WO2017016122A1 - 一种信息推送方法及装置 - Google Patents

一种信息推送方法及装置 Download PDF

Info

Publication number
WO2017016122A1
WO2017016122A1 PCT/CN2015/096452 CN2015096452W WO2017016122A1 WO 2017016122 A1 WO2017016122 A1 WO 2017016122A1 CN 2015096452 W CN2015096452 W CN 2015096452W WO 2017016122 A1 WO2017016122 A1 WO 2017016122A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
sent
result
dimension
appeal
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.)
Ceased
Application number
PCT/CN2015/096452
Other languages
English (en)
French (fr)
Inventor
谷铁峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Original Assignee
Baidu Online Network Technology Beijing Co Ltd
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 Baidu Online Network Technology Beijing Co Ltd filed Critical Baidu Online Network Technology Beijing Co Ltd
Priority to JP2017541055A priority Critical patent/JP6853179B2/ja
Priority to KR1020177021661A priority patent/KR102009787B1/ko
Publication of WO2017016122A1 publication Critical patent/WO2017016122A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/335Filtering based on additional data, e.g. user or group profiles
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation

Definitions

  • the present invention relates to the field of computers, and in particular, to an information push method and apparatus.
  • the commonly used information push method can only push information according to keywords input by the user. As long as the keywords input by the user are the same, the pushed information is the same, and the information cannot be pushed for different user needs.
  • the existing information push method cannot push information for different user requirements, which makes the information push accuracy low, and the user finds useful information for a long time, which leads to low push rate of push information and reduces information push. effectiveness.
  • One of the technical problems solved by the present invention is that the existing information push method cannot push information for different user needs.
  • an information pushing method including:
  • an information pushing apparatus including:
  • the information to be sent is pushed by the combination of the search term and the user feature information, so that the personalized personalized service can be performed for different user features, the accuracy of the information push is increased, and the user's personalization is satisfied. demand.
  • FIG. 1 shows a flow chart of an information push method according to an embodiment of the present invention.
  • FIG. 2 shows a specific flowchart of step S140 in the information pushing method according to an embodiment of the present invention.
  • FIG. 3 shows a flow chart of still another information push method according to an embodiment of the present invention.
  • FIG. 4 shows a block diagram of an information push apparatus according to an embodiment of the present invention.
  • FIG. 5 is a block diagram showing a push device 440 in an information push device according to an embodiment of the present invention.
  • Figure 6 shows a block diagram of a push device 440 in yet another information push device in accordance with an embodiment of the present invention.
  • Computer device also referred to as “computer” in the context, is meant an intelligent electronic device that can perform predetermined processing, such as numerical calculations and/or logical calculations, by running a predetermined program or instruction, which can include a processor and The memory is executed by the processor to execute a predetermined process pre-stored in the memory to execute a predetermined process, or is executed by hardware such as an ASIC, an FPGA, a DSP, or the like, or a combination of the two.
  • Computer devices include, but are not limited to, servers, personal computers, notebook computers, tablets, smart phones, and the like.
  • the computer device includes a user device and a network device.
  • the user equipment includes, but is not limited to, a computer, a smart phone, a PDA, etc.
  • the network device includes but is not limited to a single network server, a server group composed of multiple network servers, or a cloud computing based computer Or a cloud composed of a network server, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers.
  • the computer device can be operated separately to implement the present invention, and can also access the network and implement the present invention by interacting with other computer devices in the network.
  • the network in which the computer device is located includes, but is not limited to, the Internet, a wide area network, a metropolitan area network, a local area network, a VPN network, and the like.
  • the user equipment, the network equipment, the network, and the like are merely examples, and other existing or future possible computer equipment or networks, such as those applicable to the present invention, are also included in the scope of the present invention. It is included here by reference.
  • the methods discussed below can be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof.
  • the serial code or code segments can be stored in a machine or computer readable medium such as a storage medium.
  • the processor(s) can perform the necessary tasks.
  • FIG. 1 is a flow chart of an information push method in accordance with one embodiment of the present invention.
  • the information pushing method in this embodiment includes the following steps:
  • S110 Receive a search term input by a user, and obtain user feature information.
  • the user characteristic information may include gender, age, health status, ethnicity, education level (for example: doctor, undergraduate, high school or elementary school, etc.), occupation (for example: chef, journalist or lawyer, etc.) and/or geographical location. Information, etc.
  • the embodiment of the present invention does not specifically limit the manner of obtaining the user feature information, and may be obtained by the user in the form of a questionnaire, or may be obtained according to the browsing record or the login record of the user, as long as the user characteristic information can be obtained.
  • step S120 the search result input by the user is analyzed by means of word segmentation technology and/or part of speech determination, and the result of the appeal is obtained.
  • the embodiment of the present invention does not limit the specific process of obtaining the appeal result according to the search term. As long as you can get the result of the appeal. For example, if the search term entered by the user is “exercise body”, then it is determined to be a fitness-related appeal.
  • a corresponding dimension value is established for each user feature to obtain a dimension result.
  • the dimensional results may be presented and stored in a tabular form, such as the ordinate representing the user feature and the abscissa being the corresponding dimension value.
  • the ordinate is the age
  • the dimension corresponding to the abscissa is the age
  • the ordinate is the education level
  • the dimension corresponding to the abscissa is the corresponding code value or academic mark of the academic qualification
  • the ordinate is the geographic location information
  • the dimension corresponding to the abscissa The value is GPS (Global Positioning System) geographic coordinate information.
  • step S140 may specifically include the following steps:
  • Step S1401 obtaining, according to the appeal result and the dimension result, by a predetermined algorithm Get the first appeal dimension information.
  • the claim result and the dimension result may be subjected to a weighting algorithm to obtain the first appeal dimension information, and the embodiment of the present invention does not specifically limit the predetermined algorithm, as long as the first appeal dimension information obtained according to the predetermined algorithm can reflect the appeal result. And the dimension result, and the information to be sent pushed according to the first appeal dimension information can satisfy the user's search intention.
  • Step S1402 Push the information to be sent to the user according to the first appeal dimension information.
  • the information to be sent in the information repository may be stored in the following two ways:
  • the first storage mode the information to be sent in the information library corresponds to at least one appeal dimension information, and the information to be sent is correspondingly stored with at least one appeal dimension information corresponding thereto.
  • the information 1 is stored corresponding to the appeal dimension information A and B
  • the information 2 is stored corresponding to the appeal dimension information C
  • the information 3 is stored corresponding to the appeal dimension information A and C.
  • each claim dimension information in the information database corresponds to at least one information to be sent, and the appeal dimension information is correspondingly stored with at least one corresponding information to be sent.
  • the appeal dimension information A is stored corresponding to the information 1 and the information 3 to be transmitted
  • the appeal dimension information B is stored corresponding to the information 1 to be transmitted
  • the appeal dimension information C is stored corresponding to the information 2 and the information 3 to be transmitted.
  • the information to be sent stored in the information repository corresponding to the first appeal dimension information is pushed to the user.
  • the push sequence of the information to be sent may be pre-set, or may be randomly pushed, and may be pushed according to the matching degree according to the matching algorithm.
  • the embodiment of the present invention does not specifically limit the setting of the push sequence, as long as the user can pre-search.
  • the information to be sent is displayed to the user promptly and accurately.
  • step S140 may further include the following steps:
  • Step S141 The degree of correlation with the appeal result is within a threshold range, and the information to be sent that is the same as the dimension result is pushed to the user.
  • the storage side of the information to be sent in the information base can include the following two types:
  • each piece of information to be sent in the information library corresponds to at least one dimension result
  • each piece of information to be sent in the information library corresponds to at least one appeal result, and at least one corresponding to the information to be sent
  • the dimension result is stored correspondingly with at least one appeal result.
  • information 1 is stored for women aged 20 years old
  • information 2 is stored for infants and children aged 0-5 years.
  • Information 3 corresponds to fitness, male intellectuals aged 60-80 years old to store.
  • the second storage mode the result of each dimension in the information database corresponds to at least one information to be sent, and each of the appeal results in the information database corresponds to at least one information to be sent, and the dimension result corresponds to at least one to be sent.
  • the information is stored correspondingly, and the appeal result is stored corresponding to at least one information to be sent corresponding thereto.
  • age 20 corresponds to information 1 and information 2
  • age 0-5 corresponds to information 3 and information 4
  • fitness corresponds to information 1 and information 3
  • male corresponds to information 4 and information 5.
  • the specific push process may include the following three methods:
  • a first push process determining, in a repository, a first to-be-sent information set that has a correlation with the appeal result within a threshold range according to a predetermined correlation algorithm; and the first to-be-sent information set
  • the information to be sent having the same dimensional result is pushed to the user. For example, if the search term entered by the user is exercise, then the fitness, gym, square dance and aerobics are all related to exercise, then the information to be sent related to fitness, gym, square dance and aerobics should be determined. In the first set of information to be sent.
  • a second push process determining a second set of information to be sent in the information repository that is the same as the result of the dimension; and determining, in the second set of information to be sent, a result related to the appeal according to a predetermined correlation algorithm
  • the information to be sent whose relevance is within a threshold range is pushed to the user by the determined information to be sent.
  • a third type of pushing process determining, in a repository, a first set of information to be sent that has a correlation with the appeal result within a threshold range according to a predetermined correlation algorithm, and determining a number of the same information in the information base as the dimension result
  • the second set of information to be sent is obtained by intersecting the first set of information to be sent with the second set of information to be sent, and pushing the information to be sent in the intersection to the user.
  • the embodiments of the present invention do not specifically limit related algorithms, and may be configured correspondingly according to different requirements of the user, as long as the requirements of the user can be met.
  • the threshold can also be set according to the different needs of the user.
  • another information pushing method includes the following steps:
  • the dimension result is age: 20 years old, gender: female, geographical location: Haidian Huangzhuang, Zhongguancun, area code and/or latitude and longitude value, and the like.
  • the dimension result further includes: health status: unknown, ethnic: unknown.
  • S340 Determine, in a information base, a first to-be-sent information set that has a correlation with the appeal result within a threshold range according to a predetermined correlation algorithm; and determine a second information set to be sent that is the same as the dimension result in the information base. And intersecting the first set of information to be sent with the second set of information to be sent, and pushing the information to be sent in the intersection to the user.
  • the first set of information to be sent may be a fitness-related information collection related to the gym related to the gym; the second set of information to be sent may be age 20, gender, and geographic location.
  • the corresponding stored information further includes information such as a health condition and an ethnic dimension, as long as the information in which the age 20, the gender is female, and the geographic location is the content corresponding to the Haidian Huangzhuang, Zhongguancun, area code, and/or latitude and longitude values is satisfied.
  • the collection is fine.
  • the keyword input by the girl of age 19 is "sports", then she definitely wants to know some knowledge related to slimming exercise; and the keyword input by the 60-year-old male is "sports". , then he definitely wants to know some with the elderly Sports-related knowledge shows that users of different ages or genders do not have the same information to search for under the same keyword. Therefore, in this embodiment, the information to be sent is pushed by the combination of the search term and the user feature information, and the personalized personalized service can be performed for different user features, thereby increasing the accuracy of the information push and satisfying the personalized needs of the user. .
  • the information pushing device in this embodiment may be disposed on the network device side or the cloud device side, and includes the following devices:
  • a device for receiving a search term input by a user and acquiring user feature information (hereinafter referred to as "receiving device” 410);
  • first analysis device Means for obtaining a claim result based on the search term (hereinafter referred to as "first analysis device") 420;
  • Means for obtaining a dimension result according to the user feature information (hereinafter referred to as "second analysis device") 430;
  • Means for pushing information to be transmitted to the user (hereinafter referred to as "pushing device") 440 according to the result of the appeal and the result of the dimension.
  • the user characteristic information may include gender, age, health status, ethnicity, education level (for example: doctor, undergraduate, high school or elementary school, etc.), occupation (for example: chef, journalist or lawyer, etc.) and/or geography. Location information, etc.
  • the embodiment of the present invention does not specifically limit the manner of obtaining the user feature information, and may be obtained by the user in the form of a questionnaire, or may be obtained according to the browsing record or the login record of the user, as long as the user characteristic information can be obtained.
  • the search result is performed according to the splitting process and/or the part-of-speech judgment of the search word input by the user, and the appeal result is obtained.
  • the embodiment of the present invention does not limit the specific process of obtaining the appeal result according to the search term. As long as you can get the result of the appeal. For example, if the search term entered by the user is “exercise body”, then it is determined to be a fitness-related appeal.
  • a corresponding dimension value is established for each user feature to obtain a dimension result.
  • dimension results can be presented in tabular form and Storage, for example, the ordinate represents the user feature and the abscissa is the corresponding dimension value.
  • the ordinate is the age, the dimension corresponding to the abscissa is the age; the ordinate is the education level, the dimension corresponding to the abscissa is the corresponding code value or academic mark of the academic qualification; the ordinate is the geographic location information, and the dimension corresponding to the abscissa
  • the value is GPS geographic coordinate information.
  • the pushing device 440 may specifically include the following devices:
  • Means for obtaining first appeal dimension information by a predetermined algorithm according to the appeal result and the dimension result.
  • the claim result and the dimension result may be subjected to a weighting algorithm to obtain the first appeal dimension information, and the embodiment of the present invention does not specifically limit the predetermined algorithm, as long as the first appeal dimension information obtained according to the predetermined algorithm can reflect the appeal result. And the dimension result, and the information to be sent pushed according to the first appeal dimension information can satisfy the user's search intention.
  • first transmitting device 4402 Means for pushing information to be transmitted to the user (hereinafter referred to as "first transmitting device") 4402 according to the first claim dimension information.
  • the information pushing apparatus in the embodiment of the present invention may further include:
  • first storage device 4501 for storing at least one appeal dimension information in the information to be sent in the information library, and storing the information to be sent corresponding to at least one appeal dimension information corresponding thereto.
  • second storage device 4502 for storing each of the appeal dimension information in the information database corresponding to at least one piece of information to be sent, and storing the appeal dimension information corresponding to at least one piece of information to be transmitted.
  • the information to be sent stored in the information repository corresponding to the first appeal dimension information is pushed to the user.
  • the push sequence of the information to be sent may be pre-set, or may be randomly pushed, and may be pushed according to the matching degree according to the matching algorithm.
  • the embodiment of the present invention does not specifically limit the setting of the push sequence, as long as the user can pre-search.
  • the information to be sent is displayed to the user promptly and accurately.
  • the pushing device 440 is specifically The following devices can be included:
  • second transmitting device 441 for transmitting information to be sent to the user that is related to the result of the appeal within a threshold range and having the same result as the dimension.
  • the information pushing device in the embodiment of the present invention may further include:
  • third storage device corresponding to at least one dimension result of each piece of information to be sent in the information library, and corresponding to at least one appeal result of each piece of information to be sent in the information base, and at least one dimension result corresponding to the information to be sent and at least A device for performing corresponding storage (hereinafter referred to as "third storage device”) 4503.
  • each of the dimension results in the information database corresponding to at least one information to be sent, and corresponding to each of the appeal results in the information database, at least one information to be sent, and storing the dimension result corresponding to at least one information to be sent corresponding thereto
  • a device hereinafter referred to as "fourth storage device” that stores the request result in correspondence with at least one of the information to be transmitted corresponding thereto.
  • the specific sending process of the second sending device 441 includes the following three methods:
  • a first push process determining, in a repository, a first to-be-sent information set that has a correlation with the appeal result within a threshold range according to a predetermined correlation algorithm; and the first to-be-sent information set
  • the information to be sent having the same dimensional result is pushed to the user. For example, if the search term entered by the user is exercise, then the fitness, gym, square dance and aerobics are all related to exercise, then the information to be sent related to fitness, gym, square dance and aerobics should be determined. In the first set of information to be sent.
  • a second push process determining a second set of information to be sent in the information repository that is the same as the result of the dimension; and determining, in the second set of information to be sent, a result related to the appeal according to a predetermined correlation algorithm
  • the information to be sent whose relevance is within a threshold range is pushed to the user by the determined information to be sent.
  • a third push process determining and describing in the information base according to a predetermined correlation algorithm Determining, by the first set of information to be sent, the information to be sent in the threshold range, determining a second information set to be sent in the information database that is the same as the dimension result; and sending the first information to be sent and the second to be sent
  • the information set is taken as an intersection, and the information to be sent in the intersection is pushed to the user.
  • the embodiments of the present invention do not specifically limit related algorithms, and may be configured correspondingly according to different requirements of the user, as long as the requirements of the user can be met.
  • the threshold can also be set according to the different needs of the user.
  • the information pushing method and device pushes the information to be sent by combining the search term with the user feature information, and can perform targeted and personalized information push according to the feature information of the user such as gender and age.
  • Service increase the accuracy of service results, can accurately and personalized services for different user characteristics, increase the accuracy of information push, meet the personalized needs of users, and improve the user experience.
  • the search words and the user's characteristic information are used to push the information, which further improves the accuracy of pushing for different user requirements and improves the push efficiency.
  • the present invention can be implemented in software and/or a combination of software and hardware.
  • the various devices of the present invention can be implemented using an application specific integrated circuit (ASIC) or any other similar hardware device.
  • the software program of the present invention may be executed by a processor to implement the steps or functions described above.
  • the software program (including related data structures) of the present invention can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like.
  • some of the steps or functions of the present invention may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种信息推送方法及装置,其中的方法包括:接收用户输入的搜索词,并获取用户特征信息(S110);根据所述搜索词得到诉求结果(S120);根据所述用户特征信息得到维度结果(S130);根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户(S140)。该方法通过搜索词与用户特征信息结合的方式将待发送的信息进行推送,故可以针对不同的用户特征进行精准的个性化服务,增加了信息推送的准确性,满足了用户的个性化需求。

Description

一种信息推送方法及装置
相关申请的交叉引用
本申请请求于2015年7月29日提交的申请号为201510456927.0的中国专利申请的优先权,该中国专利申请的内容以引用方式被完整包含于此。
技术领域
本发明涉及计算机领域,尤其涉及一种信息推送方法及装置。
背景技术
目前常用的信息推送方法仅能根据用户输入的关键词进行信息的推送,只要用户输入的关键词相同,那么推送的信息就都相同,其并不能针对不同的用户需求进行信息的推送。现有的信息推送方法并不能针对不同的用户需求进行信息的推送,使得信息推送精准度低,用户找到对其有用的信息耗时长,从而导致推送信息的点展率低,降低了信息推送的效率。
发明内容
本发明解决的技术问题之一是现有的信息推送方法并不能针对不同的用户需求进行信息的推送。
根据本发明一方面的一个实施例,提供了一种信息推送方法,包括:
接收用户输入的搜索词,并获取用户特征信息;
根据所述搜索词得到诉求结果;
根据所述用户特征信息得到维度结果;
根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户。
根据本发明另一方面的一个实施例,提供了一种信息推送装置,包括:
用于接收用户输入的搜索词,并获取用户特征信息的装置;
用于根据所述搜索词得到诉求结果的装置;
用于根据所述用户特征信息得到维度结果的装置;
用于根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户的装置。
由于本实施例通过搜索词与用户特征信息结合的方式将待发送的信息进行推送,故可以针对不同的用户特征进行精准的个性化服务,增加了信息推送的准确性,满足了用户的个性化需求。
本领域普通技术人员将了解,虽然下面的详细说明将参考图示实施例、附图进行,但本发明并不仅限于这些实施例。而是,本发明的范围是广泛的,且意在仅通过后附的权利要求限定本发明的范围。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述,本发明的其它特征、目的和优点将会变得更明显:
图1示出了根据本发明实施例一信息推送方法的流程图。
图2示出了根据本发明实施例一信息推送方法中步骤S140的具体流程图。
图3示出了根据本发明实施例又一信息推送方法的流程图。
图4示出了根据本发明实施例一信息推送装置的框图。
图5示出了根据本发明实施例一信息推送装置中推送装置440的框图。
图6示出了根据本发明实施例又一信息推送装置中推送装置440的框图。
附图中相同或相似的附图标记代表相同或相似的部件。
具体实施方式
在更加详细地讨论示例性实施例之前应当提到的是,一些示例性实施例被描述成作为流程图描绘的处理或方法。虽然流程图将各项操作描述成顺序的处理,但是其中的许多操作可以被并行地、并发地或者同时实施。此外,各项操作的顺序可以被重新安排。当其操作完成时所述处理可以被终止,但是还可以具有未包括在附图中的附加步骤。所述处理可以对应于方法、函数、规程、子例程、子程序等等。
在上下文中所称“计算机设备”,也称为“电脑”,是指可以通过运行预定程序或指令来执行数值计算和/或逻辑计算等预定处理过程的智能电子设备,其可以包括处理器与存储器,由处理器执行在存储器中预存的存续指令来执行预定处理过程,或是由ASIC、FPGA、DSP等硬件执行预定处理过程,或是由上述二者组合来实现。计算机设备包括但不限于服务器、个人电脑、笔记本电脑、平板电脑、智能手机等。
所述计算机设备包括用户设备与网络设备。其中,所述用户设备包括但不限于电脑、智能手机、PDA等;所述网络设备包括但不限于单个网络服务器、多个网络服务器组成的服务器组或基于云计算(Cloud Computing)的由大量计算机或网络服务器构成的云,其中,云计算是分布式计算的一种,由一群松散耦合的计算机集组成的一个超级虚拟计算机。其中,所述计算机设备可单独运行来实现本发明,也可接入网络并通过与网络中的其他计算机设备的交互操作来实现本发明。其中,所述计算机设备所处的网络包括但不限于互联网、广域网、城域网、局域网、VPN网络等。
需要说明的是,所述用户设备、网络设备和网络等仅为举例,其他现有的或今后可能出现的计算机设备或网络如可适用于本发明,也应包含在本发明保护范围以内,并以引用方式包含于此。
后面所讨论的方法(其中一些通过流程图示出)可以通过硬件、软件、固件、中间件、微代码、硬件描述语言或者其任意组合来实施。当用软件、固件、中间件或微代码来实施时,用以实施必要任务的程 序代码或代码段可以被存储在机器或计算机可读介质(比如存储介质)中。(一个或多个)处理器可以实施必要的任务。
这里所公开的具体结构和功能细节仅仅是代表性的,并且是用于描述本发明的示例性实施例的目的。但是本发明可以通过许多替换形式来具体实现,并且不应当被解释成仅仅受限于这里所阐述的实施例。
应当理解的是,虽然在这里可能使用了术语“第一”、“第二”等等来描述各个单元,但是这些单元不应当受这些术语限制。使用这些术语仅仅是为了将一个单元与另一个单元进行区分。举例来说,在不背离示例性实施例的范围的情况下,第一单元可以被称为第二单元,并且类似地第二单元可以被称为第一单元。这里所使用的术语“和/或”包括其中一个或更多所列出的相关联项目的任意和所有组合。
应当理解的是,当一个单元被称为“连接”或“耦合”到另一单元时,其可以直接连接或耦合到所述另一单元,或者可以存在中间单元。与此相对,当一个单元被称为“直接连接”或“直接耦合”到另一单元时,则不存在中间单元。应当按照类似的方式来解释被用于描述单元之间的关系的其他词语(例如“处于...之间”相比于“直接处于...之间”,“与...邻近”相比于“与...直接邻近”等等)。
这里所使用的术语仅仅是为了描述具体实施例而不意图限制示例性实施例。除非上下文明确地另有所指,否则这里所使用的单数形式“一个”、“一项”还意图包括复数。还应当理解的是,这里所使用的术语“包括”和/或“包含”规定所陈述的特征、整数、步骤、操作、单元和/或组件的存在,而不排除存在或添加一个或更多其他特征、整数、步骤、操作、单元、组件和/或其组合。
还应当提到的是,在一些替换实现方式中,所提到的功能/动作可以按照不同于附图中标示的顺序发生。举例来说,取决于所涉及的功能/动作,相继示出的两幅图实际上可以基本上同时执行或者有时可以按照相反的顺序来执行。
下面结合附图对本发明作进一步详细描述。
图1是根据本发明一个实施例的信息推送方法的流程图。
结合图1中所示,本实施例所述的信息推送方法,包括如下步骤:
S110、接收用户输入的搜索词,并获取用户特征信息;
S120、根据所述搜索词得到诉求结果;
S130、根据所述用户特征信息得到维度结果;
S140、根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户。
下面对各步骤做进一步详细介绍。
步骤S110中,用户特征信息可以包括性别、年龄、健康状况、民族、受教育程度(例如:博士、本科、高中或小学等)、职业(例如:厨师、记者或律师等)和/或地理位置信息等。本发明实施例对获取用户特征信息的方式不做具体限定,可以通过问卷形式用户获得,也可以根据用户的浏览记录或登录记录获得,只要能够获得用户特征信息即可。
步骤S120中,根据对用户输入的搜索词通过分词技术进行拆分处理和/或词性判断等方式进行分析,得到诉求结果,本发明实施例对根据搜索词得到诉求结果的具体过程并不做限定,只要能得到诉求结果即可。例如:用户输入的搜索词为“锻炼身体”,那么确定为与健身有关的诉求。
步骤S130中,针对每一个用户特征建立对应的维度值,以得到维度结果。作为可选的,维度结果可以以表格形式进行展现和存储,例如纵坐标表示用户特征,横坐标为对应维度值。例如:纵坐标为年龄,横坐标对应的维度值为岁数;纵坐标为受教育程度,横坐标对应的维度值为学历对应代码值或学历标志;纵坐标为地理位置信息,横坐标对应的维度值为GPS(Global Positioning System,全球定位系统)地理坐标信息。
可选地,在一个实施例中,如图2中所示,步骤S140具体可以包括以下步骤:
步骤S1401、根据所述诉求结果和所述维度结果通过预定算法获 得第一诉求维度信息。
具体地,可以将诉求结果和维度结果进行加权算法获得第一诉求维度信息,本发明实施例对预定算法并不做具体限定,只要根据该预定算法得到的第一诉求维度信息能够体现出诉求结果和维度结果,并根据该第一诉求维度信息推送的待发送的信息能够满足用户的搜索意图即可。
步骤S1402、根据所述第一诉求维度信息将待发送的信息推送给所述用户。
作为可选的,信息库中待发送的信息的存储方式可以包括以下两种:
第一种存储方式:将信息库中每一条待发送的信息至少对应一个诉求维度信息,并将待发送的信息与其对应的至少一个诉求维度信息进行对应存储。例如,信息1对应诉求维度信息A和B进行存储,信息2对应诉求维度信息C进行存储,信息3对应诉求维度信息A和C进行存储。
第二种存储方式:将信息库中每一个诉求维度信息对应至少一条待发送的信息,并将诉求维度信息与其对应的至少一条待发送的信息进行对应存储。例如,诉求维度信息A对应待发送的信息1和信息3进行存储,诉求维度信息B对应待发送的信息1进行存储,诉求维度信息C对应待发送的信息2和信息3进行存储。
具体地,将信息库中与所述第一诉求维度信息对应存储的待发送的信息推送给所述用户。具体待发送的信息的推送顺序可以预先设置,也可以随机推送,还可以根据匹配算法按照匹配度的高低进行推送,本发明实施例对推送顺序的设置不做具体限定,只要能够将用户预搜索的待发送的信息及时快速且准确的展示给用户即可。
可选地,在一个实施例中,步骤S140具体还可以包括以下步骤:
步骤S141、将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户。
作为可选的,针对步骤S140,信息库中待发送的信息的存储方 式可以包括以下两种:
第一种存储方式:将信息库中每一条待发送的信息对应至少一个维度结果,以及将信息库中每一条待发送的信息对应至少一个诉求结果,并将待发送的信息与其对应的至少一个维度结果和至少一个诉求结果进行对应存储。例如,信息1对应健身、年龄20岁的女性进行存储,信息2对应食品安全、年龄0-5岁婴幼儿进行存储。信息3对应健身、年龄60-80岁的男性知识分子进行存储。
第二种存储方式:将信息库中每一个维度结果对应至少一个待发送的信息,以及将信息库中每一个诉求结果对应至少一个待发送的信息,将维度结果与其对应的至少一个待发送的信息进行对应存储,以及将诉求结果与其对应的至少一个待发送的信息进行对应存储。例如:年龄20岁对应信息1和信息2,年龄0-5岁对应信息3和信息4,健身对应信息1和信息3,男性对应信息4和信息5。
作为可选的,可以具体的推送过程包括以下三种方式:
第一种推送过程:在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送信息集合;并将所述第一待发送信息集合中与所述维度结果相同的待发送的信息推送给所述用户。例如:用户输入的搜索词是锻炼身体,那么健身、健身馆、广场舞和健身操等都与锻炼身体有关,则可确定健身、健身馆、广场舞和健身操相关的待发送的信息均应在第一待发送的信息集合中。
第二种推送过程:确定信息库中与所述维度结果相同的第二待发送的信息集合;并在所述第二待发送的信息集合中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的待发送的信息,将所述确定的待发送的信息推送给所述用户。
第三种推送过程:在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送的信息集合,确定信息库中与所述维度结果相同的第二待发送的信息集合;将第一待发送的信息集合与第二待发送的信息集合取交集,将交集中待发送的信息推送给所述用户。
本发明实施例对相关的算法不做具体限定,可以针对用户的不同需求进行相应的设定,只要能够满足用户的需求即可。阈值也可以根据用户的不同需求进行设定。
结合图3中所示,本实施例所述的又一信息推送方法,包括如下步骤:
S310、接收用户输入的“减肥瘦身“,并获取用户特征信息为20岁、女性、地理位置为北京市海淀区海淀黄庄地铁站。
S320、根据“减肥瘦身“得到诉求结果为健身。
S330、根据用户特性信息得到维度结果为年龄:20岁,性别:女,地理位置:海淀黄庄、中关村、地区代码和/或经纬度值等形式均可。
作为可选的,若还包括健康状况和民族维度,但获取的用户特征信息中没有健康状况和民族信息,则维度结果还包括:健康状况:未知,民族:未知。
S340、在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送的信息集合;确定信息库中与维度结果相同的第二待发送的信息集合;将第一待发送的信息集合与第二待发送的信息集合取交集,将交集中待发送的信息推送给所述用户。
作为可选的,第一待发送的信息集合可以与健身有关的、与健身馆有关的与健身俱乐部有关的信息集合;第二待发送的信息集合可以是与年龄20、性别为女以及地理位置为海淀黄庄、中关村、地区代码和/或经纬度值的维度结果对应存储的信息集合。具体还可以将中关村附近的针对20岁女性的健身场所优先推送给该用户,以便该用户可以就近进行选择。若对应存储的信息还包括例如健康状况和民族维度的信息,则只要满足其中维度结果中年龄20、性别为女以及地理位置为海淀黄庄、中关村、地区代码和/或经纬度值对应存储的信息集合即可。
根据本实施例提供的方法,例如年龄19的女孩输入的关键词是“运动”,那么她肯定很想知道一些与瘦身运动相关的知识;而年龄60岁的男性输入的关键词是“运动”,那么他肯定很想知道一些与老年人 运动相关的知识,可见,不同年龄或性别的用户根据同一关键词进行搜索想要得到的信息均不相同。因此本实施例通过搜索词与用户特征信息结合的方式将待发送的信息进行推送,可以针对不同的用户特征进行精准的个性化服务,增加了信息推送的准确性,满足了用户的个性化需求。
结合图4中所示,本实施例所述的信息推送装置,可以设置在网络设备侧或云端设备侧,包括如下装置:
用于接收用户输入的搜索词,并获取用户特征信息的装置(以下简称“接收装置”)410;
用于根据所述搜索词得到诉求结果的装置(以下简称“第一分析装置”)420;
用于根据所述用户特征信息得到维度结果的装置(以下简称“第二分析装置”)430;
用于根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户的装置(以下简称“推送装置”)440。
下面对各装置做进一步详细介绍。
接收装置410中,用户特征信息可以包括性别、年龄、健康状况、民族、受教育程度(例如:博士、本科、高中或小学等)、职业(例如:厨师、记者或律师等)和/或地理位置信息等。本发明实施例对获取用户特征信息的方式不做具体限定,可以通过问卷形式用户获得,也可以根据用户的浏览记录或登录记录获得,只要能够获得用户特征信息即可。
第一分析装置420中,根据对用户输入的搜索词进行拆分处理和/或词性判断等方式进行分析,得到诉求结果,本发明实施例对根据搜索词得到诉求结果的具体过程并不做限定,只要能得到诉求结果即可。例如:用户输入的搜索词为“锻炼身体”,那么确定为与健身有关的诉求。
第二分析装置430中,针对每一个用户特征建立对应的维度值,以得到维度结果。作为可选的,维度结果可以以表格形式进行展现和 存储,例如纵坐标表示用户特征,横坐标为对应维度值。例如:纵坐标为年龄,横坐标对应的维度值为岁数;纵坐标为受教育程度,横坐标对应的维度值为学历对应代码值或学历标志;纵坐标为地理位置信息,横坐标对应的维度值为GPS地理坐标信息。
可选地,在一个实施例中,如图5中所示,推送装置440具体可以包括以下装置:
用于根据所述诉求结果和所述维度结果通过预定算法获得第一诉求维度信息的装置(以下简称“计算装置”)4401。
具体地,可以将诉求结果和维度结果进行加权算法获得第一诉求维度信息,本发明实施例对预定算法并不做具体限定,只要根据该预定算法得到的第一诉求维度信息能够体现出诉求结果和维度结果,并根据该第一诉求维度信息推送的待发送的信息能够满足用户的搜索意图即可。
用于根据所述第一诉求维度信息将待发送的信息推送给所述用户的装置(以下简称“第一发送装置”)4402。
作为可选的,针对上述推送装置440,本发明实施例所述的信息推送装置还可以包括:
用于将信息库中每一条待发送的信息至少对应一个诉求维度信息,并将待发送的信息与其对应的至少一个诉求维度信息进行对应存储的装置(以下简称“第一存储装置”)4501。
用于将信息库中每一个诉求维度信息对应至少一条待发送的信息,并将诉求维度信息与其对应的至少一条待发送的信息进行对应存储的装置(以下简称“第二存储装置”)4502。
具体地,将信息库中与所述第一诉求维度信息对应存储的待发送的信息推送给所述用户。具体待发送的信息的推送顺序可以预先设置,也可以随机推送,还可以根据匹配算法按照匹配度的高低进行推送,本发明实施例对推送顺序的设置不做具体限定,只要能够将用户预搜索的待发送的信息及时快速且准确的展示给用户即可。
可选地,在一个实施例中,如图6中所示,推送装置440具体还 可以包括以下装置:
用于将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户的装置(以下简称“第二发送装置”)441。
作为可选的,针对第二发送装置441,本发明实施例所述的信息推送装置还可以包括:
用于将信息库中每一条待发送的信息对应至少一个维度结果,以及将信息库中每一条待发送的信息对应至少一个诉求结果,并将待发送的信息与其对应的至少一个维度结果和至少一个诉求结果进行对应存储的装置(以下简称“第三存储装置”)4503。
用于将信息库中每一个维度结果对应至少一个待发送的信息,以及将信息库中每一个诉求结果对应至少一个待发送的信息,将维度结果与其对应的至少一个待发送的信息进行对应存储,以及将诉求结果与其对应的至少一个待发送的信息进行对应存储的装置(以下简称“第四存储装置”)4504。
作为可选的,基于第三存储装置4503或第四存储装置4504中存储的待发送的信息,第二发送装置441具体的推送过程包括以下三种方式:
第一种推送过程:在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送信息集合;并将所述第一待发送信息集合中与所述维度结果相同的待发送的信息推送给所述用户。例如:用户输入的搜索词是锻炼身体,那么健身、健身馆、广场舞和健身操等都与锻炼身体有关,则可确定健身、健身馆、广场舞和健身操相关的待发送的信息均应在第一待发送的信息集合中。
第二种推送过程:确定信息库中与所述维度结果相同的第二待发送的信息集合;并在所述第二待发送的信息集合中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的待发送的信息,将所述确定的待发送的信息推送给所述用户。
第三种推送过程:在信息库中根据预定的相关度算法确定与所述 诉求结果的相关度在阈值范围内的第一待发送的信息集合,确定信息库中与所述维度结果相同的第二待发送的信息集合;将第一待发送的信息集合与第二待发送的信息集合取交集,将交集中待发送的信息推送给所述用户。
本发明实施例对相关的算法不做具体限定,可以针对用户的不同需求进行相应的设定,只要能够满足用户的需求即可。阈值也可以根据用户的不同需求进行设定。
本发明实施例提供的信息推送方法及装置,通过搜索词与用户特征信息结合的方式将待发送的信息进行推送,可以根据性别、年龄等用户的特征信息进行针对性和个性化的信息推送和服务,增加服务结果的准确性,可以针对不同的用户特征进行精准的个性化服务,增加了信息推送的准确性,满足了用户的个性化需求,提高了用户体验。同时结合搜索词与用户的特征信息进行信息的推送,更进一步提高了针对不同用户需求进行推送的精准度,提高了推送效率。
需要注意的是,本发明可在软件和/或软件与硬件的组合体中被实施,例如,本发明的各个装置可采用专用集成电路(ASIC)或任何其他类似硬件设备来实现。在一个实施例中,本发明的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地,本发明的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中,例如,RAM存储器,磁或光驱动器或软磁盘及类似设备。另外,本发明的一些步骤或功能可采用硬件来实现,例如,作为与处理器配合从而执行各个步骤或功能的电路。
对于本领域技术人员而言,显然本发明不限于上述示范性实施例的细节,而且在不背离本发明的精神或基本特征的情况下,能够以其他的具体形式实现本发明。因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本发明的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本发明内。不应将权利要求中的任何附图标 记视为限制所涉及的权利要求。此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一,第二等词语用来表示名称,而并不表示任何特定的顺序。
虽然前面特别示出并且描述了示例性实施例,但是本领域技术人员将会理解的是,在不背离权利要求书的精神和范围的情况下,在其形式和细节方面可以有所变化。这里所寻求的保护在所附权利要求书中做了阐述。

Claims (13)

  1. 一种信息推送方法,包括:
    接收用户输入的搜索词,并获取用户特征信息;
    根据所述搜索词得到诉求结果;
    根据所述用户特征信息得到维度结果;
    根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户。
  2. 根据权利要求1所述的方法,其中,所述根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户的步骤包括:
    根据所述诉求结果和所述维度结果通过预定算法获得第一诉求维度信息,根据所述第一诉求维度信息将待发送的信息推送给所述用户;或者,
    将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户。
  3. 根据权利要求2所述的方法,还包括:
    将信息库中每一条待发送的信息对应至少一个诉求维度信息,并将待发送的信息与其对应的至少一个诉求维度信息进行对应存储;或者,
    将信息库中每一个诉求维度信息对应至少一条待发送的信息,并将诉求维度信息与其对应的至少一条待发送的信息进行对应存储;或者,
    将信息库中每一条待发送的信息对应至少一个维度结果,以及将信息库中每一条待发送的信息对应至少一个诉求结果,并将待发送的信息与其对应的至少一个维度结果和至少一个诉求结果进行对应存储;或者,
    将信息库中每一个维度结果对应至少一个待发送的信息,以及将 信息库中每一个诉求结果对应至少一个待发送的信息,将维度结果与其对应的至少一个待发送的信息进行对应存储,以及将诉求结果与其对应的至少一个待发送的信息进行对应存储。
  4. 根据权利要求3所述的方法,其中,所述根据所述第一诉求维度信息将待发送的信息推送给所述用户的步骤包括:
    将信息库中与所述第一诉求维度信息对应存储的待发送的信息推送给所述用户。
  5. 根据权利要求3所述的方法,其中,所述将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户的步骤包括:
    在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送信息集合;并将所述第一待发送信息集合中与所述维度结果相同的待发送的信息推送给所述用户;或者,
    确定信息库中与所述维度结果相同的第二待发送的信息集合;并在所述第二待发送的信息集合中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的待发送的信息,将所述确定的待发送的信息推送给所述用户;或者,
    在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送的信息集合;确定信息库中与所述维度结果相同的第二待发送的信息集合;将第一待发送的信息集合与第二待发送的信息集合取交集,将交集中待发送的信息推送给所述用户。
  6. 一种信息推送装置,包括:
    用于接收用户输入的搜索词,并获取用户特征信息的装置;
    用于根据所述搜索词得到诉求结果的装置;
    用于根据所述用户特征信息得到维度结果的装置;
    用于根据所述诉求结果和所述维度结果将待发送的信息推送给 所述用户的装置。
  7. 根据权利要求6所述的装置,其中,用于根据所述诉求结果和所述维度结果将待发送的信息推送给所述用户的装置包括:
    用于根据所述诉求结果和所述维度结果通过预定算法获得第一诉求维度信息的装置,以及用于根据所述第一诉求维度信息将待发送的信息推送给所述用户的装置;或者,
    用于将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户的装置。
  8. 根据权利要求7所述的装置,还包括:
    用于将信息库中每一条待发送的信息对应至少一个诉求维度信息,并将待发送的信息与其对应的至少一个诉求维度信息进行对应存储;或者,
    用于将信息库中每一个诉求维度信息对应至少一条待发送的信息,并将诉求维度信息与其对应的至少一条待发送的信息进行对应存储的装置;或者,
    用于将信息库中每一条待发送的信息对应至少一个维度结果,以及将信息库中每一条待发送的信息对应至少一个诉求结果,并将待发送的信息与其对应的至少一个维度结果和至少一个诉求结果进行对应存储的装置;或者,
    用于将信息库中每一个维度结果对应至少一个待发送的信息,以及将信息库中每一个诉求结果对应至少一个待发送的信息,将维度结果与其对应的至少一个待发送的信息进行对应存储,以及将诉求结果与其对应的至少一个待发送的信息进行对应存储的装置。
  9. 根据权利要求8所述的装置,其中,用于根据所述第一诉求维度信息将待发送的信息推送给所述用户的装置包括:
    用于将信息库中与所述第一诉求维度信息对应存储的待发送的 信息推送给所述用户的装置。
  10. 根据权利要求8所述的装置,其中,用于将与所述诉求结果的相关度在阈值范围内,且与所述维度结果相同的待发送的信息推送给所述用户的装置包括:
    用于在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送信息集合,并将所述第一待发送信息集合中与所述维度结果相同的待发送的信息推送给所述用户的装置;或者,
    用于确定信息库中与所述维度结果相同的第二待发送的信息集合,在所述第二待发送的信息集合中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的待发送的信息,将所述确定的待发送的信息推送给所述用户的装置;或者,
    用于在信息库中根据预定的相关度算法确定与所述诉求结果的相关度在阈值范围内的第一待发送的信息集合,确定信息库中与所述维度结果相同的第二待发送的信息集合,将第一待发送的信息集合与第二待发送的信息集合取交集,用于将交集中待发送的信息推送给所述用户的装置。
  11. 一种计算机可读存储介质,所述计算机可读存储介质包括计算机指令,当所述计算机指令被执行时,如权利要求1至5中任一项所述的方法被执行。
  12. 一种计算机程序产品,当所述计算机程序产品被执行时,如权利要求1至5中任一项所述的方法被执行。
  13. 一种计算机设备,所述计算机设备包括存储器和处理器,所述存储器中存储有计算机指令,所述处理器被配置来通过执行所述计算机指令以执行如权利要求1至5中任一项所述的方法。
PCT/CN2015/096452 2015-07-29 2015-12-04 一种信息推送方法及装置 Ceased WO2017016122A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2017541055A JP6853179B2 (ja) 2015-07-29 2015-12-04 情報プッシュ方法及び装置
KR1020177021661A KR102009787B1 (ko) 2015-07-29 2015-12-04 정보 푸싱 방법 및 장치

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510456927.0 2015-07-29
CN201510456927.0A CN105045889B (zh) 2015-07-29 2015-07-29 一种信息推送方法及装置

Publications (1)

Publication Number Publication Date
WO2017016122A1 true WO2017016122A1 (zh) 2017-02-02

Family

ID=54452436

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/096452 Ceased WO2017016122A1 (zh) 2015-07-29 2015-12-04 一种信息推送方法及装置

Country Status (4)

Country Link
JP (1) JP6853179B2 (zh)
KR (1) KR102009787B1 (zh)
CN (1) CN105045889B (zh)
WO (1) WO2017016122A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180061421A1 (en) * 2016-08-31 2018-03-01 Microsoft Technology Licensing, Llc Personalization of experiences with digital assistants in communal settings through voice and query processing
CN111180080A (zh) * 2019-12-30 2020-05-19 四川华迪信息技术有限公司 一种老年健康知识库精准推送方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105045889B (zh) * 2015-07-29 2018-04-20 百度在线网络技术(北京)有限公司 一种信息推送方法及装置
CN105677927B (zh) * 2016-03-31 2019-04-12 百度在线网络技术(北京)有限公司 用于提供搜索结果的方法和装置
CN107092609B (zh) * 2016-05-10 2021-04-02 口碑控股有限公司 一种信息推送方法及装置
CN106357824B (zh) * 2016-11-16 2019-06-04 四川省亚丁胡杨人力资源集团有限公司 一种智能社区服务推荐系统
CN107507612B (zh) * 2017-06-30 2020-08-28 百度在线网络技术(北京)有限公司 一种声纹识别方法及装置
CN108280200B (zh) * 2018-01-29 2021-11-09 百度在线网络技术(北京)有限公司 用于推送信息的方法和装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070294225A1 (en) * 2006-06-19 2007-12-20 Microsoft Corporation Diversifying search results for improved search and personalization
CN103970891A (zh) * 2014-05-23 2014-08-06 三星电子(中国)研发中心 一种基于情境的用户兴趣信息查询方法
CN104077407A (zh) * 2014-07-10 2014-10-01 中国工商银行股份有限公司 一种智能数据搜索系统及方法
CN104866474A (zh) * 2014-02-20 2015-08-26 阿里巴巴集团控股有限公司 个性化数据搜索方法及装置
CN105045889A (zh) * 2015-07-29 2015-11-11 百度在线网络技术(北京)有限公司 一种信息推送方法及装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06187374A (ja) * 1992-12-15 1994-07-08 Hokkaido Nippon Denki Software Kk 検索方式
JP2001022672A (ja) * 1999-07-09 2001-01-26 Dejitaretto:Kk プッシュ型情報配信システムおよびプッシュ型情報配信方法
US8352499B2 (en) * 2003-06-02 2013-01-08 Google Inc. Serving advertisements using user request information and user information
US7885963B2 (en) * 2003-03-24 2011-02-08 Microsoft Corporation Free text and attribute searching of electronic program guide (EPG) data
JP2005085010A (ja) * 2003-09-09 2005-03-31 Fujitsu Ltd 情報サービス提供方法及び提供装置
US7720845B2 (en) * 2004-08-13 2010-05-18 Yahoo! Inc. Systems and methods for updating query results based on query deltas
JP2007243253A (ja) * 2006-03-06 2007-09-20 Fuji Xerox Co Ltd 情報配信システム及び情報配信方法
US8528102B2 (en) * 2006-10-06 2013-09-03 Broadcom Corporation Method and system for protection of customer secrets in a secure reprogrammable system
KR100892845B1 (ko) * 2007-03-29 2009-04-10 엔에이치엔(주) 노출용 광고 정보를 제공하는 방법 및 시스템
US20110184940A1 (en) * 2010-01-26 2011-07-28 Yahoo! Inc. System and method for detecting changes in the relevance of past search results
CN102609500A (zh) * 2012-02-01 2012-07-25 北京百度网讯科技有限公司 一种问题推送方法和采用该方法的问答系统和搜索引擎
CN103530299B (zh) * 2012-07-05 2017-04-12 阿里巴巴集团控股有限公司 一种搜索结果的生成方法及装置
CN104572782A (zh) * 2013-10-29 2015-04-29 中兴通讯股份有限公司 一种基于浏览器搜索的定向消息推送方法及系统
US20150127631A1 (en) * 2013-11-05 2015-05-07 International Business Machines Corporation Best available alternative dialog
CN104794122B (zh) * 2014-01-20 2020-04-17 腾讯科技(北京)有限公司 一种位置信息推荐方法、装置和系统
CN104239456B (zh) * 2014-09-02 2019-05-03 百度在线网络技术(北京)有限公司 用户特征数据的提取方法和装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070294225A1 (en) * 2006-06-19 2007-12-20 Microsoft Corporation Diversifying search results for improved search and personalization
CN104866474A (zh) * 2014-02-20 2015-08-26 阿里巴巴集团控股有限公司 个性化数据搜索方法及装置
CN103970891A (zh) * 2014-05-23 2014-08-06 三星电子(中国)研发中心 一种基于情境的用户兴趣信息查询方法
CN104077407A (zh) * 2014-07-10 2014-10-01 中国工商银行股份有限公司 一种智能数据搜索系统及方法
CN105045889A (zh) * 2015-07-29 2015-11-11 百度在线网络技术(北京)有限公司 一种信息推送方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180061421A1 (en) * 2016-08-31 2018-03-01 Microsoft Technology Licensing, Llc Personalization of experiences with digital assistants in communal settings through voice and query processing
US10832684B2 (en) * 2016-08-31 2020-11-10 Microsoft Technology Licensing, Llc Personalization of experiences with digital assistants in communal settings through voice and query processing
CN111180080A (zh) * 2019-12-30 2020-05-19 四川华迪信息技术有限公司 一种老年健康知识库精准推送方法

Also Published As

Publication number Publication date
CN105045889A (zh) 2015-11-11
JP2018508885A (ja) 2018-03-29
KR102009787B1 (ko) 2019-08-12
CN105045889B (zh) 2018-04-20
KR20170103859A (ko) 2017-09-13
JP6853179B2 (ja) 2021-03-31

Similar Documents

Publication Publication Date Title
JP6759844B2 (ja) 画像を施設に対して関連付けるシステム、方法、プログラム及び装置
JP6575335B2 (ja) ソーシャルメディアメッセージ及び施設の間のリンクを推定する方法、コンピュータシステム、及びプログラム
JP6540314B2 (ja) 施設推定方法、デバイス及びプログラム
US20190251125A1 (en) Method and system for providing recommendation query using search context
CN105045889B (zh) 一种信息推送方法及装置
JP7119124B2 (ja) 検索動作出力要素のアクションインジケータ
WO2020199662A1 (zh) 用于推送信息的方法和装置
US12451164B2 (en) Video timed anchors
US11082800B2 (en) Method and system for determining an occurrence of a visit to a venue by a user
CN106462596A (zh) 生成上下文搜索呈现
US20190034816A1 (en) Methods and system for associating locations with annotations
US20140089239A1 (en) Methods, Apparatuses and Computer Program Products for Providing Topic Model with Wording Preferences
US20210019026A1 (en) Contextual information for a displayed resource that includes an image
US20170220589A1 (en) Item recommendation method, device, and system
CN108549710B (zh) 智能问答方法、装置、存储介质及设备
JP2019522852A (ja) 文脈情報を提供するためのシステムおよび方法
WO2016078480A1 (zh) 一种用于提供时效性图片搜索结果的方法与设备
US11651280B2 (en) Recording medium, information processing system, and information processing method
KR101955920B1 (ko) 속성 언어를 이용한 검색 방법 및 장치
WO2017024684A1 (zh) 用户行为意图的获取方法、装置、设备及非易失性计算机存储介质
RU2658876C1 (ru) Способ и сервер для обработки данных датчика беспроводного устройства для создания вектора объекта, связанного с физическим положением
JP5647090B2 (ja) クエリ推薦装置及び方法及びプログラム
TWI746527B (zh) 資料推薦的處理互動方法、裝置及系統
CN119271883A (zh) 推荐兴趣点的方法、装置、设备、存储介质及程序产品
CN118779376A (zh) 基于地理位置的社交媒体数据分析与呈现方法及装置

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: 15899472

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 20177021661

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2017541055

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15899472

Country of ref document: EP

Kind code of ref document: A1