CN108205768A - Database building method and data recommendation method and device, equipment and storage medium - Google Patents
Database building method and data recommendation method and device, equipment and storage medium Download PDFInfo
- Publication number
- CN108205768A CN108205768A CN201611184581.4A CN201611184581A CN108205768A CN 108205768 A CN108205768 A CN 108205768A CN 201611184581 A CN201611184581 A CN 201611184581A CN 108205768 A CN108205768 A CN 108205768A
- Authority
- CN
- China
- Prior art keywords
- data
- vector
- product features
- commodity
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- 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
Abstract
The embodiment of the invention discloses a kind of database building method and data recommendation method and device, equipment and storage mediums.The database building method includes:User's history data and commodity historical data are obtained from data source;According to user's history data and commodity historical data, user characteristics are extracted according to pre-set user dimension, to form the user characteristics of user vector, the user characteristics vector includes at least one product features;According to user's history data and commodity historical data, product features are extracted according to default commodity dimension, to form the primary commodity feature vector of commodity, the primary commodity feature vector includes at least one user characteristics;According to default commodity association rule, each primary commodity feature vector is merged, to form secondary product features vector;The user characteristics vector, primary commodity feature vector and secondary product features vector are stored, as the recommending data set in database.The present invention can improve the accuracy paid close attention to user when information is predicted.
Description
Technical field
Big data treatment technology more particularly to a kind of database building method sum number the present embodiments relate to computer
According to recommendation method and device, equipment and storage medium.
Background technology
In the case where online retailing behavior is popularized, the behavior that commodity are bought for user is effectively predicted, is a kind of
Development trend.
In the prior art, the historical behavior data of user itself are generally based on, its behavioral data hereafter are carried out pre-
It surveys.For example, certain user often buys clothes in the past, that predicts that it is to meet its consumption row to recommend the merchandise news of garment type to the user
For.In addition to the historical data of individual subscriber count so as to the technology of prediction, the prior art generally can also use phase
The mode of closing property rule to carry out information recommendation for user.Concentration statistics usually is carried out to mass users data, determines to provide
There is its behavior pattern of the user of certain generic attribute.For example, the historical data based on a large number of users, determine age bracket 20-30 Sui,
Male user, may be interested in electrical type commodity, then for meeting the user of features described above, can predict to its push electricity
Subclass commodity meet its consumer behavior.
But in the research process for realizing the present invention, inventor has found that above-mentioned technology has a drawback in that:If it relies on
In the case history data of user, then the range of recommendation information is very limited, and the prediction result of recommendation information also tends to not meet
The development trend of consumer consumption behavior.Based on the statistics of mass users data, due to differing greatly between user, regularity is simultaneously
Unobvious, if so when the data volume of statistics is not enough, the accuracy predicted consumer consumption behavior is relatively low.
Invention content
The embodiment of the present invention provides a kind of database building method and data recommendation method and device, equipment and storage is situated between
Matter, to improve the accuracy paid close attention to user when information is predicted.
In a first aspect, an embodiment of the present invention provides a kind of database building method, including:
User's history data and commodity historical data are obtained from data source;
According to user's history data and commodity historical data, user characteristics are extracted according to pre-set user dimension, to form use
The user characteristics vector at family, the user characteristics vector include at least one product features;
According to user's history data and commodity historical data, product features are extracted according to default commodity dimension, to form quotient
The primary commodity feature vector of product, the primary commodity feature vector include at least one user characteristics;
According to default commodity association rule, each primary commodity feature vector is merged, to form secondary commodity
Feature vector;
The user characteristics vector, primary commodity feature vector and secondary product features vector are stored, as in database
Recommending data set.
Second aspect, an embodiment of the present invention provides a kind of data recommendation method, including:
Obtain online recommended requirements;
Online data and recommendation rules are obtained from the online recommended requirements;
Using the recommendation rules, based on the user characteristics vector sum product features vector in online data, database, production
Raw recommending data, wherein, the user characteristics vector includes at least one product features, and the product features vector includes
At least one user characteristics.
The third aspect, an embodiment of the present invention provides a kind of Database device, including:
Historical data acquisition module, for obtaining user's history data and commodity historical data from data source;
Product features acquisition module, for according to user's history data and commodity historical data, according to pre-set user dimension
User characteristics are extracted, to form the user characteristics of user vector, the user characteristics vector includes at least one product features;
User characteristics acquisition module, for according to user's history data and commodity historical data, according to default commodity dimension
Product features are extracted, to form the primary commodity feature vector of commodity, the primary commodity feature vector includes at least one
User characteristics;
Product features processing module, for according to default commodity association rule, by each primary commodity feature vector into
Row merges, to form secondary product features vector;
Recommending data forms module, for storing the user characteristics vector, primary commodity feature vector and secondary commodity
Feature vector, as the recommending data set in database.
Fourth aspect, an embodiment of the present invention provides a kind of data recommendation device, including:
Demand acquisition module, for obtaining online recommended requirements;
Data obtaining module, for obtaining online data and recommendation rules from the online recommended requirements;
Message processing module, for using the recommendation rules, based on the user characteristics vector in online data, database
With product features vector, recommending data is generated, wherein, the user characteristics vector includes at least one product features, described
Product features vector includes at least one user characteristics.
5th aspect, an embodiment of the present invention provides a kind of equipment, the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes the database building method that any embodiment of the present invention is provided.
6th aspect, an embodiment of the present invention provides a kind of equipment, the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processing
Device realizes that the database that any embodiment of the present invention is provided recommends method.
7th aspect, an embodiment of the present invention provides a kind of storage medium for including computer executable instructions, the meters
Calculation machine executable instruction is built when being performed by computer processor for performing the database that any embodiment of the present invention is provided
Cube method.
Eighth aspect, an embodiment of the present invention provides a kind of storage medium for including computer executable instructions, the meters
Calculation machine executable instruction is pushed away when being performed by computer processor for performing the database that any embodiment of the present invention is provided
Recommend method.
The embodiment of the present invention from data source by obtaining user's history data and commodity historical data, and extract user and quotient
The feature vector of product;According to default commodity association rule, product features vector is merged, storage user characteristics vector, primary quotient
Product feature vector and secondary product features vector, obtain recommending data library, by being counted to product features, and were recommending
In addition to the feature of consideration people in journey, it is also contemplated that the feature of commodity so that recommendation effect is more accurate.
Description of the drawings
Fig. 1 is a kind of flow diagram for database building method that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow diagram of database building method provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of flow diagram for data recommendation method that the embodiment of the present invention three provides;
Fig. 4 is a kind of flow diagram for data recommendation method that the embodiment of the present invention four provides;
Fig. 5 is a kind of flow diagram for data recommendation method that the embodiment of the present invention five provides;
Fig. 6 is a kind of structure diagram for Database device that the embodiment of the present invention six provides;
Fig. 7 is a kind of structure diagram for data recommendation device that the embodiment of the present invention seven provides;
Fig. 8 is a kind of structure diagram for equipment that the embodiment of the present invention eight provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limitation of the invention.It also should be noted that in order to just
Part related to the present invention rather than entire infrastructure are illustrated only in description, attached drawing.
Embodiment one
Fig. 1 is a kind of flow chart for database building method that the embodiment of the present invention one provides.This method is suitable for electronics
The situation of commodity transaction, this method can be performed by Database device.Database device can by software and/or
The mode of hardware is realized.As shown in Figure 1, this method includes:
S110, user's history data and commodity historical data are obtained from data source.
Off-line data is obtained from data source, filters out the user's history data of needs and commodity historical data, off-line data
It includes at least:User behavior data, user attribute data, order data and quantity in stock cell data (Stock Keeping
Unit, SKU).
Further, user's history data can include user's dynamic behaviour data and user's static attribute data;Wherein,
User's dynamic behaviour data are for example including goods browse behavior, navigator fix behavior, search engine search behavior, search result point
Hit at least one of behavior and browsing webpage behavior;It can be adopted from operation log of the user using various client softwares
Collection.User's static attribute data may include at least one of name, gender, address, height, weight and educational background, such as can be from
It is obtained in the log-on message of user.Commodity historical data may include goods orders data and commodity stocks data etc..
S120, according to user's history data and commodity historical data, user characteristics are extracted according to pre-set user dimension, with shape
Into the user characteristics vector of user, user characteristics vector includes at least one product features.
Before characteristic vector pickup is carried out to user's history data and commodity historical data, all preferably first carry out duplicate removal,
The operations such as denoising.
According to user's history data and commodity historical data, according to pre-set user dimension, used from multiple setting dimension extractions
Family feature, dimension can be the user properties that any one wishes to pay close attention to, for example, height, the moon amount of consumption, the quantity for buying mobile phone
With price etc..Dimension can be set manually, and can also be determined by way of model training based on big data statistics.It will extraction
User characteristics formed each user user characteristics vector.Include at least one product features, example in user characteristics vector
Such as, the behavior of webpage is browsed by user, it may be determined that the commodity of certain user concern are bought the behavior of commodity by user, also may be used
To determine the commodity of the user preferences.Each dimensional characteristics of the interested commodity of these users can be used as product features, be added to
In user characteristics vector.Product features can be the feature of certain particular commodity or describe commodity abstract characteristics, example
Such as, hobby color of the replacement cycle of electronic equipment or down jackets etc..
S130, according to user's history data and commodity historical data, product features are extracted according to default commodity dimension, with shape
Into the primary commodity feature vector of commodity, primary commodity feature vector includes at least one user characteristics.
According to user's history data and commodity historical data, according to pre-set user dimension, from multiple setting dimension extraction quotient
Product feature, dimension can be any one wish pay close attention to item property, for example, affiliated brand, each shop the moon sales volume,
Size, color etc..Dimension can be set manually, and can also be counted and determined by big data.The product features of extraction are formed
The primary commodity feature vector of each commodity.Primary commodity feature vector includes at least one user characteristics, can be the quotient
The frequent purchase crowd characteristic of product, the user property being suitble to.For example, the clothes of certain size, may include be suitble to height
Feature, as user characteristics etc..
The default commodity association rule of S140, basis, each primary commodity feature vector is merged, to form secondary commodity
Feature vector.
Commodity association rule is exactly the contact established according to certain same or similar parts between commodity, can be according to quotient
The attribute of product carries out free setting according to the behavioural habits of user, certain to primary commodity according to the correlation rule of default commodity
Feature vector merges, and the feature vector of secondary commodity is obtained, for example, can be according to primary commodity color, model and material
Etc. feature vectors merge, merging condition can be set according to specific needs, and the feature vector of secondary commodity is obtained after merging.It is secondary
Grade product features vector can continue to merge based on correlation rule, obtain new product features vector.
S150, storage user characteristics vector, primary commodity feature vector and secondary product features vector, as in database
Recommending data set.
The storage mode of each feature vector is unlimited, can be the array that generation includes various features, be independent feature
Vector stores respectively.Can also be the relationship for establishing composition characteristic vector between various features, the content of separation storage feature and
Relationship between feature.
The embodiment of the present invention one provide a kind of database building method, by from data source obtain user's history data and
Commodity historical data extracts the feature vector of user and commodity;And according to default commodity association rule, product features vector is closed
And and user characteristics vector, primary commodity feature vector and secondary product features vector are stored, acquisition recommending data
Library.By being counted to product features, and in recommendation process both consider people feature, by considering the feature of commodity,
So that recommending data is more accurate.
Embodiment two
Fig. 2 is a kind of flow diagram of database building method provided by Embodiment 2 of the present invention.The present embodiment be
System is further explained on the basis of above-described embodiment one.As shown in Fig. 2, this method includes:
S210, user's history data and commodity historical data are obtained from data source.
S220, according to user's history data and commodity historical data, user characteristics are extracted according to pre-set user dimension, with shape
Into the user characteristics vector of user, user characteristics vector includes at least one product features.
S230, according to user's history data and commodity historical data, product features are extracted according to default commodity dimension, with shape
Into the primary commodity feature vector of commodity, primary commodity feature vector includes at least one user characteristics.
S240, according at least one core feature set in default commodity association rule, by each primary commodity feature to
The characteristic value similarity of core feature reaches each primary commodity feature vector of setting condition and merges in amount, to form secondary
Product features vector.
Core feature is the important feature being concerned, and to the primary commodity feature vector of each commodity, is generally basede on setting
The similarity of core feature merges.Core feature and non-core feature are generally comprised in primary commodity feature vector, if one
A or multiple cores are characterized in that same or similar degree reaches certain condition, then close these primary commodity feature vectors
And.Wherein it is possible to according to a variety of different merging conditions, merge multigroup secondary product features vector.For example, work as product colour
When being core feature, 10,000 groups of primary commodity feature vectors may be merged;When product type is core feature, may only merge
Ten groups of primary commodity feature vectors.Merging condition can set according to specific needs.
Core feature can have artificial setting, and different recommended requirements or big data can also be answered to count determining to screen.
Typical core feature may include:Commodity self attributes, Sales Volume of Commodity data, commodity stocks data or the merchandise sales degree of association
Deng.
S250, storage user characteristics vector, primary commodity feature vector and secondary product features vector, as in database
Recommending data set.
S260, user characteristics vector, primary commodity feature vector and secondary in online recommended requirements and database
Product features vector generates recommending data.
Online recommended requirements are obtained according to the online demand of user, obtain the product features of user's needs and the feature of user
Vector, and primary and secondary product features vector is screened, the commodity for recommending to meet user demand are to user.
S270, basis are directed to the online response data of recommending data, corrigendum user characteristics vector, primary commodity feature vector
With the characteristic value in secondary product features vector.
According to the online demand data of user, feature vector and primary commodity feature vector and secondary features to the user
Characteristic value in vector carries out real-time update, ensures the accuracy of data.
Further, this method can also include:It receives administrator and inputs newer commodity association rule, according to newer
The feature of user characteristics vector, primary commodity feature vector and secondary product features vector in commodity association Policy Updates database
Value.
Aforesaid operations, which are equivalent to, is modified database based on manual intervention data.The source of manual intervention data can be with
Including:Ad data, trend data adjust flexible strategy evidence and random factor etc., this data enters database as fiddle factors, influences
Data result of calculation.Product features value needs in part are counted or are predicted from offline historical data and determined, manual intervention
Data can correct statistic algorithm or prediction algorithm, so as to adjust the characteristic value calculated.For example, the sale to Mr. Yu's class commodity
Volume is predicted, may be based on user and be searched for browsing data, actual purchase data and fashion trend data etc., manual intervention data can
To adjust the weight between this few class Consideration, so as to which prediction result be made to tend to be accurate.
Adjustment for feature vector characteristic value in database is also based on machine learning algorithm to be corrected.It is logical
The training learning art of computer is crossed, analyzes user feedback data and other feedback data so as to form correction data.
Commodity association rule can include following at least one:To set product features as the similar commodity of classification foundation
Merge rule;It is regular using the product features with correlation behavior as commodity association, wherein, correlation behavior include buying behavior or
Usage behavior etc..
The correlation rule of commodity is divided into static association rule and dynamic association rules, wherein, based on commodity itself specified genus
The correlation rule of property belongs to static association rule, such as:Resolution ratio, CPU processing capacities, memory of mobile phone etc. set the phase of attribute
Reach setting condition like degree, just establish the association between two kinds of commodity, here it is the correlation behaviors based on static association rule;It is dynamic
State correlation rule is the correlation rule of the buying behavior based on user, such as:When certain commodity is purchased, while buy another
The probability of kind commodity reaches setting condition, then establishes the association between both commodity, this is the pass based on dynamic association rules
Connection behavior.The form of expression of incidence relation can there are many, for example, coarseness:Have between mobile phone and data line and be generally associated with;
Fine granularity:Huawei's P9 mobile phones have with the mobile phone of millet model to be associated with;Incidence relation is also possible to specifically include association probability, example
Such as, mobile phone and the probability that data line is bought simultaneously are 70%.
A kind of database building method provided in an embodiment of the present invention obtains online recommended requirements according to the online demand of user
Recommending data is generated, and can constantly be corrected recommending data library according to the feedback data in various aspects source or intervention data, ensure
The accuracy and real-time of the data in recommending data library.
Embodiment three
Fig. 3 is a kind of flow diagram for data recommendation method that the embodiment of the present invention three provides.The present embodiment is upper
On the basis of stating embodiment recommending data library, the data recommendation method of release, this method data recommendation suitable for commodity transaction
Situation, this method can perform by data recommendation device.Data recommendation device can by the mode of software and/or hardware Lai
It realizes.As shown in figure 3, the data recommendation method includes:
S310, online recommended requirements are obtained.
The needs that online recommended requirements generate in real time generate the demand of recommending data based on the recommending data library, for example,
When user is selecting certain commodity or generation order, when logistics service provider needs to provide inventory forecast amount and need to opening client
When holding user's active Recommendations information of software, real-time online recommended requirements are produced.
S320, online data and recommendation rules are obtained from online recommended requirements.
Further, online data is obtained from online recommended requirements, wherein, it is special that online data includes at least one user
Sign and/or at least one product features;Corresponding recommendation rules are searched according to online recommended requirements.Wherein, online data can be with
Including:User information and the information of concern commodity etc..Recommendation rules are that the situation of itself determines according to the online recommended requirements
Recommending data calculation and push mode etc..
S330, using recommendation rules, based on the user characteristics vector sum product features vector in online data, database,
Recommending data is generated, wherein, user characteristics vector includes at least one product features, and product features vector includes at least one
A user characteristics.
According to user characteristics vector, the correlation rule of product features vector sum commodity, in data recommendation library and online data
In library, relevant commodity are searched for, recommending data is generated, recommends requirement of main body, requirement of main body mainly includes:User, logistics clothes
Be engaged in quotient and supplier.
An embodiment of the present invention provides a kind of data recommendation methods, according to the online recommended requirements of client, obtain in line number
According to and recommendation rules;According to recommendation rules, screening is carried out in recommending data library and online database and searches user characteristics vector
With product features vector, recommending data is generated.The data recommendation method can either provide the data of needs to the user, reduce user
Screening difficulty, additionally it is possible to user is avoided screening mistake occur, improves the accuracy of operation.
Example IV
Fig. 4 is a kind of flow diagram for data recommendation method that the embodiment of the present invention four provides.The present embodiment is upper
It states and is optimized, and specific description has been carried out by taking order suggested design as an example on the basis of embodiment, as shown in figure 4, should
Method includes:
S410, online recommended requirements are obtained.
Online recommended requirements can be that online order generates demand, such as in client software of doing shopping, when user clicks
Commodity want generate a purchase order when, generally require filling order option, for example, apparel size, color, dispatching address and
Quantity purchase etc..Commodity are clicked before backlog submission in user, that is, produce online order generation demand.
S420, online data and recommendation rules are obtained from online recommended requirements.
At least one of online data user characteristics can be that the user for preparing for order user obtained online is special
Sign;At least one of online data product features are the product features of order commodity to be generated obtained online.
S430, using recommendation rules, search matched at least one use in the database according at least one user characteristics
Family feature vector.
The user characteristics vector for including the user characteristics can be specifically to look for, can be to look for out some specific user's
Feature vector or the multiple feature vectors for finding out certain class user.
S440, matched at least one product features vector is searched in the database according at least one product features.
The product features vector for including the product features can be specifically to look for, particular commodity can be to look for out, also may be used
To be to look for out multiple feature vectors of certain class commodity.
S450, the product features vector found is screened according to the user characteristics vector found.
Aforesaid operations are equivalent to the matching for carrying out user characteristics and product features, specifically, special according to the user found
Sign vector, which carries out the product features vector found screening, may include:According to the order type of online order, from what is found
User characteristics to be matched are extracted in user characteristics vector, product features to be matched are extracted from the product features vector found;
User characteristics to be matched and product features to be matched are subjected to similarity mode;Screening obtains similarity result and reaches setting condition
Product features vector.
User characteristics to be matched and product features to be matched, can be determined by order type, for example, the order of clothes class, is treated
It can be height, weight to match user characteristics, and product features to be matched can be size.Order needs during formation
Data are standardized according to national standard and international standard, such as:The corresponding height of national standard XXL be 170CM-175CM, body
Weight 60KG-70KG, if No. XXXL of certain marque is equivalent to national standard XXL, needs to do standard to the marque at this time
Change is handled;When certain model is unsatisfactory for some national standard or international standard model, which is calculated,
Finally according to probability theory, it is standardized as standard model.Alternatively, according to various countries' national standard, international standard and other related datas, it is right
Various standardized datas carry out intra-class correlation processing, and are uniformly mapped as the national standard data.For example, 37 yards of the Europe code of footwear code,
The data such as 23 yards of China, 5 yards of the U.S., 4.5 yards of Britain are all finally the long 230mm of foot, and commodity data can be according to data mapped system
Different sizes are mapped as in country variant.
The order type of online order is if it is electronic equipment, and user characteristics to be matched include the age or electronic equipment is liked
Good tendency etc., product features to be matched may include attribute of performance or interest tags.
S460, recommending data is extracted from the product features vector after screening.
Recommending data is extracted from the product features vector after screening may include:It is carried from the product features vector after screening
Recommending data is taken, and is filled into the constraint term of online order, user is shown to as order is recommended.
When user buys commodity, the feature of user is determined according to online recommended requirements, the feature of user can be user
Height, weight, waistline, the moon amount of consumption and buy commodity type, according to the feature of user in recommending data library or in line number
It is searched and the relevant feature vector of user characteristics according in library;The product features inputted when buying commodity according to user are recommending number
According to the relevant feature vector of product features searched in library or online database with user's selection;It is screened according to user characteristics vector
User selects the feature vector of commodity, generates recommending data and recommends user, is selected for user.Meanwhile when user has selected
After certain commodity, do not need to spend a large amount of time the various definitional attributes for selecting the commodity, recommending data library is according to online
User characteristics to be matched and product features to be matched are carried out similarity mode by the order type of order;Screening obtains similarity
As a result reach the product features vector of setting condition, recommending data is extracted from the product features vector after screening, and fill extremely
In the constraint term of online order, user is shown to as order is recommended.It is different according to the commodity that user selects, it is different to choose user
Feature commodity are screened.
An embodiment of the present invention provides a kind of data recommendation methods, can be used for order recommendation process, are recommended according to online
Demand obtains user characteristics, product features and the recommendation rules in online data, according to recommendation rules, obtain user characteristics to
Amount and product features vector, screen the product features vector found according to the user characteristics vector found, from sieve
Recommending data is extracted in product features vector after choosing, and is filled into the constraint term of online order, is shown as order is recommended
To user.The data recommendation method simplifies single process under user, reduces user and inputs operation, so as to improve lower single efficiency and into list
Rate;When user being avoided to place an order do not pay attention to, wrong data are easily wrongly write or selected, reduction is cancelled the order rate;Without ginseng when being also avoided that under user single
Data are examined, selection is difficult.
Embodiment five
Fig. 5 is a kind of flow diagram for data recommendation method that the embodiment of the present invention five provides.The present embodiment is upper
It states and is optimized on the basis of embodiment, and specific description has been carried out for quantity in stock to be answered to predict, as shown in figure 5, should
Method includes:
S510, online recommended requirements are obtained.
Online recommended requirements are quantity in stock forecast demand;At least one of online data product features are quotient to be predicted
Product attribute, target recommended characteristics are unit time sales volume.
S520, online data and recommendation rules are obtained from online recommended requirements.
S530, using recommendation rules, search matched at least one quotient in the database according at least one product features
Product feature vector.
S540, at least one user characteristics vector is searched according to the product features vector found in the database.
S550, using the target recommended characteristics in online data as statistical dimension, based on the user characteristics vector found
Commodity attention rate feature carry out prediction calculating, as recommending data.
Simple illustration is carried out so that quantity in stock is predicted as an example below, it is well known that with the fast development of net purchase, also bring
The problem of new, be exactly inventory's warehousing management is less efficient, this may lead to cargo supply falls short of demand or the phenomenon that deadstock,
In order to preferably solve the problems, such as this, the present embodiment proposes a kind of data recommendation method.By online recommended requirements, obtain
Line number according to this and recommendation rules, according to recommendation rules, searches product features vector sum user characteristics vector, will be in online data
For unit interval sales volume as statistical dimension, the commodity attention rate feature based on the user characteristics vector found carries out prediction meter
It calculates, as recommending data;It can also be analyzed according to the behavioral data of user, as user's browsing pages data, user search for
Data, user add in shopping cart commodity data and user selects item property data, by user behavior analysis result data with pushing away
It recommends data and carries out intelligent decision calculating, according to behavior correlation model and behaviour psychology model, calculate that commodity are various not to be belonged to
The purchase probability of property, finally obtains the recommending data of certain user's commodity, is supplied to supplier.
The embodiment of the present invention provides a kind of data recommendation method, can be applied to during quantity in stock prediction, according to online
Recommended requirements obtain online data and recommendation rules, and search dependent merchandise feature vector and user characteristics vector, by target
For recommended characteristics as statistical dimension, the commodity attention rate feature based on the user characteristics vector found carries out prediction calculating, makees
For recommending data, and recommend goods providers.So as to, inventory's warehousing management efficiency is improved, reduces stock quantity, so as to
Reduce cost and the occupation of capital;Logistic efficiency is improved, particularly across the logistics management between storehouse and conevying efficiency;Also it improves to not
Carry out the accuracy rate of condition of merchandise prediction.
Embodiment six
Fig. 6 is a kind of structure diagram for Database device that the embodiment of the present invention six provides.It as shown in fig. 6, should
Device includes:
Historical data acquisition module 610, for obtaining user's history data and commodity historical data from data source;Commodity are special
Acquisition module 620 is levied, for according to user's history data and commodity historical data, extraction user to be special according to pre-set user dimension
Sign, to form the user characteristics of user vector, user characteristics vector includes at least one product features;User characteristics obtain mould
Block 630, for according to user's history data and commodity historical data, product features being extracted according to default commodity dimension, to be formed
The primary commodity feature vector of commodity, primary commodity feature vector include at least one user characteristics;Product features handle mould
Block 640, it is special to form secondary commodity for according to commodity association rule is preset, each primary commodity feature vector to be merged
Sign vector;Recommending data forms module 650, special for storing user characteristics vector, primary commodity feature vector and secondary commodity
Sign vector, as the recommending data set in database.
Further, user's history data include user's dynamic behaviour data and user's static attribute data;Wherein, user
Dynamic behaviour data include goods browse behavior, navigator fix behavior, search engine search behavior, search result click behavior and
Browse at least one of webpage behavior;User's static attribute data are included in name, gender, address, height, weight and educational background
At least one;Commodity historical data includes goods orders data and commodity stocks data.
Further, product features processing module 640 is specifically used for:It is set at least according in default commodity association rule
The characteristic value similarity of core feature in each primary commodity feature vector is reached each primary of setting condition by one core feature
Product features vector merges, to form secondary product features vector.
Further, core feature includes:Commodity self attributes, Sales Volume of Commodity data, commodity stocks data or commodity pin
Sell the degree of association.
Further, which further includes:Recommending data acquisition module, for according in online recommended requirements and database
User characteristics vector, primary commodity feature vector and secondary product features vector generate recommending data;Recommending data updates mould
Block, for according to the online response data for being directed to recommending data, corrigendum user characteristics vector, primary commodity feature vector and secondary
Characteristic value in product features vector.
Further, which further includes:Association rules updating module inputs newer commodity pass for receiving administrator
Connection rule, according to user characteristics vector, primary commodity feature vector and secondary in newer commodity association Policy Updates database
The characteristic value of product features vector.
Further, commodity association rule includes following at least one:To set product features as the same of classification foundation
Class commodity merge rule;It is regular using the product features with correlation behavior as commodity association, wherein, correlation behavior includes purchase
Behavior or usage behavior.
A kind of Database device is present embodiments provided, user and quotient are obtained by historical data acquisition module 610
The historical data of product, and product features acquisition module 620 and user characteristics acquisition module 630 are sent to, product features obtain mould
Block 620 is for extracting product features and user characteristics acquisition module 630 for extracting user characteristics, respectively by the commodity of extraction spy
User characteristics of seeking peace are sent to product features processing module 640, and product features processing module 640 is advised according to default commodity association
Then, each primary commodity feature vector is merged, to form secondary product features vector;Recommending data forms module 650, will
Above-mentioned user characteristics vector, primary commodity feature vector and secondary product features vector are stored, as pushing away in database
Recommend data acquisition system.By being counted to product features, and both in view of the feature of people in recommendation process, by considering commodity
Feature so that recommending data is more accurate.
A kind of Database device provided in this embodiment, a kind of database provided with any embodiment of the present invention
Method for building up belongs to same inventive concept, can perform a kind of database building method that any embodiment of the present invention is provided, tool
Standby corresponding function and advantageous effect.The not technical detail of detailed description in the present embodiment is implemented reference can be made to the present invention is arbitrary
A kind of database building method that example provides.
Embodiment seven
Fig. 7 is a kind of structure diagram for data recommendation device that the embodiment of the present invention seven provides.As shown in fig. 7, the dress
Put including:
Demand acquisition module 710, for obtaining online recommended requirements;Data obtaining module 720, for recommending to need from online
Ask middle acquisition online data and recommendation rules;Message processing module 730, for using recommendation rules, based on online data, number
According to the user characteristics vector sum product features vector in library, recommending data is generated, wherein, user characteristics vector includes at least one
A product features, product features vector include at least one user characteristics.
Further, message processing module 730, including:Online data acquisition module, for being obtained from online recommended requirements
Online data is taken, wherein, online data includes at least one user characteristics and/or at least one product features;Recommendation rules obtain
Modulus block, for searching corresponding recommendation rules according to online recommended requirements.
Further, message processing module 730, including:User characteristics vector acquisition module, for using recommendation rules,
Matched at least one user characteristics vector is searched in the database according at least one user characteristics;Product features vector obtains
Module, for searching matched at least one product features vector in the database according at least one product features;Screen mould
Block, for being screened according to the user characteristics vector found to the product features vector found;Data recommendation module is used
Recommending data is extracted in the product features vector after screening.
Further, online recommended requirements generate demand for online order;At least one of online data user characteristics
For the user characteristics for preparing for order user obtained online;At least one of online data product features are obtained to be online
Order commodity to be generated product features;Correspondingly, screening module is specifically used for:According to the order type of online order, from
User characteristics to be matched are extracted in the user characteristics vector found, quotient to be matched is extracted from the product features vector found
Product feature;User characteristics to be matched and product features to be matched are subjected to similarity mode;Screening obtains similarity result and reaches
The product features vector of setting condition.
Further, the order type of online order is clothing, then user characteristics to be matched include height or weight, treat
Include size with product features;Or the order type of online order be electronic equipment, then user characteristics to be matched include the age or
Electronic equipment hobby tendency, product features to be matched include attribute of performance or interest tags.
Further, data recommendation module is additionally operable to:Recommending data is extracted, and fill out from the product features vector after screening
It is charged in the constraint term of online order, user is shown to as order is recommended.
Further, message processing module 730, including:Product features vector acquisition module, using recommendation rules, according to
At least one product features search matched at least one product features vector in the database;User characteristics vector obtains mould
Block searches at least one user characteristics vector in the database according to the product features vector found;Data recommendation module is used
In using the target recommended characteristics in online data as statistical dimension, based on the commodity attention rate of user characteristics vector found
Feature carries out prediction calculating, as recommending data.
Further, online recommended requirements are quantity in stock forecast demand;At least one of online data product features are
Item property to be predicted, target recommended characteristics are unit time sales volume.
A kind of data recommendation device provided in an embodiment of the present invention, obtaining online recommendation by demand acquisition module 710 needs
It asks, and recommended requirements is sent to data obtaining module 720, data obtaining module 720 obtains online data according to recommended requirements
And recommendation rules, message processing module 730, using recommendation rules, based on the user characteristics vector in online data, database
With product features vector, recommending data is generated.The data recommendation device can either provide the data of needs to the user, reduce user
Screening difficulty, additionally it is possible to user is avoided screening mistake occur, improves the accuracy of operation.
A kind of data recommendation device provided in this embodiment, a kind of data recommendation provided with any embodiment of the present invention
Method belongs to same inventive concept, can perform a kind of data recommendation method that any embodiment of the present invention is provided, and has corresponding
Function and advantageous effect.The not technical detail of detailed description in the present embodiment, reference can be made to any embodiment of the present invention provides
A kind of data recommendation method.
The embodiment of the present invention additionally provides a kind of equipment, and the equipment includes:One or more processors;Storage device,
For storing one or more programs, when one or more of programs are performed by one or more of processors so that institute
It states one or more processors and realizes the database building method that any embodiment of the present invention is provided.
The embodiment of the present invention provides another equipment again, and the equipment includes:One or more processors;
Storage device, for storing one or more programs, when one or more of programs are one or more of
Processor performs so that one or more of processors realize the database recommendation side that any embodiment of the present invention is provided
Method.
The structure of above equipment is illustrated by following embodiments eight.
Embodiment eight
Fig. 8 is the structure diagram of a kind of equipment that the embodiment of the present invention eight provides.Fig. 8 shows to be used for realizing this
The block diagram of the example devices 8100 of invention embodiment.The equipment 8100 that Fig. 8 is shown is only an example, should not be to this hair
The function and use scope of bright embodiment bring any restrictions.
As shown in figure 8, equipment 8100 is showed in the form of universal computing device.The component of equipment 8100 can be included but not
It is limited to:One or more processor or processing unit 8110, system storage 8120, connection different system component (including
System storage 8120 and processing unit 8110) bus 8130.
Bus 8130 represents one or more in a few class bus structures, is controlled including memory bus or memory
Device, peripheral bus, graphics acceleration port, processor or total using the local of the arbitrary bus structures in a variety of bus structures
Line.For example, these architectures include but not limited to industry standard architecture (ISA) bus, microchannel architecture
(MAC) bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) are total
Line.
Equipment 8100 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment
8100 usable mediums accessed, including volatile and non-volatile medium, moveable and immovable medium.
System storage 8120 can include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 8121 and/or cache memory 8122.Equipment 8100 may further include it is other it is removable/no
Movably, volatile/non-volatile computer system storage medium.Only as an example, storage system 8123 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 8 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 8,
It can provide for moving the disc driver of non-volatile magnetic disk (such as " floppy disk ") read-write and to removable non-easy
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 8130.Memory 8120 can include at least one
A program product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform
The function of various embodiments of the present invention.
Program/utility 8125 with one group of (at least one) program module 8124, can be stored in and for example store
In device 8120, such program module 8124 includes but not limited to operating system, one or more application program, other programs
Module and program data may include the realization of network environment in each or certain combination in these examples.Program mould
Block 8124 usually performs function and/or method in embodiment described in the invention.
Equipment 8100 can also be with one or more external equipments 8300 (such as keyboard, sensing equipment, display 8200
Deng) communication, the equipment interacted with the equipment 8100 communication can be also enabled a user to one or more and/or with causing this
Any equipment (such as network interface card, modem etc.) that equipment 8100 can communicate with one or more of the other computing device
Communication.This communication can be carried out by input/output (I/O) interface 8140.Also, equipment 8100 can also be fitted by network
Orchestration 8150 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network, such as because of spy
Net) communication.As shown in the figure, network adapter 8150 is communicated by bus 8130 with other modules of equipment 8100.It should be understood that
Although not shown in the drawings, can other hardware and/or software module be used with bonding apparatus 8100, including but not limited to:Microcode,
Device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage
System etc..
Processing unit 8110 is stored in the program in system storage 8120 by operation, so as to perform various functions application
And data processing, such as the database building method that is provided of the embodiment of the present invention or data recommendation method are provided.
An embodiment of the present invention provides a kind of storage medium for including computer executable instructions, the computer can perform
Instruction by computer processor when being performed for performing the database building method that any embodiment of the present invention is provided.
The embodiment of the present invention provides another storage medium for including computer executable instructions again, and the computer can
Execute instruction recommends method when being performed by computer processor for performing the database that any embodiment of the present invention is provided.
The arbitrary of one or more computer-readable media may be used in the computer storage media of the embodiment of the present invention
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device or arbitrary above combination.The more specific example (non exhaustive list) of computer readable storage medium includes:Tool
There are one or the electrical connections of multiple conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or storing program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media can include in a base band or as a carrier wave part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but it is unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.
The program code included on computer-readable medium can be transmitted with any appropriate medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
It can write to perform the computer that operates of the present invention with one or more programming language or combinations
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully performs, partly perform on the user computer on the user computer, the software package independent as one performs, portion
Divide and partly perform or perform on a remote computer or server completely on the remote computer on the user computer.
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including LAN (LAN) or
Wide area network (WAN)-be connected to subscriber computer or, it may be connected to outer computer (such as is carried using Internet service
Pass through Internet connection for quotient).
Note that it above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The present invention is not limited to specific embodiment described here, can carry out for a person skilled in the art various apparent variations,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above example to the present invention
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
It can include other more equivalent embodiments, and the scope of the present invention is determined by scope of the appended claims.
Claims (26)
1. a kind of database building method, which is characterized in that including:
User's history data and commodity historical data are obtained from data source;
According to user's history data and commodity historical data, user characteristics are extracted according to pre-set user dimension, to form user's
User characteristics vector, the user characteristics vector include at least one product features;
According to user's history data and commodity historical data, product features are extracted according to default commodity dimension, to form commodity
Primary commodity feature vector, the primary commodity feature vector include at least one user characteristics;
According to default commodity association rule, each primary commodity feature vector is merged, to form secondary product features
Vector;
The user characteristics vector, primary commodity feature vector and secondary product features vector are stored, as pushing away in database
Recommend data acquisition system.
2. according to the method described in claim 1, it is characterized in that:
The user's history data include user's dynamic behaviour data and user's static attribute data;
Wherein, user's dynamic behaviour data include goods browse behavior, navigator fix behavior, search engine search behavior,
Search result clicks at least one of behavior and browsing webpage behavior;User's static attribute data include name, gender,
At least one of address, height, weight and educational background;
The commodity historical data includes goods orders data and commodity stocks data.
3. according to the method described in claim 1, it is characterized in that, according to default commodity association rule, by each primary quotient
Product feature vector merges, and is included with forming secondary product features vector:
It is according at least one core feature set in default commodity association rule, core in each primary commodity feature vector is special
Each primary commodity feature vector that the characteristic value similarity of sign reaches setting condition merges, with formed secondary product features to
Amount.
4. according to the method described in claim 3, it is characterized in that, the core feature includes:Commodity self attributes, commodity pin
Measure data, commodity stocks data or the merchandise sales degree of association.
5. it according to the method described in claim 1, it is characterized in that, further includes:
User characteristics vector, primary commodity feature vector and secondary quotient in online recommended requirements and the database
Product feature vector generates recommending data;
According to the online response data for the recommending data, the user characteristics vector, primary commodity feature vector are corrected
With the characteristic value in secondary product features vector.
6. it according to the method described in claim 1, it is characterized in that, further includes:
It receives administrator and inputs newer commodity association rule, according to institute in database described in newer commodity association Policy Updates
State the characteristic value of user characteristics vector, primary commodity feature vector and secondary product features vector.
7. according to any methods of claim 1-6, which is characterized in that the commodity association rule includes following at least one
Kind:
Merge rule using the similar commodity for setting product features as classification foundation;
It is regular using the product features with correlation behavior as commodity association, wherein, the correlation behavior include buying behavior or
Usage behavior.
8. a kind of data recommendation method, which is characterized in that including:
Obtain online recommended requirements;
Online data and recommendation rules are obtained from the online recommended requirements;
Using the recommendation rules, based on the user characteristics vector sum product features vector in online data, database, generation pushes away
Data are recommended, wherein, the user characteristics vector includes at least one product features, and the product features vector is included at least
One user characteristics.
9. according to the method described in claim 8, it is characterized in that, from the online recommended requirements obtain online data and
Recommendation rules include:
Obtain online data from the online recommended requirements, wherein, the online data include at least one user characteristics and/
Or at least one product features;
Corresponding recommendation rules are searched according to the online recommended requirements.
10. according to the method described in claim 9, it is characterized in that, using the recommendation rules, based on online data, data
User characteristics vector sum product features vector in library, generates recommending data and includes:
Using the recommendation rules, matched at least one user characteristics are searched in the database according at least one user characteristics
Vector;
Matched at least one product features vector is searched in the database according at least one product features;
The user characteristics vector according to finding screens the product features vector found;
Recommending data is extracted from the product features vector after screening.
11. according to the method described in claim 10, it is characterized in that:
The online recommended requirements generate demand for online order;
At least one of online data user characteristics are the user characteristics for preparing for order user obtained online;
At least one of online data product features are the product features of order commodity to be generated obtained online;
Include correspondingly, carrying out screening to the product features vector found according to the user characteristics vector found:
According to the order type of online order, user characteristics to be matched are extracted from the user characteristics vector found, from
Product features to be matched are extracted in the product features vector found;
The user characteristics to be matched and product features to be matched are subjected to similarity mode;
Screening obtains the product features vector that similarity result reaches setting condition.
12. according to the method for claim 11, it is characterised in that:
The order type of the online order is clothing, then the user characteristics to be matched include height or weight, described to treat
Include size with product features;Or
The order type of the online order is electronic equipment, then the user characteristics to be matched include the age or electronic equipment is liked
Good tendency, the product features to be matched include attribute of performance or interest tags.
13. according to the method for claim 11, which is characterized in that number is recommended in extraction from the product features vector after screening
According to including:
Recommending data is extracted from the product features vector after screening, and is filled into the constraint term of online order, as recommendation
Order is shown to user.
14. according to the method described in claim 9, it is characterized in that, using the recommendation rules, based on online data, data
User characteristics vector sum product features vector in library, generates recommending data and includes:
Using the recommendation rules, matched at least one product features are searched in the database according at least one product features
Vector;
Product features vector according to finding searches at least one user characteristics vector in the database;
Using the target recommended characteristics in the online data as statistical dimension, based on the commodity of user characteristics vector found
Attention rate feature carries out prediction calculating, as recommending data.
15. according to the method for claim 14, it is characterised in that:
The online recommended requirements are quantity in stock forecast demand;
At least one of online data product features are item property to be predicted, and target recommended characteristics are sold for the unit time
Amount.
16. a kind of Database device, which is characterized in that including:
Historical data acquisition module, for obtaining user's history data and commodity historical data from data source;
Product features acquisition module, for according to user's history data and commodity historical data, being extracted according to pre-set user dimension
User characteristics, to form the user characteristics of user vector, the user characteristics vector includes at least one product features;
User characteristics acquisition module, for according to user's history data and commodity historical data, being extracted according to default commodity dimension
Product features, to form the primary commodity feature vector of commodity, the primary commodity feature vector includes at least one user
Feature;
Product features processing module, for according to default commodity association rule, each primary commodity feature vector to be closed
And to form secondary product features vector;
Recommending data forms module, for storing the user characteristics vector, primary commodity feature vector and secondary product features
Vector, as the recommending data set in database.
17. device according to claim 16, which is characterized in that the product features processing module is specifically used for:
It is according at least one core feature set in default commodity association rule, core in each primary commodity feature vector is special
Each primary commodity feature vector that the characteristic value similarity of sign reaches setting condition merges, with formed secondary product features to
Amount.
18. device according to claim 16, which is characterized in that further include:
Recommending data acquisition module, it is vectorial, first for the user characteristics in online recommended requirements and the database
Grade product features vector sum secondary product features vector generates recommending data;
Recommending data update module, for according to the online response data for being directed to the recommending data, correcting the user characteristics
Characteristic value in vector, primary commodity feature vector and secondary product features vector.
19. a kind of data recommendation device, which is characterized in that including:
Demand acquisition module, for obtaining online recommended requirements;
Data obtaining module, for obtaining online data and recommendation rules from the online recommended requirements;
Message processing module, for using the recommendation rules, based on the user characteristics vector sum quotient in online data, database
Product feature vector generates recommending data, wherein, the user characteristics vector includes at least one product features, the commodity
Feature vector includes at least one user characteristics.
20. device according to claim 19, which is characterized in that described information processing module, including:
Online data acquisition module, for obtaining online data from the online recommended requirements, wherein, the online data packet
Include at least one user characteristics and/or at least one product features;
Recommendation rules acquisition module, for searching corresponding recommendation rules according to the online recommended requirements.
21. device according to claim 20, which is characterized in that described information processing module, including:
User characteristics vector acquisition module, for using the recommendation rules, according at least one user characteristics in the database
Search matched at least one user characteristics vector;
Product features vector acquisition module, for according at least one product features search in the database it is matched at least
One product features vector;
Screening module, for being screened according to the user characteristics vector found to the product features vector found;
Data recommendation module, for extracting recommending data from the product features vector after screening.
22. device according to claim 20, which is characterized in that described information processing module, including:
Product features vector acquisition module using the recommendation rules, is searched in the database according at least one product features
Matched at least one product features vector;
It is special to search at least one user in the database according to the product features vector found for user characteristics vector acquisition module
Sign vector;
Data recommendation module, for using the target recommended characteristics in the online data as statistical dimension, based on what is found
The commodity attention rate feature of user characteristics vector carries out prediction calculating, as recommending data.
23. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now database building method as described in any in claim 1-7.
24. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
Now the database as described in any in claim 8-15 recommends method.
25. a kind of storage medium for including computer executable instructions, the computer executable instructions are by computer disposal
Database building method when device performs for execution as described in any in claim 1-7.
26. a kind of storage medium for including computer executable instructions, the computer executable instructions are by computer disposal
Recommend method when device performs for performing the database as described in any in claim 8-15.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611184581.4A CN108205768B (en) | 2016-12-20 | 2016-12-20 | Database establishing method, data recommending device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611184581.4A CN108205768B (en) | 2016-12-20 | 2016-12-20 | Database establishing method, data recommending device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108205768A true CN108205768A (en) | 2018-06-26 |
CN108205768B CN108205768B (en) | 2022-07-05 |
Family
ID=62603416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611184581.4A Active CN108205768B (en) | 2016-12-20 | 2016-12-20 | Database establishing method, data recommending device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108205768B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919669A (en) * | 2019-02-25 | 2019-06-21 | 宇宙世代信息技术(深圳)有限公司 | Dimension management method, device, computer equipment and storage medium |
CN110427315A (en) * | 2019-06-18 | 2019-11-08 | 深圳壹账通智能科技有限公司 | Push away excellent test device, method and storage medium |
CN110889748A (en) * | 2019-12-02 | 2020-03-17 | 广州伊的家网络科技有限公司 | Store-merchant platform product recommendation method and device, computer equipment and storage medium |
CN111090708A (en) * | 2019-10-11 | 2020-05-01 | 支付宝(杭州)信息技术有限公司 | User characteristic output method and system based on data warehouse |
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 |
CN111429161A (en) * | 2020-04-10 | 2020-07-17 | 杭州网易再顾科技有限公司 | Feature extraction method, feature extraction device, storage medium, and electronic apparatus |
CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
CN111797319A (en) * | 2020-07-01 | 2020-10-20 | 喜大(上海)网络科技有限公司 | Recommendation method, device, equipment and storage medium |
CN112036990A (en) * | 2020-11-04 | 2020-12-04 | 北京每日优鲜电子商务有限公司 | Article information pushing method and device, electronic equipment and computer readable medium |
CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
CN112749851A (en) * | 2021-01-20 | 2021-05-04 | 陈网芹 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
CN112749322A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Commodity object information recommendation method and device and electronic equipment |
CN113779390A (en) * | 2021-08-31 | 2021-12-10 | 北京达佳互联信息技术有限公司 | Commodity information processing method and device, electronic equipment and storage medium |
CN114707075A (en) * | 2022-06-06 | 2022-07-05 | 荣耀终端有限公司 | Cold start recommendation method and device |
CN115496525A (en) * | 2022-09-06 | 2022-12-20 | 哈尔滨见微知著科技有限公司 | Big data based information processing system and method |
CN116562961A (en) * | 2023-04-19 | 2023-08-08 | 上海聚灵兽科技有限公司 | E-commerce application commodity recommendation method and device |
CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130282734A1 (en) * | 2007-12-12 | 2013-10-24 | Vast.com, Inc. | Predictive conversion systems and methods |
CN105184618A (en) * | 2015-10-20 | 2015-12-23 | 广州唯品会信息科技有限公司 | Commodity individual recommendation method for new users and system |
CN105321089A (en) * | 2014-07-16 | 2016-02-10 | 苏宁云商集团股份有限公司 | Method and system for e-commerce recommendation based on multi-algorithm fusion |
CN106127546A (en) * | 2016-06-20 | 2016-11-16 | 重庆房慧科技有限公司 | A kind of Method of Commodity Recommendation based on the big data in intelligence community |
-
2016
- 2016-12-20 CN CN201611184581.4A patent/CN108205768B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130282734A1 (en) * | 2007-12-12 | 2013-10-24 | Vast.com, Inc. | Predictive conversion systems and methods |
CN105321089A (en) * | 2014-07-16 | 2016-02-10 | 苏宁云商集团股份有限公司 | Method and system for e-commerce recommendation based on multi-algorithm fusion |
CN105184618A (en) * | 2015-10-20 | 2015-12-23 | 广州唯品会信息科技有限公司 | Commodity individual recommendation method for new users and system |
CN106127546A (en) * | 2016-06-20 | 2016-11-16 | 重庆房慧科技有限公司 | A kind of Method of Commodity Recommendation based on the big data in intelligence community |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109919669A (en) * | 2019-02-25 | 2019-06-21 | 宇宙世代信息技术(深圳)有限公司 | Dimension management method, device, computer equipment and storage medium |
CN110427315A (en) * | 2019-06-18 | 2019-11-08 | 深圳壹账通智能科技有限公司 | Push away excellent test device, method and storage medium |
CN111090708A (en) * | 2019-10-11 | 2020-05-01 | 支付宝(杭州)信息技术有限公司 | User characteristic output method and system based on data warehouse |
CN111090708B (en) * | 2019-10-11 | 2023-07-14 | 支付宝(中国)网络技术有限公司 | User characteristic output method and system based on data warehouse |
CN112749322A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Commodity object information recommendation method and device and electronic equipment |
CN110889748A (en) * | 2019-12-02 | 2020-03-17 | 广州伊的家网络科技有限公司 | Store-merchant platform product recommendation method and device, computer equipment and storage medium |
CN110889748B (en) * | 2019-12-02 | 2023-08-15 | 广州伊的家网络科技有限公司 | Store platform product recommendation method, store platform product recommendation device, computer equipment and storage medium |
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 |
CN111429161A (en) * | 2020-04-10 | 2020-07-17 | 杭州网易再顾科技有限公司 | Feature extraction method, feature extraction device, storage medium, and electronic apparatus |
CN111429161B (en) * | 2020-04-10 | 2023-10-10 | 杭州网易再顾科技有限公司 | Feature extraction method, feature extraction device, storage medium and electronic equipment |
CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
CN111797319B (en) * | 2020-07-01 | 2023-10-27 | 喜大(上海)网络科技有限公司 | Recommendation method, recommendation device, recommendation equipment and storage medium |
CN111797319A (en) * | 2020-07-01 | 2020-10-20 | 喜大(上海)网络科技有限公司 | Recommendation method, device, equipment and storage medium |
CN112348430B (en) * | 2020-10-19 | 2021-09-07 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
CN112348430A (en) * | 2020-10-19 | 2021-02-09 | 北京中恒云科技有限公司 | User data analysis method, computer equipment and storage medium |
CN112036990A (en) * | 2020-11-04 | 2020-12-04 | 北京每日优鲜电子商务有限公司 | Article information pushing method and device, electronic equipment and computer readable medium |
CN112749851B (en) * | 2021-01-20 | 2021-09-07 | 国网江苏省电力有限公司信息通信分公司 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
CN112749851A (en) * | 2021-01-20 | 2021-05-04 | 陈网芹 | Big data demand prediction method based on artificial intelligence and big data cloud service center |
CN113779390A (en) * | 2021-08-31 | 2021-12-10 | 北京达佳互联信息技术有限公司 | Commodity information processing method and device, electronic equipment and storage medium |
CN114707075A (en) * | 2022-06-06 | 2022-07-05 | 荣耀终端有限公司 | Cold start recommendation method and device |
CN115496525A (en) * | 2022-09-06 | 2022-12-20 | 哈尔滨见微知著科技有限公司 | Big data based information processing system and method |
CN116562961A (en) * | 2023-04-19 | 2023-08-08 | 上海聚灵兽科技有限公司 | E-commerce application commodity recommendation method and device |
CN116823408A (en) * | 2023-08-29 | 2023-09-29 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
CN116823408B (en) * | 2023-08-29 | 2023-12-01 | 小舟科技有限公司 | Commodity recommendation method, device, terminal and storage medium based on virtual reality |
Also Published As
Publication number | Publication date |
---|---|
CN108205768B (en) | 2022-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
CN110580649B (en) | Method and device for determining commodity potential value | |
CN108960992A (en) | A kind of information recommendation method and relevant device | |
US20020032645A1 (en) | System and method for score calculation | |
CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
CN105718184A (en) | Data processing method and apparatus | |
US20070294149A1 (en) | Catalog based price search | |
CN111079015B (en) | Recommendation method and device, computer equipment and storage medium | |
CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
US20130073618A1 (en) | Information Providing System, Information Providing method, Information Providing Device, Program, And Information Storage Medium | |
CN111027895A (en) | Stock prediction and behavior data collection method, apparatus, device and medium for commodity | |
CN111737418B (en) | Method, apparatus and storage medium for predicting relevance of search term and commodity | |
CN111738805B (en) | Behavior log-based search recommendation model generation method, device and storage medium | |
CN110580489B (en) | Data object classification system, method and equipment | |
CN108734587A (en) | The recommendation method and terminal device of financial product | |
CN112488863A (en) | Dangerous seed recommendation method and related equipment in user cold start scene | |
CN113689259A (en) | Commodity personalized recommendation method and system based on user behaviors | |
CN106779926A (en) | Correlation rule generation method, device and terminal | |
CN111767459A (en) | Item recommendation method and device | |
CN115935185A (en) | Training method and device for recommendation model | |
CN110570271A (en) | information recommendation method and device, electronic equipment and readable storage medium | |
CN110175883A (en) | A kind of sort method, device, electronic equipment and non-volatile memory medium | |
CN111177564A (en) | Product recommendation method and device | |
CN115907926A (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
CN110135902A (en) | Object composition method, apparatus, electronic equipment and computer readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |