheme, obtain any account number to the evaluation information of the default dimension of any commodity in online shopping mall it
Before, first determine whether unit judges receive user account number and carried out evaluation information to a certain commodity, if user was carried out
Evaluation, then second acquisition unit chooses evaluation information of the user account number to commodity, based on user account number personal evaluation's information
To confirm commodity fraction, if not receiving evaluation information of the user account number to a certain commodity, then averaging unit is obtained and removed
The commodity fraction that other user account numbers evaluated outside the user account number are drawn to the evaluation information of this commodity, will be all
The commodity fraction average of user account number as this commodity to should user account number commodity fraction.
In any of the above-described technical scheme, it is preferable that default dimensions comprise at least:Commodity price, return of goods number, point
Hit number, purchase number commercial quality, item property, the total volume of commodities.
In this embodiment, the more than number of clicks of default dimensions of restriction, in addition to commodity price, return of goods number,
Buy number, commercial quality, item property.Number of clicks, purchase number are more, and fraction is higher;Commodity price is higher, and fraction is got over
It is low;Commercial quality is higher, and fraction is higher, item property more meets user's request, and fraction is higher;The total volume of commodities is more, and fraction is got over
It is high.
The additional aspect and advantage of the present invention will become obvious in following description section, or the practice by the present invention
Recognize.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become in the description from combination accompanying drawings below to embodiment
Substantially and it is readily appreciated that, wherein:
Fig. 1 shows the schematic flow sheet of the Method of Commodity Recommendation of the online shopping mall of one embodiment of the present of invention;
Fig. 2 shows the schematic flow sheet of the Method of Commodity Recommendation of the online shopping mall of an alternative embodiment of the invention;
Fig. 3 shows the schematic block diagram of the commercial product recommending system of the online shopping mall of one embodiment of the present of invention;
Fig. 4 shows the schematic block diagram of the commercial product recommending system of the online shopping mall of an alternative embodiment of the invention.
Embodiment
It is below in conjunction with the accompanying drawings and specific real in order to be more clearly understood that aforementioned aspect of the present invention, feature and advantage
Mode is applied the present invention is further described in detail.It should be noted that in the case where not conflicting, the implementation of the application
Feature in example and embodiment can be mutually combined.
Many details are elaborated in the following description to facilitate a thorough understanding of the present invention, still, the present invention may be used also
To be different from other modes described here using other to implement, therefore, protection scope of the present invention is not limited to following public affairs
The limitation for the specific embodiment opened.
The embodiment of first aspect present invention, proposes a kind of Method of Commodity Recommendation of online shopping mall, and Fig. 1 shows the present invention
One embodiment online shopping mall Method of Commodity Recommendation schematic flow sheet:
Step 102, the data message and store product information for logging in any account number of online shopping mall are obtained;
Step 104, commodity in online shopping mall are scored according to data message and store product information, to obtain commodity
Fraction;
Step 106, commercial product recommending order is determined according to commodity fraction.
The Method of Commodity Recommendation of the online shopping mall of the embodiment, when a certain user logs in online shopping mall, acquisition user account number
Information, then obtain the data message of account, data message reflects user in the operation information of online shopping mall, feedback information
Deng, while product information in market is obtained, such as certain product population, according to the data message of acquisition and store product information pair
Commodity are scored in online shopping mall, obtain the fraction of all commodity, because the scoring process is to store based on each user
What the data such as middle different operation information and feedback information were carried out, so after scoring of the different users to commodity in store
Divide difference, commercial product recommending order is determined according to commodity fraction, the higher commodity of score, recommendation order is more forward, realizes for not
With the personalized customization of user, recommendation method of the invention is not limited only to number of clicks to the dimension of considering of commodity, includes user
Operation information and feedback information etc. is a variety of considers dimension, in addition, the recommendation method of the present invention is to commodity product(s) data in store
Correlation, the commercial product recommending order difference for different total quantitys can be achieved so that on the one hand the commodity of recommendation more meet user needs
Ask, be on the other hand more conducive to the O&M operation in store, more practicality, science.
Fig. 2 shows the schematic flow sheet of the Method of Commodity Recommendation of the online shopping mall of an alternative embodiment of the invention.Its
In, the Method of Commodity Recommendation includes:
Step 202, the default dimensions of species commodity are determined according to the species of commodity;
Step 204, the corresponding relation of default dimensions and species commodity is stored;
Step 206, the data message for logging in any account number of online shopping mall is obtained;
Step 208, judge whether to receive the evaluation information of any account number, it is no, then into step 210, it is then to enter step
Rapid 212;
Step 210, the institute drawn according to other account numbers in addition to any account number to the evaluation information of any commodity is obtained
Some commodity fractions, using the average value of all commodity fractions as commodity fraction;
Step 212, evaluation information of any account number to the default dimensions of any commodity in online shopping mall is obtained;
Step 214, according to preset rules, the evaluation information of default dimensions is converted into the fraction of respective dimensions;
Step 216, the store product information of any commodity is obtained;
Step 218, according to preset rules, the store product information of any commodity is converted into the fraction of respective dimensions;
Step 220, the weight of the fraction of each respective dimensions and respective dimensions is subjected to product, to obtain any commodity
Commodity fraction;
Step 222, commercial product recommending order is determined according to commodity fraction.
In this embodiment, before each user logs in online shopping mall, commodity are determined previously according to the species of commodity
Default dimensions, default dimensions comprise at least:Commodity price, return of goods number, number of clicks, purchase number, commodity matter
Amount, item property.Limit the more than number of clicks of default dimensions, in addition to commodity price, return of goods number, purchase number,
Commercial quality, item property, the total volume of commodities.Number of clicks, purchase number are more, and fraction is higher;Commodity price is higher, and fraction is got over
It is low;Commercial quality is higher, and fraction is higher, item property more meets user's request, and fraction is higher;The total volume of commodities is more, and fraction is got over
It is high.The default dimensions of variety classes commodity are different, such as, the default dimensions of vegetables are freshness, price, aesthetic feeling,
Nutritive value, yield (certain species vegetables total amount/store active users in store) number, number of clicks, purchase number, the return of goods
Vegetables are scored by number according to this 8 dimensions.For this dimension of certain yield of vegetables number, the species vegetable in store is used
Standard of the numerical value that the number of users of current active is drawn in the total amount of dish divided by store as evaluation yield number, numerical value is higher, should
Dimension scores are higher, such as, number of being enlivened at present in store is 500 people, and tomato total amount is 1000 kilograms, and broccoli total amount is
2000 kilograms, then the yield number of tomato is 1000/500, often 2 kilograms for each person, and broccoli is often 4 kilograms for each person, that
Store for other dimension scores it is consistent in the case of, with regard to the high broccoli of preferential recommendation yield number, realize that vegetables total amount is more
Vegetables preferentially sell.Finally, the dimensions of every kind of commodity and the corresponding relation of commodity are stored so that user is directed to all business
Product carry out operation or the feedback information of default dimension, and then carry out commodity scoring.
In this embodiment, after user logs in online shopping mall, commodity in store are operated, number of operations can turn
Evaluation information is turned to, carrying out feedback to feedback dimension switchs to evaluation information, obtains user account number and commodity in online shopping mall are evaluated
Information, according to store default rule, these evaluation informations are converted into the score of the dimension, such as tomato:It is fresh this
Dimension, it can be divided into:A is very fresh, fraction 1, and B is than comparatively fresh, fraction 0.8, C dulls, less fresh, fraction 0.4,
D is very poor, has a rotten vestige, fraction 0.2, provides the weight of each dimension, then the fraction and the dimension of each dimension
Weight carries out product, and the weight setting of dimension that is important with respect to user or more paying close attention to is higher, less important or less close
The dimension weight setting of note is lower, and then the 3rd acquiring unit obtains the store product information of any commodity, the second conversion again
Unit obtains the score of respective dimensions further according to the store product information of any commodity, finally gives the total score of commodity, as
The commodity fraction of the commodity.Such as:Fresh dimension scores 0.6, mouthfeel dimension scores 0.5, price dimension scores 0.4, aesthetic feeling dimension
Score 0.5 is spent, nutritive value dimension scores 0.5, yield score 0.5, number of clicks score 0.6, purchase number score 0.4, is moved back
Goods number score 0.5, weight are respectively to go 1,1,1,0.8,1,1,1,1, so 0.6 × 1+0.5 of tomato score × 1+0.4 ×
1+0.5 × 0.8+0.5 × 1+0.5 × 1+0.6 × 1+0.4 × 1+0.5 × 1=4.4.In this way, the different evaluation letter of different user
Retire into private life and ring commodity fraction, different user concern dimension is not all to set the dimension weighted, so final each user sees
Recommendation order it is different, more meet the demand of each user, realize personalized customization;In addition, commodity final score is also and store
Middle product information is related, the commodity preferential recommendation more favourable to store O&M.
In this embodiment, obtain any account number to the evaluation information of the default dimension of any commodity in online shopping mall it
Before, it is first determined whether receive user account number carried out evaluation information to a certain commodity, if user carried out evaluation, then
Evaluation information of the user account number to commodity is chosen, commodity fraction is confirmed based on user account number personal evaluation information, if do not had
Have and received evaluation information of the user account number to a certain commodity, then obtain other use evaluated in addition to the user account number
The commodity fraction that family account number is drawn to the evaluation information of this commodity, using the commodity fraction average of all user account numbers as this business
Product to should user account number commodity fraction.That is have the preferential calculation individual of personal evaluation, if personal void value, takes
Average value, such as:Zhang have purchased a bag tomato, and do Feedback Evaluation to tomato, fresh, mouthfeel, price,
The dimensions such as aesthetic feeling, nutritive value are evaluated, then the tomato score of Zhang is just derived from oneself evaluation score.If Zhang
Do not buy broccoli, then the broccoli score of Zhang is exactly average of all users to broccoli, by that analogy
Zhang just has the score of all dishes, then sorts from big to small, here it is the recommendation order that Zhang sees, according to this row
Sequence rule, the recommendation order that each user sees should be different.
The embodiment of second aspect of the present invention, proposes a kind of commercial product recommending system 300 of online shopping mall, and Fig. 3 shows this
The schematic block diagram of the commercial product recommending system 300 of the online shopping mall of one embodiment of invention.As shown in figure 3, the business of online shopping mall
Product commending system 300 includes:Acquiring unit 10, scoring unit 12, recommendation unit 14.Wherein, acquiring unit 10, stepped on for obtaining
Record the data message and store product information of any account number of online shopping mall;Score unit 12, for according to data message and store
Product information scores commodity in online shopping mall, to obtain commodity fraction;Recommendation unit 14, for true according to commodity fraction
Determine commercial product recommending order.
The commercial product recommending system 300 of online shopping mall in the embodiment, when a certain user logs in online shopping mall, acquiring unit
10 obtain the information of user account number, then obtain the data message of account, and data message reflects operation of the user in online shopping mall
Information, feedback information etc., while product information in market is obtained, such as certain product population, scoring unit 12 is according to acquisition
Data message and store product information score commodity in online shopping mall, obtain the fraction of all commodity, because the scoring
Process is that the data such as operation information and feedback information different in store are carried out based on each user, so different users
Score after scoring to commodity in store is different, and recommendation unit 14 determines commercial product recommending order according to commodity fraction, and score is got over
High commodity, recommendation order is more forward, realizes the personalized customization for different user, and the recommendation method of the present invention is to commodity
Dimension of considering be not limited only to number of clicks, operation information and feedback information comprising user etc. be a variety of considers dimension in addition, this
The recommendation method of invention is related to commodity product(s) data in store, and the achievable commercial product recommending order for different total quantitys is not
Together so that on the one hand the commodity of recommendation more meet user's request, be on the other hand more conducive to the O&M operation in store, more practical
Property, science.
Fig. 4 shows the schematic block diagram of the commercial product recommending system 400 of the online shopping mall of an alternative embodiment of the invention.Such as
Shown in Fig. 4, the commercial product recommending system 400 of online shopping mall includes:First acquisition unit 20, scoring unit 22, recommendation unit 24, really
Order member 26, memory cell 28, judging unit 30, averaging unit 32.Scoring unit 22 specifically includes:Second acquisition unit 220,
First conversion unit 222, the 3rd acquiring unit 224, the second conversion unit 226, computing unit 228.
Wherein, first acquisition unit 20, the data message of any account number of online shopping mall is logged in for obtaining;Score unit
22, for being scored according to data message commodity in online shopping mall, to obtain commodity fraction;Recommendation unit 24, for root
Commercial product recommending order is determined according to commodity fraction;Determining unit 26, for determining that the default of species commodity is commented according to the species of commodity
Fractional dimension;Memory cell 28, for storing the corresponding relation of default dimensions and species commodity;Judging unit 30, for sentencing
The disconnected evaluation information for whether receiving any account number;Averaging unit 32, for when not receiving the evaluation information of any account number,
All commodity fractions drawn according to other account numbers in addition to any account number to the evaluation information of any commodity are obtained, will be all
The average value of commodity fraction is as commodity fraction;Second acquisition unit 220, specifically for when receiving evaluation information, carrying out
Any account number is obtained in online shopping mall the step of the evaluation information of the default dimension of any commodity;Conversion unit 222, for root
According to preset rules, the evaluation information of default dimensions is converted into the fraction of respective dimensions;3rd acquiring unit 224, is used for
Obtain the store product information of any commodity;Second conversion unit 226, for according to preset rules, by the store of any commodity
Product information is converted into the fraction of respective dimensions;Computing unit 228, for by the fraction of each respective dimensions and respective dimensions
Weight carries out product, to obtain the commodity fraction of any commodity.
The commercial product recommending system 400 of online shopping mall in the embodiment, when a certain user logs in online shopping mall, first obtains
Unit 20 obtains the information of user account number, then obtains the data message of account, and data message reflects user in online shopping mall
Operation information, feedback information etc., scoring unit 22 score commodity in online shopping mall according to the data message of acquisition, obtained
The fraction of all commodity, because the scoring process is to operation information and feedback information different in store etc. based on each user
What data were carried out, so the score after scoring of the different users to commodity in store is different, recommendation unit 24 is according to commodity point
Number determines commercial product recommending order, and the higher commodity of score, recommendation order is more forward, realizes that the personalization for different user is determined
System, and the recommendation method of the present invention is not limited only to number of clicks to the dimension of considering of commodity, the operation information comprising user and anti-
Feedforward information etc. is a variety of to consider dimension, and the commodity of recommendation more meet user's request, more practicality, science.
In this embodiment, before each user logs in online shopping mall, species of the determining unit 26 previously according to commodity
The default dimensions of commodity are determined, default dimensions comprise at least:Commodity price, return of goods number, number of clicks, purchase time
Number, commercial quality, item property.Limit the more than number of clicks of default dimensions, in addition to commodity price, return of goods number,
Buy number, commercial quality, item property, the total volume of commodities.Number of clicks, purchase number are more, and fraction is higher;Commodity price is got over
Height, fraction are lower;Commercial quality is higher, and fraction is higher, item property more meets user's request, and fraction is higher;The total volume of commodities is got over
More, fraction is higher.The default dimensions of variety classes commodity are different, such as, the default dimensions of vegetables are freshness, valency
Lattice, aesthetic feeling, nutritive value, yield (certain vegetables total amount/store active users in store) number, number of clicks, purchase number,
Return of goods number, vegetables are scored according to this 8 dimensions.For this dimension of certain yield of vegetables number, using should in store
Standard of the numerical value that the number of users of current active is drawn in the total amount of species vegetables divided by store as evaluation yield number, numerical value are got over
Height, the dimension scores are higher, such as, number of being enlivened at present in store is 500 people, and tomato total amount is 1000 kilograms, broccoli
Total amount is 2000 kilograms, then the yield number of tomato is 1000/500, and per 2 kilograms for each person, broccoli is per for each person 4,000
Gram, then store for other dimension scores it is consistent in the case of, with regard to the high broccoli of preferential recommendation yield number, realize that vegetables are total
The more vegetables of amount are preferentially sold.Finally, memory cell 28 stores the dimensions of every kind of commodity and the corresponding relation of commodity so that
User carries out operation or the feedback information of default dimension for all commodity, and then carries out commodity scoring.
In this embodiment, after user logs in online shopping mall, commodity in store are operated, number of operations can turn
Evaluation information is turned to, feedback is carried out to feedback dimension and switchs to evaluation information, second acquisition unit 220 obtains user account number to online
These evaluation informations are converted into the dimension by information on commodity comment on store, the first conversion unit 222 according to store default rule
The score of degree, such as tomato:This fresh dimension, can be divided into:A is very fresh, fraction 1, and B is than comparatively fresh, fraction 0.8, C
Dull, less fresh, fraction 0.4, D is very poor, has a rotten vestige, fraction 0.2, provides the weight of each dimension, so
Afterwards the weight of the fraction of each dimension and the dimension is carried out product by computing unit 228, important with respect to user or more pay close attention to
The weight setting of dimension is higher, and dimension weight setting that is less important or less paying close attention to is lower, then the 3rd obtains list
Member 224 obtains the store product information of any commodity, store product information of second conversion unit 226 further according to any commodity again
The score of respective dimensions is obtained, finally gives the total score of commodity, the commodity fraction as the commodity.Such as:Fresh dimension obtains
Divide 0.6, mouthfeel dimension scores 0.5, price dimension scores 0.4, aesthetic feeling dimension scores 0.5, nutritive value dimension scores 0.5, produce
Point 0.5 is measured, number of clicks score 0.6, purchase number score 0.4, return of goods number score 0.5, weight is respectively to go 1,1,1,
0.8,1,1,1,1, so 0.6 × 1+0.5 of tomato score × 1+0.4 × 1+0.5 × 0.8+0.5 × 1+0.5 × 1+0.6 × 1+
0.4 × 1+0.5 × 1=4.4.In this way, the different evaluation informational influence commodity fraction of different user, different user concern dimension is not
It is all that the dimension weighted is set, so the recommendation order that final each user sees is different, more meets the need of each user
Ask, realize personalized customization.
In this embodiment, obtain any account number to the evaluation information of the default dimension of any commodity in online shopping mall it
Before, first determine whether that unit 30 judges whether that receive user account number carried out evaluation information to a certain commodity, if user is carried out
Cross evaluation, then second acquisition unit 220 chooses evaluation information of the user account number to commodity, based on user account number personal evaluation
Information confirms commodity fraction, if not receiving evaluation information of the user account number to a certain commodity, then averaging unit 32
The commodity fraction that other user account numbers evaluated in addition to the user account number are drawn to the evaluation information of this commodity is obtained,
Using the commodity fraction average of all user account numbers as this commodity to should user account number commodity fraction.That is there is individual
The preferential calculation individual's of evaluation, if personal void value, averages, such as:Zhang have purchased a bag tomato, and right
Tomato has been cooked Feedback Evaluation, is evaluated in dimensions such as fresh, mouthfeel, price, aesthetic feeling, nutritive values, then the west of Zhang
Red persimmon score is just derived from oneself evaluation score.If Zhang does not buy broccoli, then the broccoli score of Zhang is just
It is average of all users to broccoli, Zhang just has the score of all dishes by that analogy, then arranges from big to small
Sequence, here it is the recommendation order that Zhang sees, according to this ordering rule, the recommendation order that each user sees should be different
's.
In the description of this specification, the description of term " one embodiment ", " some embodiments ", " specific embodiment " etc.
Mean to combine at least one reality that specific features, structure, material or the feature that the embodiment or example describe are contained in the present invention
Apply in example or example.In this manual, identical embodiment or reality are not necessarily referring to the schematic representation of above-mentioned term
Example.Moreover, description specific features, structure, material or feature can in any one or more embodiments or example with
Suitable mode combines.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (10)
- A kind of 1. Method of Commodity Recommendation of online shopping mall, it is characterised in that including:Obtain the data message and store product information for logging in any account number of online shopping mall;Commodity in the online shopping mall are scored according to the data message and the store product information, to obtain commodity Fraction;The recommendation order of the commodity is determined according to the commodity fraction.
- 2. the Method of Commodity Recommendation of online shopping mall according to claim 1, it is characterised in that obtain and log in the online business Before the data message and store product information in city, in addition to:The default dimensions of the species commodity are determined according to the species of the commodity;Store the corresponding relation of the default dimensions and the species commodity.
- 3. the Method of Commodity Recommendation of online shopping mall according to claim 2, it is characterised in that according to the data message and The store product information scores commodity in the online shopping mall, to obtain commodity fraction, specifically includes:Obtain evaluation information of any account number to the default dimensions of any commodity in the online shopping mall;According to preset rules, the evaluation information of the default dimensions is converted into the fraction of respective dimensions;Obtain described appoint The store product information of one commodity;According to the preset rules, the store product information of any commodity is converted into dividing for respective dimensions Number;The weight of the fraction of each respective dimensions and the respective dimensions is subjected to product, to obtain any commodity The commodity fraction.
- 4. the Method of Commodity Recommendation of online shopping mall according to claim 3, it is characterised in that obtain any account number pair In the online shopping mall before the evaluation information of the default dimension of any commodity, in addition to:Judge whether to receive the evaluation information of any account number;When receiving the evaluation information, carry out obtaining any account number and any commodity in the online shopping mall are preset The step of evaluation information of dimension;When not receiving the evaluation information of any account number, obtain according to its "their" deposit in addition to any account number Number all commodity fractions drawn to the evaluation information of any commodity, the average value of all commodity fractions is made For the commodity fraction of any commodity.
- 5. the Method of Commodity Recommendation of the online shopping mall according to any one of claim 2 to 4, it is characterised in that described pre- If dimensions comprise at least:Commodity price, return of goods number, number of clicks, purchase number, commercial quality, item property, commodity Total amount.
- A kind of 6. commercial product recommending system of online shopping mall, it is characterised in that including:First acquisition unit, the data message and store product information of any account number of online shopping mall are logged in for obtaining;Score unit, for being commented according to the data message and the store product information commodity in the online shopping mall Point, to obtain commodity fraction;Recommendation unit, for determining the recommendation order of the commodity according to the commodity fraction.
- 7. the commercial product recommending system of online shopping mall according to claim 6, it is characterised in that also include:Determining unit, for determining the default dimensions of the species commodity according to the species of the commodity;Memory cell, for storing the corresponding relation of the default dimensions and the species commodity.
- 8. the commercial product recommending system of online shopping mall according to claim 7, it is characterised in that the scoring unit specifically wraps Include:Second acquisition unit, for obtaining any account number to the default dimensions of any commodity in the online shopping mall Evaluation information;First conversion unit, for according to preset rules, the evaluation information of the default dimensions to be converted into respective dimensions Fraction;3rd acquiring unit, for obtaining the store product information of any commodity;Second conversion unit, for according to the preset rules, the store product information of any commodity to be turned Turn to the fraction of respective dimensions;Computing unit, for the weight of the fraction of each respective dimensions and the respective dimensions to be carried out into product, to obtain The commodity fraction of any commodity.
- 9. the commercial product recommending system of online shopping mall according to claim 8, it is characterised in that also include:Judging unit, for judging whether to receive the evaluation information of any account number;The second acquisition unit, specifically for when receiving the evaluation information, carrying out obtaining any account number to institute The step of stating the evaluation information of the default dimension of any commodity in online shopping mall;Averaging unit, any account is removed for when not receiving the evaluation information of any account number, obtaining basis All commodity fractions that other account numbers outside number are drawn to the evaluation information of any commodity, by all commodity Commodity fraction of the average value of fraction as any commodity.
- 10. the commercial product recommending system of the online shopping mall according to any one of claim 7 to 9, it is characterised in that described pre- If dimensions comprise at least:Commodity price, return of goods number, number of clicks, purchase number, commercial quality, item property, commodity Total amount.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711048948.4A CN107767227A (en) | 2017-10-31 | 2017-10-31 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
PCT/CN2018/079648 WO2019085372A1 (en) | 2017-10-31 | 2018-03-20 | Commodity recommendation method and commodity recommendation system for online shopping mall |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711048948.4A CN107767227A (en) | 2017-10-31 | 2017-10-31 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107767227A true CN107767227A (en) | 2018-03-06 |
Family
ID=61271485
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711048948.4A Pending CN107767227A (en) | 2017-10-31 | 2017-10-31 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107767227A (en) |
WO (1) | WO2019085372A1 (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108665312A (en) * | 2018-05-08 | 2018-10-16 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
CN109300021A (en) * | 2018-11-29 | 2019-02-01 | 爱保科技(横琴)有限公司 | Insure recommended method and device |
CN109325795A (en) * | 2018-08-02 | 2019-02-12 | 深圳春沐源控股有限公司 | The application method of store discount coupon and the application system of store discount coupon |
WO2019085372A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳春沐源控股有限公司 | Commodity recommendation method and commodity recommendation system for online shopping mall |
CN110363604A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Page generation method and device |
CN111062768A (en) * | 2019-10-28 | 2020-04-24 | 林佳 | Commodity recommendation method and commodity recommendation system for online shopping mall |
CN111415216A (en) * | 2020-02-11 | 2020-07-14 | 广州探途网络技术有限公司 | Commodity recommendation method and device, server and storage medium |
WO2020215751A1 (en) * | 2019-04-23 | 2020-10-29 | 北京三快在线科技有限公司 | Recommendation method, electronic device and readable storage medium |
CN113159905A (en) * | 2021-05-20 | 2021-07-23 | 深圳马六甲网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium for new user |
CN113409124A (en) * | 2021-07-08 | 2021-09-17 | 山东大学 | Bulk commodity recommendation method and system based on Bayesian regression analysis |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110175892B (en) * | 2019-05-27 | 2021-06-29 | 成都魔方城科技有限公司 | Bidirectional thermal ball recommendation method and system based on consumer behaviors |
CN110348946A (en) * | 2019-06-13 | 2019-10-18 | 深圳市中农易讯信息技术有限公司 | A kind of Method of Commodity Recommendation, device, storage medium and equipment |
TWI826881B (en) * | 2021-12-22 | 2023-12-21 | 阿物科技股份有限公司 | System and method for awakening non-shopping consumers |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102426686A (en) * | 2011-09-29 | 2012-04-25 | 南京大学 | Internet information product recommending method based on matrix decomposition |
CN103426102A (en) * | 2013-08-02 | 2013-12-04 | 苏州两江科技有限公司 | Commodity feature recommending method based on body classification |
CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
CN106600372A (en) * | 2016-12-12 | 2017-04-26 | 武汉烽火信息集成技术有限公司 | Commodity recommending method and system based on user behaviors |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104408648A (en) * | 2014-12-09 | 2015-03-11 | 北京博雅立方科技有限公司 | Method and device for choosing items |
CN106469392A (en) * | 2015-08-20 | 2017-03-01 | 阿里巴巴集团控股有限公司 | Select and recommend to show the method and device of object |
CN106408377A (en) * | 2016-08-31 | 2017-02-15 | 广东华邦云计算股份有限公司 | Shopping recommended method and system |
CN107767227A (en) * | 2017-10-31 | 2018-03-06 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
-
2017
- 2017-10-31 CN CN201711048948.4A patent/CN107767227A/en active Pending
-
2018
- 2018-03-20 WO PCT/CN2018/079648 patent/WO2019085372A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102426686A (en) * | 2011-09-29 | 2012-04-25 | 南京大学 | Internet information product recommending method based on matrix decomposition |
CN103426102A (en) * | 2013-08-02 | 2013-12-04 | 苏州两江科技有限公司 | Commodity feature recommending method based on body classification |
CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
CN106600372A (en) * | 2016-12-12 | 2017-04-26 | 武汉烽火信息集成技术有限公司 | Commodity recommending method and system based on user behaviors |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019085372A1 (en) * | 2017-10-31 | 2019-05-09 | 深圳春沐源控股有限公司 | Commodity recommendation method and commodity recommendation system for online shopping mall |
CN110363604B (en) * | 2018-04-09 | 2022-06-07 | 北京京东尚科信息技术有限公司 | Page generation method and device |
CN110363604A (en) * | 2018-04-09 | 2019-10-22 | 北京京东尚科信息技术有限公司 | Page generation method and device |
CN108665312A (en) * | 2018-05-08 | 2018-10-16 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
CN108665312B (en) * | 2018-05-08 | 2020-09-29 | 京东数字科技控股有限公司 | Method and apparatus for generating information |
CN109325795A (en) * | 2018-08-02 | 2019-02-12 | 深圳春沐源控股有限公司 | The application method of store discount coupon and the application system of store discount coupon |
CN109300021A (en) * | 2018-11-29 | 2019-02-01 | 爱保科技(横琴)有限公司 | Insure recommended method and device |
WO2020215751A1 (en) * | 2019-04-23 | 2020-10-29 | 北京三快在线科技有限公司 | Recommendation method, electronic device and readable storage medium |
CN111062768A (en) * | 2019-10-28 | 2020-04-24 | 林佳 | Commodity recommendation method and commodity recommendation system for online shopping mall |
CN111415216A (en) * | 2020-02-11 | 2020-07-14 | 广州探途网络技术有限公司 | Commodity recommendation method and device, server and storage medium |
CN111415216B (en) * | 2020-02-11 | 2023-11-07 | 广州探途网络技术有限公司 | Commodity recommendation method, commodity recommendation device, server and storage medium |
CN113159905A (en) * | 2021-05-20 | 2021-07-23 | 深圳马六甲网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium for new user |
CN113409124A (en) * | 2021-07-08 | 2021-09-17 | 山东大学 | Bulk commodity recommendation method and system based on Bayesian regression analysis |
Also Published As
Publication number | Publication date |
---|---|
WO2019085372A1 (en) | 2019-05-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107767227A (en) | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall | |
Beneke et al. | The development of a consumer value proposition of private label brands and the application thereof in a South African retail context | |
Santos | From intangibility to tangibility on service quality perceptions: a comparison study between consumers and service providers in four service industries | |
Baek et al. | A cross-cultural comparison of fast food restaurant selection criteria between Korean and Filipino college students | |
Işıklar et al. | Using a multi-criteria decision making approach to evaluate mobile phone alternatives | |
Moran | Consuming relief: Food stamps and the new welfare of the new deal | |
CN106910083A (en) | The method and device of commodity object information is provided | |
Robinson et al. | Customer loyalty | |
CN107527273A (en) | Grouping of commodities based on internet matches marketing method and system at random | |
CN107092647B (en) | Method and device for providing resource combination | |
CN105279661A (en) | Commodity object information providing method and apparatus | |
CN107424045A (en) | A kind of order generation method of Recommendations, apparatus and system | |
CN107944897A (en) | Data label dissemination system, method, server and client side | |
Wang et al. | Shoppers’ logistics activities in omni-channel retailing: A conceptualisation and an exploration on perceptual differences in effort valuation | |
Rahim et al. | Malaysian coffee culture: attributes considered to purchase coffee beverages | |
Lee | A Study on the impact of coffee service quality on customer satisfaction and loyalty | |
Tamba et al. | Consumer preferences on the purchase of cayenne pepper in Bali Province market | |
Padillo Jr et al. | Modelling the priority attributes of customer loyalty in Philippine single-dish restaurants | |
CN107491994A (en) | A kind of pricing method and system based on scoring | |
Demir | Supply chain management practices in an alternative food network: the first organic marketplace of Turkey | |
CN105894295A (en) | Dynamic association shopping evaluation method | |
Dang et al. | Assessing market integration in ASEAN with retail price data | |
Hamlett et al. | Regulating UK supermarkets: an oral-history perspective | |
Abdelmawgoud | Meals Pricing Strategies in The Egyptian Hotels: An Analytical Study | |
Danthanarayana et al. | Role of restaurant attributes and customer perceived value in shaping customer satisfaction: a sem based analysis in beach restaurants in South Coast, Sri Lanka |
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: 20180306 |
|
RJ01 | Rejection of invention patent application after publication |