CN103942255A - Personalized information recommending system and method - Google Patents
Personalized information recommending system and method Download PDFInfo
- Publication number
- CN103942255A CN103942255A CN201410100955.4A CN201410100955A CN103942255A CN 103942255 A CN103942255 A CN 103942255A CN 201410100955 A CN201410100955 A CN 201410100955A CN 103942255 A CN103942255 A CN 103942255A
- Authority
- CN
- China
- Prior art keywords
- user
- server
- information
- analysis
- recommendation
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a personalized information recommending system. The system comprises a geographical location information acquisition device, a transaction database server, an analysis server, a recommending server, a user client and a merchant client, wherein the input end of the analysis server is respectively connected with the geographical location information acquisition device and the transaction database server; the input end of the recommending server is connected with the output end of the analysis server; the user client is in two-way connection with the recommending server; the merchant client is in two-way connection with the recommending server. Through the system, clustering analysis can be performed on transaction data of a user based on the geographical location information technology, and situation model analysis can be performed according to the geographical location of the user, the clustering analysis result and the situation analysis result are combined so that more effective personalized recommending can be performed, and a basis is provided for accurate marketing of a merchant.
Description
Technical field
The present invention relates to information recommendation field, be specifically related to a kind of Personalized Information Recommendation System and recommend method thereof.
Background technology
Along with the development of mobile communications network and intelligent terminal, mobile e-business has welcome unprecedented development.Personalized recommendation is as the effective means of " information overload " problem of solution, experience the user who improves e-commerce website, increase aspects such as buying conversion ratio and cross-selling and brought into play great effect, but traditional personalized recommendation system is all the buying behavior based on user, the user behavior history such as collection behavior are recommended, do not consider the peculiar user's space-time characterisation of mobile e-business, and the processing power of mobile terminal device is poor, input and output are limited in one's ability, the factors such as wireless network bandwidth is weak make it have higher requirement to the degree of accuracy of recommending, therefore, traditional personalized recommendation system is not suitable for the personalized recommendation field in mobile e-business epoch.
Summary of the invention
The invention provides a kind of Personalized Information Recommendation System and recommend method thereof, based on geographical location information, to for carrying out effective personalized recommendation, market accurately according to information for trade company provides simultaneously.
For achieving the above object, the invention provides a kind of Personalized Information Recommendation System, be characterized in, this system comprises:
Geographical location information acquisition device, it obtains user's positional information;
Transaction data base server, its storage user's Transaction Information;
Analysis server, its input end connects respectively geographical location information acquisition device and transaction data base server, and user's consumer behavior is carried out cluster analysis and carried out scenario analysis according to user's geographical location information;
Recommendation server, the output terminal of its input end linking parsing server, arranges generation recommendation results according to the result of the cluster result of Analysis server, scenario analysis and trade company;
Subscription client, its two-way connection recommendation server, for user provides recommendation information;
Trade company's client, its two-way connection recommendation server, controls the recommendation results of recommending user.
Above-mentioned geographical location information acquisition device adopts GPS device.
Above-mentioned subscription client adopts mobile terminal.
A recommend method for above-mentioned Personalized Information Recommendation System, is characterized in, the method comprises:
Analysis server receives and carries out cluster analysis according to user's trading information data and obtains cluster result;
Analysis server receives and carries out scenario analysis according to user's geographical location information and obtains scenario analysis result;
Recommendation server produces recommendation results according to cluster result and scenario analysis result.
Above-mentioned geographical location information acquisition device obtains user's positional information, is sent to Analysis server.
Above-mentioned transaction data base server stores user's Transaction Information, is sent to Analysis server.
Above-mentioned cluster analysis comprises: calculate user's similarity, according to similarity result, setting threshold, is less than user's spacing the sub-clustering of threshold value, forms tuftlet, merges tuftlet and obtains cluster result.
Above-mentioned user's spacing computing method adopt Jensen-Shannon distance to calculate, and formula is:
(1)
In formula (1),
,
with
represent the probability distribution of two user characteristicses,
two Kullback – Leibler distances between distribution.
The method that above-mentioned merging tuftlet obtains cluster result comprise adopt bunch between merging method repeatedly merge subclass; Between bunch, merging method is by calculating the connectivity between two bunches
and similarity
differentiate two bunches and whether can merge into a class;
Connectivity between bunch
be expressed as:
(2)
In formula 2,
represent connection bunch
with
the similar value sum on limit,
represent handle
be divided into the similar value sum on two roughly equal bunch limits that required cut-out is minimum;
Similarity between bunch
be expressed as:
(3)
In formula 3,
represent connection bunch
with
the mean value of similar value on limit,
represent handle
be divided into the mean value of the similar value on two roughly equal bunch limits that required cut-out is minimum.
Above-mentioned scenario analysis comprises:
Gather user's geographical location information, and then utilize the geographical location information of collecting to collect ambient condition information and temporal information;
Utilize environmental information and temporal information correspondence to obtain scenario analysis result;
Filter out incongruent scenario analysis result according to default user's request.
The information recommendation technology of Personalized Information Recommendation System of the present invention and recommend method thereof and prior art is compared, its advantage is, in personalized recommendation system based on geographical location information service of the present invention, user's transaction data is carried out to cluster analysis, and carry out contextual model analysis according to user's geographic position, cluster analysis result and scenario analysis result are combined, can carry out more effectively personalized recommendation, and foundation is provided to the precision marketing of trade company.
Brief description of the drawings
Fig. 1 is the system module figure of Personalized Information Recommendation System of the present invention;
Fig. 2 is the schematic diagram of cluster analysis in recommendation method for personalized information of the present invention;
Fig. 3 is mobile e-business personalized recommendation service model schematic diagram in recommendation method for personalized information of the present invention.
Embodiment
Below in conjunction with accompanying drawing, further illustrate specific embodiments of the invention.
As shown in Figure 1, the invention discloses a kind of Personalized Information Recommendation System, this system comprises: geographical location information acquisition device, transaction data base server, Analysis server, recommendation server, subscription client and trade company's client.
Geographical location information acquisition device output terminal linking parsing server input end, utilizes this device to obtain user's precise position information, for Analysis server analysis.In the present embodiment, geographical location information acquisition device can adopt GPS device.
Transaction data base server output terminal linking parsing server input end, storage user's trading information data, for Analysis server analysis.
Analysis server input end connects respectively geographical location information acquisition device and transaction data base server, output terminal connects recommendation server, the trading information data obtaining from transaction data base server carries out cluster analysis, and the geographical location information obtaining from geographical location information acquisition device is carried out to scenario analysis, the analysis result of gained is for recommendation server.
The output terminal of recommendation server input end linking parsing server, output terminal respectively communication is connected to subscription client and trade company's client.Recommendation server basis obtains the configuration information of cluster result, scenario analysis result and the trade company of customer transaction data from Analysis server, and produces recommendation results according to obtained information.
The two-way connection recommendation server of subscription client, receives the device of recommendation information, for user provides recommendation information as user.In the present embodiment, subscription client can use for consumer, can adopt mobile terminal.
The two-way connection recommendation server of trade company's client, trade company can recommend by trade company's client control user's recommendation results, helps trade company to market more accurately.
The present invention also discloses a kind of recommend method of Personalized Information Recommendation System, and the method includes the steps of:
Step 1, geographical location information acquisition device obtain user's positional information, are sent to Analysis server.Transaction data base server stores user's Transaction Information, is sent to Analysis server.
Step 2, Analysis server receive and carry out cluster analysis according to user's trading information data and obtain cluster result.
As shown in Figure 2, cluster analysis comprises: first calculate the similarity between user, according to similarity result, set threshold values
, user's spacing is less than to threshold values
sub-clustering, be divided into relatively little bunch, and then by design herein bunch between merge algorithm repeatedly merge subclass and obtain last gathering result.Next illustrate distance between user computing method and bunch between merging method.
1) user's spacing computing method adopt Jensen-Shannon distance (Jensen-Shannon Divergence, JSD) to calculate, and formula is:
(1)
In formula (1),
,
with
represent the probability distribution of two user characteristicses,
two Kullback – Leibler distances (KL Divergence) between distribution.
2) merge tuftlet obtain the method for cluster result comprise adopt bunch between merging method repeatedly merge subclass; Between bunch, merging method is by calculating the connectivity between two bunches
and similarity
differentiate two bunches and whether can merge into a class;
Connectivity between bunch
be expressed as:
(2)
In formula 2,
represent connection bunch
with
the similar value sum on limit,
represent handle
be divided into the similar value sum on two roughly equal bunch limits that required cut-out is minimum;
Similarity between bunch
be expressed as:
(3)
In formula 3,
represent connection bunch
with
the mean value of similar value on limit,
represent handle
be divided into the mean value of the similar value on two roughly equal bunch limits that required cut-out is minimum.
Step 3, in carrying out cluster analysis, Analysis server receives and also carries out scenario analysis according to user's geographical location information and obtain scenario analysis result.
Carry out situation filtration and need to carry out following 3 steps: the collection of (1) contextual information: the geographical location information of collecting user by positioning system, and then utilize the geographical location information collected to collect the information such as temperature, the activity of holding of surrounding environment, collect date, season, festivals or holidays, weekend equal time information; (2) contextual information of collecting is carried out to rule-based reasoning, obtain available contextual model; (3) filter out in conjunction with contextual model and user's demand analysis the recommendation information that does not meet current contextual model, personalized recommendation information is presented to user accurately.
Step 4, recommendation server basis obtain the configuration information of cluster result, scenario analysis result and the trade company of customer transaction data from Analysis server, and produce recommendation results according to obtained characteristic information.
In most cases, subscription client, for example mobile terminal, identifying user identity that can be unique, therefore,, as long as user allows, can collect specific user's configuration information and positional information more accurately by mobile terminal, and the position of geographical location information service-user is changing, personalized recommendation wants to respond fast the variation of customer location and demand thereof.
As shown in Figure 3, be the mobile e-business personalized recommendation service model based on geographical location information service.
Collect user's characteristic information according to user and user's trading activity, the population characteristic's information being provided while registration as user, more detailed user's characteristic information needs the trading activity of digging user, in the following way digging user characteristic information: (1) user fixed cycle article of consumption: the periodic exchange hour of user, place, commodity; (2) the residing particular time of user: can be inferred and the residing particular time of user by the commodity of user's long term purchase, for example user often buys baby paper diaper and illustrates that there is the baby of firm birth in user family; (3) the loyal brand of user: the trading activity by user also deducibility goes out the brand that user is loyal; (4) level of consumption: the amount of consumption in user's set time.Feature by the trading activity to a large number of users, evaluation and user is carried out cluster analysis, draws different class of subscribers, and each classification has represented the specific consumer group's consumptive characteristics, and this is an important evidence of carrying out personalized recommendation for user.
Trade company's characteristic information is easier to collect, introduction by trade company, official website, user's the information such as trading activity and evaluation thereof can be collected the various information such as type, business hours, business scale, merchandising, commodity price and the pouplarity of trade company easily, equally, we also need trade company to carry out cluster analysis, trade company is sorted out, carry out personalized recommendation according to the feature of classification and classification to client, the frequent Dao Yijia of for example user restaurant goes consumption, and he probably also likes other another restaurant of family of same class.
Only consider that user's consumer behavior and feature also can not accomplish effective personalized recommendation far away, for example tourism route commending system is diverse in the recommended route in summer and winter, therefore, we also need to catch in step 3 user's contextual information, user's space-time characterisation is the important component part of contextual information, make full use of user's geographical location information, the information such as ambient condition information and time is removed to carry out sight and is filtered the key that becomes effective personalized recommendation, this is the binding site of geographical location information service and mobile e-business personalized recommendation application just.
After customer consumption, can evaluate consumption experience, these trading activities and evaluation go on record again, and these data can go again to optimize the model that we set up, and personalized recommendation next time can be more accurate.
Although content of the present invention has been done detailed introduction by above preferred embodiment, will be appreciated that above-mentioned description should not be considered to limitation of the present invention.Read after foregoing those skilled in the art, for multiple amendment of the present invention and substitute will be all apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (10)
1. a Personalized Information Recommendation System, is characterized in that, this system comprises:
Geographical location information acquisition device, it obtains user's positional information;
Transaction data base server, its storage user's Transaction Information;
Analysis server, its input end connects respectively described geographical location information acquisition device and transaction data base server, and user's consumer behavior is carried out cluster analysis and carried out scenario analysis according to user's geographical location information;
Recommendation server, its input end connects the output terminal of described Analysis server, according to the result of the cluster result of Analysis server, scenario analysis and trade company, generation recommendation results is set;
Subscription client, the described recommendation server of its two-way connection, for user provides recommendation information;
Trade company's client, the described recommendation server of its two-way connection, controls the recommendation results of recommending user.
2. Personalized Information Recommendation System as claimed in claim 1, is characterized in that, described geographical location information acquisition device adopts GPS device.
3. Personalized Information Recommendation System as claimed in claim 1, is characterized in that, described subscription client adopts mobile terminal.
4. a recommend method for the Personalized Information Recommendation System as described in any one claim in claims 1 to 3, is characterized in that, the method comprises:
Analysis server receives and carries out cluster analysis according to user's trading information data and obtains cluster result;
Analysis server receives and carries out scenario analysis according to user's geographical location information and obtains scenario analysis result;
Recommendation server produces recommendation results according to cluster result and scenario analysis result.
5. recommend method as claimed in claim 4, is characterized in that, described geographical location information acquisition device obtains user's positional information, is sent to Analysis server.
6. recommend method as claimed in claim 4, is characterized in that, described transaction data base server stores user's Transaction Information, is sent to Analysis server.
7. recommend method as claimed in claim 4, is characterized in that, described cluster analysis comprises: calculate user's similarity, according to similarity result, setting threshold, is less than user's spacing the sub-clustering of threshold value, forms tuftlet, merges tuftlet and obtains cluster result.
8. recommend method as claimed in claim 7, is characterized in that, described user's spacing computing method adopt Jensen-Shannon distance to calculate, and formula is:
(1)
In formula (1),
,
with
represent the probability distribution of two user characteristicses,
two Kullback – Leibler distances between distribution.
9. recommend method as claimed in claim 7, is characterized in that, the method that described merging tuftlet obtains cluster result comprise adopt bunch between merging method repeatedly merge subclass; Between bunch, merging method is by calculating the connectivity between two bunches
and similarity
differentiate two bunches and whether can merge into a class;
Connectivity between bunch
be expressed as:
(2)
In formula 2,
represent connection bunch
with
the similar value sum on limit,
represent handle
be divided into the similar value sum on two roughly equal bunch limits that required cut-out is minimum;
Similarity between bunch
be expressed as:
(3)
In formula 3,
represent connection bunch
with
the mean value of similar value on limit,
represent handle
be divided into the mean value of the similar value on two roughly equal bunch limits that required cut-out is minimum.
10. recommend method as claimed in claim 4, is characterized in that, described scenario analysis comprises:
Gather user's geographical location information, and then utilize the geographical location information of collecting to collect ambient condition information and temporal information;
Utilize environmental information and temporal information correspondence to obtain scenario analysis result;
Filter out incongruent scenario analysis result according to default user's request.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410100955.4A CN103942255A (en) | 2014-03-19 | 2014-03-19 | Personalized information recommending system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410100955.4A CN103942255A (en) | 2014-03-19 | 2014-03-19 | Personalized information recommending system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103942255A true CN103942255A (en) | 2014-07-23 |
Family
ID=51189923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410100955.4A Pending CN103942255A (en) | 2014-03-19 | 2014-03-19 | Personalized information recommending system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103942255A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574101A (en) * | 2014-12-10 | 2015-04-29 | 百度在线网络技术(北京)有限公司 | Method, equipment and system for verifying electronic ticket |
CN105069651A (en) * | 2015-08-06 | 2015-11-18 | 北京优凯澜信息技术有限公司 | Artwork O2O platform implementation method |
CN105069633A (en) * | 2015-08-06 | 2015-11-18 | 北京优凯澜信息技术有限公司 | Artwork O2O platform implementation method |
CN105072591A (en) * | 2015-08-11 | 2015-11-18 | 中山大学 | Method and system for pushing individualized information based on mobile terminal |
CN105516928A (en) * | 2016-01-15 | 2016-04-20 | 中国联合网络通信有限公司广东省分公司 | Position recommending method and system based on position crowd characteristics |
WO2016101881A1 (en) * | 2014-12-23 | 2016-06-30 | 百度在线网络技术(北京)有限公司 | Method and apparatus for information recommendation realized by computer, and computer device |
CN107424012A (en) * | 2017-07-31 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of intelligent shopping guide method, intelligent shopping guide equipment |
CN107798551A (en) * | 2016-09-07 | 2018-03-13 | 银联国际有限公司 | Bank card data analysis system based on POS terminal |
CN109388738A (en) * | 2017-08-03 | 2019-02-26 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
CN110009428A (en) * | 2019-04-10 | 2019-07-12 | 南京思德展示科技股份有限公司 | Commercial space digitizes cloud platform |
CN110460645A (en) * | 2015-08-04 | 2019-11-15 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method and device |
CN110770779A (en) * | 2017-10-13 | 2020-02-07 | 美的集团股份有限公司 | Method and system for providing personalized live information exchange |
CN110969483A (en) * | 2019-11-29 | 2020-04-07 | 支付宝实验室(新加坡)有限公司 | Method and device for identifying positions of merchants and electronic equipment |
CN112686701A (en) * | 2020-12-31 | 2021-04-20 | 江苏省广电有线信息网络股份有限公司无锡分公司 | Merchant recommendation method based on regional information |
CN113674028A (en) * | 2021-08-24 | 2021-11-19 | 深圳市微云信众技术有限公司 | SaaS cloud system for bank third-party payment aggregation marketing platform |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
CN102460431A (en) * | 2009-05-08 | 2012-05-16 | 佐科姆有限公司 | System and method for behavioural and contextual data analytics |
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN103065258A (en) * | 2012-12-25 | 2013-04-24 | 苏州博康生物医疗科技有限公司 | Method for achieving intelligent service platform |
CN103258022A (en) * | 2013-05-07 | 2013-08-21 | 天津大学 | Local commerce service recommendation system and method based on user interest |
CN103631946A (en) * | 2013-12-11 | 2014-03-12 | 北京光年无限科技有限公司 | Content pushing system based on geographic positions |
-
2014
- 2014-03-19 CN CN201410100955.4A patent/CN103942255A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102460431A (en) * | 2009-05-08 | 2012-05-16 | 佐科姆有限公司 | System and method for behavioural and contextual data analytics |
CN102421062A (en) * | 2011-12-01 | 2012-04-18 | 中国联合网络通信集团有限公司 | Method and system for pushing application information |
CN102750647A (en) * | 2012-06-29 | 2012-10-24 | 南京大学 | Merchant recommendation method based on transaction network |
CN103065258A (en) * | 2012-12-25 | 2013-04-24 | 苏州博康生物医疗科技有限公司 | Method for achieving intelligent service platform |
CN103258022A (en) * | 2013-05-07 | 2013-08-21 | 天津大学 | Local commerce service recommendation system and method based on user interest |
CN103631946A (en) * | 2013-12-11 | 2014-03-12 | 北京光年无限科技有限公司 | Content pushing system based on geographic positions |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104574101B (en) * | 2014-12-10 | 2020-05-22 | 百度在线网络技术(北京)有限公司 | Method, equipment and system for verifying electronic ticket |
CN104574101A (en) * | 2014-12-10 | 2015-04-29 | 百度在线网络技术(北京)有限公司 | Method, equipment and system for verifying electronic ticket |
WO2016101881A1 (en) * | 2014-12-23 | 2016-06-30 | 百度在线网络技术(北京)有限公司 | Method and apparatus for information recommendation realized by computer, and computer device |
CN110460645A (en) * | 2015-08-04 | 2019-11-15 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method and device |
CN105069651A (en) * | 2015-08-06 | 2015-11-18 | 北京优凯澜信息技术有限公司 | Artwork O2O platform implementation method |
CN105069633A (en) * | 2015-08-06 | 2015-11-18 | 北京优凯澜信息技术有限公司 | Artwork O2O platform implementation method |
CN105072591A (en) * | 2015-08-11 | 2015-11-18 | 中山大学 | Method and system for pushing individualized information based on mobile terminal |
CN105516928A (en) * | 2016-01-15 | 2016-04-20 | 中国联合网络通信有限公司广东省分公司 | Position recommending method and system based on position crowd characteristics |
CN107798551A (en) * | 2016-09-07 | 2018-03-13 | 银联国际有限公司 | Bank card data analysis system based on POS terminal |
CN107798551B (en) * | 2016-09-07 | 2023-07-11 | 银联国际有限公司 | Bank card data analysis system based on POS equipment |
CN107424012A (en) * | 2017-07-31 | 2017-12-01 | 京东方科技集团股份有限公司 | A kind of intelligent shopping guide method, intelligent shopping guide equipment |
CN109388738B (en) * | 2017-08-03 | 2022-04-12 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
CN109388738A (en) * | 2017-08-03 | 2019-02-26 | 北京京东尚科信息技术有限公司 | Information-pushing method and device |
CN110770779A (en) * | 2017-10-13 | 2020-02-07 | 美的集团股份有限公司 | Method and system for providing personalized live information exchange |
CN110770779B (en) * | 2017-10-13 | 2022-05-24 | 美的集团股份有限公司 | Method and system for providing personalized live information exchange |
CN110009428A (en) * | 2019-04-10 | 2019-07-12 | 南京思德展示科技股份有限公司 | Commercial space digitizes cloud platform |
CN110969483A (en) * | 2019-11-29 | 2020-04-07 | 支付宝实验室(新加坡)有限公司 | Method and device for identifying positions of merchants and electronic equipment |
CN110969483B (en) * | 2019-11-29 | 2023-10-10 | 支付宝实验室(新加坡)有限公司 | Method and device for identifying merchant position and electronic equipment |
CN112686701A (en) * | 2020-12-31 | 2021-04-20 | 江苏省广电有线信息网络股份有限公司无锡分公司 | Merchant recommendation method based on regional information |
CN113674028A (en) * | 2021-08-24 | 2021-11-19 | 深圳市微云信众技术有限公司 | SaaS cloud system for bank third-party payment aggregation marketing platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103942255A (en) | Personalized information recommending system and method | |
CN109359244B (en) | Personalized information recommendation method and device | |
CN108876526B (en) | Commodity recommendation method and device and computer-readable storage medium | |
CN108121737B (en) | Method, device and system for generating business object attribute identifier | |
JP5784236B2 (en) | Mobile ads that use data networks based on intelligence data related to internet-enabled devices, derived using graph models | |
US9183497B2 (en) | Performance-efficient system for predicting user activities based on time-related features | |
US8983976B2 (en) | Dynamically expiring crowd-sourced content | |
US20100131335A1 (en) | User interest mining method based on user behavior sensed in mobile device | |
WO2016206196A1 (en) | Method and device for obtaining user attribute information, and server | |
KR101712591B1 (en) | Personalized Advertisement Service System Using Sensitiveness-Based User Characteristic Analysis | |
CN106062731A (en) | Systems and methods for using spatial and temporal analysis to associate data sources with mobile devices | |
CN108628866B (en) | Data fusion method and device | |
CN103559636A (en) | Restaurant management system based on cloud computing and intelligent analysis | |
CN102663627A (en) | Personalized recommendation method | |
CN102594905A (en) | Method for recommending social network position interest points based on scene | |
CN103853948A (en) | User identity recognizing and information filtering and searching method and server | |
CN102385727A (en) | ID-value assessment device, ID-value assessment system, and ID-value assessment method | |
KR102000076B1 (en) | Method and server for recommending online sales channel on online shoppingmall intergrated management system | |
CN102033883A (en) | Method, device and system for improving data transmission speed of website | |
CN102663626A (en) | Collaborative filtering recommended method based on provincial characteristics | |
CN107801202A (en) | A kind of user's portrait method based on WiFi accesses | |
EP2518680A1 (en) | Location based consumer profiling | |
CN113454669A (en) | Characterizing a place by user visited features | |
CN102164153A (en) | Method and system for generating electronic map of mobile terminal | |
CN103593764A (en) | A service and location record system based on android cell phones |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140723 |