CN107944007A - Recommend method in a kind of personalized dining room of combination contextual information - Google Patents
Recommend method in a kind of personalized dining room of combination contextual information Download PDFInfo
- Publication number
- CN107944007A CN107944007A CN201711292888.0A CN201711292888A CN107944007A CN 107944007 A CN107944007 A CN 107944007A CN 201711292888 A CN201711292888 A CN 201711292888A CN 107944007 A CN107944007 A CN 107944007A
- Authority
- CN
- China
- Prior art keywords
- dining room
- preference
- user
- contextual information
- cold
- 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
- 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
Abstract
Method is recommended in a kind of personalized dining room the present invention relates to combination contextual information, including establishes rule base, cold-start phase and Users'Data Analysis stage;Wherein, short-term preference rules and fixed preference rules are contained in the rule base of foundation.In cold-start phase, recommendation is provided for new user using cold data, allows user to accomplish that few input does not input even during cold start-up as far as possible, so as to reduce the Operating Complexity of mobile subscriber.In the Users'Data Analysis stage, abundant contextual information, including environment, weather condition, season time are combined, and most effective recommendation is provided to the user according to the short-term preference and fixed preference of user.When system accumulates enough data, applicating cooperation filter algorithm improves recommendation results.The present invention combines situation category information, and considers system cold start-up problem, applicating cooperation filter algorithm and rule-based proposed algorithm, makes to recommend the precision in personalized dining room to greatly improve for user.
Description
Technical field
The present invention relates to the technical field of information recommendation, more particularly to a kind of personalized dining room of combination contextual information to push away
Recommend method.
Background technology
With the popularization of global positioning system (GPS) and the fast development of mobile terminal technology, location Based service
(LBS) by more and more extensive use in work and everyday environments.Location Based service is moved by telecommunications and runed
The radio communication network (such as GSM nets, CDMA nets) of business or exterior positioning method (such as GPS) obtain the position of mobile terminal user
Information, under the support of GIS platform, can provide appropriate information service for the user needed, at home, with
Masses' point is chosen as representing, and provides what is recommended including location Based services such as food and drink, hotel, tourism, amusement and recreation for consumer
Mobile App, increasingly receives an acclaim.
Current most of dining room commending systems based on location-based service are only absorbed in the fixation preference of analysis user, so as to do
Go out to recommend, for example user is accustomed to the selection price range in dining room, taste, the environment in place, the service level etc. in dining room.But
With the difference of contextual information, user can produce some short-term preferences for being different from fixed preference, for example in the winter time, user more has
It may select Chafing dish restaurants rather than outdoor barbecue dining room;In the morning, user is more likely to selection congee powder dining room.These can be with shadow
Ringing the contextual information of the short-term preference of user includes the time residing for user, place, weather, season etc..And existing commending system
Influence of this kind of contextual information to the short-term preference of user is not considered.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, will combine situation category information, and consider system cold start-up
Problem, applicating cooperation filter algorithm and rule-based proposed algorithm, there is provided one kind recommends more accurately to combine contextual information
Personalized dining room recommend method.
To achieve the above object, technical solution provided by the present invention is:
It is divided into three phases, respectively establishes rule base, cold-start phase and Users'Data Analysis stage;
Wherein, short-term preference rules and fixed preference rules are contained in the rule base of foundation;
In cold-start phase, recommendation is provided for new user using cold data, allows user to accomplish during cold start-up as far as possible few
Input does not input even, so as to reduce the Operating Complexity of mobile subscriber, concretely comprises the following steps:First by contextual information and rule base
The matching of short-term preference rules, obtain the short-term preference of user;Again by the fixation preference rules in subscriber data and rule base
Match somebody with somebody, obtain the fixation preference of user;Match meter finally by the short-term preference that gets and the attribute in fixed preference and dining room
Calculate the recommendation probability in dining room.
After cold-start phase, a large number of users feedback data and interactive data of accumulation can be used for carrying out data mining and divide
User behavior is analysed, i.e., is concretely comprised the following steps into Users'Data Analysis stage, this stage:The rule of cold-start phase are changed first
Then, the collaborative filtering based on user and based on scene is then carried out, draws collaborative filtering as a result, finally will be rule-based
The result (recommendation results that i.e. cold-start phase is drawn) that proposed algorithm is obtained is mixed with collaborative filtering result, is drawn most
Targeted customer is simultaneously recommended in the dining room of the result by whole recommendation results.
Further, short-term preference rules are initially based on general knowledge and establish, and in user and personalized dining room commending system
Corrected in real time when interacting;The fixed preference rules are determined by analyzing data.Two kinds of rules be (if ...
Then ...) sentence, is mainly created using the static attribute or multidate information of user.
Further, the rule of cold-start phase is changed in the Users'Data Analysis stage, is specially:Pass through analysis of history number
According to lookup correlation rule and again each regular probability in computation rule storehouse.
Further, the collaborative filtering based on user and based on scene is carried out in the Users'Data Analysis stage, is drawn
Collaborative filtering result concretely comprises the following steps:
Determine first with the most like neighbor user of targeted customer and obtain the dining room selection of similar neighborhood, so as to be pushed away
Recommend result;Then contextual information is added, is obtained in selection of the similar users to dining room being in targeted customer under identical situation,
Obtain recommendation results;Finally two recommendation results are combined together, draw collaborative filtering result.
In the present solution, the data of input include:
Contextual information, including the location of user, weather, time, environment;
Individual subscriber data, including mobile telephone registration information:Such as gender, age and other people informations;And mobile equipment
Information:Such as operating system, mobile phone model, mobile phone popular software;
Dining room information, includes the classification in dining room, attribute and some essential informations.Restaurant category includes chafing dish, Guangdong dishes, river
Dish, barbecue etc..Food and drink attribute includes price, environment, scoring, taste, atmosphere, whether provides wireless network etc..Substantially believe in dining room
Breath includes place, business hours, phone etc..
User journal, scoring and interaction data of the record user to dining room, are supported with updating the rule of cold-start phase,
And the data basis provided for the later collaborative filtering stage.
Compared with prior art, this programme principle and advantage are as follows:
This programme combination situation category information, and consider system cold start-up problem, applicating cooperation filter algorithm and based on rule
Proposed algorithm then, devises a triphasic recommendation method, makes to recommend the precision in personalized dining room to carry significantly for user
It is high.
Brief description of the drawings
Fig. 1 is the FB(flow block) that method is recommended in a kind of personalized dining room of combination contextual information of the present invention;
Fig. 2 is the flow chart of cold-start phase in a kind of personalized dining room recommendation method of combination contextual information of the present invention;
Fig. 3 is the flow of collaborative filtering recommending in a kind of personalized dining room recommendation method of combination contextual information of the present invention
Figure.
Embodiment
With reference to specific embodiment, the invention will be further described:
Referring to shown in attached drawing 1, method is recommended in a kind of personalized dining room of combination contextual information described in the present embodiment, including
Establish rule base, cold-start phase and Users'Data Analysis stage.
Wherein, short-term preference rules and fixed preference rules are contained in the rule base of foundation;
In cold-start phase, since cold-start phase lacks historical data and user feedback scoring, plus discrete dining room
Number of attributes is very huge, and mobile end subscriber is relatively low to the tolerance of complex operations, and the present embodiment selection is rule-based
Algorithm to provide recommendation for new user, as shown in Fig. 2, detailed process is as follows:
First contextual information is matched with the short-term preference rules in rule base, obtains the short-term preference of user, is specially:
User is to the preference probability in i types dining room under different situations:
Wherein, Ti, WiAnd EiRepresent respectively under current time, weather and environment to the preference probability in i types dining room;I=1,
2,3 ..., s, s are the quantity of restaurant category;
Assuming that KiFor the preference probability of dining room species, then the short-term preference of user is expressed as:K1,K2,K3,…,Ki;Wherein, Ki
=1/3 (Ti+Wi+Ei)。
After obtaining short-term preference, then carry out the acquisition that user fixes preference;, will during calculating user and fixing preference
Fixation preference rules in rule base match with user property, to calculate the preference probability of each dining room property value.So use
Family is fixed preference and can be expressed as:
Wherein, i=1,2,3 ..., m, represent the quantity of the value of each attribute in dining room;J=1,2,3 ..., n, represent meal
The quantity of Room attribute;Each row represent preference probability of the user to the property value of dining room particular community in formula.For example, table 1 below is retouched
Preference probability of the user to each property value of the dining atmosphere properties in certain dining room is stated.
Table 1
After getting fixation preference and the short-term preference of user, by matching and counting the attribute of above-mentioned rule and dining room
Calculation obtains the recommendation probability in the dining room.For example, the attribute in some dining room and the user preference probability of each particular community are as follows
Shown in table 2:
Table 2
Finally, matched meter by the short-term preference that gets and the attribute in fixed preference and dining room in cold-start phase
The recommendation probability in dining room is calculated, calculation formula is as follows:
After cold-start phase, into the Users'Data Analysis stage.The stage comprises the following steps:
S1, the rule for changing cold-start phase:
I.e. by analysis of history data, correlation rule and again each regular probability in computation rule storehouse are searched.
S2, carry out collaborative filtering based on user and based on scene, draws collaborative filtering as a result, as shown in figure 3, tool
Body process is as follows:
First determine with the most like neighbor user of targeted customer and obtain the dining room selection of similar neighborhood, so as to be recommended
As a result;Then contextual information is added, obtains in selection of the similar users to dining room being in targeted customer under identical situation, obtains
To recommendation results;Finally two recommendation results are combined together, draw collaborative filtering result.
S3, the result for finally being obtained rule-based proposed algorithm and collaborative filtering result mix, and draw most
Targeted customer is simultaneously recommended in the dining room of the result by whole recommendation results.
The present embodiment combination situation category information, and consider system cold start-up problem, applicating cooperation filter algorithm and is based on
The proposed algorithm of rule, devises a triphasic recommendation method, makes to recommend the precision in personalized dining room significantly for user
Improve.
The examples of implementation of the above are only the preferred embodiments of the invention, and the implementation model of the present invention is not limited with this
Enclose, therefore the change that all shape, principles according to the present invention are made, it should all cover within the scope of the present invention.
Claims (6)
1. method is recommended in a kind of personalized dining room of combination contextual information, it is characterised in that:Including establishing rule base, cold start-up rank
Section and Users'Data Analysis stage;
Wherein, short-term preference rules and fixed preference rules are contained in the rule base of foundation;
In cold-start phase, first contextual information is matched with the short-term preference rules in rule base, obtains the short-term preference of user;
Subscriber data is matched with the fixation preference rules in rule base again, obtains the fixation preference of user;Finally by what is got
Short-term preference and the attribute in fixed preference and dining room, which match, calculates the recommendation probability in dining room;
In the Users'Data Analysis stage, the rule of cold-start phase is changed first, is then carried out based on user and based on scene
Collaborative filtering, draws collaborative filtering as a result, the result and collaborative filtering that are finally obtained rule-based proposed algorithm
As a result mix, draw consequently recommended result and targeted customer is recommended into the dining room of the result.
2. method is recommended in a kind of personalized dining room of combination contextual information according to claim 1, it is characterised in that:It is described
Short-term preference rules, it is initially based on general knowledge foundation, and is carried out when user interacts with personalization dining room commending system
Corrigendum in real time;The fixed preference rules are determined by analyzing data.
3. method is recommended in a kind of personalized dining room of combination contextual information according to claim 1, it is characterised in that:It is described
User fixes the acquisition of preference in cold-start phase, specific as follows:
Fixation preference rules in the attribute and rule base of subscriber data are matched, calculate the preference of each dining room property value
Probability, then show that user fixes preference and is:
Wherein, i=1,2,3 ..., m, represent the quantity of the value of each attribute in dining room;J=1,2,3 ..., n, represent that dining room belongs to
The quantity of property;Each row represent preference probability of the user to the property value of dining room particular community in formula.
4. method is recommended in a kind of personalized dining room of combination contextual information according to claim 1, it is characterised in that:It is described
Matched in cold-start phase by the short-term preference and the attribute in fixed preference and dining room that get and calculate the recommendation in dining room
Probability, calculation formula are as follows:
<mrow>
<mi>P</mi>
<mo>=</mo>
<msub>
<mi>K</mi>
<mi>i</mi>
</msub>
<mo>&times;</mo>
<mfrac>
<mn>1</mn>
<mi>n</mi>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>p</mi>
<mi>i</mi>
</msub>
</mrow>
Wherein, KiFor the preference probability of dining room species, piFor the corresponding preference probability of dining room attribute.
5. method is recommended in a kind of personalized dining room of combination contextual information according to claim 1, it is characterised in that:It is described
The rule of cold-start phase is changed in the Users'Data Analysis stage, is specially:By analysis of history data, correlation rule is searched simultaneously
Recalculate the regular probability of each in rule base.
6. method is recommended in a kind of personalized dining room of combination contextual information according to claim 1, it is characterised in that:It is described
The collaborative filtering based on user and based on scene is carried out in the Users'Data Analysis stage, draws the specific of collaborative filtering result
Step is:
Determine first with the most like neighbor user of targeted customer and obtain the dining room selection of similar neighborhood, so as to obtain recommending knot
Fruit;Then contextual information is added, obtains in selection of the similar users to dining room being in targeted customer under identical situation, obtains
Recommendation results;Finally two recommendation results are combined together, draw collaborative filtering result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711292888.0A CN107944007A (en) | 2018-02-06 | 2018-02-06 | Recommend method in a kind of personalized dining room of combination contextual information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711292888.0A CN107944007A (en) | 2018-02-06 | 2018-02-06 | Recommend method in a kind of personalized dining room of combination contextual information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944007A true CN107944007A (en) | 2018-04-20 |
Family
ID=61945251
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711292888.0A Pending CN107944007A (en) | 2018-02-06 | 2018-02-06 | Recommend method in a kind of personalized dining room of combination contextual information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944007A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109829108A (en) * | 2019-01-28 | 2019-05-31 | 北京三快在线科技有限公司 | Information recommendation method, device, electronic equipment and readable storage medium storing program for executing |
CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等(上海)信息科技股份有限公司 | A kind of dining room recommended method and system |
CN113157752A (en) * | 2021-03-12 | 2021-07-23 | 北京航空航天大学 | Scientific and technological resource recommendation method and system based on user portrait and situation |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060074883A1 (en) * | 2004-10-05 | 2006-04-06 | Microsoft Corporation | Systems, methods, and interfaces for providing personalized search and information access |
US7181438B1 (en) * | 1999-07-21 | 2007-02-20 | Alberti Anemometer, Llc | Database access system |
CN102789499A (en) * | 2012-07-16 | 2012-11-21 | 浙江大学 | Collaborative filtering method on basis of scene implicit relation among articles |
CN104008184A (en) * | 2014-06-10 | 2014-08-27 | 百度在线网络技术(北京)有限公司 | Method and device for pushing information |
CN107133262A (en) * | 2017-03-30 | 2017-09-05 | 浙江大学 | A kind of personalized POI embedded based on many influences recommends method |
-
2018
- 2018-02-06 CN CN201711292888.0A patent/CN107944007A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7181438B1 (en) * | 1999-07-21 | 2007-02-20 | Alberti Anemometer, Llc | Database access system |
US20060074883A1 (en) * | 2004-10-05 | 2006-04-06 | Microsoft Corporation | Systems, methods, and interfaces for providing personalized search and information access |
CN102789499A (en) * | 2012-07-16 | 2012-11-21 | 浙江大学 | Collaborative filtering method on basis of scene implicit relation among articles |
CN104008184A (en) * | 2014-06-10 | 2014-08-27 | 百度在线网络技术(北京)有限公司 | Method and device for pushing information |
CN107133262A (en) * | 2017-03-30 | 2017-09-05 | 浙江大学 | A kind of personalized POI embedded based on many influences recommends method |
Non-Patent Citations (2)
Title |
---|
任子亭等: "移动社会网络中基于位置的个性化餐馆推荐建模研究", 《无线互联科技》 * |
许明峰: "基于排列融合的组推荐系统研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110020186A (en) * | 2018-05-08 | 2019-07-16 | 美味不用等(上海)信息科技股份有限公司 | A kind of dining room recommended method and system |
CN109829108A (en) * | 2019-01-28 | 2019-05-31 | 北京三快在线科技有限公司 | Information recommendation method, device, electronic equipment and readable storage medium storing program for executing |
CN109829108B (en) * | 2019-01-28 | 2020-12-04 | 北京三快在线科技有限公司 | Information recommendation method and device, electronic equipment and readable storage medium |
CN113157752A (en) * | 2021-03-12 | 2021-07-23 | 北京航空航天大学 | Scientific and technological resource recommendation method and system based on user portrait and situation |
CN113157752B (en) * | 2021-03-12 | 2022-10-28 | 北京航空航天大学 | Scientific and technological resource recommendation method and system based on user portrait and situation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9043222B1 (en) | User interface for geofence associated content | |
US8140561B2 (en) | Service recommendation system and service recommendation method | |
WO2016008453A1 (en) | Intelligent service interaction platform apparatus, system and realizing method thereof | |
CN102713906B (en) | Location-based search | |
CN106973367B (en) | User terminal of mobile communication network and method for providing telephone directory service to the same | |
US20080198995A1 (en) | System and method for providing a search portal with enhanced results | |
CN107944007A (en) | Recommend method in a kind of personalized dining room of combination contextual information | |
CN104158937B (en) | Information prompting method and client and electronic equipment based on address book contact | |
CN101902688A (en) | Counting and acquiring system and method of navigation information | |
CN107589855A (en) | A kind of method and apparatus according to geographical position recommended candidate word | |
CN102624756B (en) | Data download terminal and data download method | |
US8233879B1 (en) | Mobile device personalization based on previous mobile device usage | |
US20120089584A1 (en) | Method and mobile terminal for performing personalized search | |
CN105912358A (en) | Intelligent electronic device and setting method thereof | |
US20160165048A1 (en) | Methods and systems for automated business dialing | |
CN104967669A (en) | Method of pushing information to nearby specific user mobile terminals | |
WO2006014439A2 (en) | Hotspot location record database | |
CN102523273A (en) | System for providing location-based service | |
CN105072090A (en) | Method, system and computer-readable medium for synchronizing spot information | |
CN104537113B (en) | Social networking system searching method | |
CN106776618A (en) | The method and device that ticketing data is inquired about and ticketing service is recommended | |
KR102125620B1 (en) | Server for providing cafe recommnedation information based on emotion, and method for recommending cafe using thereof | |
KR20230021998A (en) | Customized local festival recommendation service and method using user mydata | |
CN103313184B (en) | User profile supplying method and device | |
KR101089646B1 (en) | Method and apparatus for content recommendation |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180420 |
|
WD01 | Invention patent application deemed withdrawn after publication |