WO2018076695A1 - Système de recommandation intelligente et procédé de recommandation intelligente - Google Patents

Système de recommandation intelligente et procédé de recommandation intelligente Download PDF

Info

Publication number
WO2018076695A1
WO2018076695A1 PCT/CN2017/087060 CN2017087060W WO2018076695A1 WO 2018076695 A1 WO2018076695 A1 WO 2018076695A1 CN 2017087060 W CN2017087060 W CN 2017087060W WO 2018076695 A1 WO2018076695 A1 WO 2018076695A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
module
user
recommendation
network device
Prior art date
Application number
PCT/CN2017/087060
Other languages
English (en)
Chinese (zh)
Inventor
韩仁彬
Original Assignee
上海斐讯数据通信技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 上海斐讯数据通信技术有限公司 filed Critical 上海斐讯数据通信技术有限公司
Publication of WO2018076695A1 publication Critical patent/WO2018076695A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location
    • 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

Definitions

  • This application relates to the field of information technology applications, and more particularly to the field of advertising of the Internet/mobile Internet.
  • the key factor to measure the pros and cons of a recommendation system is the accuracy of the recommendation. So the core technical question is how to extract the data, how to mine the user information to analyze its behavior characteristics to understand the user's preferences and potential preferences, and finally recommend the personality accordingly. .
  • the present invention provides a solution to this technical problem from a new perspective.
  • Clustering analysis as an unsupervised machine learning method, refers to how to automatically divide data objects into different clusters for a data object set, so that the same cluster Objects have a high degree of similarity under certain metrics, while data objects in different clusters have low similarities.
  • Cluster analysis is widely used in the frontier fields of machine learning, data mining, speech recognition, image segmentation, business analysis and bioinformatics processing.
  • the traditional clustering algorithm mainly includes five categories: they are based on partitioning clustering algorithm, layer-based clustering algorithm, density-based clustering algorithm, grid-based clustering algorithm and model-based clustering. algorithm.
  • the K-means algorithm is a partition-based clustering algorithm, which is simple and fast, and is known for its efficiency.
  • the original K-means algorithm has some defects: 1) The original algorithm requires the user to give the K value, that is, the number of clusters. This value is mainly derived from experience, so it is difficult to determine the K value; 2) The algorithm is sensitive to the initial clustering center. The advantages and disadvantages of the initial center selection will affect the clustering result and affect the efficiency of the algorithm. 3) The algorithm is sensitive to abnormal data, which will cause the result to fall into the local optimal solution.
  • the recommendation system refers to analyzing the user's behavior characteristics by recording the user's relevant historical data for intelligent recommendation, and is widely used in various fields such as e-commerce, content-based media, life service, and search. For example, an e-commerce website evaluates a user's browsing data and purchase records to judge their interests and economic ability to recommend products that they may like.
  • the location data records the user's historical location trajectory, which reflects the user's behavior patterns and living habits to some extent.
  • the data collected by the existing recommendation system is not comprehensive. Most of them collect relevant data from their own platforms for mining analysis. For example, the news site extracts and analyzes the user history browsing data, and the catering APP extracts and analyzes the user's catering records and related. . Relatively speaking, most current location data services only utilize the visualization of the trajectory data itself, that is, provide a wide range of services (catering, entertainment, travel) from the user's current location.
  • the present invention deeply analyzes the potential value of the location data from the perspective of location data, and provides a complete set of solutions for the data mining to improve the recommendation system and improve the accuracy of the recommendation.
  • the present invention is directed to the above problems, and the present invention is achieved by the following technical solutions:
  • An intelligent recommendation method comprising the following steps:
  • S400 screening and classifying a mass of the basic information and behavior activity information of the user
  • S500 Send corresponding recommendation information to the user.
  • the basic information includes: gender, age, occupation, etc.;
  • the behavioral activity information includes: address information, consumption information, time information of staying, and the like.
  • the step S200 includes: S210: input basic information of the user by using an input module of the smart mobile terminal;
  • S220 Acquire, by the navigation positioning module, the time recording module, the electronic payment module, or the electronic sign-in module of the smart mobile terminal, behavior activity information of the user.
  • the step S400 includes: S410: determining, by the trajectory module of the network device, a latitude and longitude of a location of occurrence of a behavior (feature) of the user in different time periods of the day;
  • the trajectory module determines an address name of a location where the behavior activity (feature) occurs according to the latitude and longitude query map database (for example, Baidu map, Gaode map, Google map, 360 map, or self-built map database, etc.) For example: XX Hotel, XX Playground, XX Sports Hall, XX Tea House, XX Bar, XX Bookstore, XX Cinema, XX Museum, XX Health Museum, XX Beauty Salon, XX Supermarket, XX Shopping Mall, XX Tourist Attractions).
  • the latitude and longitude query map database for example, Baidu map, Gaode map, Google map, 360 map, or self-built map database, etc.
  • the step S500 includes at least one of the following steps:
  • the recommendation module of the network device sends the corresponding recommendation information to the user, where the recommendation information is the behavior activity of the user that occurs in the same time period in the history record.
  • Frequency-ordered behavioral activity (feature) related location information is the recommendation information that is the behavior activity of the user that occurs in the same time period in the history record.
  • the system recommends travel information to users who have traveled during this time, and recommends hotel information to users at noon or evening.
  • the recommendation module of the network device sends the corresponding recommendation information to the user, where the recommendation information is sorted by the frequency of the behavior activity of the user around the certain location.
  • the behavior related activity information
  • the system will recommend the product promotion discount information or the surrounding leisure and entertainment information of the shopping mall.
  • the recommendation module of the network device sends the same recommendation information to the user who has the same behavior activity.
  • Information or beauty salon activities send the latest book information, performance information and poetry information to the literary youth, based on individual frequency statistics, according to the statistics of behavior characteristics, the same kind of people (have common behavior characteristics) People) put the same label.
  • the smart recommendation method after the step S200, includes S300: storing a large amount of basic information and behavior activity information of the user.
  • the step S300 includes: S310: filtering a plurality of basic information and behavior activity information of the user by using a data filtering module of the network device;
  • S320 Store, by the data storage of the network device, basic information and behavior activity information of the user that massively filters out redundant information.
  • the invention also provides a recommendation system:
  • An intelligent recommendation system includes an intelligent mobile terminal and a network device; the smart mobile terminal includes an information collection module, a communication module, and a display module;
  • the information collection module is configured to acquire basic information and behavior activity information of the user
  • the communication module is configured to transmit basic information and behavior activity information of the user to the network device;
  • the network device is configured to send recommendation information to the smart mobile terminal
  • the display module is configured to graphically and/or acoustically display the recommendation information.
  • the basic information includes: gender, age, occupation, etc.;
  • the behavior activity information includes: address information, consumption information, time information of staying, and the like.
  • the information collection module includes an input module, a navigation and positioning module, a time recording module, or an electronic payment module.
  • the input module is configured to input basic information
  • the navigation and positioning module is configured to acquire latitude and longitude of the smart mobile terminal
  • the time recording module is configured to determine a dwell time of the smart mobile terminal at the latitude and longitude;
  • the electronic payment module is configured to determine the payment situation of the smart mobile terminal at the latitude and longitude condition
  • It also includes an electronic sign-in module for presenting the electronic sign-in at the time of subsequent consumption, and deducting the amount of the sign-in purchase from the pre-payment.
  • the network device includes a trajectory module, a feature classification module, and a recommendation module,
  • the trajectory module is configured to perform a map query on a latitude and longitude of the behavior information of the user, and determine an address name of the location where the behavior activity occurs and a corresponding time;
  • the feature classification module is configured to encode, analyze, classify, count, and mark the basic information and behavior activity information of the user; form a user number-timestamp-longitude-latitude, and further form a data processing a set of behavioral characteristics of each of the users;
  • the recommendation module is configured to send recommendation information to the corresponding smart mobile terminal of the user according to the result of the categorization, statistics, and marking.
  • the network device further includes a data screening module and a data storage.
  • the data screening module is configured to filter the basic information and behavior activity information of the uploaded user, reduce the amount of data, and remove redundant data.
  • the data storage is configured to store a plurality of basic information and behavior activity information of the user that filters out redundant information;
  • the learning module is configured to re-analyze, re-categorize, re-statistic, and re-mark the growing basic information and behavior activity information of the user to form a behavior feature set of each of the users.
  • the present invention overcomes the technical problem of recommending history-related information to the user by simply accessing the user's access history or consumption history.
  • the present invention overcomes the technical problem of passively only actively obtaining information around the location of the user through the user.
  • the invention gives a powerful recommendation function of the intelligent recommendation system, including actively recommending corresponding information according to the time characteristics of the user behavior activity; and actively recommending the location around the location according to the location characteristics of the user at the time.
  • the invention gives the intelligent recommendation system a data processing function for filtering, sorting and sorting big data.
  • the invention has the advantages of simple use, good operability, strong recommendation information and wide application.
  • FIG. 1 is a schematic structural view of a system according to a first embodiment of the present invention
  • FIG. 2 is a schematic flow chart of a first embodiment of the present invention
  • FIG. 3 is a schematic diagram of a smart mobile terminal module according to a first embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a network device module according to a first embodiment of the present invention.
  • FIG. 5 is a schematic diagram of data flow direction according to a second embodiment of the present invention.
  • Intelligent mobile terminal-100 information collection module-110, input module 112, navigation and positioning module-113, time recording module-114, electronic payment module-115, communication module-120, display module-130; network device-200 module, Data screening module-210, data storage-220, track module-230, feature classification module-240, recommendation module-250.
  • the client/terminal, network device, and trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the client, mobile terminal or network device in the present invention comprises a processor, including a single core processor or a multi-core processor.
  • a processor may also be called one or more microprocessors, central processing units (CPUs), and the like. More specifically, the processor can be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, Or a processor that implements a combination of instruction sets.
  • CISC complex instruction set computing
  • RISC reduced instruction set computing
  • VLIW very long instruction word
  • the processor can also be one or more dedicated processors, such as an application specific integrated circuit (ASIC), field programmable gate array (FPGA), digital signal processor (DSP), network processor, graphics processor, network processor, A communications processor, cryptographic processor, coprocessor, embedded processor, or any other type of logical component capable of processing instructions.
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • DSP digital signal processor
  • graphics processor graphics processor
  • network processor A communications processor
  • cryptographic processor cryptographic processor
  • coprocessor coprocessor
  • embedded processor embedded processor
  • the client, mobile terminal or network device in the present invention includes a memory for storing big data, and may include one or more volatile storage devices such as random access memory (RAM), dynamic RAM (DRAM), synchronous DRAM. (SDRAM), static RAM (SRAM) or other type of storage device.
  • RAM random access memory
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM.
  • SRAM static RAM
  • the memory can store information including sequences of instructions executed by the processor or any other device. For example, a variety of operating systems, device drivers, firmware (eg, input and output base systems or BIOS), and/or executable code and/or data of an application can be loaded into memory and executed by the processor.
  • BIOS input and output base systems
  • the operating system of the client, mobile terminal or network device in the present invention may be any type of operating system, such as Microsoft's Windows, Windows Phone, Apple IOS, Google's Android, and Linux, Unix operating system or other real-time. Or an embedded operating system such as VxWorks.
  • FIG. 2 is a schematic flow chart of a first embodiment of the present invention:
  • An intelligent recommendation method comprising the following steps:
  • S200 acquires basic information and behavior activity information of the user
  • S400 (system) screening and classifying a mass of the basic information and behavior activity information of the user;
  • S500 Send corresponding recommendation information to the user of the system.
  • the smart recommendation method includes: S210: input basic information of the user by using an input module of the smart mobile terminal; the basic information includes: gender, age, occupation, and the like.
  • S220 Acquire, by the navigation positioning module, the time recording module, the electronic payment module, or the electronic sign-in module of the smart mobile terminal, behavior activity information of the user.
  • the behavioral activity information includes: address information, consumption information, time information of staying, and the like.
  • the step S400 includes:
  • S410 determining, by the trajectory module of the network device, a latitude and longitude of a location of occurrence of a behavior (feature) of the user in different time periods of the day;
  • the trajectory module determines an address name of a location where the behavior activity (feature) occurs according to the latitude and longitude query map database (for example, Baidu map, Gaode map, Google map, 360 map, or self-built map database, etc.).
  • the latitude and longitude query map database for example, Baidu map, Gaode map, Google map, 360 map, or self-built map database, etc.
  • the key of the S420 step is to convert the latitude and longitude information represented by the pure number into specific place information, and the relevant behavioral activity characteristics of the user can be obtained only from the specific place information.
  • the key of the S410 step is to attach the time information on the basis of the latitude and longitude information (address name), because the passage of a short time has no meaning for the recommendation system.
  • the user only spends a long time at the location, indicating the user's characteristic preferences for the behavioral activity.
  • the step S500 includes at least one of the following steps:
  • the recommendation module of the network device sends the corresponding recommendation information to the user, where the recommendation information is the behavior activity of the user that occurs in the same time period in the history record.
  • Frequency-ordered behavioral activity (feature) related location information is the recommendation information that is the behavior activity of the user that occurs in the same time period in the history record.
  • the system recommends travel information to users who have traveled during this time, recommend outdoor leisure information to users on weekends, and recommend hotel information to users at noon or evening.
  • the recommendation module of the network device sends the corresponding recommendation information to the user, where the recommendation information is sorted by the frequency of the behavior activity of the user around the certain location.
  • the behavior related activity information
  • the system will recommend the product promotion discount information or the surrounding leisure and entertainment information of the shopping mall.
  • the recommendation module of the network device sends the same recommendation information to the user who has the same behavior activity.
  • the smart recommendation method after the step S200, includes S300: (system) stores a large amount of basic information and behavior activity information of the user.
  • the step S300 includes: S310: filtering a plurality of basic information and behavior activity information of the user by using a data filtering module of the network device;
  • S320 Store, by the data storage of the network device, basic information and behavior activity information of the user that massively filters out redundant information.
  • FIG. 1 is a schematic structural diagram of a system according to a first embodiment of the present invention:
  • An intelligent recommendation system includes an intelligent mobile terminal 100 and a network device 200; the smart mobile terminal 100 includes an information collection module 110, a communication module 120, and a display module 130;
  • the information collection module 110 is configured to acquire basic information and behavior activity information of the user;
  • the communication module 120 is configured to transmit basic information and behavior activity information of the user to the network device;
  • the network device 200 is configured to send recommendation information to the smart mobile terminal
  • the display module 130 is configured to display the recommendation information in a graphical and/or acoustic manner.
  • the display screen sends warning information in a graphical display manner; the speaker sends an early warning message in a voice manner.
  • FIG. 3 is a schematic diagram of a smart mobile terminal module according to a first embodiment of the present invention.
  • the information recommendation module 110 includes an input module 112, a navigation and positioning module 113, a time recording module 114, or an electronic device.
  • Payment module 115 is a schematic diagram of a smart mobile terminal module according to a first embodiment of the present invention.
  • the information recommendation module 110 includes an input module 112, a navigation and positioning module 113, a time recording module 114, or an electronic device.
  • Payment module 115 payment module 115,
  • the input module 112 is configured to input basic information; the basic information includes: gender, age, occupation, and the like; and the behavior activity information includes: address information, consumption information, time information of staying, and the like.
  • the navigation and positioning module 113 is configured to acquire the latitude and longitude of the user's intelligent mobile terminal; the navigation and positioning module includes a GPS system sub-module, a Galileo system sub-module, a GLONASS system sub-module, or a Beidou system sub-module.
  • the time recording module 114 is configured to determine a dwell time of the smart mobile terminal at the latitude and longitude;
  • the electronic payment module 115 is configured to determine a payment situation of the smart mobile terminal in the latitude and longitude;
  • It also includes an electronic sign-in module for presenting the electronic sign-in at the time of subsequent consumption, and deducting the amount of the sign-in purchase from the pre-payment.
  • FIG. 4 is a schematic diagram of a network device module according to a first embodiment of the present invention.
  • the smart recommendation system includes a trajectory module 230, a feature classification module 240, and a recommendation module 250.
  • the trajectory module 230 is configured to perform latitude and longitude on the behavior information of the user a map query to determine an address name of the place where the behavior activity occurs and a corresponding time;
  • the feature classification module 240 is configured to encode, analyze, classify, count, and mark a plurality of basic information and behavior activity information of the user; form a user number-timestamp-longitude-latitude, and further form each of the Describe the user's behavioral feature set; filtering, analyzing, mining, and classifying big data to provide a technical basis for subsequent extraction of classification features and recommendation of corresponding information to corresponding people;
  • the recommendation module 250 is configured to send recommendation information to the corresponding smart mobile terminal of the user according to the result of the classification, statistics, and marking.
  • the smart recommendation system further includes a data filtering module 210 and a data storage 220.
  • the data screening module 210 is configured to filter the uploaded basic information and behavior activity information of the user; reduce the amount of data, and remove redundant data.
  • the data storage 220 is configured to store a large amount of basic information and behavior activity information of the user that filters out redundant information;
  • the network device further includes a learning module for reanalysing, reclassifying, re-stating, and re-marking the growing basic information and behavioral activity information of the user to form a behavior feature set of each of the users.
  • the system provided in this embodiment is composed of four large blocks.
  • the user's historical trajectory is composed of time-continuous location points.
  • the system's server needs to receive and process data at a very high frequency (for example, once every 10 seconds), the amount of users accumulated per day * the amount of user data, Even T-levels can be reached, so massive amounts of big data are stored in data store 220, a distributed system infrastructure consisting of Hadoop.
  • the system's solution to big data The main solution is to proceed from the following two aspects:
  • FIG. 5 is a schematic diagram of data flow direction according to a second embodiment of the present invention.
  • the data screening module 210 uses the spark streaming distributed real-time data processing engine to receive and process data, load balance the server, and make the system real-time.
  • Location data itself is characterized by redundancy and repeatability. For example, if a user can rest for more than a few hours at night, the data in this time period is highly repetitive, and there is a need for screening and culling in terms of data storage, communication, and processing. That is to say, the location data is clustered, and the representative location data is selected, which may be referred to as the user's trajectory feature point.
  • the trajectory module 230 calculates that the difference between the geographic location data represents the distance (the calculation method is the squared difference formula), and according to this feature, the K-Means clustering algorithm is adopted, and the clustering is based on the square difference being smaller than the K value (K value according to the data)
  • the scale of the quantity is dynamically adjusted under the two factors of whether the trajectory feature points remain representative and server performance after balanced clustering. According to the above, a trajectory feature point set (referred to as a feature data set) of the user capable of embodying the user behavior feature is obtained.
  • the machine learning algorithm applied by the feature classification module 240 is an item-based collaborative filtering algorithm (collaborative filtering is generally divided into user-based and item-based).
  • collaborative filtering is generally divided into user-based and item-based.
  • the reason is that the item items extracted by the data set are relatively stable in scale, and the number of users is constantly increasing. Using this algorithm in accordance with the characteristics of the recommended system can reduce the overhead of the system.
  • the format of the feature dataset is user number-timestamp-longitude-latitude (the location is to be combined with the address name).
  • the POI of the corresponding location is obtained from the location data, and the location feature is extracted according to the POI, and is used to analyze the user's life trajectory (time + location) and habit hobbies (behavior frequency, time + behavior, location + behavior).
  • This module gets a set of behavioral characteristics for each user.
  • Recommendation Module 250 the key to making recommendations is to recommend the right project at the right time.
  • the process is to first analyze the set of behavioral characteristics, starting from three points,
  • the first point requests the POI information of the location according to the current location information of the user, matches the behavior feature set of the user, and filters out the first few recommendations with high matching degree.
  • the second point analyzes the behavior of the current time frequency in the user history according to the behavior feature set, and recommends to the user.
  • the above two points are the analysis results starting from the user's own preferences.
  • the third point is to discover the potential hobbies of users by comparing the behavior characteristics of different users, and the users with higher similarity match each other. For example, user A and user B have similar behavioral feature sets, that is, they have common interests, so the system classifies them as similar people. When recommending user A, they can search for the same behavioral feature set. A project different from A's behavioral feature set is recommended to User A. That is to recommend to A a project that he may like but still do not know, that is, potential hobbies. The theoretical premise is that similar users are more likely to agree on an unknown behavior.
  • a new direction based on geographic location data and/or time node data service is proposed. Not only the geographical location data and time node data are used from the surface, but the analysis is deeper and deeper, and the value of geographical location data and time node data is improved.
  • the traditional recommendation algorithm adds location data to make the recommendation smarter and more accurate.

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

L'invention concerne un système de recommandation intelligente et un procédé de recommandation intelligente, le procédé comprenant les étapes suivantes consistant : S200 : à acquérir des informations de base et des informations d'activité comportementale d'un utilisateur ; S300 : à mémoriser les informations de base et les informations d'activité comportementale de l'utilisateur ; S400: à cribler et à classifier la masse d'informations de base et d'informations d'activité comportementale de l'utilisateur ; et S500 : à envoyer à l'utilisateur des informations de recommandation correspondantes.
PCT/CN2017/087060 2016-10-31 2017-06-02 Système de recommandation intelligente et procédé de recommandation intelligente WO2018076695A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610928866.8 2016-10-31
CN201610928866.8A CN106570722B (zh) 2016-10-31 2016-10-31 一种智能推荐系统及智能推荐方法

Publications (1)

Publication Number Publication Date
WO2018076695A1 true WO2018076695A1 (fr) 2018-05-03

Family

ID=58534579

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/087060 WO2018076695A1 (fr) 2016-10-31 2017-06-02 Système de recommandation intelligente et procédé de recommandation intelligente

Country Status (2)

Country Link
CN (1) CN106570722B (fr)
WO (1) WO2018076695A1 (fr)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109344339A (zh) * 2018-09-28 2019-02-15 中山乐心电子有限公司 动态活动信息的发布方法、系统和推荐方法
CN110069468A (zh) * 2019-03-18 2019-07-30 平安普惠企业管理有限公司 一种获取用户需求的方法及装置、电子设备
CN111325504A (zh) * 2020-02-12 2020-06-23 上海东普信息科技有限公司 派件轨迹推荐方法、装置、系统、设备及存储介质
CN111797309A (zh) * 2020-06-19 2020-10-20 一汽奔腾轿车有限公司 一种基于出行模式的车载智能推荐装置及方法
CN111866033A (zh) * 2019-04-24 2020-10-30 北京京东尚科信息技术有限公司 用于发送信息的方法和装置
CN112187623A (zh) * 2020-09-28 2021-01-05 国网浙江省电力有限公司培训中心 一种信息发布管理系统
CN114239707A (zh) * 2021-12-08 2022-03-25 新国脉文旅科技有限公司 一种基于ai智能识别的用户行为分析系统及方法
CN115564500A (zh) * 2022-11-17 2023-01-03 曹县人民医院 大数据管理方法及大数据管理系统

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106570722B (zh) * 2016-10-31 2020-10-30 华讯高科股份有限公司 一种智能推荐系统及智能推荐方法
CN107291888B (zh) * 2017-06-21 2020-12-01 苏州发飚智能科技有限公司 基于机器学习统计模型的入住酒店附近生活推荐系统方法
CN107172590B (zh) * 2017-06-30 2020-07-10 北京奇虎科技有限公司 基于移动终端的活动状态信息处理方法、装置及移动终端
CN107341693A (zh) * 2017-07-06 2017-11-10 中国联合网络通信集团有限公司 旅游用户筛选的方法和旅游用户筛选的系统
CN107481093A (zh) * 2017-07-21 2017-12-15 北京京东尚科信息技术有限公司 个性化店铺预测方法和装置
CN107679905A (zh) * 2017-09-28 2018-02-09 千寻位置网络有限公司 基于用户位置的市场指导方法及系统、服务终端、存储器
CN108198103A (zh) * 2017-12-01 2018-06-22 深圳市科迈爱康科技有限公司 教学方法、装置及计算机可读存储介质
CN108235126B (zh) * 2017-12-15 2020-03-27 北京小度互娱科技有限公司 在视频中插入推荐信息的方法和装置
CN107967358A (zh) * 2017-12-21 2018-04-27 广东欧珀移动通信有限公司 目标地点的推荐方法、装置、存储介质及移动终端
CN109993181B (zh) * 2017-12-29 2021-08-06 中国移动通信集团山西有限公司 异常行为模式识别方法、装置、设备及介质
CN108389268B (zh) * 2018-02-07 2021-10-19 浙江莲荷科技有限公司 缴费方法、系统及设备
CN108876432A (zh) * 2018-05-15 2018-11-23 中国联合网络通信集团有限公司 智能客服的信息处理方法、装置及客服终端
CN109697652A (zh) * 2018-06-29 2019-04-30 京东方科技集团股份有限公司 一种商场的商品推荐方法和服务器
CN109165786A (zh) * 2018-08-31 2019-01-08 深圳春沐源控股有限公司 一种导游方案的规划方法及服务器
CN109636679A (zh) * 2018-12-19 2019-04-16 航天物联网技术有限公司 一种基于人工智能的交互式旅游行程规划方法
CN112528718B (zh) * 2019-10-15 2022-03-01 北京金山顶尖科技股份有限公司 参数大数据解析系统
CN111026934A (zh) * 2019-12-20 2020-04-17 中科寒武纪科技股份有限公司 智能推荐方法及相关设备
CN111242723B (zh) * 2020-01-02 2020-09-15 平安科技（深圳）有限公司 用户子女情况判断方法、服务器及计算机可读存储介质
CN111190521A (zh) * 2020-04-10 2020-05-22 杭州万知科技有限公司 一种医疗界面的动态调整方法、装置
CN112257776B (zh) * 2020-10-21 2023-07-04 中国联合网络通信集团有限公司 终端推荐方法、系统、计算机设备及存储介质
CN112258126B (zh) * 2020-11-06 2022-03-04 拉扎斯网络科技（上海）有限公司 位置数据的校验方法、装置及计算设备
CN112418758A (zh) * 2020-11-17 2021-02-26 国网电子商务有限公司 一种为货主智能推荐承运商的方法及系统
CN118521437B (zh) * 2024-07-24 2024-09-17 南京信息工程大学 一种基于协同演化多目标算法的跨城旅游规划方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102385636A (zh) * 2011-12-22 2012-03-21 陈伟 一种智能搜索方法和装置
CN104967552A (zh) * 2014-11-12 2015-10-07 腾讯科技（深圳）有限公司 消息推送方法及装置
CN105354196A (zh) * 2014-08-19 2016-02-24 北京羽扇智信息科技有限公司 信息推送方法和信息推送装置
US9280252B1 (en) * 2013-03-08 2016-03-08 Allstate Insurance Company Configuring an application task list of an application based on previous selections of application tasks
CN105975641A (zh) * 2016-07-15 2016-09-28 合网络技术（北京）有限公司 视频推荐方法及装置
CN106570722A (zh) * 2016-10-31 2017-04-19 上海斐讯数据通信技术有限公司 一种智能推荐系统及智能推荐方法
CN106656741A (zh) * 2016-09-30 2017-05-10 北京奇虎科技有限公司 一种信息推送方法和系统

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103596128B (zh) * 2012-08-16 2019-02-22 腾讯科技（深圳）有限公司 一种信息提供方法、装置、系统及移动终端
CN105357232A (zh) * 2014-08-09 2016-02-24 星际空间（天津）科技发展有限公司 一种基于位置感知的信息推送系统、方法
CN104239466A (zh) * 2014-09-02 2014-12-24 百度在线网络技术（北京）有限公司 向用户推荐项目的方法、装置及设备
CN105989127A (zh) * 2015-02-15 2016-10-05 阿里巴巴集团控股有限公司 一种进行信息推送的方法、装置与系统
CN104796468A (zh) * 2015-04-14 2015-07-22 蔡宏铭 实现同行人即时通讯及同行信息共享的方法和系统
CN105357637B (zh) * 2015-10-28 2019-06-11 同济大学 一种位置和行为信息预测系统及方法
CN105740347A (zh) * 2016-01-25 2016-07-06 四川长虹电器股份有限公司 基于gps的用户信息采集与行为分析方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102385636A (zh) * 2011-12-22 2012-03-21 陈伟 一种智能搜索方法和装置
US9280252B1 (en) * 2013-03-08 2016-03-08 Allstate Insurance Company Configuring an application task list of an application based on previous selections of application tasks
CN105354196A (zh) * 2014-08-19 2016-02-24 北京羽扇智信息科技有限公司 信息推送方法和信息推送装置
CN104967552A (zh) * 2014-11-12 2015-10-07 腾讯科技（深圳）有限公司 消息推送方法及装置
CN105975641A (zh) * 2016-07-15 2016-09-28 合网络技术（北京）有限公司 视频推荐方法及装置
CN106656741A (zh) * 2016-09-30 2017-05-10 北京奇虎科技有限公司 一种信息推送方法和系统
CN106570722A (zh) * 2016-10-31 2017-04-19 上海斐讯数据通信技术有限公司 一种智能推荐系统及智能推荐方法

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109344339A (zh) * 2018-09-28 2019-02-15 中山乐心电子有限公司 动态活动信息的发布方法、系统和推荐方法
CN109344339B (zh) * 2018-09-28 2022-03-18 中山乐心电子有限公司 动态活动信息的发布方法、系统和推荐方法
CN110069468A (zh) * 2019-03-18 2019-07-30 平安普惠企业管理有限公司 一种获取用户需求的方法及装置、电子设备
CN111866033A (zh) * 2019-04-24 2020-10-30 北京京东尚科信息技术有限公司 用于发送信息的方法和装置
CN111866033B (zh) * 2019-04-24 2024-04-12 北京京东尚科信息技术有限公司 用于发送信息的方法和装置
CN111325504A (zh) * 2020-02-12 2020-06-23 上海东普信息科技有限公司 派件轨迹推荐方法、装置、系统、设备及存储介质
CN111797309A (zh) * 2020-06-19 2020-10-20 一汽奔腾轿车有限公司 一种基于出行模式的车载智能推荐装置及方法
CN111797309B (zh) * 2020-06-19 2024-04-16 一汽奔腾轿车有限公司 一种基于出行模式的车载智能推荐装置及方法
CN112187623A (zh) * 2020-09-28 2021-01-05 国网浙江省电力有限公司培训中心 一种信息发布管理系统
CN112187623B (zh) * 2020-09-28 2022-07-22 国网浙江省电力有限公司培训中心 一种信息发布管理系统
CN114239707A (zh) * 2021-12-08 2022-03-25 新国脉文旅科技有限公司 一种基于ai智能识别的用户行为分析系统及方法
CN115564500A (zh) * 2022-11-17 2023-01-03 曹县人民医院 大数据管理方法及大数据管理系统

Also Published As

Publication number Publication date
CN106570722B (zh) 2020-10-30
CN106570722A (zh) 2017-04-19

Similar Documents

Publication Publication Date Title
WO2018076695A1 (fr) Système de recommandation intelligente et procédé de recommandation intelligente
US10841743B2 (en) Branching mobile-device to system-namespace identifier mappings
US11809465B2 (en) Matching anonymized user identifiers across differently anonymized data sets
US11762818B2 (en) Apparatus, systems, and methods for analyzing movements of target entities
Hu et al. A graph-based approach to detecting tourist movement patterns using social media data
WO2016206196A1 (fr) Procédé et dispositif d'obtention d'informations d'attributs d'utilisateur, et serveur
Chen et al. Assessing destination satisfaction by social media: An innovative approach using Importance-Performance Analysis
US9483498B2 (en) Apparatus and method for profiling users
McKenzie et al. How where is when? On the regional variability and resolution of geosocial temporal signatures for points of interest
US20160110381A1 (en) Methods and systems for social media-based profiling of entity location by associating entities and venues with geo-tagged short electronic messages
JP2019508766A (ja) 地理的エリアのヒートマップを生成するシステム、方法、およびデバイス
Gong et al. Crowd characterization for crowd management using social media data in city events
Falcone et al. What is this place? Inferring place categories through user patterns identification in geo-tagged tweets
Daggitt et al. Tracking urban activity growth globally with big location data
CN105894089A (zh) 一种征信模型的建立方法、征信确定方法及对应装置
Peng et al. Perceiving Beijing’s “city image” across different groups based on geotagged social media data
WO2017157184A1 (fr) Procédé et dispositif pour déterminer des informations d'attribut d'un emplacement géographique
JP2020537252A (ja) 類似のモバイル装置を予測するためのシステムと方法
KR20210065773A (ko) 빅데이터 기반의 감성정보 분석평가 시스템 및 그 구동방법
Kotzias et al. Addressing the Sparsity of Location Information on Twitter.
Nuzir et al. Dynamic Land-Use Map Based on Twitter Data.
Hladík et al. Spatial-temporal analysis of retail and services using Facebook Places data: A case study in Brno, Czech Republic
Graells-Garrido et al. Measuring the local complementarity of population, amenities and digital activities to identify and understand urban areas of interest
McKenzie et al. Uncovering spatiotemporal biases in place-based social sensing
Mukhina et al. Spatiotemporal filtering pipeline for efficient social networks data processing algorithms

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17864665

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17864665

Country of ref document: EP

Kind code of ref document: A1