WO2017041369A1 - 基于人工智能的人机交互的交互引导方法和装置 - Google Patents

基于人工智能的人机交互的交互引导方法和装置 Download PDF

Info

Publication number
WO2017041369A1
WO2017041369A1 PCT/CN2015/096339 CN2015096339W WO2017041369A1 WO 2017041369 A1 WO2017041369 A1 WO 2017041369A1 CN 2015096339 W CN2015096339 W CN 2015096339W WO 2017041369 A1 WO2017041369 A1 WO 2017041369A1
Authority
WO
WIPO (PCT)
Prior art keywords
topic
data
user
guiding
map
Prior art date
Application number
PCT/CN2015/096339
Other languages
English (en)
French (fr)
Inventor
�田�浩
吴华
李大任
佘俏俏
忻舟
徐倩
周超
高原
王德胜
肖天久
徐冉
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 WO2017041369A1 publication Critical patent/WO2017041369A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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
    • G06F16/332Query formulation
    • G06F16/3329Natural language query formulation or dialogue systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/279Recognition of textual entities
    • G06F40/289Phrasal analysis, e.g. finite state techniques or chunking
    • G06F40/295Named entity recognition

Definitions

  • the present invention relates to the field of artificial intelligence technologies, and in particular, to an interactive guidance method and apparatus for human-computer interaction based on artificial intelligence.
  • AI Artificial Intelligence is a branch of computer science, abbreviated as AI. It is a new technical science that studies and develops theories, methods, techniques and application systems for simulating, extending and extending human intelligence.
  • the person In the traditional human-computer interaction process, the person is in an active position and the machine is in a passive position.
  • the user actively proposes a topic, and the machine receives and parses the topic proposed by the user, and selects an appropriate response feedback from the pre-established dialog library to the user; or the machine further clarifies the topic proposed by the user through further interaction, and makes a reasoning through the knowledge base to calculate a suitable
  • the feedback is sent to the user.
  • an object of the present invention is to provide an interactive guidance method for human-computer interaction based on artificial intelligence, which can improve the continuity of human-computer interaction and make human-computer interaction more smooth and natural.
  • a second object of the present invention is to provide an interactive guidance device for human-computer interaction based on artificial intelligence.
  • an embodiment of the first aspect of the present invention provides an interactive guidance method for human-computer interaction based on artificial intelligence, comprising: S1, receiving interaction information input by a user, and determining a current topic according to the interaction information; S2 And obtaining, by the topic map, a plurality of candidate guidance topics related to the current topic, where the topic map includes a plurality of topics and an association relationship between the topics; S3, acquiring user image data of the user; And S4, root And selecting, according to the user portrait data, a guiding topic from the plurality of candidate guiding topics related to the current topic, and feeding back the guiding topic to the user.
  • the artificial intelligence-based human-computer interaction interactive guidance method determines the current topic by receiving the interaction information input by the user, and obtains a plurality of candidate guidance topics related to the current topic based on the topic map, and then combines the user's users.
  • the portrait data selects the guiding topic from the candidate guiding topics, and feeds the guiding topic to the user, which improves the continuity of the human-computer interaction and makes the human-computer interaction more smooth and natural.
  • the embodiment of the second aspect of the present invention provides an interactive guidance device for human-computer interaction based on artificial intelligence, comprising: a determining module, configured to receive interaction information input by a user, and determine a current topic according to the interaction information; And obtaining, by the topic map, a plurality of candidate guidance topics related to the current topic, where the topic map includes a plurality of topics and an association relationship between the topics; and an obtaining module, configured to acquire the user User image data; and a feedback module, configured to select a guiding topic from the plurality of candidate guiding topics related to the current topic according to the user portrait data, and feed back the guiding topic to the user.
  • the artificial intelligence-based human-computer interaction interactive guiding device of the embodiment of the present invention determines the current topic by receiving the interaction information input by the user, and obtains a plurality of candidate guidance topics related to the current topic based on the topic map, and then combines the user's user.
  • the portrait data selects the guiding topic from the candidate guiding topics, and feeds the guiding topic to the user, which improves the continuity of the human-computer interaction and makes the human-computer interaction more smooth and natural.
  • the third aspect of the embodiments of the present invention discloses a storage medium for storing an application, and the application is used to execute an artificial intelligence-based interactive interaction method according to the first aspect of the present invention.
  • a fourth aspect of the embodiments of the present invention discloses an apparatus, including: one or more processors; a memory; one or more modules, the one or more modules being stored in the memory when When multiple processors are executing, do the following:
  • FIG. 1 is a flow chart of an artificial intelligence based interactive guidance method for human-computer interaction according to an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of the effect of a topic map in accordance with one embodiment of the present invention.
  • FIG. 3 is a schematic diagram showing the effect of network text data as semi-structured data according to an embodiment of the present invention.
  • FIG. 4 is a diagram showing the effect of network text data as structured data according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of an effect of acquiring user browsing behavior data according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of the effect of establishing a topic map according to an embodiment of the present invention.
  • FIG. 7 is a first schematic structural diagram of an interactive guidance device for human-computer interaction based on artificial intelligence according to an embodiment of the present invention.
  • FIG. 8 is a schematic structural diagram 2 of an interactive guidance device for human-computer interaction based on artificial intelligence according to an embodiment of the present invention.
  • FIG. 1 is a flow chart of an artificial intelligence based interactive guidance method for human-computer interaction according to an embodiment of the present invention.
  • the artificial intelligence-based interactive guidance method for human-computer interaction may include:
  • S1 Receive interaction information input by the user, and determine a current topic according to the interaction information.
  • the interaction information input by the user may be received first, for example: “Is the dream space look good?”, and then the interaction information is subjected to requirement identification and correlation calculation, thereby determining that the current topic is “the dream space evaluation”.
  • the topic map may include a plurality of topics and associations between topics.
  • a plurality of candidate guidance topics related to the current topic may be acquired based on the pre-established topic map. For example, if the current topic is "Privacy Dream Space Evaluation", you can obtain a number of guiding topics related to "Pirates of Dreams” based on the topic map, such as "Nolan's film”, “Leonardo's movie”, etc. And their relationship with the "dream space evaluation”.
  • the user portrait data is a collection of data such as attributes, states, interests, and the like of the user, and can be acquired by the user actively input or according to the historical interaction record of the user, and then integrated, thereby generating personalized user portrait data about the user.
  • the user's intention information may be determined according to the user image data and the context information of the interaction information, and then the guidance topic is selected from a plurality of candidate guidance topics related to the current topic according to the user's intention information, and the guidance topic is fed back to the user.
  • a guided topic can be an extension of the current topic.
  • the current topic can be “Chicken Practice”. After the current topic interaction ends, the current topic can be extended.
  • the user portrait data such as “user is a pregnant woman”, the user can be fed back to the topic “How to eat chicken in a pregnant woman is better”.
  • the guiding topic can also be a recommendation based on the current topic. For example, if the interactive information is “Is the dream space to look good?”, the current topic can be “the dream space evaluation”. After the current topic interaction ends, based on the current topic, and combined with user portrait data such as "users like to watch movies", the user can be fed back to guide the topic "Nolan's movie.”
  • the user's intention information When the user's intention information cannot be determined based on the user image data and the context information of the interaction information, the user's intention information needs to be clarified.
  • the interactive information is “How to go to the Forbidden City?”, while Beijing, Shenyang, and Taipei all have “Forbidden City”. Therefore, it is necessary to clarify the user’s intention information, and can return a question of clarification to the user according to the interactive information. “Excuse me. Which is the Forbidden City to go to?”.
  • step S2 the artificial intelligence based human interaction interaction guiding method may further include step S5.
  • a node in the topic map represents a topic or a requirement put forward by the user, and each node may include a reply of the corresponding topic and a resource satisfying the user's requirement, and the associated node may pass the edge. Correlation is made to form a meshed topic map.
  • the method for establishing the topic map is as follows: the topic association data can be obtained, and then the topic map is established according to the topic association data.
  • obtaining topic related data can be divided into two cases.
  • the first case the network text data can be obtained first, and the topic related data is obtained from the network text data.
  • network text data can be divided into unstructured data, semi-structured data and structured data.
  • the topic association data can be obtained based on entity extraction and syntax analysis.
  • unstructured data may include news, forums, blogs, videos, and the like.
  • the text text data "the most eye-catching Nobel Prize for Literature is the winner, the Frenchman Modiano is the lucky one of the new department. Of course, many times the nomination is always the same as the Nobel Prize. Haruki Murakami is still the one.
  • the network text data is semi-structured data, based on page structure analysis, tag extraction, and entity recognition Related data.
  • the semi-structured data may include Wikipedia, Baidu Encyclopedia and other encyclopedic data, or thematic data.
  • the "off-the-life" of "Djokovic", including “family life” and “charity activities” can be obtained based on page structure analysis, tag extraction, and entity recognition.
  • the topic related data is obtained from the knowledge map.
  • the structured data may include knowledge map data. For example, as shown in Figure 4, the film “The Dream Space” and the movie “Star Crossing" are directed by "Christopher Nolan.”
  • the second case the user's search behavior data or browsing behavior data may be obtained first, and then the topic association data is generated according to the search behavior data or the browsing behavior data.
  • the search behavior data of the user may be acquired, and the corresponding search object is obtained according to the search behavior data, and then the topic association data is generated according to the search object. For example, if the user continuously searches for "Nolan”, “Nolan's Movie” and “Christian Bell", the above topics can be correlated to generate topic related data.
  • the browsing behavior data of the user may also be obtained, and the corresponding browsing object is obtained according to the browsing behavior data, and the topic related data is generated according to the browsing object. For example, as shown in FIG. 5, multiple news or videos that are clicked when a user browses a webpage may be associated to generate topic related data.
  • the topic map may be established according to the topic association data by one or more of the RandomWalk algorithm, the association analysis algorithm, and the collaborative filtering algorithm.
  • q1, q2, q3, and q1', q2', q3', and q4' are topics
  • d1, d2, d3, and d4 are resource data.
  • the resource data d1 and d2 are associated with the topic q1; the resource data d1, d2, d3 are associated with the topic q2; the resource data d4 is associated with the topic q3, and the topic with the associated relationship and the resource data are used. Solid lines are connected.
  • the topic q1' is a topic that the user issues after the resource data d1 or d4 is browsed according to the resource data d1 or d4, and the relationship between them has a sequential relationship.
  • the topic q2' is a topic issued based on the resource data d2
  • the topic q3' is a topic issued based on the resource data d2 or d3
  • the topic q4' is a topic issued based on the resource data d3 or d4.
  • the topic q1 and the topic q1' have an association relationship
  • the topic q1 and the topic q2' have an association relationship, etc.
  • the topic map as shown in Fig. 2 is established.
  • the artificial intelligence-based human-computer interaction interactive guidance method determines the current topic by receiving the interaction information input by the user, and obtains a plurality of candidate guidance topics related to the current topic based on the topic map, and then combines the user's users.
  • the portrait data selects the guiding topic from the candidate guiding topics, and feeds the guiding topic to the user, which improves the continuity of the human-computer interaction and makes the human-computer interaction more smooth and natural.
  • the present invention also provides an interactive guidance device for human-computer interaction based on artificial intelligence.
  • FIG. 7 is a first schematic structural diagram of an interactive guidance device for human-computer interaction based on artificial intelligence according to an embodiment of the present invention.
  • the artificial intelligence-based human-computer interaction interactive guiding device may include: a determining module 110, an obtaining module 120, an obtaining module 130, and a feedback module 140.
  • the determining module 110 is configured to receive interaction information input by the user, and determine a current topic according to the interaction information.
  • the determining module 110 may first receive the interaction information input by the user, for example: “Is the dream space look good?”, and then perform the requirement identification and the correlation calculation on the interaction information, thereby determining that the current topic is “the dream space evaluation”.
  • the obtaining module 120 is configured to obtain a plurality of candidate guiding topics related to the current topic based on the topic map.
  • the topic map may include a plurality of topics and associations between topics.
  • the obtaining module 120 may acquire a plurality of candidate guiding topics related to the current topic based on the pre-established topic map. For example, if the current topic is "Privacy Dream Space Evaluation", you can obtain a number of guiding topics related to "Pirates of Dreams” based on the topic map, such as "Nolan's film”, “Leonardo's movie”, etc. And their relationship with the "dream space evaluation”.
  • the obtaining module 130 is configured to acquire user image data of the user.
  • the user portrait data is a collection of data such as attributes, states, interests, and the like of the user, and can be acquired by the user actively input or according to the historical interaction record of the user, and then integrated, thereby generating personalized user portrait data about the user.
  • the feedback module 140 is configured to select a guiding topic from a plurality of candidate guiding topics related to the current topic according to the user portrait data, and feed back the guiding topic to the user.
  • the feedback module 140 may determine the intention information of the user according to the context information of the user image data and the interaction information, and then select a guidance topic from the plurality of candidate guidance topics related to the current topic according to the intention information of the user, and provide feedback to the user. Guide the topic.
  • a guided topic can be an extension of the current topic.
  • the current topic can be “Chicken Practice”. After the current topic interaction ends, the current topic can be extended.
  • the user portrait data such as “user is a pregnant woman”, the user can be fed back to the topic “How to eat chicken in a pregnant woman is better”.
  • the guiding topic can also be a recommendation based on the current topic. For example, if the interactive information is “Is the dream space to look good?”, the current topic can be “the dream space evaluation”. After the current topic interaction ends, based on the current topic, and combined with user portrait data such as "users like to watch movies", the user can be fed back to guide the topic "Nolan's movie.”
  • the user's intention information When the user's intention information cannot be determined based on the user image data and the context information of the interaction information, the user's intention information needs to be clarified.
  • the interactive information is “How to go to the Forbidden City?”, while Beijing, Shenyang, and Taipei all have “Forbidden City”. Therefore, it is necessary to clarify the user’s intention information, and can return a question of clarification to the user according to the interactive information. “Excuse me. Which is the Forbidden City to go to?”.
  • the artificial intelligence-based human-computer interaction interactive guiding apparatus of the embodiment of the present invention may further include an establishing module 150.
  • the setup module 150 is used to build a topic map.
  • a node in the topic map represents a topic or a requirement put forward by the user, and each node may include a reply of the corresponding topic and a resource satisfying the user's requirement, and the associated node may pass the edge. Correlation is made to form a meshed topic map.
  • the establishing module 150 includes an obtaining unit 151 and an establishing unit 152.
  • the obtaining unit 151 can acquire topic related data.
  • the acquisition unit 151 acquires topic association data and can be divided into two cases.
  • the first case the network text data can be obtained first, and the topic related data is obtained from the network text data.
  • network text data can be divided into unstructured data, semi-structured data and structured data.
  • the topic association data can be obtained based on entity extraction and syntax analysis.
  • unstructured data may include news, forums, blogs, videos, and the like.
  • the text text data "the most eye-catching Nobel Prize for Literature is the winner, the Frenchman Modiano is the lucky one of the new department. Of course, many times the nomination is always the same as the Nobel Prize. Haruki Murakami is still the one.
  • the topic-related data is obtained based on page structure analysis, tag extraction, and entity recognition.
  • the semi-structured data may include Wikipedia, Baidu Encyclopedia and other encyclopedic data, or thematic data.
  • the "off-the-life" of "Djokovic", including “family life” and “charity activities” can be obtained based on page structure analysis, tag extraction, and entity recognition.
  • the topic related data is obtained from the knowledge map.
  • the structured data may include knowledge map data. For example, as shown in Figure 4, the film “The Dream Space” and the movie “Star Crossing" are directed by "Christopher Nolan.”
  • the second case the user's behavior data can be obtained first, and then the topic association data is generated according to the behavior data.
  • the behavior data may include search behavior data and browsing behavior data.
  • the search behavior data of the user may be acquired, and the corresponding search object is obtained according to the search behavior data, and then the topic association data is generated according to the search object. For example, if the user continuously searches for "Nolan”, “Nolan's Movie” and “Christian Bell", the above topics can be correlated to generate topic related data.
  • the browsing behavior data of the user may also be obtained, and the corresponding browsing object is obtained according to the browsing behavior data, and the topic related data is generated according to the browsing object. For example, as shown in FIG. 5, multiple news or videos that are clicked when a user browses a webpage may be associated to generate topic related data.
  • the establishing unit 152 may establish a topic map according to the topic association data by one or more of a RandomWalk algorithm, an association analysis algorithm, and a collaborative filtering algorithm.
  • q1, q2, q3, and q1', q2', q3', and q4' are topics
  • d1, d2, d3, and d4 are resource data.
  • the resource data d1 and d2 are associated with the topic q1;
  • the resource data d1, d2, d3 are associated with the topic q2;
  • the resource data d4 is associated with the topic q3, and the topic with the associated relationship and the resource data are used.
  • Solid lines are connected. Based on the RandomWalk algorithm, it is possible to iteratively calculate the relationship between the topic q1 and the resource data d3, which are connected by a dotted line.
  • the topic q1' is a topic that the user issues after the resource data d1 or d4 is browsed according to the resource data d1 or d4, and the relationship between them has a sequential relationship.
  • the topic q2' is a topic issued based on the resource data d2
  • the topic q3' is a topic issued based on the resource data d2 or d3
  • the topic q4' is a topic issued based on the resource data d3 or d4.
  • the topic q1 and the topic q1' have an association relationship
  • the topic q1 and the topic q2' have an association relationship, etc.
  • the topic map as shown in Fig. 2 is established.
  • the artificial intelligence-based human-computer interaction interactive guiding device of the embodiment of the present invention determines the current topic by receiving the interaction information input by the user, and obtains a plurality of candidate guidance topics related to the current topic based on the topic map, and then combines the user's user.
  • the portrait data selects the guiding topic from the candidate guiding topics, and feeds the guiding topic to the user, which improves the continuity of the human-computer interaction and makes the human-computer interaction more smooth and natural.
  • the present invention also provides a storage medium for storing an application for performing an artificial intelligence-based human-computer interaction interactive guidance method according to any of the embodiments of the present invention.
  • the present invention also provides an apparatus comprising: one or more processors; a memory; one or more modules, one or more modules stored in the memory when being one or more processors Perform the following operations when performing:
  • S2' obtains a plurality of candidate guidance topics related to the current topic based on the topic map.
  • first and second are used for descriptive purposes only, and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Machine Translation (AREA)

Abstract

一种基于人工智能的人机交互的交互引导方法和装置,其中,方法包括以下步骤:S1、接收用户输入的交互信息,并根据交互信息确定当前话题;S2、基于话题图谱获得多个与当前话题相关的待选引导话题;S3、获取用户的用户画像数据;以及S4、根据用户画像数据从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。上述基于人工智能的人机交互的交互引导方法和装置,通过接收用户输入的交互信息确定当前话题,并基于话题图谱获得多个与当前话题相关的待选引导话题,再结合用户的用户画像数据从待选引导话题中选择引导话题,以及向用户反馈引导话题,提高了人机交互的持续性,使人机交互更加流畅、自然。

Description

基于人工智能的人机交互的交互引导方法和装置
相关申请的交叉引用
本申请要求百度在线网络技术(北京)有限公司于2015年9月7日提交的、发明名称为“基于人工智能的人机交互的交互引导方法和装置”的、中国专利申请号“201510564818.0”的优先权。
技术领域
本发明涉及人工智能技术领域,尤其涉及一种基于人工智能的人机交互的交互引导方法和装置。
背景技术
人工智能(Artificial Intelligence)是计算机科学的一个分支,英文缩写为AI,是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。
在传统的人机交互过程中,人处于主动的位置,机器处于被动的位置。用户主动提出话题,机器接收并解析用户提出的话题,从预先建立的对话库中选择合适的回答反馈给用户;或者机器通过进一步交互,明确用户提出的话题,通过知识库进行推理,计算出合适的回答反馈给用户。
但是,在当前话题结束后,机器需要继续等待用户提出的下一个话题,然后再进行回答。由于缺乏话题之间的关联的信息,机器无法主动地延续或者引导出新的话题,无法像人与人之间那样进行持续地交互,缺乏主动性和联想力。
发明内容
本发明旨在至少在一定程度上解决相关技术中的技术问题之一。为此,本发明的一个目的在于提出一种基于人工智能的人机交互的交互引导方法,能够提高人机交互的持续性,使人机交互更加流畅、自然。
本发明的第二个目的在于提出一种基于人工智能的人机交互的交互引导装置。
为了实现上述目的,本发明第一方面实施例提出了一种基于人工智能的人机交互的交互引导方法,包括:S1、接收用户输入的交互信息,并根据所述交互信息确定当前话题;S2、基于话题图谱获得多个与所述当前话题相关的待选引导话题,其中,所述话题图谱包括多个话题及所述话题之间的关联关系;S3、获取所述用户的用户画像数据;以及S4、根 据所述用户画像数据从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
本发明实施例的基于人工智能的人机交互的交互引导方法,通过接收用户输入的交互信息确定当前话题,并基于话题图谱获得多个与当前话题相关的待选引导话题,再结合用户的用户画像数据从待选引导话题中选择引导话题,以及向用户反馈引导话题,提高了人机交互的持续性,使人机交互更加流畅、自然。
本发明第二方面实施例提出了一种基于人工智能的人机交互的交互引导装置,包括:确定模块,用于接收用户输入的交互信息,并根据所述交互信息确定当前话题;获得模块,用于基于话题图谱获得多个与所述当前话题相关的待选引导话题,其中,所述话题图谱包括多个话题及所述话题之间的关联关系;获取模块,用于获取所述用户的用户画像数据;以及反馈模块,用于根据所述用户画像数据从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
本发明实施例的基于人工智能的人机交互的交互引导装置,通过接收用户输入的交互信息确定当前话题,并基于话题图谱获得多个与当前话题相关的待选引导话题,再结合用户的用户画像数据从待选引导话题中选择引导话题,以及向用户反馈引导话题,提高了人机交互的持续性,使人机交互更加流畅、自然。
本发明实施例第三方面公开了一种存储介质,用于存储应用程序,所述应用程序用于执行本发明第一方面实施例所述的基于人工智能的人机交互的交互引导方法。
本发明实施例第四方面公开了一种设备,包括:一个或者多个处理器;存储器;一个或者多个模块,所述一个或者多个模块存储在所述存储器中,当被所述一个或者多个处理器执行时进行如下操作:
接收用户输入的交互信息,并根据所述交互信息确定当前话题;
基于话题图谱获得多个与所述当前话题相关的待选引导话题,其中,所述话题图谱包括多个话题及所述话题之间的关联关系;
获取所述用户的用户画像数据;以及
根据所述用户画像数据从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
附图说明
本发明所述的和/或附加的方面和优点从下面结合附图对实施例的描述中将变得明显和容易理解,其中:
图1是根据本发明一个实施例的基于人工智能的人机交互的交互引导方法的流程图。
图2是根据本发明一个实施例的话题图谱的效果示意图。
图3是根据本发明一个实施例的网络文本数据为半结构化数据时的效果示意图。
图4是根据本发明一个实施例的网络文本数据为结构化数据时的效果示意图。
图5是根据本发明一个实施例的获取用户浏览行为数据的效果示意图。
图6是根据本发明一个实施例的建立话题图谱的效果示意图。
图7是根据本发明一个实施例的基于人工智能的人机交互的交互引导装置的结构示意图一。
图8是根据本发明一个实施例的基于人工智能的人机交互的交互引导装置的结构示意图二。
具体实施方式
下面详细描述本发明的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的模块或具有相同或类似功能的模块。下面通过参考附图描述的实施例是示例性的,旨在用于解释本发明,而不能理解为对本发明的限制。
下面参考附图描述本发明实施例的基于人工智能的人机交互的交互引导方法和装置。
图1是根据本发明一个实施例的基于人工智能的人机交互的交互引导方法的流程图。
如图1所示,基于人工智能的人机交互的交互引导方法可包括:
S1、接收用户输入的交互信息,并根据交互信息确定当前话题。
具体地,可先接收用户输入的交互信息例如:“盗梦空间好看吗?”,然后对该交互信息进行需求识别以及相关性计算,从而确定当前话题为“盗梦空间评价”。
S2、基于话题图谱获得多个与当前话题相关的待选引导话题。
其中,话题图谱可包括多个话题及话题之间的关联关系。
具体地,可基于预先建立的话题图谱获取多个与当前话题相关的待选引导话题。例如:当前话题为“盗梦空间评价”,则可根据话题图谱获取多个与“盗梦空间评价”相关的引导话题如“诺兰导演的电影”、“莱昂纳多主演的电影”等,及它们与“盗梦空间评价”之间的关联关系。
S3、获取用户的用户画像数据。
其中,用户画像数据为用户的属性、状态、兴趣等数据的集合,可通过用户主动输入或者根据用户的历史交互记录获取,然后对其进行整合,从而生成关于用户的个性化的用户画像数据。
S4、根据用户画像数据从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
具体地,可根据用户画像数据和交互信息的上下文信息确定用户的意图信息,然后根据用户的意图信息从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
举例来说,引导话题可以是当前话题的延伸。例如:交互信息为“鸡肉怎么做?”,则当前话题可为“鸡肉的做法”。当前话题交互结束后,可对当前话题延伸,结合用户画像数据如“用户为孕妇”,则可向用户反馈引导话题“孕妇如何吃鸡肉比较好”。
当然,引导话题也可以是基于当前话题的推荐。例如:交互信息为“盗梦空间好看吗?”,则当前话题可为“盗梦空间评价”。当前话题交互结束后,可基于当前话题,并结合用户画像数据如“用户喜欢看电影”,则可向用户反馈引导话题“诺兰的电影”。
而当无法根据用户画像数据和交互信息的上下文信息确定用户的意图信息时,则需要对用户的意图信息进行澄清。例如:交互信息为“去故宫怎么走?”,而北京、沈阳和台北都有“故宫”,因此需要对用户的意图信息进行澄清,可根据交互信息向用户返回意图澄清的问句“请问您是要去哪个故宫?”。
另外,在步骤S2之前,基于人工智能的人机交互的交互引导方法还可包括步骤S5。
S5、建立话题图谱。
如图2所示,话题图谱中的一个节点表示用户提出的一个话题或一个需求,每个节点中可包含有对应话题的回复和满足用户需求的资源,而有关联的节点之间可通过边进行关联,从而形成网状的话题图谱。
具体地,建立话题图谱的方法如下:可获取话题关联数据,然后根据话题关联数据建立话题图谱。
更具体地,获取话题关联数据可分为两种情况。
第一种情况:可先获取网络文本数据,并从网络文本数据中获取话题关联数据。其中,网络文本数据可分为非结构化数据、半结构化数据和结构化数据。
当网络文本数据为非结构化数据时,可基于实体提取和句法分析获取话题关联数据。其中,非结构化数据可包括新闻、论坛、博客、视频等。例如:对于网络文本数据“最受瞩目的诺贝尔文学奖花开有主,法国人莫迪亚诺成为新科幸运者。当然,多次提名总是和诺奖失之交臂的村上春树还是那个“离诺奖最近的人”。中国诗人北岛,也只是让国人狂热了一回。”,可基于实体提取技术提取实体信息“诺贝尔文学奖”、“法国人莫迪亚诺”、“村上春树”、“中国诗人北岛”,并基于句法分析获知上述实体信息之间存在关联。更进一步地,还可分析出法国人莫迪亚诺是诺贝尔文学奖获得者,村上春树和中国诗人北岛没有获得诺贝尔文学奖等。
当网络文本数据为半结构化数据时,基于页面结构分析、标签提取、实体识别获取话 题关联数据。其中,半结构化数据可包括维基百科、百度百科等百科数据,或者专题数据等。例如:如图3所示,可基于页面结构分析、标签提取、实体识别,获取“德约科维奇”的“场下生活”包括“家庭生活”和“慈善活动”。
当网络文本数据为结构化数据时,从知识图谱中获取话题关联数据。其中,结构化数据可包括知识图谱数据。例如:如图4所示,电影“盗梦空间”和电影“星际穿越”的导演为“克里斯托弗.诺兰”。
第二种情况:可先获取用户的搜索行为数据或浏览行为数据,然后根据搜索行为数据或浏览行为数据生成话题关联数据。
具体地,可获取用户的搜索行为数据,并根据搜索行为数据获取对应的搜索对象,然后根据搜索对象生成话题关联数据。例如:用户连续搜索了“诺兰”、“诺兰的电影”和“克里斯蒂安.贝尔”,则可对上述话题进行关联,从而生成话题关联数据。
当然,也可以获取用户的浏览行为数据,并根据浏览行为数据获取对应的浏览对象,根据浏览对象生成话题关联数据。例如:如图5所示,可将用户浏览网页时点击的多个新闻或视频进行关联,从而生成话题关联数据。
在获取话题关联数据之后,可通过RandomWalk算法、关联分析算法、协同过滤算法中的一种或多种,根据话题关联数据建立话题图谱。举例来说,如图6所示,q1、q2、q3以及q1’、q2’、q3’、q4’为话题,d1、d2、d3和d4为资源数据。从图6中可知,资源数据d1和d2与话题q1相关联;资源数据d1、d2、d3与话题q2相关联;资源数据d4与话题q3相关联,具有关联关系的话题和资源数据之间用实线相连。基于RandomWalk算法可迭代计算出话题q1和资源数据d3之间具有关联关系,它们之间用虚线相连。而话题q1’为用户在浏览了资源数据d1或d4后,根据资源数据d1或d4发出的话题,它们之间的关联关系具有顺序关系。同理,话题q2’为根据资源数据d2发出的话题,话题q3’为根据资源数据d2或d3发出的话题,话题q4’为根据资源数据d3或d4发出的话题。进一步地,可推导出话题q1和话题q1’具有关联关系,话题q1和话题q2’具有关联关系等,最终建立如图2所示的话题图谱。
本发明实施例的基于人工智能的人机交互的交互引导方法,通过接收用户输入的交互信息确定当前话题,并基于话题图谱获得多个与当前话题相关的待选引导话题,再结合用户的用户画像数据从待选引导话题中选择引导话题,以及向用户反馈引导话题,提高了人机交互的持续性,使人机交互更加流畅、自然。
为实现上述目的,本发明还提出一种基于人工智能的人机交互的交互引导装置。
图7是根据本发明一个实施例的基于人工智能的人机交互的交互引导装置的结构示意图一。
如图7所示,该基于人工智能的人机交互的交互引导装置可包括:确定模块110、获得模块120、获取模块130和反馈模块140。
确定模块110用于接收用户输入的交互信息,并根据交互信息确定当前话题。
具体地,确定模块110可先接收用户输入的交互信息例如:“盗梦空间好看吗?”,然后对该交互信息进行需求识别以及相关性计算,从而确定当前话题为“盗梦空间评价”。
获得模块120用于基于话题图谱获得多个与当前话题相关的待选引导话题。
其中,话题图谱可包括多个话题及话题之间的关联关系。
具体地,获得模块120可基于预先建立的话题图谱获取多个与当前话题相关的待选引导话题。例如:当前话题为“盗梦空间评价”,则可根据话题图谱获取多个与“盗梦空间评价”相关的引导话题如“诺兰导演的电影”、“莱昂纳多主演的电影”等,及它们与“盗梦空间评价”之间的关联关系。
获取模块130用于获取用户的用户画像数据。
其中,用户画像数据为用户的属性、状态、兴趣等数据的集合,可通过用户主动输入或者根据用户的历史交互记录获取,然后对其进行整合,从而生成关于用户的个性化的用户画像数据。
反馈模块140用于根据用户画像数据从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
具体地,反馈模块140可根据用户画像数据和交互信息的上下文信息确定用户的意图信息,然后根据用户的意图信息从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
举例来说,引导话题可以是当前话题的延伸。例如:交互信息为“鸡肉怎么做?”,则当前话题可为“鸡肉的做法”。当前话题交互结束后,可对当前话题延伸,结合用户画像数据如“用户为孕妇”,则可向用户反馈引导话题“孕妇如何吃鸡肉比较好”。
当然,引导话题也可以是基于当前话题的推荐。例如:交互信息为“盗梦空间好看吗?”,则当前话题可为“盗梦空间评价”。当前话题交互结束后,可基于当前话题,并结合用户画像数据如“用户喜欢看电影”,则可向用户反馈引导话题“诺兰的电影”。
而当无法根据用户画像数据和交互信息的上下文信息确定用户的意图信息时,则需要对用户的意图信息进行澄清。例如:交互信息为“去故宫怎么走?”,而北京、沈阳和台北都有“故宫”,因此需要对用户的意图信息进行澄清,可根据交互信息向用户返回意图澄清的问句“请问您是要去哪个故宫?”。
另外,如图8所示,本发明实施例的基于人工智能的人机交互的交互引导装置还可包括建立模块150。
建立模块150用于建立话题图谱。
如图2所示,话题图谱中的一个节点表示用户提出的一个话题或一个需求,每个节点中可包含有对应话题的回复和满足用户需求的资源,而有关联的节点之间可通过边进行关联,从而形成网状的话题图谱。
具体地,建立模块150包括获取单元151和建立单元152。
获取单元151可获取话题关联数据。
获取单元151获取话题关联数据可分为两种情况。
第一种情况:可先获取网络文本数据,并从网络文本数据中获取话题关联数据。其中,网络文本数据可分为非结构化数据、半结构化数据和结构化数据。
当网络文本数据为非结构化数据时,可基于实体提取和句法分析获取话题关联数据。其中,非结构化数据可包括新闻、论坛、博客、视频等。例如:对于网络文本数据“最受瞩目的诺贝尔文学奖花开有主,法国人莫迪亚诺成为新科幸运者。当然,多次提名总是和诺奖失之交臂的村上春树还是那个“离诺奖最近的人”。中国诗人北岛,也只是让国人狂热了一回。”,可基于实体提取技术提取实体信息“诺贝尔文学奖”、“法国人莫迪亚诺”、“村上春树”、“中国诗人北岛”,并基于句法分析获知上述实体信息之间存在关联。更进一步地,还可分析出法国人莫迪亚诺是诺贝尔文学奖获得者,村上春树和中国诗人北岛没有获得诺贝尔文学奖等。
当网络文本数据为半结构化数据时,基于页面结构分析、标签提取、实体识别获取话题关联数据。其中,半结构化数据可包括维基百科、百度百科等百科数据,或者专题数据等。例如:如图3所示,可基于页面结构分析、标签提取、实体识别,获取“德约科维奇”的“场下生活”包括“家庭生活”和“慈善活动”。
当网络文本数据为结构化数据时,从知识图谱中获取话题关联数据。其中,结构化数据可包括知识图谱数据。例如:如图4所示,电影“盗梦空间”和电影“星际穿越”的导演为“克里斯托弗.诺兰”。
第二种情况:可先获取用户的行为数据,然后根据行为数据生成话题关联数据。其中,行为数据可包括搜索行为数据和浏览行为数据。
具体地,可获取用户的搜索行为数据,并根据搜索行为数据获取对应的搜索对象,然后根据搜索对象生成话题关联数据。例如:用户连续搜索了“诺兰”、“诺兰的电影”和“克里斯蒂安.贝尔”,则可对上述话题进行关联,从而生成话题关联数据。
当然,也可以获取用户的浏览行为数据,并根据浏览行为数据获取对应的浏览对象,根据浏览对象生成话题关联数据。例如:如图5所示,可将用户浏览网页时点击的多个新闻或视频进行关联,从而生成话题关联数据。
在获取单元151获取话题关联数据之后,建立单元152可通过RandomWalk算法、关联分析算法、协同过滤算法中的一种或多种,根据话题关联数据建立话题图谱。
举例来说,如图6所示,q1、q2、q3以及q1’、q2’、q3’、q4’为话题,d1、d2、d3和d4为资源数据。从图6中可知,资源数据d1和d2与话题q1相关联;资源数据d1、d2、d3与话题q2相关联;资源数据d4与话题q3相关联,具有关联关系的话题和资源数据之间用实线相连。基于RandomWalk算法可迭代计算出话题q1和资源数据d3之间具有关联关系,它们之间用虚线相连。而话题q1’为用户在浏览了资源数据d1或d4后,根据资源数据d1或d4发出的话题,它们之间的关联关系具有顺序关系。同理,话题q2’为根据资源数据d2发出的话题,话题q3’为根据资源数据d2或d3发出的话题,话题q4’为根据资源数据d3或d4发出的话题。进一步地,可推导出话题q1和话题q1’具有关联关系,话题q1和话题q2’具有关联关系等,最终建立如图2所示的话题图谱。
本发明实施例的基于人工智能的人机交互的交互引导装置,通过接收用户输入的交互信息确定当前话题,并基于话题图谱获得多个与当前话题相关的待选引导话题,再结合用户的用户画像数据从待选引导话题中选择引导话题,以及向用户反馈引导话题,提高了人机交互的持续性,使人机交互更加流畅、自然。
为了实现上述实施例,本发明还提出了一种存储介质,用于存储应用程序,该应用程序用于执行本发明任一个实施例所述的基于人工智能的人机交互的交互引导方法。
为了实现上述实施例,本发明还提出了一种设备,包括:一个或者多个处理器;存储器;一个或者多个模块,一个或者多个模块存储在存储器中,当被一个或者多个处理器执行时进行如下操作:
S1’、接收用户输入的交互信息,并根据交互信息确定当前话题。
S2’、基于话题图谱获得多个与当前话题相关的待选引导话题。
S3’、获取用户的用户画像数据。
S4’、根据用户画像数据从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
在本发明中,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本发明的描述中,“多个”的含义是至少两个,例如两个,三个等,除非另有明确具体的限定。
在本说明书中,对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且,描述的具体特征或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外,在不相互矛盾的情况下,本领域的技术人员可以将本说明书中描述的不同实施例或示例以 及不同实施例或示例的特征进行结合和组合。
尽管上面已经示出和描述了本发明的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本发明的限制,本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (18)

  1. 一种基于人工智能的人机交互的交互引导方法,其特征在于,包括以下步骤:
    S1、接收用户输入的交互信息,并根据所述交互信息确定当前话题;
    S2、基于话题图谱获得多个与所述当前话题相关的待选引导话题,其中,所述话题图谱包括多个话题及所述话题之间的关联关系;
    S3、获取所述用户的用户画像数据;以及
    S4、根据所述用户画像数据从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
  2. 如权利要求1所述的方法,其特征在于,在所述步骤S2之前,还包括:
    S5、建立所述话题图谱。
  3. 如权利要求2所述的方法,其特征在于,所述步骤S5具体包括:
    获取话题关联数据;以及
    根据所述话题关联数据建立所述话题图谱。
  4. 如权利要求3所述的方法,其特征在于,所述获取话题关联数据,具体包括:
    获取网络文本数据;
    当所述网络文本数据为非结构化数据时,基于实体提取和句法分析获取所述话题关联数据;或者
    当所述网络文本数据为半结构化数据时,基于页面结构分析、标签提取、实体识别获取所述话题关联数据;或者
    当所述网络文本数据为结构化数据时,从知识图谱中获取所述话题关联数据。
  5. 如权利要求3所述的方法,其特征在于,所述获取话题关联数据,包括:
    获取所述用户的搜索行为数据,并根据所述搜索行为数据获取对应的搜索对象,以及根据所述搜索对象生成所述话题关联数据;或者
    获取所述用户的浏览行为数据,并根据所述浏览行为数据获取对应的浏览对象,根据所述浏览对象生成所述话题关联数据。
  6. 如权利要求3所述的方法,其特征在于,所述根据所述话题关联数据建立所述话题图谱,具体包括:
    通过RandomWalk算法、关联分析算法、协同过滤算法中的一种或多种,根据所述话题关联数据建立所述话题图谱。
  7. 如权利要求1所述的方法,其特征在于,所述根据所述交互信息确定当前话题,具体包括:
    对所述交互信息进行需求识别以及相关性计算以确定所述当前话题。
  8. 如权利要求1所述的方法,其特征在于,所述步骤S4具体包括:
    根据所述用户画像数据和所述交互信息的上下文信息确定所述用户的意图信息;
    根据所述用户的意图信息从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
  9. 一种基于人工智能的人机交互的交互引导装置,其特征在于,包括:
    确定模块,用于接收用户输入的交互信息,并根据所述交互信息确定当前话题;
    获得模块,用于基于话题图谱获得多个与所述当前话题相关的待选引导话题,其中,所述话题图谱包括多个话题及所述话题之间的关联关系;
    获取模块,用于获取所述用户的用户画像数据;以及
    反馈模块,用于根据所述用户画像数据从所述多个与所述当前话题相关的待选引导话题中选择引导话题,并向所述用户反馈所述引导话题。
  10. 如权利要求9所述的装置,其特征在于,还包括:
    建立模块,用于建立所述话题图谱。
  11. 如权利要求10所述的装置,其特征在于,所述建立模块,具体包括:
    获取单元,用于获取话题关联数据;以及
    建立单元,用于根据所述话题关联数据建立所述话题图谱。
  12. 如权利要求11所述的装置,其特征在于,所述获取单元,具体用于:
    获取网络文本数据;
    当所述网络文本数据为非结构化数据时,基于实体提取和句法分析获取所述话题关联数据;或者
    当所述网络文本数据为半结构化数据时,基于页面结构分析、标签提取、实体识别获取所述话题关联数据;或者
    当所述网络文本数据为结构化数据时,从知识图谱中获取所述话题关联数据。
  13. 如权利要求11所述的装置,其特征在于,所述获取单元,具体用于:
    获取所述用户的搜索行为数据,并根据所述搜索行为数据获取对应的搜索对象,以及根据所述搜索对象生成所述话题关联数据;或者
    获取所述用户的浏览行为数据,并根据所述浏览行为数据获取对应的浏览对象,根据所述浏览对象生成所述话题关联数据。
  14. 如权利要求11所述的装置,其特征在于,所述建立单元,具体用于:
    通过RandomWalk算法、关联分析算法、协同过滤算法中的一种或多种,根据所述话题关联数据建立所述话题图谱。
  15. 如权利要求9所述的装置,其特征在于,所述确定模块,具体用于:
    对所述交互信息进行需求识别以及相关性计算以确定所述当前话题。
  16. 如权利要求9所述的装置,其特征在于,所述反馈模块,具体用于:
    根据所述用户画像数据和所述交互信息的上下文信息确定所述用户的意图信息,并根据所述用户的意图信息从所述多个与所述当前话题相关的待选引导话题中选择引导话题,以及向所述用户反馈所述引导话题。
  17. 一种存储介质,其特征在于,用于存储应用程序,所述应用程序用于执行权利要求1至8中任一项所述的基于人工智能的人机交互的交互引导方法。
  18. 一种设备,其特征在于,包括:
    一个或者多个处理器;
    存储器;
    一个或者多个模块,所述一个或者多个模块存储在所述存储器中,当被所述一个或者多个处理器执行时进行如下操作:
    接收用户输入的交互信息,并根据交互信息确定当前话题。
    基于话题图谱获得多个与当前话题相关的待选引导话题。
    获取用户的用户画像数据。
    根据用户画像数据从多个与当前话题相关的待选引导话题中选择引导话题,并向用户反馈引导话题。
PCT/CN2015/096339 2015-09-07 2015-12-03 基于人工智能的人机交互的交互引导方法和装置 WO2017041369A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510564818.0A CN105138671A (zh) 2015-09-07 2015-09-07 基于人工智能的人机交互的交互引导方法和装置
CN201510564818.0 2015-09-07

Publications (1)

Publication Number Publication Date
WO2017041369A1 true WO2017041369A1 (zh) 2017-03-16

Family

ID=54724018

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/096339 WO2017041369A1 (zh) 2015-09-07 2015-12-03 基于人工智能的人机交互的交互引导方法和装置

Country Status (2)

Country Link
CN (1) CN105138671A (zh)
WO (1) WO2017041369A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110704596A (zh) * 2019-09-29 2020-01-17 北京百度网讯科技有限公司 基于话题的对话方法、装置和电子设备
CN111427993A (zh) * 2019-11-15 2020-07-17 西安海的电子科技有限公司 一种基于安卓系统的多对话实现方法
CN112163085A (zh) * 2020-10-30 2021-01-01 珠海格力电器股份有限公司 陪伴机器人的交互方法和装置、存储介质、电子装置
CN114331789A (zh) * 2022-03-07 2022-04-12 联通高新大数据人工智能科技(成都)有限公司 一种廉洁知识智能推荐方法、装置、设备及存储介质

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105701208B (zh) * 2016-01-13 2018-11-30 北京光年无限科技有限公司 一种面向问答系统的问答评价方法及装置
CN107391512B (zh) * 2016-05-17 2021-05-11 北京邮电大学 知识图谱预测的方法和装置
CN106448670B (zh) * 2016-10-21 2019-11-19 竹间智能科技(上海)有限公司 基于深度学习和强化学习的自动回复对话系统
CN106557410B (zh) * 2016-10-25 2019-05-31 北京百度网讯科技有限公司 基于人工智能的用户行为分析方法和装置
CN106559321A (zh) * 2016-12-01 2017-04-05 竹间智能科技(上海)有限公司 动态调整对话策略的方法及系统
CN106843461B (zh) * 2016-12-13 2020-06-26 北京光年无限科技有限公司 一种用于机器人的交互输出方法以及机器人
CN106599179B (zh) * 2016-12-13 2020-02-14 竹间智能科技(上海)有限公司 融合知识图谱和记忆图谱的人机对话控制方法及装置
CN106777364A (zh) * 2017-01-22 2017-05-31 竹间智能科技(上海)有限公司 话题驱动的人工智能回应方法及装置
CN107025278A (zh) * 2017-03-27 2017-08-08 竹间智能科技(上海)有限公司 基于人机对话的用户画像自动提取方法及装置
CN107833082B (zh) * 2017-09-15 2022-04-12 唯品会(海南)电子商务有限公司 一种商品图片的推荐方法和装置
CN107967308B (zh) * 2017-11-16 2021-04-23 百度在线网络技术(北京)有限公司 一种智能交互的处理方法、装置、设备和计算机存储介质
CN108108340B (zh) * 2017-11-28 2021-07-23 北京光年无限科技有限公司 用于智能机器人的对话交互方法及系统
CN108197189B (zh) * 2017-12-26 2020-07-28 上海科大讯飞信息科技有限公司 主动交互方法及装置
CN108415932B (zh) * 2018-01-23 2023-12-22 思必驰科技股份有限公司 人机对话方法及电子设备
CN108804603B (zh) * 2018-05-29 2021-07-23 北京灵智优诺科技有限公司 人机书面对话方法及系统、服务器、介质
CN109002477B (zh) * 2018-06-19 2022-04-12 深圳市元征科技股份有限公司 信息处理方法、装置、终端及介质
CN109683727B (zh) * 2018-12-26 2021-07-16 联想(北京)有限公司 一种数据处理方法及装置
CN109783733B (zh) * 2019-01-15 2020-11-06 腾讯科技(深圳)有限公司 用户画像生成装置及方法、信息处理装置及存储介质
CN111177339B (zh) * 2019-12-06 2023-07-25 百度在线网络技术(北京)有限公司 对话生成方法、装置、电子设备及存储介质
CN111046160A (zh) * 2019-12-16 2020-04-21 联想(北京)有限公司 交互方法、交互装置以及计算机系统
CN112052321A (zh) * 2020-09-02 2020-12-08 平安科技(深圳)有限公司 人机对话方法、装置、计算机设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102063453A (zh) * 2010-05-31 2011-05-18 百度在线网络技术(北京)有限公司 一种用于基于用户的需求进行搜索的方法和设备
US20110295688A1 (en) * 2010-05-28 2011-12-01 Microsoft Corporation Defining user intent
CN102831220A (zh) * 2012-08-23 2012-12-19 江苏物联网研究发展中心 一种面向主题定制的新闻情报提取系统
CN103226569A (zh) * 2013-03-21 2013-07-31 天脉聚源(北京)传媒科技有限公司 一种视频提供方法、装置和系统
CN104254851A (zh) * 2012-03-17 2014-12-31 海智网聚网络技术(北京)有限公司 用于向用户推荐内容的方法和系统

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1145901C (zh) * 2003-02-24 2004-04-14 杨炳儒 一种基于信息挖掘的智能决策支持构造方法
WO2009127264A2 (en) * 2008-04-16 2009-10-22 Tomasz Wojcicki System and method for specifying and implementing it systems
CN102456018B (zh) * 2010-10-18 2016-03-02 腾讯科技(深圳)有限公司 一种交互搜索方法及装置
CN102184262A (zh) * 2011-06-15 2011-09-14 悠易互通(北京)广告有限公司 基于web的文本分类挖掘系统及方法
CN103000052A (zh) * 2011-09-16 2013-03-27 上海先先信息科技有限公司 人机互动的口语对话系统及其实现方法
CN102866990B (zh) * 2012-08-20 2016-08-03 北京搜狗信息服务有限公司 一种主题对话方法和装置
CN103577579B (zh) * 2013-11-08 2015-01-21 南方电网科学研究院有限责任公司 基于用户潜在需求的资源推荐方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110295688A1 (en) * 2010-05-28 2011-12-01 Microsoft Corporation Defining user intent
CN102063453A (zh) * 2010-05-31 2011-05-18 百度在线网络技术(北京)有限公司 一种用于基于用户的需求进行搜索的方法和设备
CN104254851A (zh) * 2012-03-17 2014-12-31 海智网聚网络技术(北京)有限公司 用于向用户推荐内容的方法和系统
CN102831220A (zh) * 2012-08-23 2012-12-19 江苏物联网研究发展中心 一种面向主题定制的新闻情报提取系统
CN103226569A (zh) * 2013-03-21 2013-07-31 天脉聚源(北京)传媒科技有限公司 一种视频提供方法、装置和系统

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110704596A (zh) * 2019-09-29 2020-01-17 北京百度网讯科技有限公司 基于话题的对话方法、装置和电子设备
CN110704596B (zh) * 2019-09-29 2023-03-31 北京百度网讯科技有限公司 基于话题的对话方法、装置和电子设备
CN111427993A (zh) * 2019-11-15 2020-07-17 西安海的电子科技有限公司 一种基于安卓系统的多对话实现方法
CN112163085A (zh) * 2020-10-30 2021-01-01 珠海格力电器股份有限公司 陪伴机器人的交互方法和装置、存储介质、电子装置
CN114331789A (zh) * 2022-03-07 2022-04-12 联通高新大数据人工智能科技(成都)有限公司 一种廉洁知识智能推荐方法、装置、设备及存储介质
CN114331789B (zh) * 2022-03-07 2022-06-24 联通高新大数据人工智能科技(成都)有限公司 一种廉洁知识智能推荐方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN105138671A (zh) 2015-12-09

Similar Documents

Publication Publication Date Title
WO2017041369A1 (zh) 基于人工智能的人机交互的交互引导方法和装置
US11709901B2 (en) Personalized search filter and notification system
WO2017041372A1 (zh) 基于人工智能的人机交互方法和系统
US9594852B2 (en) Filtering suggested structured queries on online social networks
KR102048216B1 (ko) 온라인 소셜 네트워크에서 질의를 위한 인버스 연산자의 사용
KR101845434B1 (ko) 온라인 소셜 네트워크에서 질의를 위한 검색 의도
JP6420481B2 (ja) オンライン・ソーシャル・ネットワーク上のキー・オーサーによるコンテンツの検索
JP2017142844A5 (zh)
US9582503B2 (en) Interactive addition of semantic concepts to a document
US11227011B2 (en) Content recommendations
US9922125B1 (en) Selecting content using entity properties
US20160357872A1 (en) Event networks and event view construction and display
US10956948B2 (en) System and method for hotel discovery and generating generalized reviews
US20170099249A1 (en) Method and system for classifying a question
KR101785597B1 (ko) 소셜 네트워킹 시스템에서 컨텍스트-기반 객체 검색
US9501530B1 (en) Systems and methods for selecting content
CN107408125B (zh) 用于查询答案的图像
US10146856B2 (en) Computer-implemented method and system for creating scalable content
CN104035972A (zh) 一种基于微博的知识推荐方法与系统
US9727545B1 (en) Selecting textual representations for entity attribute values
US20160335359A1 (en) Processing search queries and generating a search result page including search object related information
US20160335358A1 (en) Processing search queries and generating a search result page including search object related information
US20160335365A1 (en) Processing search queries and generating a search result page including search object information
US10909112B2 (en) Method of and a system for determining linked objects
Feitosa et al. Hybrid model for information filtering in location based social networks using text mining

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: 15903472

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: 15903472

Country of ref document: EP

Kind code of ref document: A1