CN106157114A - Have dinner based on user the homepage proposed algorithm of behavior modeling - Google Patents
Have dinner based on user the homepage proposed algorithm of behavior modeling Download PDFInfo
- Publication number
- CN106157114A CN106157114A CN201610525045.XA CN201610525045A CN106157114A CN 106157114 A CN106157114 A CN 106157114A CN 201610525045 A CN201610525045 A CN 201610525045A CN 106157114 A CN106157114 A CN 106157114A
- Authority
- CN
- China
- Prior art keywords
- user
- homepage
- behavior
- data
- proposed algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- 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
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q30/0277—Online advertisement
-
- 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
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses the homepage proposed algorithm of a kind of behavior modeling of having dinner based on user, comprising: step 1, utilize application end to bury method a little and obtain user's all application operatings behavioral data；Step 2, uses SVM that all customer data carries out cluster analysis, forms one and presort；Step 3, in assuming to presort, each sorted users behavior is close, being modeled the user of each classification, in then using neutral net to classify this personal behavior model in each classification, all customer data learns, and obtains the solution of optimum after iterating again；Step 4, the model obtained by utilization, substitute into the behavioral data that user is nearest, obtain the recommendation information of this user in real time.The present invention solves in current methods relative to solidification, cannot improve and recommend the difficulty of conversion ratio, is presorted by SVM and determines sorted users model, and by real-time algorithm model Dynamic recommendation, reduces maintenance cost, improve the recommendation conversion ratio of homepage.
Description
Technical field
The present invention relates to personalized recommendation technology, especially relate to the homepage recommendation of a kind of behavior modeling of having dinner based on user
Algorithm.
Background technology
Current various types of dining platform, application emerge in an endless stream, preferably the most suitable to targeted customer's active push
Dining room, and lure that it carries out consumption of making a reservation into, for the application relevant to food and drink, be an important proposition.
Below as a example by application of making a reservation, generally in the homepage of application, have special column and recommend to user for showing
Dining room.Conventional method is mainly cut from following several respects:
One, the profit margin for enterprise self considers, enterprise self being obtained in that, the dining room of high profit is placed on homepage
Recommend；
Two, consider for consumer consumption behavior focus, the dining room of user's focus consumption is placed in homepage；
Three, for movable, the needs of business tie-up, relevant dining room is placed in homepage and recommends；
Four, based on the correlation analysis of consuming behavior between user, recommend user consumption trade company once to use in another
The homepage at family；
Five, big data analysis based on a large number of users consumption data is recommended.
For enterprise's consumption is made a reservation, the most existing several homepage proposed algorithm only can accomplish to recommend,
But customer consumption is converted and still suffers from certain disappearance.The recommendation behavior either considered for enterprise's self-view, or
Consume the recommendation behavior of result based on user, all can be limited to user's current consumption behavior, do not kissed with recommended dining room
Close.Even by the analysis of mass data, still there is a strong possibility, owing between user, behavior difference is excessive, analyzes model and crosses plan
Close, cause final recommendation to try to go south by driving the chariot north.Still further aspect, above-mentioned various recommendation methods are required for greatly being arranged, only by backstage
Effective within a certain period of time, need manpower constantly to update, lose ageing.End user is by recommending the conversion ratio in dining room
Can not be obviously improved, and it also requires manpower constantly safeguards corresponding recommendation function.It is difficult to user is provided real valency
Value, it more difficult to improve user's conversion ratio and income for enterprise.
Summary of the invention
It is an object of the invention to provide the homepage proposed algorithm of a kind of behavior modeling of having dinner based on user, it is as dynamically
, based on user behavior modeling real-time recommendation algorithm, by gather the consuming behavior of user, the operation behavior of application, to mistake
Toward the evaluation of consumption, and the behavior that user's real consumption converts, set up the real-time consumption behavior model of user, by a large number
The data collection of user, carries out learning improvement to consumption model, uses model dynamically in user's homepage, and real-time recommendation is to user
Some meet its consuming behavior, the dining room of current consumption interest, and the final recommendation improving user is made a reservation conversion ratio.
For solving above-mentioned technical problem, embodiments of the present invention provide the head of a kind of behavior modeling of having dinner based on user
Page proposed algorithm, comprising:
Step 1, utilizes application end to bury method a little and obtains user's all application operatings behavioral data；
Step 2, uses SVM that all customer data carries out cluster analysis, forms one and presort；
Step 3, it is assumed that in presorting, each sorted users behavior is close, then is modeled the user of each classification, so
In using neutral net to classify this personal behavior model in each classification afterwards, all customer data learns, and repeatedly changes
Optimum solution is obtained for rear；
Step 4, the model obtained by utilization, substitute into the behavioral data that user is nearest, obtain the recommendation of this user in real time
Breath；
Wherein, step 3 is updated by continuous iteration and ensures the real-time of model.
In step 1, the user data gathered includes search condition, clicks dining room, consumption data, evaluating data, function
The time of staying.
In step 3, described neutral net is many hidden layers BP neutral net.
In step 3, described neutral net is 53 input nodes, the neutral net of 5 output nodes.
In step 3, iterative target is the dining room that user at most consumes front 5.
The present invention solve in current methods relative to solidification, cannot improve recommend conversion ratio difficulty, presorted by SVM
Determine sorted users model, and by real-time algorithm model Dynamic recommendation, be also no longer necessary to special messenger to recommending dining room to tie up
Protect, reduce certain maintenance cost, improve the recommendation conversion ratio of homepage.
Accompanying drawing explanation
Fig. 1 is the present invention to have dinner in the homepage proposed algorithm of behavior modeling training flow chart of presorting based on user；
Fig. 2 is the present invention to have dinner neural network structure figure in the homepage proposed algorithm of behavior modeling based on user.
Detailed description of the invention
For the technological means making the present invention realize, creation characteristic, reach purpose and be easy to understand with effect, below knot
Close specific embodiment, the present invention is expanded on further.
What the embodiment of the present invention was provided a kind of is intended to by adopting based on the have dinner homepage proposed algorithm of behavior modeling of user
The collection consuming behavior of user, the operation behavior of application, evaluation to passing consumption, and the behavior that user's real consumption converts,
Set up the real-time consumption behavior model of user；By the data collection to a large number of users, consumption model is carried out learning improvement, makes
With model dynamically in user's homepage, to user, some meet its consuming behavior to real-time recommendation, the dining room of current consumption interest,
Improve eventually the recommendation of user to make a reservation conversion ratio.
Have steps of based on the have dinner homepage proposed algorithm of behavior modeling of user with regard to provided by the present invention:
The first step, utilizes application end to bury method a little and obtains user's all application operatings behavioral data, the client of user
End employing is buried a program and is carried out data acquisition and belong to prior art, and not in this to go forth, and for this step carries out data
Collection needs to make as described below: in data acquisition, uses the log pattern of client application, all behaviour to user
Carry out " getting ready " record as behavior, and return server, regather the consuming behavior data of this user, comprehensively its history evaluation number
According to etc., form the user behavior data storehouse of each user's independence, current 11770 user data, remove too low liveness
User, having 11329 parts of user data can use, and the portion of user data example collected sees table 1, and this form is with source data
ID is 1234 to carry out respective description, in Table 1, has ID field, user's relevant field, order relevant field, meal
Room relevant field, hospital's relevant field, operation relevant field, and user's relevant field is further subdivided into user's sex, average
Visitor's unit price, order relevant field is further subdivided into quantity on order, the Annual distribution that places an order, meal time distribution, dining room related words
Section be further subdivided into dining dining room record, dining room click on record, restaurant search record, dining room per capita, the style of cooking, hospital's related words
Section is further subdivided into hospital's click, hospital position, and operates the relevant order entry that is further subdivided into and click on, in Table 1, and bag
Include data after source data, pretreated study data and normalization, as a example by the relevant field of dining room, its restaurant search record
Middle source data is: South Beauty, takes out, Sichuan cuisine；Pretreated study data are: South Beauty, take out, Sichuan cuisine；After normalization
Data are: South Beauty, take out, Sichuan cuisine.In table 1, above-mentioned data have outside initial data, and it is right to enumerate further in second step
Process content in data.
Second step, then needs after collecting initial data to use SVM that all customer data is carried out cluster analysis, is formed
Presorting for one, this step is to carry out the training of SVM for the data obtained, and the present invention is to use SVM to cluster, specifically
Presort training flow chart shown in Figure 1, when being normalized for the data collected, only numerical value class data
Being normalized, concrete data message sees table 1, it is considered to morning, user was the most active, then pass through morning every day useful to institute
Family behavioral data carries out SVC and presorts, and determines the refined user colony belonging to user, owing to SVC belongs to non-parametric without supervision
Clustering algorithm, can well process substantial amounts of user characteristic data, and without formulating initial cluster core, by 11329 use
Obtain the different representation data of each user (53 dimension) after the user data pretreatment that family same day is up-to-date to import SVC and classify,
The result obtained sees table 2.
Table 2
| Classification | I | II | III | IV | V | VI |
| Every class number of users | 3277 | 2546 | 2344 | 1995 | 1043 | 124 |
It should be noted that the result presorted is as the data of self-assembling formation, it is not necessary to be clearly bound, the present invention is only
Need to know and specifically have a few class, such as six classes shown in table 2, such as I class number of users is 3277, and II class number of users is
2546, Group III number of users is 2344, and IV class number of users is 1995, and V class number of users is 1043, and VI class number of users is
124。
3rd step, it is assumed that in presorting, each sorted users behavior is close, then is modeled the user of each classification, so
In using neutral net to classify this personal behavior model in each classification afterwards, all customer data learns, and repeatedly changes
Obtain optimum solution for rear, specifically incite somebody to action, after completing to presort, user in obtained classification is used many hidden layers BP nerve net
Network (carries out convergence based on LM to calculate), carries out the study optimization of personal behavior model, uses user data in all classes, uses many
Complicated user behavior can be modeled by the neural network structure of hidden layer the most accurately, and neural network structure is shown in Figure 2,
Parameters of Neural Network Structure is as follows: using 53 input nodes, 3 hidden layers, 5 output nodes (at most consume the dining room of front 5 with user
As iterative target) neutral net, use Sigmod excitation function, as a example by I class user, carry out learning after iteration, substantially in
0.12 error is converged on during 80 iteration.
4th step, after the model of each classification obtained by study, every 10 minutes, uses up-to-date user behavior data, right
The recommendation dining room of user is updated, to ensure that user obtains real-time dining room and recommends, it is recommended that information sees table 3.
Table 3
| ID | Former recommendation dining room | Now recommend dining room |
| 1234 | 1829,2854,2287,11938,22354 | 22354,22842,1892,11938,2584 |
Omit the description for known technology in full.
Claims (5)
1. the homepage proposed algorithm of a behavior modeling of having dinner based on user, it is characterised in that including:
Step 1, utilizes application end to bury method a little and obtains user's all application operatings behavioral data；
Step 2, uses SVM that all customer data carries out cluster analysis, forms one and presort；
Step 3, it is assumed that in presorting, each sorted users behavior is close, then is modeled the user of each classification, the most right
During personal behavior model in each classification uses neutral net to classify this, all customer data learns, after iterating
Obtain optimum solution；
Step 4, the model obtained by utilization, substitute into the behavioral data that user is nearest, obtain the recommendation information of this user in real time；
Wherein, step 3 is updated by continuous iteration and ensures the real-time of model.
The homepage proposed algorithm of behavior modeling of having dinner based on user the most according to claim 1, it is characterised in that step 1
In, the user data gathered includes search condition, clicks dining room, consumption data, evaluating data, the function time of staying.
The homepage proposed algorithm of behavior modeling of having dinner based on user the most according to claim 1, it is characterised in that step 3
In, described neutral net is many hidden layers BP neutral net.
4. according to the homepage proposed algorithm of the behavior modeling of having dinner based on user described in claim 1 or 3, it is characterised in that step
In rapid 3, described neutral net is 53 input nodes, the neutral net of 5 output nodes.
The homepage proposed algorithm of behavior modeling of having dinner based on user the most according to claim 1, it is characterised in that step 3
In, iterative target is the dining room that user at most consumes front 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610525045.XA CN106157114A (en) | 2016-07-06 | 2016-07-06 | Have dinner based on user the homepage proposed algorithm of behavior modeling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610525045.XA CN106157114A (en) | 2016-07-06 | 2016-07-06 | Have dinner based on user the homepage proposed algorithm of behavior modeling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106157114A true CN106157114A (en) | 2016-11-23 |
Family
ID=58061140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610525045.XA Pending CN106157114A (en) | 2016-07-06 | 2016-07-06 | Have dinner based on user the homepage proposed algorithm of behavior modeling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106157114A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107196788A (en) * | 2017-05-02 | 2017-09-22 | 阿里巴巴集团控股有限公司 | A kind of processing method for burying point data, device, server and client |
| CN107239978A (en) * | 2017-06-23 | 2017-10-10 | 北京好豆网络科技有限公司 | The analysis method and device of cuisines content |
| CN107453946A (en) * | 2017-07-20 | 2017-12-08 | 阿里巴巴集团控股有限公司 | Field management method and device and electronic equipment |
| CN108319542A (en) * | 2017-01-17 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Information processing method, apparatus and system |
| CN108364067A (en) * | 2018-01-05 | 2018-08-03 | 华南师范大学 | Deep learning method and robot system based on data segmentation |
| CN108921673A (en) * | 2018-07-16 | 2018-11-30 | 广州友米科技有限公司 | Method of Commodity Recommendation based on big data |
| CN114240518A (en) * | 2022-02-17 | 2022-03-25 | 檀沐信息科技(深圳)有限公司 | Big data-based user management analysis method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040172267A1 (en) * | 2002-08-19 | 2004-09-02 | Jayendu Patel | Statistical personalized recommendation system |
| CN104615608A (en) * | 2014-04-28 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Data mining processing system and method |
| US20160048537A1 (en) * | 2014-08-15 | 2016-02-18 | Hungry-For-More Enterprises, L.L.C. | System and computer method for visually guiding a user to a current interest |
-
2016
- 2016-07-06 CN CN201610525045.XA patent/CN106157114A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040172267A1 (en) * | 2002-08-19 | 2004-09-02 | Jayendu Patel | Statistical personalized recommendation system |
| CN104615608A (en) * | 2014-04-28 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Data mining processing system and method |
| US20160048537A1 (en) * | 2014-08-15 | 2016-02-18 | Hungry-For-More Enterprises, L.L.C. | System and computer method for visually guiding a user to a current interest |
Non-Patent Citations (1)
| Title |
|---|
| 王国霞等: ""个性化推荐系统综述"", 《计算机工程与应用》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319542A (en) * | 2017-01-17 | 2018-07-24 | 百度在线网络技术（北京）有限公司 | Information processing method, apparatus and system |
| CN107196788A (en) * | 2017-05-02 | 2017-09-22 | 阿里巴巴集团控股有限公司 | A kind of processing method for burying point data, device, server and client |
| CN107239978A (en) * | 2017-06-23 | 2017-10-10 | 北京好豆网络科技有限公司 | The analysis method and device of cuisines content |
| CN107453946A (en) * | 2017-07-20 | 2017-12-08 | 阿里巴巴集团控股有限公司 | Field management method and device and electronic equipment |
| CN107453946B (en) * | 2017-07-20 | 2020-07-17 | 阿里巴巴集团控股有限公司 | Field management method and device and electronic equipment |
| CN108364067A (en) * | 2018-01-05 | 2018-08-03 | 华南师范大学 | Deep learning method and robot system based on data segmentation |
| CN108364067B (en) * | 2018-01-05 | 2023-11-03 | 华南师范大学 | Deep learning method based on data segmentation and robot system |
| CN108921673A (en) * | 2018-07-16 | 2018-11-30 | 广州友米科技有限公司 | Method of Commodity Recommendation based on big data |
| CN108921673B (en) * | 2018-07-16 | 2021-06-01 | 广州天高软件科技有限公司 | Commodity recommendation method based on big data |
| CN114240518A (en) * | 2022-02-17 | 2022-03-25 | 檀沐信息科技(深圳)有限公司 | Big data-based user management analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106157114A (en) | Have dinner based on user the homepage proposed algorithm of behavior modeling | |
| Kuivanen et al. | A comparison of statistical and participatory clustering of smallholder farming systems–A case study in Northern Ghana | |
| Evans et al. | A dynamic model of household decision-making and parcel level landcover change in the eastern Amazon | |
| D’Urso et al. | Fuzzy clustering of human activity patterns | |
| VanWey et al. | Theories underlying the study of human-environment interactions | |
| Karali et al. | The effect of farmer attitudes and objectives on the heterogeneity of farm attributes and management in Switzerland | |
| Shyng et al. | Using FSBT technique with Rough Set Theory for personal investment portfolio analysis | |
| CN108960488A (en) | A kind of accurate prediction technique of saturation loading spatial distribution based on deep learning and Multi-source Information Fusion | |
| Brown et al. | Integration of social spatial data to assess conservation opportunities and priorities | |
| CN108897778A (en) | A kind of image labeling method based on multi-source big data analysis | |
| Dossche et al. | Detecting people’s and landscape’s identity in a changing mountain landscape. An example from the northern Apennines | |
| CN105653522A (en) | Non-classified relation recognition method for plant field | |
| Whitsed et al. | A hybrid genetic algorithm with local optimiser improves calibration of a vegetation change cellular automata model | |
| CN104008177B (en) | Rule base structure optimization and generation method and system towards linguistic indexing of pictures | |
| CN107729377A (en) | Customer classification method and system based on data mining | |
| Xuezhu et al. | USING SOCIAL MEDIA TO EXPLORE PERCEPTIONS OF ECOSYSTEM SERVICES BY NATURE-BASED SOLUTION PROJECTS. | |
| CN107885857A (en) | A kind of search results pages user's behavior pattern mining method, apparatus and system | |
| CN110109902A (en) | A kind of electric business platform recommender system based on integrated learning approach | |
| Steinmann et al. | Contribution profiles of voluntary mappers in OpenStreetMap | |
| Kobayashi et al. | Aesthetic design based on the analysis of questionnaire results using deep learning techniques | |
| CN112785156A (en) | Industrial leader identification method based on clustering and comprehensive evaluation | |
| CN110489665B (en) | Microblog personalized recommendation method based on scene modeling and convolutional neural network | |
| Daneshmandi et al. | A hybrid data mining model to improve customer response modeling in direct marketing | |
| CN107220321A (en) | Solid threedimensional embodies in a kind of literary scape conversion method and its system | |
| Chouhan et al. | A survey and analysis of various agricultural crops classification techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161123 |
|
| RJ01 | Rejection of invention patent application after publication |