WO2018006368A1 - 基于虚拟机器人的广告植入方法和系统 - Google Patents

基于虚拟机器人的广告植入方法和系统 Download PDF

Info

Publication number
WO2018006368A1
WO2018006368A1 PCT/CN2016/089212 CN2016089212W WO2018006368A1 WO 2018006368 A1 WO2018006368 A1 WO 2018006368A1 CN 2016089212 W CN2016089212 W CN 2016089212W WO 2018006368 A1 WO2018006368 A1 WO 2018006368A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement
input information
information
user
behavior
Prior art date
Application number
PCT/CN2016/089212
Other languages
English (en)
French (fr)
Inventor
邱楠
杨新宇
王昊奋
Original Assignee
深圳狗尾草智能科技有限公司
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 深圳狗尾草智能科技有限公司 filed Critical 深圳狗尾草智能科技有限公司
Priority to PCT/CN2016/089212 priority Critical patent/WO2018006368A1/zh
Priority to CN201680001791.7A priority patent/CN106462886A/zh
Publication of WO2018006368A1 publication Critical patent/WO2018006368A1/zh

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
    • 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
    • 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
    • G06Q30/0242—Determining effectiveness of advertisements
    • 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
    • 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
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement

Definitions

  • the present invention relates to the field of robot interaction technologies, and in particular, to a virtual robot based advertisement implantation method and system.
  • virtual robots As a kind of entertainment and auxiliary tools, virtual robots are used in human life. Virtual robots interact with users as close as possible to human behaviors to meet the psychological needs of users.
  • Virtual robots are offered to users as a commercial tool, and in general, the placement of advertisements is required as a way to get rewards.
  • the way of advertising is mainly based on active implantation, such as mandatory pop-up pages, and some online-embedded advertisements, which are not reviewed and are relatively rogue.
  • a method for advertising an advertisement based on a virtual robot comprising:
  • the advertising policy is implanted into the interaction with the user according to a preset advertising policy.
  • identifying key factors associated with the advertisement in the multimodal input information includes:
  • the keywords associated with the advertisement in the voice information are identified based on the voice information in the multimodal input information.
  • identifying key factors associated with the advertisement in the multimodal input information includes:
  • the method for advertising an advertisement further comprises:
  • the habit behavior characteristics and the library A new advertising strategy is associated, wherein the new advertising strategy is an advertising strategy for the same good or service that is preset according to customary behavioral characteristics.
  • the embedding the advertising policy into the interaction with the user according to the preset advertising policy further includes:
  • the user's approval information in the further multi-modal input information is judged, and the user is subjected to the second supplementary implantation according to the approval information.
  • a virtual robot based advertising implant system comprising:
  • a multi-modal input information acquisition module configured to acquire multi-modal input information of the user and the robot
  • a key factor identification module configured to identify, according to the multimodal input information, a key factor associated with a preset advertising policy in the multimodal input information
  • the advertisement embedding module is configured to embed the advertisement policy into the interaction with the user according to the preset advertising policy according to the key factor.
  • the key factor identification module comprises:
  • the keyword identification unit is configured to identify a keyword associated with the advertisement in the voice information according to the voice information in the multimodal input information.
  • the key factor identification module comprises:
  • the key behavior recognition unit identifies the key behavior associated with the advertisement in the behavior information according to the behavior information in the multimodal input information.
  • the system further comprises:
  • the habitual behavior association module is configured to record the occurrence of key factors. If the number of occurrences of the same key factor exceeds a preset value, a habitual behavior characteristic is generated according to the key factor, and a new advertisement association is established according to the habit behavior characteristic: Habitual behavioral traits are associated with new advertising strategies in the library.
  • the system further comprises:
  • a second implanting module configured to determine, according to further multimodal input information after the user views the embedded advertisement, the user's approval information in the further multimodal input information, according to the approval letter The user is given a second supplemental implant.
  • the present invention has the following advantages: by acquiring multi-modal input information with the robot, the multi-modal input information is identified by key factors, thereby embedding an advertisement to the user according to the key factors of identification, which is a Passive advertising implants further reduce the user's dislike of advertising compared with traditional active advertising. At the same time, advertising strategies are preset, so each advertisement can be pre-approved to ensure advertising. Orderly and healthy.
  • Embodiment 1 is a flow chart of a method according to Embodiment 1 of the present invention.
  • FIG. 2 is a schematic diagram of a system according to a second embodiment of the present invention.
  • Computer devices include user devices and network devices.
  • the user equipment or the client 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 network server. cloud.
  • the computer device can operate alone to carry out the invention, and can also access the network and implement the invention through interoperation 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.
  • first means “first,” “second,” and the like may be used herein to describe the various elements, but the elements should not be limited by these terms, and the terms are used only to distinguish one element from another.
  • the term “and/or” used herein includes any and all combinations of one or more of the associated listed items. When a unit is referred to as being “connected” or “coupled” to another unit, it can be directly connected or coupled to the other unit, or an intermediate unit can be present.
  • FIG. 1 is a specific embodiment of a virtual robot-based advertisement embedding method provided, the method comprising the steps of:
  • the multi-modal input information of the user is obtained through operation of the smart terminal, wherein the smart terminal may include a handheld mobile terminal such as a mobile phone, a tablet, or the like, or a non-handheld terminal device such as a computer or a smart TV.
  • the multimodal input information includes one or more of voice information, gesture information, expression information, scene information, image information, video information, face information, pupil iris information, light sense information, and fingerprint information.
  • the intelligent terminal is provided with a multi-modal input and input module, such as a microphone, a sensor, a camera, a touch screen, etc., and the information input through the multi-modal input information between the user and the robot is included.
  • the key factor is the identification factor of the triggered advertisement
  • the key factors will include multiple, and the key factors also include different categories, each of which is related to one or more preset advertising strategies. Linked, or, multiple key factors point to a default advertising strategy.
  • the key factor in identifying the multi-modal input information is to preset the key factors in the system.
  • the information segment in the multi-modal input information is preset in the system.
  • the key factors are compared. If there is a matching information segment, the information segment is considered to be a key factor.
  • the advertising policy is implanted into interaction with the user according to a preset advertising policy.
  • the advertisement is triggered, and the advertising policy is implanted into the interaction with the user according to the pre-designed advertising strategy.
  • the preset advertising strategy refers to the manner in which the advertisement is displayed, including voice, video, etc., and the preset advertising strategy may be pre-made and stored in the system, or obtained through a networked server.
  • identifying key factors associated with the advertisement in the multimodal input information includes: identifying the voice information in the voice information according to the multimodal input information Report the associated keywords.
  • the interaction between the user and the robot includes voice interaction, and the voice information is extracted from the multi-modal input information for separate analysis, and the information segments in the voice information are matched with the predicted keywords in the system, if matched
  • the advertising policy is embedded in the interaction with the user in accordance with a predetermined advertising policy associated with the keyword. For example, if the user interacts with the robot, he says, “The weather is hot, I want to buy a fan”, in which “buy a fan” is used as a keyword to match the default keywords in the system.
  • the robot can be based on the user's semantics, voice interaction Respond: "I have been using the XX brand fan, which has the function of intelligently adjusting the wind, which can prevent me from catching a fan for a long time.”
  • This kind of advertising method puts the advertisement into the voice in a popular and less direct way.
  • the preset advertising strategy can correspond to multiple keywords, and any matching keyword is recognized in the multi-modal input information, which will trigger the insertion of the advertisement.
  • identifying the key factors associated with the advertisement in the multimodal input information includes: identifying the key behavior associated with the advertisement in the behavior information according to the behavior information in the multimodal input information. For example, when the user interacts with the robot, the current behavior of the user is drinking water, thereby identifying the “drinking water” behavior information through the smart terminal, and the information is associated with a preset advertising strategy in the system, triggering the virtual robot. The feedback is also the action of drinking water. At this time, the virtual robot can drink the branded beverage (filled in the advertisement).
  • the system can recognize the behavior information of “entering the coffee shop”, wherein the behavior information of “entering the coffee shop” is associated with the preset advertising strategy.
  • the scene information (such as signboards, interiors, etc.) that the robot scene (ie, the cafe) feeds back is also information that cooperates with the corresponding advertisement.
  • the advertisement embedding method further includes the steps of:
  • S40 Recording the occurrence of key factors. If the number of occurrences of the same key factor exceeds a preset value, generating a custom behavior characteristic according to the key factor, and establishing a new advertisement association according to the custom behavior characteristic: the habit behavior characteristic and the library
  • the new advertising strategy is associated, wherein the new advertising strategy is an advertising strategy for the same product or service that is preset according to the custom behavior characteristics.
  • identifying a key factor in the user's multimodal input information, and the associated advertising strategy is a beverage advertisement, implanting a XXX branded beverage advertisement to the user, such as a robot passing
  • the advertising message for voice implantation is: "I love to drink XXX brand tea, do you like it?" If the default value is three, then the third key factor is identified, the key factor is associated with the library.
  • the new advertising strategy (relative to the associated time), when the same key factor is identified for the fourth time, is implanted according to the new advertising strategy, for example: "Do you still drink XXX tea?"
  • Ad policies that are preset for the same product or service are only different from previous advertising strategies.
  • the advertisement embedding method further includes the steps of:
  • S50 Determine further authorization information of the user in the further multimodal input information according to the further multimodal input information after the user views the embedded advertisement, and perform a second supplementary implantation according to the approval information.
  • the embedded advertisement is taken as part of the multimodal input information with the user. Therefore, when the robot uses the advertisement as the multimodal input information, the user also responds correspondingly to further multimodal input information.
  • the user's approval information for the advertisement in the further multimodal input information For example, if a key factor such as "what is this" or "give me” is identified from the voice message, the user is implanted with the product or service associated with the advertisement. For another example, if a key factor such as “don't want” or “not feeling good” is recognized from the voice information, another preset alternate advertising strategy may be implanted, and if there is no backup advertising strategy, no implantation is performed.
  • the embodiment provides a virtual robot-based advertisement insertion system, which includes: a multi-modal input information acquisition module 10 for acquiring multi-modal input information of a user and a robot; and a key factor identification module 20 And for identifying, according to the multimodal input information, a key factor associated with the preset advertising policy in the multimodal input information; the advertisement implanting module 30 is configured to follow the preset advertisement according to the key factor.
  • the policy embeds the advertising strategy into the interaction with the user.
  • the key factor identification module includes: a keyword identification unit, configured to identify a keyword associated with the advertisement in the voice information according to the voice information in the multimodal input information.
  • the key factor identification module further includes: a key behavior recognition unit that identifies the key behavior associated with the advertisement in the behavior information according to the behavior information in the multimodal input information.
  • the system further includes: a habitual behavior association module 40, configured to record the occurrence of key factors, and if the number of occurrences of the same key factor exceeds a preset value, generating a habitual behavior characteristic according to the key factor, according to The custom behavioral feature establishes a new advertising association: associating the customary behavioral characteristics with new advertising strategies in the library.
  • a habitual behavior association module 40 configured to record the occurrence of key factors, and if the number of occurrences of the same key factor exceeds a preset value, generating a habitual behavior characteristic according to the key factor, according to The custom behavioral feature establishes a new advertising association: associating the customary behavioral characteristics with new advertising strategies in the library.
  • the system further includes: a secondary implanting module 50, configured to determine, according to further multimodal input information after the user views the embedded advertisement, the user's approval information in the further multimodal input information, A second supplemental implantation is performed to the user based on the approval information.
  • a secondary implanting module 50 configured to determine, according to further multimodal input information after the user views the embedded advertisement, the user's approval information in the further multimodal input information, A second supplemental implantation is performed to the user based on the approval information.

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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)
  • Manipulator (AREA)

Abstract

一种基于虚拟机器人的广告植入方法，包括：获取用户与机器人的交互信息（S10）；根据交互信息，识别交互信息中与预设的广告策略相关联的关键因素（S20）；根据关键因素，按照预设的广告策略将该广告策略植入与用户的交互中（S30）。还提供了一种虚拟机器人的广告植入系统。通过获取与机器人的多模态输入信息，对多模态输入信息进行关键因素的识别，从而根据识别的关键因素向用户通过交互的方式加入广告，这是一种被动式的广告植入，与传统的主动式广告相比，进一步减小了用户对广告的反感，同时，广告策略都是预设的，因此每一个广告都是可预先进行审核，确保广告的有序和健康。

Description

基于虚拟机器人的广告植入方法和系统 技术领域
本发明涉及机器人交互技术领域，尤其涉及一种基于虚拟机器人的广告植入方法和系统。
背景技术
虚拟机器人作为一种娱乐和辅助的工具被应用于人类的生活中，虚拟机器人以尽可能的接近人类的行为方式与用户进行交互，满足用户的心理需求。
虚拟机器人作为一种商业的工具被提供给用户，通常，需要进行广告的植入以作为一种获取回报的方式。目前来说，广告的植入方式主要是采用主动式植入的方式，例如强制性弹出页面，以及一些在线植入的广告，这种广告没有审核，比较流氓。
因此，上述问题亟待解决。
发明内容
本发明的目的是提供一种被动式的加入广告的基于虚拟机器人的广告植入方法和系统。
本发明的目的是通过以下技术方案来实现的：
一种基于虚拟机器人的广告植入方法，包括：
获取用户与机器人的多模态输入信息；
根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素；
根据所述关键因素，按照预设的广告策略将该广告策略植入与用户的交互中。
优选的，识别多模态输入信息中与广告相关联的关键因素包括：
根据多模态输入信息中的语音信息，识别语音信息中与广告相关联的关键词。
优选的，识别多模态输入信息中与广告相关联的关键因素包括：
根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的 关键行为。
优选的，所述广告植入方法还包括：
对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联，其中，所述新的广告策略是根据习惯行为特征而预设的针对同一商品或服务的广告策略。
优选的，按照预设的广告策略将该广告策略植入与用户的交互中还包括：
根据用户阅览所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信息向用户进行第二次补充植入。
一种基于虚拟机器人的广告植入系统，包括：
多模态输入信息获取模块，用于获取用户与机器人的多模态输入信息；
关键因素识别模块，用于根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素；
广告植入模块，用于根据所述关键因素，按照预设的广告策略将该广告策略植入与用户的交互中。
优选的，所述关键因素识别模块包括：
关键词识别单元，用于根据多模态输入信息中的语音信息，识别语音信息中与广告相关联的关键词。
优选的，所述关键因素识别模块包括：
关键行为识别单元，根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的关键行为。
优选的，所述系统还包括：
习惯行为关联模块，用于对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联。
优选的，所述系统还包括：
二次植入模块，用于根据用户阅览所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信 息向用户进行第二次补充植入。
相比现有技术，本发明具有以下优点：通过获取与机器人的多模态输入信息，对多模态输入信息进行关键因素的识别，从而根据识别的关键因素向用户植入广告，这是一种被动式的广告植入，与传统的主动式广告相比，进一步减小了用户对广告的反感，同时，广告策略都是预设的，因此每一个广告都是可预先进行审核，确保广告的有序和健康。
附图说明
图1是本发明实施例一的方法流程图；
图2是本发明实施例二的系统示意图。
具体实施方式
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。各项操作的顺序可以被重新安排。当其操作完成时处理可以被终止，但是还可以具有未包括在附图中的附加步骤。处理可以对应于方法、函数、规程、子例程、子程序等等。
计算机设备包括用户设备与网络设备。其中，用户设备或客户端包括但不限于电脑、智能手机、PDA等；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的由大量计算机或网络服务器构成的云。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。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。
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。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。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。
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。
下面结合附图和较佳的实施例对本发明作进一步说明。
实施例一
如图1所示为提供的一种基于虚拟机器人的广告植入方法的具体实施例，该方法包括步骤：
S10、获取用户与机器人的多模态输入信息。
具体的，获取用户的多模态输入信息是通过智能终端的操作，其中，智能终端可以包括手持的移动终端如手机、平板等，或是非手持的终端设备如电脑、智能电视等。其中，所述多模态输入信息包括语音信息、手势信息、表情信息、场景信息、图像信息、视频信息、人脸信息、瞳孔虹膜信息、光感信息和指纹信息中的其中一种或几种。智能终端设置有多模态输入输入模块，如麦克风、传感器、摄像头、触摸屏等，通过这些输入的信息，包括了用户与机器人之间交互的多模态输入信息。
S20、根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素。
具体的，本步骤中，所述关键因素是触发广告的识别因素，关键因素将包括多个，同时关键因素也包含不同的种类，每个关键因素都与一个或多个预设的广告策略相关联，或者，多个关键因素都指向一个预设的广告策略。其中，识别多模态输入信息中的关键因素，是通过对关键因素进行预设在系统中，当多模态输入信息发生时，将多模态输入信息中的信息段与系统中预设的关键因素进行对比，若具有匹配信息段，则认为该信息段为关键因素。
S30、根据所述关键因素，按照预设的广告策略将该广告策略植入与用户的交互中。
具体的，当检测到多模态输入信息中包含了关键因素，则触发广告，按照预先设计好的广告策略将该广告策略植入与用户的交互中。其中，所预设的广告策略是指广告的展示方式，包括语音、视频等，预设的广告策略可以是预先制作好存放于系统中，或者通过联网的服务器中获取的。
在本实施例中，步骤S20中，识别多模态输入信息中与广告相关联的关键因素包括：根据多模态输入信息中的语音信息，识别语音信息中与广 告相关联的关键词。具体的，用户与机器人的交互包括有语音的交互，从多模态输入信息中将语音信息提取出来进行单独的分析，将语音信息中的信息段与系统中预测的关键词进行匹配，若匹配结果为是，则按照与该关键词相关联的预设的广告策略将该广告策略植入与用户的交互中。例如，若用户与机器人交互时说：“天气好热，我想去买个风扇”，其中，“买个风扇”作为关键词与系统中预设的关键词产生匹配，此时可向用户植入有关风扇的广告，而植入广告的方式也是采用非直接性质的广告植入，而是可以以一种模拟普通人交互的形式，例如，机器人可以根据用户的语义，以语音交互的方式进行回应：“我一直使用XX牌风扇，它具有智能调节风力的功能，可以避免我长时间吹风扇而感冒”，这种广告方式通过通俗而不太直接的方式将广告植入了语音中。又如，若用户与机器人交互时说：“天气好热，我需要一个风扇”，同样的，“我需要一个风扇”作为关键词与系统中预设的关键词匹配，也就是说，对于一个预设的广告策略，可以对应多个关键词，任何一个与之匹配的关键词在多模态输入信息中被识别，都会触发广告的植入。
在本实施例中，步骤S20中，识别多模态输入信息中与广告相关联的关键因素包括：根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的关键行为。例如，当用户在与机器人的交互过程中，用户当前的行为为喝水，从而通过智能终端识别到“喝水”行为信息，该信息与系统中的预设的广告策略相关联，触发虚拟机器人反馈时也为喝水的动作，此时，虚拟机器人喝的东西可以是广告植入的品牌饮料(完成广告植入)。又如，当用户场景切换为咖啡厅时，从而系统可以识别到“进入咖啡厅”的行为信息，其中，“进入咖啡厅”这一行为信息与预设的广告策略进行关联，此时，虚拟机器人场景(即咖啡厅)所反馈的场景信息如招牌、内饰等也是与对应广告合作的信息。
在本实施例中，所述广告植入方法还包括步骤：
S40、对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联，其中，所述新的广告策略是根据习惯行为特征而预设的针对同一商品或服务的广告策略。例如，识别到用户的多模态输入信息中关键因素，与其相关联的广告策略为饮料广告，向用户植入XXX品牌的饮料广告，例如机器人通过 语音植入的广告信息为：“我爱喝XXX品牌的茶饮，你喜欢吗”；如果预设值为三，那么第三次识别到相同的关键因素时，将该关键因素关联到库中的新的广告策略(相对于关联时间来说)，在第四次识别到相同的关键因素时，则根据新的广告策略进行植入，例如：“还是喝XXX茶饮吗？”，仍然是针对同一产品或服务而预设的广告策略，只是与之前的广告策略有所不同。
在本实施例中，所述广告植入方法还包括步骤：
S50、根据用户阅览所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信息向用户进行第二次补充植入。本实施例中将植入的广告作为了与用户多模态输入信息中的一部分，因此，当机器人以广告作为多模态输入信息时，用户同样做出相应的回应即进一步多模态输入信息，通过判断进一步多模态输入信息中用户对广告的认可信息。例如，从语音信息中若识别到“这是什么”、“给我看看”等关键因素后，向用户植入与之相关联的产品或服务介绍广告。又如，若从语音信息中识别到“不想要”、“感觉不太好”等关键因素时，可植入预设的另一备用广告策略，若没有备用广告策略，则不进行植入。
实施例二
基于上述实施例，本实施例提供一种基于虚拟机器人的广告植入系统，其包括：多模态输入信息获取模块10，用于获取用户与机器人的多模态输入信息；关键因素识别模块20，用于根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素；广告植入模块30，用于根据所述关键因素，按照预设的广告策略将该广告策略植入与用户的交互中。
本实施例中，所述关键因素识别模块包括：关键词识别单元，用于根据多模态输入信息中的语音信息，识别语音信息中与广告相关联的关键词。
本实施例中，所述关键因素识别模块还包括：关键行为识别单元，根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的关键行为。
本实施例中，所述系统还包括：习惯行为关联模块40，用于对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联。
本实施例中，所述系统还包括：二次植入模块50，用于根据用户阅览所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信息向用户进行第二次补充植入。
以上内容是结合具体的优选实施方式对本发明所作的进一步详细说明，不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干简单推演或替换，都应当视为属于本发明的保护范围。

Claims (10)

  1. 一种基于虚拟机器人的广告植入方法，其特征在于，包括：
    获取用户与机器人的多模态输入信息；
    根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素；
    根据所述关键因素，按照预设的广告策略将该广告策略植入与用户的交互中。
  2. 根据权利要求1所述的基于虚拟机器人的广告植入方法，其特征在于，识别多模态输入信息中与广告相关联的关键因素包括：
    根据多模态输入信息中的语音信息，识别语音信息中与广告相关联的关键词。
  3. 根据权利要求1所述的基于虚拟机器人的广告植入方法，其特征在于，识别多模态输入信息中与广告相关联的关键因素包括：
    根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的关键行为。
  4. 根据权利要求1所述的基于虚拟机器人的广告植入方法，其特征在于，所述广告植入方法还包括：
    对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联，其中，所述新的广告策略是根据习惯行为特征而预设的针对同一商品或服务的广告策略。
  5. 根据权利要求1所述的基于虚拟机器人的广告植入方法，其特征在于，按照预设的广告策略将该广告策略植入与用户的交互中还包括：
    根据用户阅览(或听或看)多模态输入信息中所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信息向用户进行第二次补充植入。
  6. 一种基于虚拟机器人的广告植入系统，其特征在于，包括：
    多模态输入信息获取模块，用于获取用户与机器人的多模态输入信息；
    关键因素识别模块，用于根据所述多模态输入信息，识别多模态输入信息中与预设的广告策略相关联的关键因素；
    广告植入模块，用于根据所述关键因素，按照预设的广告策略将该广 告策略植入与用户的交互中。
  7. 根据权利要求6所述的基于虚拟机器人的广告植入系统，其特征在于，所述关键因素识别模块包括：
    关键词识别单元，用于根据多模态输入信息中的语音信息，识别语音信息中与广告相关联的关键词。
  8. 根据权利要求6所述的基于虚拟机器人的广告植入系统，其特征在于，所述关键因素识别模块包括：
    关键行为识别单元，根据多模态输入信息中的行为信息，识别行为信息中与广告相关联的关键行为。
  9. 根据权利要求6所述的基于虚拟机器人的广告植入系统，其特征在于，所述系统还包括：
    习惯行为关联模块，对关键因素的发生进行记录，若同一关键因素出现的次数超出预设值，则根据该关键因素生成习惯行为特征，根据所述习惯行为特征建立新的广告关联：将习惯行为特征与库中的新的广告策略进行关联，其中，所述新的广告策略是根据习惯行为特征而预设的针对同一商品或服务的广告策略。
  10. 根据权利要求6所述的基于虚拟机器人的广告植入系统，其特征在于，所述系统还包括：
    二次植入模块，用于根据用户阅览所植入的广告后的进一步多模态输入信息，判断进一步多模态输入信息中用户的认可信息，根据所述认可信息向用户进行第二次补充植入。
PCT/CN2016/089212 2016-07-07 2016-07-07 基于虚拟机器人的广告植入方法和系统 WO2018006368A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/089212 WO2018006368A1 (zh) 2016-07-07 2016-07-07 基于虚拟机器人的广告植入方法和系统
CN201680001791.7A CN106462886A (zh) 2016-07-07 2016-07-07 基于虚拟机器人的广告植入方法和系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/089212 WO2018006368A1 (zh) 2016-07-07 2016-07-07 基于虚拟机器人的广告植入方法和系统

Publications (1)

Publication Number Publication Date
WO2018006368A1 true WO2018006368A1 (zh) 2018-01-11

Family

ID=58215712

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/089212 WO2018006368A1 (zh) 2016-07-07 2016-07-07 基于虚拟机器人的广告植入方法和系统

Country Status (2)

Country Link
CN (1) CN106462886A (zh)
WO (1) WO2018006368A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110990553A (zh) * 2019-12-18 2020-04-10 上海智勘科技有限公司 智能音箱语音交互系统与保险代理人的耦合方法及系统
CN110992073A (zh) * 2019-10-25 2020-04-10 深圳市讯呼信息技术有限公司 一种新商业广告服务机器人

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107765852A (zh) * 2017-10-11 2018-03-06 北京光年无限科技有限公司 基于虚拟人的多模态交互处理方法及系统
CN108470533A (zh) * 2018-03-30 2018-08-31 南京七奇智能科技有限公司 基于虚拟人的增强型智能交互广告系统及装置
CN109949086A (zh) * 2019-03-12 2019-06-28 东莞市美誉信息科技有限公司 广告播放方法、装置、服务后台及计算机可读存储介质
CN110517096A (zh) * 2019-08-30 2019-11-29 百度在线网络技术（北京）有限公司 内容植入方法、装置、电子设备及存储介质

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101030283A (zh) * 2006-03-03 2007-09-05 腾讯科技（深圳）有限公司 一种发布广告的方法和系统
CN101262494A (zh) * 2008-01-23 2008-09-10 华为技术有限公司 对发布信息进行处理的方法、客户端、服务器和系统
CN103455800A (zh) * 2013-09-09 2013-12-18 苏州大学 基于智能识别的广告系统及相应广告推送方法
CN103514554A (zh) * 2012-11-15 2014-01-15 Tcl集团股份有限公司 一种智能设备的广告投放方法及该智能设备
CN104065672A (zh) * 2013-03-18 2014-09-24 华为技术有限公司 广告推送方法、客户端及广告推送系统
US20150161651A1 (en) * 2013-12-09 2015-06-11 Andres C. Rodriguez Software-conversation-agent interactive advertising systems and methods
CN104835059A (zh) * 2015-04-27 2015-08-12 东华大学 一种基于体感交互技术的智能广告投放系统
CN105205097A (zh) * 2015-08-18 2015-12-30 耿懿超 一种信息推送方法及信息推送装置
CN105260908A (zh) * 2015-09-28 2016-01-20 魔线科技(深圳)有限公司 基于聊天会话内容推送靶向广告的方法及系统
CN105654343A (zh) * 2015-09-16 2016-06-08 颜陈煜 实现基于客户网络行为定点发送广告及联系客户的系统和方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104602130A (zh) * 2015-02-15 2015-05-06 科大讯飞股份有限公司 实现交互式广告的方法及系统
CN105335498A (zh) * 2015-10-23 2016-02-17 广东小天才科技有限公司 一种基于语音信息进行信息推荐的方法和系统
CN105427137A (zh) * 2015-12-17 2016-03-23 上海出版印刷高等专科学校 互动电子海报装置

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101030283A (zh) * 2006-03-03 2007-09-05 腾讯科技（深圳）有限公司 一种发布广告的方法和系统
CN101262494A (zh) * 2008-01-23 2008-09-10 华为技术有限公司 对发布信息进行处理的方法、客户端、服务器和系统
CN103514554A (zh) * 2012-11-15 2014-01-15 Tcl集团股份有限公司 一种智能设备的广告投放方法及该智能设备
CN104065672A (zh) * 2013-03-18 2014-09-24 华为技术有限公司 广告推送方法、客户端及广告推送系统
CN103455800A (zh) * 2013-09-09 2013-12-18 苏州大学 基于智能识别的广告系统及相应广告推送方法
US20150161651A1 (en) * 2013-12-09 2015-06-11 Andres C. Rodriguez Software-conversation-agent interactive advertising systems and methods
CN104835059A (zh) * 2015-04-27 2015-08-12 东华大学 一种基于体感交互技术的智能广告投放系统
CN105205097A (zh) * 2015-08-18 2015-12-30 耿懿超 一种信息推送方法及信息推送装置
CN105654343A (zh) * 2015-09-16 2016-06-08 颜陈煜 实现基于客户网络行为定点发送广告及联系客户的系统和方法
CN105260908A (zh) * 2015-09-28 2016-01-20 魔线科技(深圳)有限公司 基于聊天会话内容推送靶向广告的方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992073A (zh) * 2019-10-25 2020-04-10 深圳市讯呼信息技术有限公司 一种新商业广告服务机器人
CN110990553A (zh) * 2019-12-18 2020-04-10 上海智勘科技有限公司 智能音箱语音交互系统与保险代理人的耦合方法及系统

Also Published As

Publication number Publication date
CN106462886A (zh) 2017-02-22

Similar Documents

Publication Publication Date Title
WO2018006368A1 (zh) 基于虚拟机器人的广告植入方法和系统
US11341534B2 (en) Server-based intelligent and personalized advertisement with augmented reality enhancement
WO2019218851A1 (zh) 一种广告推送方法、装置、设备及存储介质
US20160026871A1 (en) Obtaining information from an environment of a user of a wearable camera system
US9558397B2 (en) Method and apparatus for automated analysis and identification of a person in image and video content
US20200004291A1 (en) Wearable apparatus and methods for processing audio signals
CN105957525A (zh) 一种语音助手的交互方法以及用户设备
JPWO2015125375A1 (ja) 情報処理装置、制御方法、プログラム、およびシステム
CN111797249A (zh) 一种内容推送方法、装置与设备
CN104021398A (zh) 一种可穿戴智能设备及辅助身份识别的方法
CN107809654A (zh) 电视机系统及电视机控制方法
CN106650632A (zh) 身份识别方法、装置及电子设备
CN109074679A (zh) 具有增强现实强化的基于场景的实时广告
CN103902040A (zh) 用于移动终端的处理装置、处理方法和电子设备
US20110176025A1 (en) Video information processing apparatus, video information processing method, and computer-readable storage medium
CN112399239A (zh) 视频播放方法及装置
CN106844780A (zh) 图片发送方法和图片发送系统
CN103440307A (zh) 媒体信息提供方法及装置
CN107992825A (zh) 一种基于增强现实的人脸识别的方法及系统
CN107908347A (zh) 一种基于照片的消息发送方法及终端设备
US20220075881A1 (en) Information Processing Apparatus, Information Processing Method, and Information Processing Program
CN107688826A (zh) 基于光感的人机识别方法及应用其的广告投放方法和系统
CN106055708A (zh) 一种图片生成和展示方法、装置及终端设备
CN106774838A (zh) 智能眼镜及其显示信息的方法及装置
CN110990817A (zh) 一种人脸识别验证身份及信息的方法、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: 16907873

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: 16907873

Country of ref document: EP

Kind code of ref document: A1