CN110415091A - Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing - Google Patents
Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN110415091A CN110415091A CN201910722846.9A CN201910722846A CN110415091A CN 110415091 A CN110415091 A CN 110415091A CN 201910722846 A CN201910722846 A CN 201910722846A CN 110415091 A CN110415091 A CN 110415091A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- shop
- vector
- commodity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
- G06Q30/0256—User search
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing.The shop and Method of Commodity Recommendation, comprising the following steps: S1 obtains data to be predicted, and the data to be predicted include user data and store merchandise data；S2 obtains the user characteristics vector of characterization user data according to the user data of step S1 and store merchandise data and characterizes the store merchandise feature vector of store merchandise data；S3 inputs user characteristics vector sum store merchandise feature vector in neural network model, output probability vector；S4 predicts the shopping need of user, and corresponding shop and commodity within the scope of recommended user's certain distance according to the probability vector.
Description
Technical field
The present invention relates to big data fields, and in particular to a kind of shop and Method of Commodity Recommendation, device, equipment and readable deposits
Storage media.
Background technique
With the continuous development of society, future city will carry more populations, thus the sustainable development in city seems
It is particularly important.The starting point of smart city is the networking and digitlization under modern information technologies development, and final purpose is will thereon
It is raised to the height of integration, cluster, coordinated management, is combined with Green Sustainable, livable urban environment is constructed.Wisdom city
City based on the generation information technologies such as Internet of Things, cloud computing, big data, spatial geographic information be integrated, by perceiving, point
The every key message for analysing, integrating city operations core system, it is living to urban service, public safety, environmental protection, the people's livelihood, industry and commerce
Various demands including dynamic make intelligent response, realize information-based urban planning administration, infrastructure intelligence, public service just
Victoryization.
Existing Precision Marketing Method mostly according to history purchase data and search history come Recommendations, shop etc.,
The personal information of user is not analyzed comprehensively, so that being obtained to the purchase and consumption requirement forecasting of user not accurate enough.
Summary of the invention
It is an object of the invention to overcome the above-mentioned deficiency in the presence of the prior art, a kind of shop and commercial product recommending are provided
Method, apparatus, equipment and readable storage medium storing program for executing, the shop and Method of Commodity Recommendation are tied by analyzing user data
Internet of Things, big data and neural network are closed, is precisely drawn a portrait to user, predicts the shopping needs of user, it is corresponding to recommend
Shop or commodity.
In order to achieve the above-mentioned object of the invention, the present invention provides following technical schemes:
A kind of shop and Method of Commodity Recommendation, comprising the following steps:
S1, obtains data to be predicted, and the data to be predicted include user data and store merchandise data；
S2, according to the user data of step S1 and store merchandise data obtain the user characteristics vector of characterization user data with
And the store merchandise feature vector of characterization store merchandise data；
S3 inputs user characteristics vector sum store merchandise feature vector in neural network model, output probability vector；
S4, the shopping need of user is predicted according to the probability vector, and recommends corresponding shop and commodity.
Preferably, the user characteristics vector includes history shopping information, search information, the level of consumption, shopping style, year
Age, identity, gender information.
Preferably, the user characteristics vector further includes location information.
Preferably, the neural network model that the step S3 is used also is needed using training sample training, to update nerve net
The parameter of each layer of network model, and then improve the prediction accuracy of neural network model；Training process the following steps are included:
T1 inputs the sample data building sample database marked, and the sample data includes user data and store merchandise
Data；
Data in sample database are stated in the form of feature vector, obtain sample of users feature vector and sample by T2
Store merchandise feature vector；
T3, using sample of users feature vector and sample store merchandise feature vector to the parameter value in neural network model
It is trained, undated parameter value.
Preferably, the user characteristics vector is drawn a portrait to analyze by user and be obtained, and specific acquisition modes are as follows:
Step A1 inputs user data to be measured, obtains the static of user by SQL query and data cleansing and draws a portrait, described
Static state portrait includes age, occupation, gender, marital status, children's status data；
Step A2, the user data input multi-tag study prediction model after SQL query and data cleansing, obtain
The dynamic image of user, the dynamic image include the purchase and consumption demand of user.
Preferably, the data cleansing in the step A1 refers to the unchartered data information of removal, the off-specification
Data information include repeat record information, illegal value, noise data, null value and missing values and privacy information.
Preferably, the prediction process of the multi-tag study prediction model is as follows:
The data of A21, input multi-tag study prediction model are classified according to tag class, obtain the data for every
The feature vector of one label；
A22, the prediction that the feature vector of each label obtains each label by the corresponding classifier of the label are general
Rate vector；
The prediction probability vector of A23, each label obtain prediction result by multi-tag classifier.
A kind of shop and the device for recommending the commodity, comprising: data acquisition module, data processing module, model module and mould
Type training module；
Wherein, data acquisition module, for obtaining user data and store merchandise data；
Data processing module, user data and store merchandise data conversion for that will be used to obtain are feature vector, and
By feature vector input model module；
Model module, for the purchase and consumption demand using Neural Network model predictive future；
Model training module updates model parameter for the sample data training neural network model using sample database.
A kind of shop and commercial product recommending equipment, comprising:
Memory, for storing computer program；
Processor when for executing the computer program, realizes shop and the step of Method of Commodity Recommendation.
A kind of readable storage medium storing program for executing is stored with computer program, the computer program quilt on the readable storage medium storing program for executing
When processor executes, shop is realized and the step of Method of Commodity Recommendation.
Compared with prior art, beneficial effects of the present invention:.
User can be analyzed in conjunction with big data, make accurate portrait, to predict the shopping needs of user, to recommend
Corresponding shop and commodity etc. information.
Detailed description of the invention:
Fig. 1 is the flow chart in the shop and Method of Commodity Recommendation of exemplary embodiment of the present 1；
Fig. 2 is the shop of exemplary embodiment of the present 1 and the training process flow chart of Method of Commodity Recommendation；
Fig. 3 is the flow chart in the shop of exemplary embodiment of the present 1 and the training process step T3 of Method of Commodity Recommendation；
Fig. 4 is the acquisition flow chart in the shop of exemplary embodiment of the present 1 and the user characteristics of Method of Commodity Recommendation；
Fig. 5 is that the shop of exemplary embodiment of the present 1 and the multi-tag of Method of Commodity Recommendation learn the pre- of prediction model
Survey process flow diagram flow chart；
Fig. 6 is the structural schematic diagram of shop and the device for recommending the commodity in exemplary embodiment of the present 2；
Fig. 7 is the structural schematic diagram of shop and commercial product recommending equipment in exemplary embodiment of the present 3；
Fig. 8 is the concrete structure schematic diagram of shop and commercial product recommending equipment in exemplary embodiment of the present 3.
Specific embodiment
Below with reference to test example and specific embodiment, the present invention is described in further detail.But this should not be understood
It is all that this is belonged to based on the technology that the content of present invention is realized for the scope of the above subject matter of the present invention is limited to the following embodiments
The range of invention.
Embodiment 1
As shown in Figure 1, the present embodiment provides a kind of shop and Method of Commodity Recommendation, comprising the following steps:
Step S1, obtains data to be predicted, and the data to be predicted include user data and store merchandise data；
Wherein, user data includes age, occupation, gender, location information, marital status, children's situation, history shopping letter
The data such as breath and search history；Store merchandise data include the number such as store-type, firm name, store locations, product name
According to.
Step S2, according to the user data of step S1 and store merchandise data obtain the user characteristics of characterization user data to
The store merchandise feature vector of amount and characterization store merchandise data；
Step S3, by user characteristics vector sum store merchandise feature vector input neural network model in, output probability to
Amount；
Step S4 recommends corresponding shop and commodity according to the probability vector.
It is made a phone call with mobile phone, when sending and receiving short message, the behaviors of browsing webpage etc. occur, a large amount of data will be generated, these
The data generated are denoted as user data, by analyzing these user data, user characteristics vector are obtained, in conjunction with quotient
Shop merchandise news predicts the purchase and consumption demand of user, recommends corresponding businessman or commodity.Above-mentioned user's purchase and consumption demand is pre-
Survey method obtains cell phone apparatus by modules such as WiFi probe device, GPS device, bluetooth module, RFID module, communication modules
MAC Address (network interface card MAC) and IMEI code (mobile phone string code) and other information, the data of acquisition pass through data fusion, data
Statistics, data analysis etc., realize intelligent decision.Above-mentioned shop and commercial product recommending pass through the technologies such as Internet of Things, cloud computing, big data
It combines, preferably user data is arranged, counted and is analyzed, comprehensively consider the information of user's various aspects, predict its purchase
Object consumption demand reduces user and obtains the time for collecting merchandise news, faster more accurately provides the letter of purchase commodity needed for it
Breath；It is directed to businessman simultaneously, can quickly find its potential customers, realizes precision marketing.
Existing shop and Method of Commodity Recommendation mostly according to history purchase data and search history come Recommendations with
And shop etc., this implementation the method based on a large amount of user data that has generated obtain the user characteristics of characterization user data to
Amount, the user characteristics vector include history shopping information, search information, the level of consumption, shopping style, age, identity, gender
Information.In the user characteristics vector and store merchandise feature vector input neural network model, probability vector is obtained, according to general
Rate vector recommends corresponding shop and commodity.
Such as user characteristics vector shows that the nearest search history of user is job hunting, identity is graduating student, gender male,
The types commodity associated with job hunting such as Western-style clothes, certificate photo shooting can then be recommended；After confirming the type of merchandise, pass through neural network mould
Pattern synthesis considers the level of consumption of user, shopping style, the information such as evaluation of commodity, obtains probability vector, i.e., to Western-style clothes and card
Part is ranked up according to commodity such as shootings, to recommend the commodity of corresponding businessman.
Wherein user characteristics vector further includes location information.
Such as user characteristics vector shows that the nearest shopping history of user is fitness equipment, the note that there is gymnasium in track occurs
Record can then recommend the commodity such as body-building meal；If the level of consumption of user be medium and seafood allergy, can recommend non-seafood with
The body-building meal commodity that its level of consumption matches, and comprehensively consider dispatching distance, recommend the body-building of corresponding businessman to eat.
Comprehensively consider the information such as shopping history, the level of consumption, shopping tendency, age, occupation and the position of user, recommends
Corresponding shop and commodity within the scope of user's certain distance；Such as the user in position A, shopping history before show the use
The nigh shop B in family bought commodity C, and needed to buy commodity C according to consumption frequency prediction user, i.e. recommendation shop B's
Commodity C is to user；If user bought commodity C, but frequent search same type commodity commodity D recently, then recommended distance is nearest
Shop where commodity D is to user；Specific prediction process is controlled by neural network model, and above-mentioned recommendation results are only that may go out
Existing example.
Above-mentioned shop and Method of Commodity Recommendation are combined by technologies such as Internet of Things, cloud computing, big datas, preferably to
User data is arranged, counted and is analyzed, and the information of user's various aspects is comprehensively considered, its purchase and consumption demand is predicted, in conjunction with it
Position information recommends shop and commodity, faster more accurately provides the information of purchase commodity needed for it；It is directed to quotient simultaneously
Family can quickly find its potential customers, realize precision marketing.
The neural network model that step S3 is used also is needed using training sample training, to update each layer of neural network model
Parameter, and then improve the prediction accuracy of neural network model；As shown in Fig. 2, training process the following steps are included:
Step T1 inputs the sample data building sample database marked, and the sample data includes user data and shop
Commodity data；
Step T2 states the data in sample database in the form of feature vector, obtain sample of users feature vector and
Sample store merchandise feature vector；
Step T3, using sample of users feature vector and sample store merchandise feature vector to the ginseng in neural network model
Numerical value is trained, undated parameter value.
As shown in figure 3, the detailed step of step T3 undated parameter value is as described below:
The user characteristics vector sum sample store merchandise feature vector of one sample is input to neural network mould by step T31
In type, output probability is obtained by the operation of neural network model；
Step T32 compares output probability with the true value for having marked sample, obtains deviation；
Step T33 thens follow the steps T34 if deviation is greater than preset threshold；If deviation is less than preset threshold, instruct
White silk terminates；
Step T34 corrects each layer of neural network model of parameter value, undated parameter value according to deviation, and more varies
This, executes step T31 to T33.
The sample is labelled with true purchase merchandise news, is trained by using the sample marked, with adjustment
The parameter of model, the shop and merchandise news for recommending it are more accurate.By training neural network, neural network model is improved
Prediction precision.
It is obtained as shown in figure 4, user characteristics vector draws a portrait to analyze by user, specific acquisition modes are as follows:
Step A1 inputs user data to be measured, obtains the static of user by SQL query and data cleansing and draws a portrait, described
Static state portrait includes the data such as age, occupation, gender, marital status, children's situation；
Step A2, the user data input multi-tag study prediction model after SQL query and data cleansing, obtain
The dynamic image of user, the dynamic image include user's purchase and consumption demand；Purchase and consumption demand information includes the purchase of user
Object commodity, shopping preferences, do shopping dynamics, shopping interval time etc..
As shown in figure 5, the data cleansing in step A1 refers to the unchartered data information of removal, such as repetition is recorded, no
Legitimate value, noise data, null value and missing values and privacy information.
Wherein, the prediction process of multi-tag study prediction model is as follows:
The data of A21, input multi-tag study prediction model are classified according to tag class, obtain the data for every
The feature vector of one label；
A22, the prediction that the feature vector of each label obtains each label by the corresponding classifier of the label are general
Rate vector；
The prediction probability vector of A23, each label obtain prediction result by multi-tag classifier.
The classification method used in the present embodiment step A21 is k-means clustering method.It is adopted in the present embodiment step A22
Classifier is XGBOOST classifier or GBDT classifier；The multi-tag classifier then used is the classification of XGBOOST multi-tag
Device or GBDT multi-tag classifier.
Multi-tag study prediction model need to be trained using the sample marked, to adjust the parameter of model, obtain it
The user characteristics vector arrived is related to shopping, for example, history shopping information, search information, the level of consumption, shopping style etc., with
More accurately recommend shop and merchandise news.
The present embodiment is combined by big data with neural network, and data mining, data analysis and data application are carried out, with
The shop to match with purchase and consumption demand and merchandise news are provided, help user to be best understood from shop and commodity, more rapidly
Buy the commodity for meeting user's shopping need.
Embodiment 2
Corresponding to above method embodiment, the present embodiment additionally provides a kind of shop and the device for recommending the commodity, hereafter retouches
The shop stated and the device for recommending the commodity can correspond to each other reference with above-described shop and Method of Commodity Recommendation.
Shown in Figure 6, which comprises the following modules: data acquisition module 101, data processing module 102, pattern die
Block 103 and model training module 104；
Wherein, data acquisition module 101, for obtaining user data and store merchandise data；The present embodiment can pass through
Mobile phone or mobile terminal etc. acquire user data；The user data of acquisition include the WIFI such as mobile phone or mobile terminal MAC Address,
It according to the MAC Address and IMEI of cell phone apparatus, is compared by cloud big data, positions the identity of user, get corresponding hand
The information such as machine number, APP used in everyday.
Data processing module 102, user data and store merchandise data conversion for will acquire are feature vector, and will
Feature vector input model module 103；
Model module 103, for the purchase and consumption demand using Neural Network model predictive future；The present embodiment uses
MapReduce Computational frame calculates the mass data of distributed storage, realizes that data sharing, data are melted on this basis
It closes, statistical analysis, intelligent decision.
Model training module 104, for the sample data training neural network model using sample database, more new model ginseng
Number.
Data processing module 102 further includes that user draws a portrait analysis module, draws a portrait analysis module for user data by user
Be converted to user characteristics vector；
The user draws a portrait analysis module including inquiring cleaning module and multi-tag study prediction module；The inquiry is clear
Mold cleaning block obtains the static portrait of user for rejecting unchartered data information；The multi-tag learns prediction module
User tag is obtained using XGBOOST classifier, user data is converted into user characteristics vector, to predict that the shopping of user disappears
Take demand.
Using device provided by the embodiment of the present invention, user data and store merchandise data are obtained；Data pass through data
Processing module 102 is converted to corresponding feature vector, purchase and consumption demand is predicted by model module, with offer and purchase and consumption
The shop and merchandise news that demand matches help user to be best understood from shop and commodity, faster buy and meet use
The commodity of family shopping need.
Embodiment 3
Corresponding to above method embodiment, the present embodiment additionally provides a kind of shop and commercial product recommending equipment, hereafter retouches
A kind of shop stated and commercial product recommending equipment can correspond to each other reference with a kind of above-described shop and Method of Commodity Recommendation.
Shown in Figure 7, the shop and commercial product recommending equipment include:
Memory D l, for storing computer program；
Processor D2 realizes shop and the Method of Commodity Recommendation of above method embodiment when for executing computer program
Step.
Specifically, referring to FIG. 8, for shop provided in this embodiment and commercial product recommending equipment concrete structure schematic diagram,
The shop and commercial product recommending equipment can generate bigger difference because configuration or performance are different, may include one or one with
Upper processor (central processing units, CPU；Or GPU, NPU, FPGA etc.) 322 (for example, one or one with
Upper processor) and memory 332, one or more storage application programs 342 or data 344 storage medium 330 (such as
One or more mass memory units).Wherein, memory 332 and storage medium 330 can be of short duration storage or persistently deposit
Storage.The program for being stored in storage medium 330 may include one or more modules (diagram does not mark), and each module can be with
Including being operated to the series of instructions in data processing equipment.Further, central processing unit 322 can be set to and store
Medium 330 communicates, and the series of instructions operation in storage medium 330 is executed on the pre- measurement equipment 301 of user's administration business demand.
Shop and commercial product recommending equipment 301 can also include one or more power supplys 326, one or more have
Line or radio network interface 350, one or more input/output interfaces 358, and/or, one or more operation systems
System 341.For example, Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
Step in shop as described above and Method of Commodity Recommendation can be by shop and the structure of commercial product recommending equipment
It realizes.
Embodiment 4
Corresponding to above method embodiment, the present embodiment additionally provides a kind of readable storage medium storing program for executing, and described below one
Kind of readable storage medium storing program for executing can correspond to each other reference with a kind of above-described shop and Method of Commodity Recommendation.
A kind of readable storage medium storing program for executing is stored with computer program on readable storage medium storing program for executing, and computer program is held by processor
The step of shop and the Method of Commodity Recommendation of above method embodiment are realized when row.
The readable storage medium storing program for executing be specifically as follows USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), the various program storage generations such as random access memory (Random Access Memory, RAM), magnetic or disk
The readable storage medium storing program for executing of code.
The above, the only detailed description of the specific embodiment of the invention, rather than limitation of the present invention.The relevant technologies
The technical staff in field is not in the case where departing from principle and range of the invention, various replacements, modification and the improvement made
It should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of shop and Method of Commodity Recommendation, which comprises the following steps:
S1, obtains data to be predicted, and the data to be predicted include user data and store merchandise data；
S2 obtains the user characteristics vector and table of characterization user data according to the user data of step S1 and store merchandise data
Levy the store merchandise feature vector of store merchandise data；
S3 inputs user characteristics vector sum store merchandise feature vector in neural network model, output probability vector；
S4, the shopping need of user is predicted according to the probability vector, and recommends corresponding shop and commodity.
2. shop according to claim 1 and Method of Commodity Recommendation, which is characterized in that the user characteristics vector includes going through
History shopping information, search information, the level of consumption, shopping style, age, identity, gender information.
3. shop according to claim 2 and Method of Commodity Recommendation, which is characterized in that the user characteristics vector further includes
Location information.
4. shop according to claim 1 and Method of Commodity Recommendation, which is characterized in that the nerve net that the step S3 is used
Network model also needs to update the parameter of each layer of neural network model, and then to improve neural network model using training sample training
Prediction accuracy；Training process the following steps are included:
T1 inputs the sample data building sample database marked, and the sample data includes user data and store merchandise data；
Data in sample database are stated in the form of feature vector, obtain sample of users feature vector and sample shop by T2
Product features vector；
T3 carries out the parameter value in neural network model using sample of users feature vector and sample store merchandise feature vector
Training, undated parameter value.
5. shop according to claim 1 and Method of Commodity Recommendation, which is characterized in that the user characteristics vector passes through use
Family portrait analysis obtains, and specific acquisition modes are as follows:
Step A1 inputs user data to be measured, obtains the static of user by SQL query and data cleansing and draws a portrait, the static state
Portrait includes age, occupation, gender, marital status, children's status data；
Step A2, the user data input multi-tag study prediction model after SQL query and data cleansing, obtain user
Dynamic image, the dynamic image includes the purchase and consumption demand of user.
6. shop according to claim 5 and Method of Commodity Recommendation, which is characterized in that the data cleansing in the step A1
Refer to the unchartered data information of removal, the unchartered data information include the information for repeating record, illegal value,
Noise data, null value and missing values and privacy information.
7. shop according to claim 5 and Method of Commodity Recommendation, which is characterized in that the multi-tag learns prediction model
Prediction process it is as follows:
The data of A21, input multi-tag study prediction model are classified according to tag class, obtain the data for each
The feature vector of label；
A22, the feature vector of each label by the corresponding classifier of the label obtain the prediction probability of each label to
Amount；
The prediction probability vector of A23, each label obtain prediction result by multi-tag classifier.
8. a kind of for implementing shop and the commercial product recommending in the described in any item shops of claim 1 to 7 and Method of Commodity Recommendation
Device characterized by comprising data acquisition module, data processing module, model module and model training module；
Wherein, data acquisition module, for obtaining user data and store merchandise data；
Data processing module, user data and store merchandise data conversion for that will be used to obtain are feature vector, and will be special
Levy vector input model module；
Model module, for the purchase and consumption demand using Neural Network model predictive future；
Model training module updates model parameter for the sample data training neural network model using sample database.
9. a kind of shop and commercial product recommending equipment characterized by comprising
Memory, for storing computer program；
Processor when for executing the computer program, realizes that shop and commodity as described in claim l to 7 any one push away
The step of recommending method.
10. a kind of readable storage medium storing program for executing, which is characterized in that be stored with computer program, the meter on the readable storage medium storing program for executing
When calculation machine program is executed by processor, shop is realized as described in any one of claim 1 to 7 and the step of Method of Commodity Recommendation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910722846.9A CN110415091A (en) | 2019-08-06 | 2019-08-06 | Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910722846.9A CN110415091A (en) | 2019-08-06 | 2019-08-06 | Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110415091A true CN110415091A (en) | 2019-11-05 |
Family
ID=68366215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910722846.9A Pending CN110415091A (en) | 2019-08-06 | 2019-08-06 | Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415091A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110830586A (en) * | 2019-11-13 | 2020-02-21 | 秒针信息技术有限公司 | Method and device for reducing influence of multi-user sharing equipment on target audience concentration |
| 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 |
| CN110910221A (en) * | 2019-11-27 | 2020-03-24 | 山东浪潮人工智能研究院有限公司 | Market intelligent shopping guide method and system based on artificial intelligence |
| CN110969516A (en) * | 2019-12-25 | 2020-04-07 | 清华大学 | Commodity recommendation method and device |
| CN111242723A (en) * | 2020-01-02 | 2020-06-05 | 平安科技（深圳）有限公司 | User child and child condition judgment method, server and computer readable storage medium |
| CN111311332A (en) * | 2020-02-28 | 2020-06-19 | 北京互金新融科技有限公司 | User data processing method and device |
| CN111340565A (en) * | 2020-03-20 | 2020-06-26 | 北京爱笔科技有限公司 | Information recommendation method, device, equipment and storage medium |
| CN111353815A (en) * | 2020-02-24 | 2020-06-30 | 苏宁云计算有限公司 | Potential user prediction method and system |
| CN111353688A (en) * | 2020-02-05 | 2020-06-30 | 口碑(上海)信息技术有限公司 | User resource allocation method and device |
| CN111368205A (en) * | 2020-03-09 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Data recommendation method and 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 |
| 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 |
| CN111639989A (en) * | 2020-04-28 | 2020-09-08 | 上海风秩科技有限公司 | Commodity recommendation method and readable storage medium |
| CN112200601A (en) * | 2020-09-11 | 2021-01-08 | 深圳市法本信息技术股份有限公司 | Item recommendation method and device and readable storage medium |
| CN112488799A (en) * | 2020-12-14 | 2021-03-12 | 北京易兴元石化科技有限公司 | Oil data processing method and device based on refueling station end and storage medium |
| CN111507366B (en) * | 2019-11-07 | 2021-06-08 | 马上消费金融股份有限公司 | Training method of recommendation probability model, intelligent completion method and related device |
| CN115205011A (en) * | 2022-06-15 | 2022-10-18 | 海南大学 | Bank user portrait model generation method based on LSF-FC algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| EP3433818A1 (en) * | 2016-03-21 | 2019-01-30 | The Procter and Gamble Company | Systems and methods for providing customized product recommendations |
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
| CN109509054A (en) * | 2018-09-30 | 2019-03-22 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, electronic device and storage medium under mass data |
-
2019
- 2019-08-06 CN CN201910722846.9A patent/CN110415091A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| EP3433818A1 (en) * | 2016-03-21 | 2019-01-30 | The Procter and Gamble Company | Systems and methods for providing customized product recommendations |
| CN109509054A (en) * | 2018-09-30 | 2019-03-22 | 平安科技（深圳）有限公司 | Method of Commodity Recommendation, electronic device and storage medium under mass data |
| CN109359244A (en) * | 2018-10-30 | 2019-02-19 | 中国科学院计算技术研究所 | A kind of recommendation method for personalized information and device |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507366B (en) * | 2019-11-07 | 2021-06-08 | 马上消费金融股份有限公司 | Training method of recommendation probability model, intelligent completion method and related device |
| CN110830586A (en) * | 2019-11-13 | 2020-02-21 | 秒针信息技术有限公司 | Method and device for reducing influence of multi-user sharing equipment on target audience concentration |
| CN110910221A (en) * | 2019-11-27 | 2020-03-24 | 山东浪潮人工智能研究院有限公司 | Market intelligent shopping guide method and system based on artificial intelligence |
| 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 |
| 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 |
| CN110969516A (en) * | 2019-12-25 | 2020-04-07 | 清华大学 | Commodity recommendation method and device |
| CN110969516B (en) * | 2019-12-25 | 2024-04-26 | 清华大学 | Commodity recommendation method and device |
| CN111242723A (en) * | 2020-01-02 | 2020-06-05 | 平安科技（深圳）有限公司 | User child and child condition judgment method, server and computer readable storage medium |
| CN111353688A (en) * | 2020-02-05 | 2020-06-30 | 口碑(上海)信息技术有限公司 | User resource allocation method and device |
| CN111353688B (en) * | 2020-02-05 | 2024-02-27 | 口碑(上海)信息技术有限公司 | User resource allocation method and device |
| 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 |
| CN111353815A (en) * | 2020-02-24 | 2020-06-30 | 苏宁云计算有限公司 | Potential user prediction method and system |
| CN111353815B (en) * | 2020-02-24 | 2024-03-01 | 苏宁云计算有限公司 | Potential user prediction method and system |
| CN111311332A (en) * | 2020-02-28 | 2020-06-19 | 北京互金新融科技有限公司 | User data processing method and device |
| CN111368205A (en) * | 2020-03-09 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Data recommendation method and device, computer equipment and storage medium |
| CN111340565A (en) * | 2020-03-20 | 2020-06-26 | 北京爱笔科技有限公司 | Information recommendation method, device, equipment and storage medium |
| 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 |
| 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 |
| CN111639989B (en) * | 2020-04-28 | 2024-02-02 | 上海秒针网络科技有限公司 | Commodity recommendation method and readable storage medium |
| CN111639989A (en) * | 2020-04-28 | 2020-09-08 | 上海风秩科技有限公司 | Commodity recommendation method and readable storage medium |
| CN112200601A (en) * | 2020-09-11 | 2021-01-08 | 深圳市法本信息技术股份有限公司 | Item recommendation method and device and readable storage medium |
| CN112200601B (en) * | 2020-09-11 | 2024-05-14 | 深圳市法本信息技术股份有限公司 | Item recommendation method, device and readable storage medium |
| CN112488799A (en) * | 2020-12-14 | 2021-03-12 | 北京易兴元石化科技有限公司 | Oil data processing method and device based on refueling station end and storage medium |
| CN112488799B (en) * | 2020-12-14 | 2024-04-09 | 北京易兴元石化科技有限公司 | Petroleum data processing method and device based on gas station end and storage medium |
| CN115205011B (en) * | 2022-06-15 | 2023-08-08 | 海南大学 | Bank user portrait model generation method based on LSF-FC algorithm |
| CN115205011A (en) * | 2022-06-15 | 2022-10-18 | 海南大学 | Bank user portrait model generation method based on LSF-FC algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110415091A (en) | Shop and Method of Commodity Recommendation, device, equipment and readable storage medium storing program for executing | |
| Bachir et al. | Inferring dynamic origin-destination flows by transport mode using mobile phone data | |
| CN106778876B (en) | User classification method and system based on mobile user track similarity | |
| CN105532030B (en) | For analyzing the devices, systems, and methods of the movement of target entity | |
| CN110428231A (en) | Administrative information recommended method, device, equipment and readable storage medium storing program for executing | |
| CN109902708A (en) | A kind of recommended models training method and relevant apparatus | |
| CN107391680A (en) | Content recommendation method, device and equipment | |
| CN108022152A (en) | The automatic commending system of user's commodity and recommendation method based on image recognition | |
| CN108256590B (en) | A kind of similar traveler recognition methods based on compound first path | |
| CN110444297A (en) | Medical information recommended method, device, equipment and readable storage medium storing program for executing | |
| CN106600052A (en) | User attribute and social network detection system based on space-time locus | |
| Wind et al. | Inferring stop-locations from wifi | |
| CN113590936A (en) | Information pushing method and device | |
| JP2016167149A (en) | Program, equipment, and method that estimate number of persons with which contract is expected to be made at shop according to market area | |
| Zhao et al. | MDLF: A multi-view-based deep learning framework for individual trip destination prediction in public transportation systems | |
| Mao et al. | Utilizing multi-source data in popularity prediction for shop-type recommendation | |
| Alhazzani et al. | Urban Attractors: Discovering patterns in regions of attraction in cities | |
| Yang et al. | K-means based clustering on mobile usage for social network analysis purpose | |
| CN106600053B (en) | User attribute prediction system based on space-time trajectory and social network | |
| Bendimerad et al. | Contextual subgraph discovery with mobility models | |
| Wang et al. | A Comparative Study on Contract Recommendation Model: Using Macao Mobile Phone Datasets | |
| CN111222923A (en) | Method and device for judging potential customer, electronic equipment and storage medium | |
| Liu et al. | Identification of multi-attribute functional urban areas under a perspective of community detection: A case study | |
| Al-Molegi et al. | Regions-of-interest discovering and predicting in smartphone environments | |
| CN109828995A (en) | A kind of diagram data detection method, the system of view-based access control model feature |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |