CN106991522A - A kind of new model score in predicting method based on content - Google Patents
A kind of new model score in predicting method based on content Download PDFInfo
- Publication number
- CN106991522A CN106991522A CN201710155801.9A CN201710155801A CN106991522A CN 106991522 A CN106991522 A CN 106991522A CN 201710155801 A CN201710155801 A CN 201710155801A CN 106991522 A CN106991522 A CN 106991522A
- Authority
- CN
- China
- Prior art keywords
- comfortableness
- similarity
- new model
- score
- quality
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 description 10
- 239000011159 matrix material Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000013215 result calculation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of new model score in predicting method based on content, first, the essential information and score information of automotive type configuration information are collected, is stored in database;For the score in predicting of new model, by typing new model parameter information, the vehicle parameter information in database is taken out successively and is compared dyad with new model;Then, similarity is tried to achieve with Method of Cosine according to vector table, and similarity is ranked up and preserved respectively by quality, comfortableness;Then result obtains the corresponding quality score of vehicle, comfortableness scoring, attention rate respectively by quality, comfortableness after sorting;Finally, the appraisal result obtained is weighted, tries to achieve the quality score of prediction, the comfortableness scoring of prediction and the attention rate of prediction.The inventive method has the advantages that low complexity, efficiency high, without cold start-up problem.
Description
Technical field
The invention belongs to content-based recommendation field, more particularly to a kind of new model score in predicting side based on content
Method.
Background technology
4 S auto shop selling operation is one of the main business in 4S shops.Take the Forecasting Methodology of science, founding mathematical models,
Based on new model configuration parameter, the related score in predicting of new model and attention rate prediction are provided, company manager can be slapped
Hold and understand new model market potential demand, obtain potential income, maximize each income segmented market.
Existing commending system is broadly divided into 2 classes:Collaborative filtering recommending and content-based recommendation.Collaborative filtering
Recommend user's rating matrix, it is necessary to huge, while in this automobile commending system, because new model is without score information, concern
Information is spent, there are problems that cold start-up and rating matrix Sparse Problems, therefore be not used to the score in predicting to new model.
And content-based recommendation method, by extracting the attributive character of article, tried to achieve based on goods attribute similar
Spend and then deploy corresponding calculate.Huge user group and scoring is not needed to record, it is only necessary to which what is inputted during new model typing matches somebody with somebody
Confidence is ceased, and based on new model content, i.e. new model configuration information, prediction appraisal result is obtained by accordingly calculating, and is predicted
As a result do not influenceed by user and scoring, it is only information-related with automobile type configuration.
The existing method and system related to score in predicting recommendation includes:
1) Chinese patent CN106326390A is disclosed in a kind of recommendation method based on collaborative filtering, this method by meter
Similarity builds item similarity matrix between calculation project, and obtains the nearest-neighbors set of projects according to similarity matrix, then
Prediction of the user to project is calculated according to nearest-neighbors set to score.
The problem of the method is present be:Need to build huge item similarity matrix, nearest-neighbors set and try to achieve use
Prediction of the family to project is scored, and calculates complicated, and can not solve the problems, such as that cold start-up, the i.e. appearance to new projects can not be immediately generated
Score in predicting is recommended.
2) Chinese patent CN105430505A provides a kind of IPTV program commending methods based on combined strategy, this method
Propose, by user's score data storehouse, using content-based recommendation method to be recommended, solve the problems, such as cold start-up.
The problem of the method is present be:Recommendation results are most like top n program, and the side such as weighted calculation is not continued through
Formula tries to achieve the more intuitively recommendation results such as prediction scoring.
3) Chinese patent CN104866490A discloses a kind of video intelligent and recommends to propose to pass through data in method, this method
Pretreatment generation message of film and TV, is used in combination the recommendation method based on content and based on collaboration, and generation is directed to optimal of user
Property recommendation list, with preferable recommendation effect.
The problem of the method is present be:The recommendation method based on content and based on collaboration is used in combination and although improves recommendation
Effect, but the response time is also increased simultaneously, complicated also refined to code of formula that vector is built brings difficulty.
By exemplified as above as can be seen that the existing prediction scored article is with recommending method, formula is complicated, calculate the time
Expense is big, need a large number of users scoring record, and there are problems that.
The content of the invention
The technical problems to be solved by the invention are to provide a kind of new model score in predicting method based on content, this method
Calculate simple, code refining, block prediction scoring and add prediction accuracy, there is preferable Research Significance and application value.
In order to solve the above technical problems, the technical solution adopted by the present invention is:
A kind of new model score in predicting method based on content, comprises the following steps:
Step 1:Collect each automobile type configuration information of automobile, including essential information and score information;
Step 2:Typing new model configuration information, including mass parameter and comfortableness parameter;
Step 3:By new model configuration information, it is compared, is converted into known automobile type configuration information in database successively
0-1 vector tables;
New model configuration information is set as N1, known automobile type configuration information is S in databasek(k=1,2 ..., n);Create
Vector is by N1, S1Vector turns to 0-1 vector tables, and first row represents automobile type configuration feature, and secondary series represents N1It is special comprising configuration
Levy, the 3rd row represent S1Included configuration feature, 0 indicates without this configuration feature, and 1 indicates this configuration feature;
To the N after conversion1、S1Carry out Method of Cosine calculating:
Step 4:New model and other automobile type configuration information in database are traveled through, vectorization simultaneously tries to achieve new model and database
In all known vehicles quality similarity and comfortableness similarity, obtain the list of quality similarity and comfortableness similarity row
Table;
Step 5:According to quality similarity list, the quality score of the higher vehicle of k similarity before taking out, attention rate and right
The quality similarity answered;According to comfortableness similarity list, the comfortableness scoring of the higher vehicle of k similarity, attention rate before taking
And corresponding comfortableness similarity;
Step 6:The data tried to achieve according to step 5, obtain the forecast quality scoring of new model, i.e.,:
Quality score:R1=a × m;
Wherein, a=(a1,a2,a3,..,ak) be step 5 quality similarity list before k vehicle quality score;M=
(m1,m2,m3...,mk) be step 5 quality similarity list before k vehicle quality similarity.
Further, the essential information of the automobile type configuration information includes mass parameter, comfortableness parameter, score information bag
Include quality score, comfortableness scoring and attention rate scoring.
Further, in addition to prediction comfortableness scoring, i.e.,:
Comfortableness scores:R2=b × n;
Wherein b=(b1,b2,b3,..,bk) scored for the comfortableness of k vehicle before step 5 comfortableness similarity list;n
=(n1,n2,n3,..,nk) be step 5 comfortableness similarity list before k vehicle comfortableness similarity.
Further, in addition to prediction attention rate, i.e.,:
Attention rate:H1=p × m, H2=q × n,
Wherein, p=(p1,p2,p3,..,pk) be step 5 quality similarity list before k vehicle attention rate;Q=(q1,
q2,q3,..,qk) be step 5 comfortableness similarity list before k vehicle attention rate, the two synthesis new model predict attention rate
H。
Compared with prior art, the beneficial effects of the invention are as follows:1) have the response time is short, encode simple, code to refine
Advantage;2) cold start-up effectively is solved the problems, such as, new model can be instantly available score in predicting;3) without a large number of users colony and scoring
Record;4) vector, which is built, takes up space small, calculates simple, no complicated formulas calculating;5) automobile type configuration information is divided into mass parameter
With comfortableness parameter, by calculating corresponding quality similarity and comfortableness similarity, obtain corresponding quality score prediction, relax
Adaptive score in predicting, adds the score in predicting degree of accuracy.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the inventive method.
Fig. 2 is part automobile type configuration hum pattern.
Fig. 3 is part vehicle attention rate, quality score and comfortableness scoring figure.
Fig. 4 is new model N in example1With known vehicle S10-1 vector tables after comparing.
Fig. 5 is the list after quality sequencing of similarity.
Fig. 6 is the list after comfortableness sequencing of similarity.
Embodiment
The present invention is further illustrated with reference to the accompanying drawings and detailed description.As shown in figure 1, based on content
New car score in predicting method is comprised the steps of:
Step one:Collect each automobile type configuration information of automobile essential information and score information (Fig. 2 be part configuration information,
Fig. 3 is part attention rate, quality score and comfortableness scoring).Wherein automobile type configuration information includes mass parameter (gearbox, hair
Motivation etc.), comfortableness parameter (body structure, chair type etc.), score information include quality score, comfortableness scoring and pay close attention to
Degree.
Step 2:Typing new model configuration information (mass parameter and comfortableness parameter).
Step 3:By new model configuration information, it is compared, is converted into known automobile type configuration information in database successively
0-1 vector tables.If new model configuration information is N1, known automobile type configuration information is S in databasek(k=1,2 ..., n), with new
Vehicle with exemplified by first vehicle is compared in database, if N1={ A1,A2,A3,A4,A5,A6,A7,A8, S1={ A1,A2,A4,A5,
A7,B1,B2, wherein Ak, BkRepresent automobile type configuration feature.
Vector space is created as shown in figure 4, by N1, S1Vector turns to 0-1 vector tables;First row represents automobile type configuration feature,
Secondary series represents N1Included configuration feature, the 3rd row represent S1Included configuration feature, 0 indicates to represent without this configuration feature, 1
There is this configuration feature.N in this example1It is converted into { 1,1,1,1,1,1,1,1,0,0 }, S1Be converted into 1,1,0,1,1,0,1,0,1,
1}.The inventive method effectively reduces 0-1 vector table length, reduces computation complexity.
To the N after conversion1、S1Carry out Method of Cosine calculating:Formula n=in this example
10, bring corresponding 0-1 values into calculating, try to achieve corresponding N1With S1Quality similarity and comfortableness similarity.
New model and other automobile type configuration information in database are traveled through, vectorization simultaneously tries to achieve new model with owning in database
The quality similarity and comfortableness similarity of known vehicle, obtain the list of quality similarity and comfortableness similarity list, respectively
It is ranked up from high to low;
Step 4:According to the list after quality sequencing of similarity, the quality score of the higher vehicle of k similarity before taking out,
Attention rate and corresponding quality similarity, as shown in Figure 5.Similarly, according to the list after comfortableness sequencing of similarity, k before taking
Comfortableness scoring, attention rate and the corresponding comfortableness similarity of the higher vehicle of similarity, as shown in Figure 6.
Step 5:The data tried to achieve according to step 4, obtain the forecast quality scoring of new model, prediction comfortableness and comment respectively
Divide and prediction attention rate, specific formula for calculation is as shown in table 1.
The score in predicting result calculation formula of table 1
The specific calculating process of step 5 is:
Quality score:R1=a × m
Wherein, a=(a1,a2,a3,..,ak) be step 4 quality sequencing of similarity after list before k vehicle quality
Scoring, m=(m1,m2,m3...,mk) be step 4 quality sequencing of similarity after list before k vehicle quality similarity.
Predict comfortableness scoring:R2=b × n
Wherein, b=(b1,b2,b3,..,bk) represent after step 4 comfortableness sequencing of similarity before list the easypro of k vehicle
Adaptive scores, n=(n1,n2,n3,..,nk) represent the comfortableness of k vehicle before list after step 4 comfortableness sequencing of similarity
Similarity.
Predict attention rate:H1=p × m, H2=q × n,
Wherein, p=(p1,p2,p3,..,pk) be k vehicle before list after step 4 quality sequencing of similarity attention rate,
Q=(q1,q2,q3,..,qk) be k vehicle before list after step 4 comfortableness sequencing of similarity attention rate, the two synthesis is newly
Vehicle prediction attention rate H.
Claims (4)
1. a kind of new model score in predicting method based on content, it is characterised in that comprise the following steps:
Step 1:Collect each automobile type configuration information of automobile, including essential information and score information;
Step 2:Typing new model configuration information, including mass parameter and comfortableness parameter;
Step 3:By new model configuration information, be compared successively with known automobile type configuration information in database, be converted into 0-1 to
Scale;
New model configuration information is set as N1, known automobile type configuration information is S in databasek(k=1,2 ..., n);Create vector
By N1, S1Vector turns to 0-1 vector tables, and first row represents automobile type configuration feature, and secondary series represents N1Included configuration feature, the
Three row represent S1Included configuration feature, 0 indicates without this configuration feature, and 1 indicates this configuration feature;
To the N after conversion1、S1Carry out Method of Cosine calculating:
Step 4:New model and other automobile type configuration information in database are traveled through, vectorization simultaneously tries to achieve new model and institute in database
There are the quality similarity and comfortableness similarity of known vehicle, obtain the list of quality similarity and comfortableness similarity list;
Step 5:According to quality similarity list, the quality score of the higher vehicle of k similarity before taking out, attention rate and corresponding
Quality similarity;According to comfortableness similarity list, before taking the comfortableness of the higher vehicle of k similarity score, attention rate and right
The comfortableness similarity answered;
Step 6:The data tried to achieve according to step 5, obtain the forecast quality scoring of new model, i.e.,:
Quality score:R1=a × m;
Wherein, a=(a1,a2,a3,..,ak) be step 5 quality similarity list before k vehicle quality score;M=(m1,m2,
m3...,mk) be step 5 quality similarity list before k vehicle quality similarity.
2. a kind of new model score in predicting method based on content as claimed in claim 1, it is characterised in that the vehicle is matched somebody with somebody
The essential information of confidence breath includes mass parameter, comfortableness parameter, and score information includes quality score, comfortableness scoring and paid close attention to
Degree scoring.
3. a kind of new model score in predicting method based on content as claimed in claim 1, it is characterised in that also including prediction
Comfortableness scores, i.e.,:
Comfortableness scores:R2=b × n;
Wherein b=(b1,b2,b3,..,bk) scored for the comfortableness of k vehicle before step 5 comfortableness similarity list;N=(n1,
n2,n3,..,nk) be step 5 comfortableness similarity list before k vehicle comfortableness similarity.
4. a kind of new model score in predicting method based on content as claimed in claim 1, it is characterised in that also including prediction
Attention rate, i.e.,:
Attention rate:H1=p × m, H2=q × n,
Wherein, p=(p1,p2,p3,..,pk) be step 5 quality similarity list before k vehicle attention rate;Q=(q1,q2,
q3,..,qk) be k vehicle before step 5 comfortableness similarity list attention rate, the two synthesis new model predicts attention rate H.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710155801.9A CN106991522A (en) | 2017-03-16 | 2017-03-16 | A kind of new model score in predicting method based on content |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710155801.9A CN106991522A (en) | 2017-03-16 | 2017-03-16 | A kind of new model score in predicting method based on content |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106991522A true CN106991522A (en) | 2017-07-28 |
Family
ID=59413113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710155801.9A Pending CN106991522A (en) | 2017-03-16 | 2017-03-16 | A kind of new model score in predicting method based on content |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106991522A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109218770A (en) * | 2018-10-19 | 2019-01-15 | 深圳市轱辘汽车维修技术有限公司 | A kind of appraisal procedure, device and the equipment of Automobile Service video |
CN110517064A (en) * | 2017-11-16 | 2019-11-29 | 北京新意互动数字技术有限公司 | A kind of competing product model analysis method and system of core |
CN111507771A (en) * | 2020-04-21 | 2020-08-07 | 北京思特奇信息技术股份有限公司 | Content income prediction method and system |
CN112100489A (en) * | 2020-08-27 | 2020-12-18 | 北京百度网讯科技有限公司 | Object recommendation method, device and computer storage medium |
CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
CN113298283A (en) * | 2020-10-19 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Content object prediction method and device and content object recommendation method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130117147A1 (en) * | 2011-11-07 | 2013-05-09 | Nathan J. Ackerman | Similarity and Relatedness of Content |
CN103530416A (en) * | 2013-10-28 | 2014-01-22 | 海南大学 | Project data forecasting grading library generating and project data pushing method and project data forecasting grading library generating and project data pushing system |
CN104834969A (en) * | 2015-05-05 | 2015-08-12 | 东南大学 | Film evaluation prediction method and system |
CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
CN106202328A (en) * | 2016-07-01 | 2016-12-07 | 中国传媒大学 | A kind of recommendation method for new projects' cold start-up |
-
2017
- 2017-03-16 CN CN201710155801.9A patent/CN106991522A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130117147A1 (en) * | 2011-11-07 | 2013-05-09 | Nathan J. Ackerman | Similarity and Relatedness of Content |
CN103530416A (en) * | 2013-10-28 | 2014-01-22 | 海南大学 | Project data forecasting grading library generating and project data pushing method and project data forecasting grading library generating and project data pushing system |
CN104834969A (en) * | 2015-05-05 | 2015-08-12 | 东南大学 | Film evaluation prediction method and system |
CN106097204A (en) * | 2016-06-24 | 2016-11-09 | 北京航空航天大学 | A kind of work commending system towards cold start-up User and recommendation method |
CN106202328A (en) * | 2016-07-01 | 2016-12-07 | 中国传媒大学 | A kind of recommendation method for new projects' cold start-up |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110517064A (en) * | 2017-11-16 | 2019-11-29 | 北京新意互动数字技术有限公司 | A kind of competing product model analysis method and system of core |
CN109218770A (en) * | 2018-10-19 | 2019-01-15 | 深圳市轱辘汽车维修技术有限公司 | A kind of appraisal procedure, device and the equipment of Automobile Service video |
CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
CN111507771A (en) * | 2020-04-21 | 2020-08-07 | 北京思特奇信息技术股份有限公司 | Content income prediction method and system |
CN112100489A (en) * | 2020-08-27 | 2020-12-18 | 北京百度网讯科技有限公司 | Object recommendation method, device and computer storage medium |
CN113298283A (en) * | 2020-10-19 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Content object prediction method and device and content object recommendation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106991522A (en) | A kind of new model score in predicting method based on content | |
Zuo et al. | Tag-aware recommender systems based on deep neural networks | |
CN107273438B (en) | Recommendation method, device, equipment and storage medium | |
CN102075851B (en) | Method and system for acquiring user preference in mobile network | |
CN107833117B (en) | Bayesian personalized sorting recommendation method considering tag information | |
CN103793537B (en) | System for recommending individual music based on multi-dimensional time series analysis and achieving method of system | |
CN101482884A (en) | Cooperation recommending system based on user predilection grade distribution | |
CN108334592B (en) | Personalized recommendation method based on combination of content and collaborative filtering | |
CN106105096A (en) | System and method for continuous social communication | |
CN103198086A (en) | Information processing device, information processing method, and program | |
CN108665323A (en) | A kind of integrated approach for finance product commending system | |
CN101452472A (en) | Information processing device, method, and program | |
CN106157156A (en) | A kind of cooperation recommending system based on communities of users | |
CN109903138B (en) | Personalized commodity recommendation method | |
CN110019943A (en) | Video recommendation method, device, electronic equipment and storage medium | |
CN110083764A (en) | A kind of collaborative filtering cold start-up way to solve the problem | |
Lai et al. | Hybrid recommendation models for binary user preference prediction problem | |
CN112699310A (en) | Cold start cross-domain hybrid recommendation method and system based on deep neural network | |
CN107506419B (en) | Recommendation method based on heterogeneous context sensing | |
Bahl et al. | A novel hybrid approach towards movie recommender systems | |
CN106202515A (en) | A kind of Mobile solution based on sequence study recommends method and commending system thereof | |
CN104572915A (en) | User event relevance calculation method based on content environment enhancement | |
Yang et al. | Design and application of handicraft recommendation system based on improved hybrid algorithm | |
CN105868422A (en) | Collaborative filtering recommendation method based on elastic dimensional feature vector optimized extraction | |
Cao et al. | A Recommendation Approach Based on Product Attribute Reviews: Improved Collaborative Filtering Considering the Sentiment Polarity. |
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: 20170728 |