WO2015109902A1 - Procédé, dispositif et appareil de traitement d'informations personnalisées, et support d'informations non volatil - Google Patents

Procédé, dispositif et appareil de traitement d'informations personnalisées, et support d'informations non volatil Download PDF

Info

Publication number
WO2015109902A1
WO2015109902A1 PCT/CN2014/093941 CN2014093941W WO2015109902A1 WO 2015109902 A1 WO2015109902 A1 WO 2015109902A1 CN 2014093941 W CN2014093941 W CN 2014093941W WO 2015109902 A1 WO2015109902 A1 WO 2015109902A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
client
class
personalized information
sent
Prior art date
Application number
PCT/CN2014/093941
Other languages
English (en)
Chinese (zh)
Inventor
陈晓昕
吴先超
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Publication of WO2015109902A1 publication Critical patent/WO2015109902A1/fr

Links

Images

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
    • 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
    • G06F16/903—Querying

Definitions

  • the present invention relates to input method technology, and in particular, to a method, device, device and non-volatile computer storage medium for processing personalized information.
  • the input method refers to the encoding method used to input various characters into the terminal.
  • the client of the input method software can provide a candidate term matching the input information associated with the input behavior of the user according to the user input behavior, so that the user can perform the upper screen selection.
  • the prior art provides a technical solution that can only provide candidate terms that match the input information associated with the user input behavior, resulting in reduced flexibility in the processing of user input behavior.
  • aspects of the present invention provide a method, apparatus, and apparatus for processing personalized information and a non-volatile computer storage medium for improving the flexibility of processing of user input behavior.
  • An aspect of the present invention provides a method for processing personalized information, including:
  • the shared resource is sent to users in each of the classes.
  • the personalized information includes at least one of resource information and user attribute information of the client.
  • the resource information of the client includes at least one of the following information:
  • the function plugin for the client is the function plugin for the client.
  • the user attribute information includes at least one of the following information:
  • the age of the user is the age of the user.
  • the shared resource is sent to other clients than the client corresponding to the users in each class.
  • Another aspect of the present invention provides a processing apparatus for personalized information, including:
  • a receiving unit configured to receive personalized information related to user input behavior sent by at least two clients
  • a clustering unit configured to cluster users corresponding to the at least two clients according to the personalized information to obtain at least one class
  • An obtaining unit configured to obtain, according to the personalized information sent by the client corresponding to the user in each class, the shared resource of each class;
  • a sending unit configured to send the shared resource to a user in each of the classes.
  • the personalized information received by the receiving unit includes at least one of resource information and user attribute information of the client.
  • the resource information of the client includes at least one of the following information:
  • the function plugin for the client is the function plugin for the client.
  • the user attribute information includes at least one of the following information:
  • the age of the user is the age of the user.
  • the shared resource is sent to other clients than the client corresponding to the users in each class.
  • an apparatus comprising:
  • One or more processors are One or more processors;
  • One or more programs the one or more programs being stored in the memory, when executed by the one or more processors:
  • the shared resource is sent to users in each of the classes.
  • a nonvolatile computer storage medium storing one or more programs when the one or more programs are executed by a device causes The device:
  • the shared resource is sent to users in each of the classes.
  • the embodiment of the present invention receives the personalized information related to the user input behavior sent by the at least two clients, and then performs the user corresponding to the at least two clients according to the personalized information.
  • Clustering to obtain at least one class, so that the shared resources of each class are obtained according to the personalized information sent by the client corresponding to the user in each class, and sent to the users in each class
  • the shared resource can analyze the acquired personalized information related to the user input behavior, and then perform personalized resource recommendation to the user according to the analyzed result, thereby improving the flexibility of processing the user input behavior.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the purpose of the personalized push can be effectively improved.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the utilization rate of the personalized information related to the user input behavior can be effectively improved.
  • FIG. 1 is a schematic flowchart of a method for processing personalized information according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of a device for processing personalized information according to another embodiment of the present invention.
  • terminals involved in the embodiments of the present invention may include, but are not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and a personal computer (Personal Computer, PC). ), MP3 player, MP4 player, etc.
  • PDA personal digital assistant
  • PC Personal Computer
  • FIG. 1 is a schematic flowchart of a method for processing personalized information according to an embodiment of the present invention, as shown in FIG. 1 .
  • execution entities of 101 to 104 may be push devices, and may be located in a server on the network side for online push.
  • the client may be an input method application installed on the terminal, or may be a webpage of the browser, as long as the objective existence form of the input behavior of the user can be realized, this embodiment can No particular limitation is imposed.
  • the client may be not limited to the input method application installed on the terminal, and may be other applications, such as an instant messaging application, a video application, etc., which is not specifically limited in this embodiment. .
  • each user may have different input habits.
  • each user has a vocabulary collection that he or she prefers to use; or, for example, each user may have his or her own preferred client input style, etc.; or, for example, each user may have different occupations and identities, There will be a collection of vocabulary that you use often;
  • the users corresponding to the at least two clients are clustered according to the personalized information to obtain at least one class.
  • the shared resources of each class are obtained according to the personalized information sent by the client corresponding to the user in each class, and the shared resources are sent to the users in each class, and the shared resources can be
  • the obtained personalized information related to the user input behavior is analyzed, and then the personalized resource recommendation is performed to the user according to the analyzed result, thereby improving the flexibility of the processing of the user input behavior.
  • the personalized information received by performing 101 may include, but is not limited to, at least one of resource information and user attribute information of a client, where This is not particularly limited.
  • the resource information of the client may include, but is not limited to, at least one of the following information:
  • the function plugin for the client is the function plugin for the client.
  • the client's thesaurus may include, but is not limited to, at least one of a learning vocabulary, a custom vocabulary, and a communication vocabulary. Specifically, each vocabulary of the client can be composed of several terms.
  • the learning vocabulary includes the client's upper screen entry.
  • a custom terminology includes user-defined terms.
  • the address book includes the address book imported by the client.
  • the user attribute information includes at least one of the following information:
  • the age of the user is the age of the user.
  • the client obtains the user attribute information, and may adopt each of the prior art.
  • the scheme is not repeated here.
  • the client may obtain the user attribute information according to at least one of the resource information of the client and/or the registration information of the user of the client.
  • various clustering algorithms in the prior art for example, a Kmeans clustering algorithm, etc.
  • the users corresponding to the at least two clients are clustered to obtain at least one class.
  • the clustering algorithm refer to related content in the prior art, and details are not described herein again.
  • users corresponding to the same client such as skin, such as skin can be divided into one class.
  • the user corresponding to the client with the same font can be divided into one class.
  • the user corresponding to the client of the specified number of terms in the thesaurus may be divided into one class.
  • the personalized information sent by the client corresponding to the user in each class may be analyzed and organized to obtain the shared resource of the class. .
  • the specific combining operation sent by the client corresponding to the user in each class may be selectively combined.
  • the personalized information sent by the client corresponding to each user may be directly merged as a shared resource of the class; or, for example, only the personalized information sent by the client corresponding to the partial user may be merged.
  • As a shared resource of the class; or, for example, only the personalized information sent by the client corresponding to one of the users may be selected as the shared resource of the class.
  • the font of the client sent by the client corresponding to user A may be As a shared resource
  • A may also use the font B of the client sent by the client corresponding to the user B as a shared resource, or the font A of the client sent by the client corresponding to the user A, and the user B.
  • the font B of the client sent by the corresponding client is used as a shared resource, which is not limited in this embodiment.
  • the shared resource may be specifically sent to the client corresponding to the user in each class, for example, an input method client .
  • the shared resource may be sent to a client other than the client corresponding to a user in each class. , for example, a browser.
  • the shared resource may be pushed to the user in other manners, and the embodiment does not specifically limit this.
  • the sharing request sent by the client corresponding to the user in each class may be further received; correspondingly, in 104 Specifically, the shared resource may be sent to a user in each class according to the sharing request.
  • a function button may be added in the user interface of the client, and the user may trigger the client to send the sharing request by clicking the function button.
  • the user input behavior is related to
  • the personalized information is further clustered according to the personalized information, and the users corresponding to the at least two clients are clustered to obtain at least one class, so that the client corresponding to the user in each class is sent.
  • Personalized information obtain the shared resources of each class, and send the shared resources to users in each class, and can analyze the acquired personalized information related to the user input behavior, and then according to The results of the analysis provide personalized resource recommendations to the user, thereby increasing the flexibility of the processing of user input behavior.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the purpose of the personalized push can be effectively improved.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the utilization rate of the personalized information related to the user input behavior can be effectively improved.
  • the processing device of the personalized information of the present embodiment may include a receiving unit 21, a clustering unit 22, an obtaining unit 23, and a transmitting unit 24.
  • the receiving unit 21, And a clustering unit 22, configured to cluster the users corresponding to the at least two clients according to the personalized information, where the personalized information related to the user input behavior is sent by the at least two clients.
  • the processing device for personalized information provided in this embodiment may be a push device, and may be located in a server on the network side to perform online push.
  • the client may be an input method application installed on the terminal, or may be a webpage of the browser, as long as the objective existence form of the input behavior of the user can be realized, this embodiment can No particular limitation is imposed.
  • the client may be not limited to the input method application installed on the terminal, and may be other applications, such as an instant messaging application, a video application, etc., which is not specifically limited in this embodiment. .
  • each user may have different input habits.
  • each user has a vocabulary collection that he or she prefers to use; or, for example, each user may have his or her own preferred client input style, etc.; or, for example, each user may have different occupations and identities, There will be a collection of vocabulary that you use often;
  • the receiving unit receives the personalized information related to the user input behavior sent by the at least two clients, and then the clustering unit clusters the users corresponding to the at least two clients according to the personalized information.
  • the obtaining unit is capable of obtaining the shared resources of each class according to the personalized information sent by the client corresponding to the user in each class, and is sent by the sending unit to each class User sends the share
  • the source can analyze the acquired personalized information related to the user input behavior, and then perform personalized resource recommendation to the user according to the analyzed result, thereby improving the flexibility of processing the user input behavior.
  • the personalized information received by the receiving unit 21 may include, but is not limited to, at least one of resource information and user attribute information of the client, and the implementation For example, this is not particularly limited.
  • the resource information of the client may include, but is not limited to, at least one of the following information:
  • the function plugin for the client is the function plugin for the client.
  • the client's thesaurus may include, but is not limited to, at least one of a learning vocabulary, a custom vocabulary, and a communication vocabulary. Specifically, each vocabulary of the client can be composed of several terms.
  • the learning vocabulary includes the client's upper screen entry.
  • a custom terminology includes user-defined terms.
  • the address book includes the address book imported by the client.
  • the user attribute information includes at least one of the following information:
  • the age of the user is the age of the user.
  • the client obtains the user attribute information, and various solutions in the prior art may be used, and details are not described herein again.
  • the client may obtain the user attribute information according to at least one of the resource information of the client and/or the registration information of the user of the client.
  • the clustering unit 22 may specifically use various clustering algorithms in the prior art, for example, a Kmeans clustering algorithm, according to the personalized information.
  • the users corresponding to the at least two clients are clustered to obtain at least one class.
  • the clustering algorithm refer to related content in the prior art, and details are not described herein again.
  • the clustering unit 22 may divide users corresponding to the same client such as skin, such as skin, into one class.
  • the clustering unit 22 may divide the users corresponding to the clients with the same font into one class.
  • the clustering unit 22 may divide the user corresponding to the client of the specified number of terms in the thesaurus into one class.
  • the obtaining unit 23 may specifically analyze and organize the personalized information sent by the client corresponding to the user in each class to obtain the shared resource of the class.
  • the obtaining unit 23 may perform a selective combining operation on the personalized information sent by the client corresponding to the user in each class.
  • the personalized information sent by the client corresponding to each user may be directly merged as a shared resource of the class; or, for example, it is also possible to merge only the personalized information sent by the client corresponding to some users as the shared resource of the class; or, for example, only select the client sent by one of the users. Personalize the information as a shared resource for that class.
  • the obtaining unit 23 can correspond to the user A.
  • the font A of the client sent by the client is used as a shared resource, or the obtaining unit 23 may also use the font B of the client sent by the client corresponding to the user B as a shared resource, or the obtaining unit 23 may also correspond to the user A.
  • the font A of the client sent by the client and the font B of the client sent by the client corresponding to the user B are used as a shared resource, which is not limited in this embodiment.
  • the sending unit 24 may specifically send the shared resource to the client corresponding to the user in each class, for example, an input method client. end.
  • the sending unit 24 may specifically send the sharing to other clients except the client corresponding to users in each class.
  • Resources for example, browsers.
  • the sending unit 24 may specifically push the shared resource to the user in other manners, which is not specifically limited in this embodiment.
  • the receiving unit 21 may further receive a sharing request sent by the client corresponding to the user in each class; correspondingly, Specifically, the sending unit 24 may send the shared resource to a user in each class according to the sharing request.
  • a function button may be added in the user interface of the client, and the user may trigger the sending unit 24 to send the sharing request by clicking the function button.
  • the receiving unit receives the personalized information related to the user input behavior sent by the at least two clients, and then the clustering unit, according to the personalized information, the user corresponding to the at least two clients.
  • the clustering unit performs the personalized information related to the user input behavior sent by the at least two clients.
  • the sending unit sends the The user in the class sends the shared resource, and can analyze the acquired personalized information related to the user input behavior, and then perform personalized resource recommendation to the user according to the analyzed result, thereby improving the processing of the user input behavior.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the purpose of the personalized push can be effectively improved.
  • the shared resources obtained according to the personalized information related to the user input behavior provided by other users can be actively pushed to the user, and the utilization rate of the personalized information related to the user input behavior can be effectively improved.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined. Or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-described integrated unit implemented in the form of a software functional unit can be stored in a computer readable storage medium.
  • the above software functional unit is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to perform the methods of the various embodiments of the present invention. Part of the steps.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

L'invention concerne un procédé, un dispositif et un appareil de traitement d'informations personnalisées, ainsi qu'un support d'informations non volatil. Le procédé consiste : à recevoir des informations personnalisées qui sont associées à des comportements d'entrée d'utilisateur et sont envoyées par au moins deux clients (101) ; puis, selon les informations personnalisées, à grouper des utilisateurs correspondant audits deux clients de façon à obtenir au moins un groupe (102) ; à obtenir une ressource partagée de chaque groupe selon les informations personnalisées envoyées par les clients correspondant aux utilisateurs dans chaque groupe (103) ; et à envoyer la ressource partagée aux utilisateurs dans chaque groupe (104), de telle sorte qu'une analyse peut être réalisée sur les informations personnalisés acquises associées à des comportements d'entrée d'utilisateur, et des ressources personnalisées peuvent être recommandées aux utilisateurs selon un résultat d'analyse, permettant ainsi d'améliorer la flexibilité du traitement des comportements d'entrée d'utilisateur.
PCT/CN2014/093941 2014-01-26 2014-12-16 Procédé, dispositif et appareil de traitement d'informations personnalisées, et support d'informations non volatil WO2015109902A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410036751.9 2014-01-26
CN201410036751.9A CN103778232A (zh) 2014-01-26 2014-01-26 个性化信息的处理方法及装置

Publications (1)

Publication Number Publication Date
WO2015109902A1 true WO2015109902A1 (fr) 2015-07-30

Family

ID=50570467

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/093941 WO2015109902A1 (fr) 2014-01-26 2014-12-16 Procédé, dispositif et appareil de traitement d'informations personnalisées, et support d'informations non volatil

Country Status (2)

Country Link
CN (1) CN103778232A (fr)
WO (1) WO2015109902A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103778232A (zh) * 2014-01-26 2014-05-07 百度在线网络技术（北京）有限公司 个性化信息的处理方法及装置
CN106446078A (zh) * 2016-09-08 2017-02-22 乐视控股（北京）有限公司 一种信息的推荐方法和推荐装置
CN107395695B (zh) * 2017-07-05 2020-09-01 上海精数信息科技有限公司 业务推送方法及装置
CN109743323B (zh) * 2019-01-08 2022-06-28 中国石油大学(华东) 一种基于区块链技术的资源共享策略

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398834A (zh) * 2007-09-29 2009-04-01 北京搜狗科技发展有限公司 一种针对输入信息的处理方法和装置及一种输入法系统
CN101420313A (zh) * 2007-10-22 2009-04-29 北京搜狗科技发展有限公司 一种针对客户端用户群进行聚类的方法和系统
CN101470732A (zh) * 2007-12-26 2009-07-01 北京搜狗科技发展有限公司 一种辅助词库的生成方法和装置
EP2677758A1 (fr) * 2012-06-19 2013-12-25 Thomson Licensing Système de recommandation de contenu d'ouverture conceptuelle
CN103778232A (zh) * 2014-01-26 2014-05-07 百度在线网络技术（北京）有限公司 个性化信息的处理方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101398834A (zh) * 2007-09-29 2009-04-01 北京搜狗科技发展有限公司 一种针对输入信息的处理方法和装置及一种输入法系统
CN101420313A (zh) * 2007-10-22 2009-04-29 北京搜狗科技发展有限公司 一种针对客户端用户群进行聚类的方法和系统
CN101470732A (zh) * 2007-12-26 2009-07-01 北京搜狗科技发展有限公司 一种辅助词库的生成方法和装置
EP2677758A1 (fr) * 2012-06-19 2013-12-25 Thomson Licensing Système de recommandation de contenu d'ouverture conceptuelle
CN103778232A (zh) * 2014-01-26 2014-05-07 百度在线网络技术（北京）有限公司 个性化信息的处理方法及装置

Also Published As

Publication number Publication date
CN103778232A (zh) 2014-05-07

Similar Documents

Publication Publication Date Title
JP6967612B2 (ja) 情報検索方法、装置及びシステム
US10229684B2 (en) Method, interaction device, server, and system for speech recognition
US11361045B2 (en) Method, apparatus, and computer-readable storage medium for grouping social network nodes
JP2018036621A (ja) 情報入力方法および装置
WO2017084541A1 (fr) Procédé et appareil pour envoyer une image d'expression pendant une session d'appel
US11374884B2 (en) Managing and displaying online messages along timelines
US10467308B2 (en) Method and system for processing social media data for content recommendation
CN108432200B (zh) 用于保护和控制对私密个人信息的访问的方法
US10002127B2 (en) Connecting people based on content and relational distance
JP5961320B2 (ja) ソーシャル・メデイアにおけるユーザの分類方法、コンピュータ・プログラム及びコンピュータ
WO2018145577A1 (fr) Procédé et dispositif de recommandation d'expression faciale
JP6161227B2 (ja) 入力リソースプッシュ方法、システム、コンピューター記憶媒体及びデバイス
US11392272B2 (en) Group-based communication system and apparatus configured to render suggested graphical objects
WO2017206376A1 (fr) Procédé de recherche, dispositif de recherche et support de stockage informatique non volatil
WO2015109902A1 (fr) Procédé, dispositif et appareil de traitement d'informations personnalisées, et support d'informations non volatil
WO2015120713A1 (fr) Procédé et appareil d'acquisition d'une entrée, support de stockage informatique et dispositif associé
CN112929253B (zh) 一种虚拟形象交互方法和装置
WO2015149321A1 (fr) Moteur numérique personnel d'autonomisation de l'utilisateur et son procédé d'exploitation
CN112532507B (zh) 用于呈现表情图像、用于发送表情图像的方法和设备
US11055375B2 (en) Method of and system for determining a next state for a recommendation block to be displayed in web browser
US11100188B2 (en) Method of and system for selectively presenting a recommendation block in browser application
CN111967599A (zh) 用于训练模型的方法、装置、电子设备及可读存储介质
CN111291184A (zh) 表情的推荐方法、装置、设备及存储介质
CN112307281A (zh) 一种实体推荐方法及装置
US20230281391A1 (en) Systems and methods for biomedical information extraction, analytic generation and visual representation thereof

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: 14879328

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: 14879328

Country of ref document: EP

Kind code of ref document: A1