CN107066567B - Topic detection-based user portrait modeling method and system in text conversation - Google Patents
Topic detection-based user portrait modeling method and system in text conversation Download PDFInfo
- Publication number
- CN107066567B CN107066567B CN201710217263.1A CN201710217263A CN107066567B CN 107066567 B CN107066567 B CN 107066567B CN 201710217263 A CN201710217263 A CN 201710217263A CN 107066567 B CN107066567 B CN 107066567B
- Authority
- CN
- China
- Prior art keywords
- topic
- topics
- user
- map
- main
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user portrait modeling method and a system based on topic detection in text conversation, wherein the method comprises the following steps: obtaining, by a topic identification system, a plurality of topics of text input by a user, the plurality of topics including a primary topic and a secondary topic; mapping a plurality of topics into a topic relation graph with a graph structure to form a topic map; and updating the topic map by a logic rule or a machine learning method to obtain the user portrait of the user. The topic in the user dialogue text is divided into the main topic and the secondary topic, the topic map is established for the main topic and the secondary topic, the topic map is updated according to the topic contained in the dialogue content of each user, the user portrait of the user is obtained, and the user personality factors are considered in the man-machine dialogue process according to the user portrait, so that the man-machine dialogue is more intelligent.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to the field of artificial intelligence conversation.
Background
The existing artificial intelligence dialogue system models the user by the user's own information, such as sex, age, hometown, occupation, etc., and does not regard the user's personality, such as interested topics, as the factor forming the user portrait. In a person-to-person natural conversation, frequently chatting topics represent personal interests. Therefore, topics of interest to the user are important factors in the user representation in the artificial intelligence dialog system.
Therefore, the technical defects in the prior art are as follows: in the existing man-machine conversation system, no conversation topic factor representing the personality of the user is added into the portrait of the user, so that more intelligent answers cannot be given according to the personality of the user in the man-machine conversation process.
Disclosure of Invention
The invention provides a user portrait modeling method and system based on topic detection in character conversation, which divides topics in a user conversation text into main topics and secondary topics, updates a topic map according to topics contained in conversation content of each user by establishing a topic map for the main topics and the secondary topics to obtain a user portrait of the user, and enables man-machine conversation to be more intelligent by considering user individual factors in the man-machine conversation process according to the user portrait.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
in a first aspect, the present invention provides a topic detection-based user portrait modeling method in text dialog, including:
step S1, obtaining a plurality of topics of the text input by the user through a topic identification system, wherein the topics comprise a main topic and a secondary topic;
step S2, mapping the multiple topics into a topic relation graph with a graph structure to form a topic map;
and step S3, updating the topic map through a logic rule or a machine learning method to obtain the user portrait of the user.
The invention provides a user portrait modeling method based on topic detection in text conversation, which has the technical scheme that: firstly, obtaining a plurality of topics of text input by a user through a topic identification system, wherein the topics comprise main topics and secondary topics; then, mapping the multiple topics into a topic relation graph with a graph structure to form a topic map; and finally, updating the topic map by a logic rule or a machine learning method to obtain the user portrait of the user.
The topic in the user dialogue text is divided into a main topic and a secondary topic, a topic map is established for the main topic and the secondary topic, the topic map is updated according to the topic contained in the dialogue content of each user, the user portrait of the user is obtained, and the user portrait is more intelligent in man-machine dialogue process by considering the individual factors of the user according to the user portrait.
Further, in step S1, specifically, the method includes:
obtaining a text input by a user;
and detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
Further, in step S2, specifically, the method includes:
according to a main topic and a secondary topic contained in the plurality of topics, the main topic and the secondary topic are represented in the form of points, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topic and the secondary topic according to the association strength between the main topic and the secondary topic to obtain a plurality of connecting lines;
and forming a topic map according to the points and the connecting lines.
Further, in the step S3, the topic map is updated by a method of a logic rule, specifically:
calculating topic map strength between two of the plurality of topics, the topic map strength representing the strength of association between two of the plurality of topics;
and updating the topic map according to the topic map strength.
Further, in step S3, the topic map is updated by a machine learning method, specifically:
calculating a frequency value of common occurrence between every two of the plurality of topics;
and updating the topic map according to the frequency value.
In a second aspect, the present invention provides a topic detection-based user representation modeling system in text dialog, comprising:
the topic acquisition module is used for acquiring a plurality of topics of the text input by the user through a topic identification system, wherein the topics comprise main topics and secondary topics;
the topic map establishing module is used for mapping the topics into a topic relation map with a graph structure to form a topic map;
and the user portrait module is used for updating the topic map through a logic rule or a machine learning method to obtain the user portrait of the user.
The invention provides a topic detection-based user portrait modeling system in text conversation, which adopts the technical scheme that: the topic acquisition module is used for acquiring a plurality of topics of a text input by a user through a topic identification system, wherein the topics comprise main topics and secondary topics; then, the topic map building module is used for mapping the topics into a topic relation map with a graph structure to form a topic map; and finally, updating the topic map through a user portrait module by a logic rule or a machine learning method to obtain the user portrait of the user.
The topic detection-based user portrait modeling system in the character dialogue divides topics in a user dialogue text into main topics and secondary topics, establishes topic maps for the main topics and the secondary topics, updates the topic maps according to topics contained in dialogue contents of each user to obtain user portraits of the user, and considers user individuality factors in a man-machine dialogue process according to the user portraits to enable man-machine dialogue to be more intelligent.
Further, the topic acquisition module is specifically configured to:
obtaining a text input by a user;
and detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
Further, the topic map establishing module is specifically configured to:
according to a main topic and a secondary topic contained in the plurality of topics, the main topic and the secondary topic are represented in the form of points, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topic and the secondary topic according to the association strength between the main topic and the secondary topic to obtain a plurality of connecting lines;
and forming a topic map according to the points and the connecting lines.
Further, the user profile module is specifically configured to:
calculating topic map strength between two of the plurality of topics, the topic map strength representing the strength of association between two of the plurality of topics;
and updating the topic map according to the topic map strength.
Further, the user profile module is specifically configured to:
calculating a frequency value of common occurrence between every two of the plurality of topics;
and updating the topic map according to the frequency value.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below.
FIG. 1 is a flowchart illustrating a method for modeling a user portrait based on topic detection in text dialog according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a system for modeling a user portrait based on topic detection in text dialog according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
Example one
FIG. 1 is a flowchart illustrating a method for modeling a user portrait based on topic detection in text dialog according to a first embodiment of the present invention; as shown in fig. 1, a user portrait modeling method based on topic detection in text dialog according to an embodiment of the present invention includes:
step S1, obtaining a plurality of topics of the text input by the user through a topic identification system, wherein the topics comprise a main topic and a secondary topic;
step S2, mapping a plurality of topics into a topic relation graph with a graph structure to form a topic map;
step S3, updating topic map through logic rule or machine learning method to obtain user image of user.
The invention provides a user portrait modeling method based on topic detection in text conversation, which has the technical scheme that: firstly, obtaining a plurality of topics of a text input by a user through a topic identification system, wherein the topics comprise a main topic and a secondary topic; then, mapping a plurality of topics into a topic relation graph with a graph structure to form a topic map; and finally, updating the topic map by a logic rule or a machine learning method to obtain the user portrait of the user.
The topic in the user dialogue text is divided into the main topic and the secondary topic, the topic map is established for the main topic and the secondary topic, the topic map is updated according to the topic contained in the dialogue content of each user, the user portrait of the user is obtained, and according to the user portrait, in the man-machine dialogue process, the user personality factor is considered, so that the artificial intelligent dialogue is more like a real person, the interesting topics of the user are understood, and the personalized and more natural man-machine interaction is achieved.
Specifically, in step S1, specifically:
obtaining a text input by a user;
detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
The main topic is a large range to which the content of the text representing the input belongs, and the secondary topic represents a smaller range relative to the main topic, such as "i like eating banana", the main topic is "food", and the secondary topic is "fruit", so that the content of the text is divided into the main topic and the secondary topic, which is convenient for classification and establishment of relationship.
Preferably, the detection of topics is performed by logic rules and machine learning methods.
The topic detection is carried out according to a certain logic rule or a machine learning method, so that the speed and the accuracy of the detection can be increased.
Specifically, in step S2, specifically:
according to a main topic and a secondary topic contained in a plurality of topics, the main topic and the secondary topic are represented in a point form, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topics and the points of the secondary topics according to the correlation strength between the main topics and the secondary topics to obtain a plurality of connecting lines;
and forming a topic map according to the plurality of points and the plurality of connecting lines.
The topic itself is represented in a point form, and a connecting line between the points represents the degree of association between the two topics, so that the representation form is simple and clear and is easier to understand; for example, the correlation degree between the topic "food" and the topic "fruit" is large, the correlation degree between the topic "tree" and the topic "ginkgo tree" is large, and the correlation degree between the topic "fruit" and the topic "ginkgo tree" is small, so that according to the relationship between the main topic and the secondary topic, and in combination with the correlation degree between the topics, the topics contained in the text content can be quickly searched and updated, and a more personalized user map is obtained.
Specifically, in step S3, the topic map is updated by a method of logic rules, specifically:
calculating topic map strength between every two topics in the plurality of topics, wherein the topic map strength represents the association strength between every two topics in the plurality of topics;
and updating the topic map according to the topic map strength.
The topic map strength is predefined and represents the strength of association between every two topics in a plurality of topics, specifically, the strength of the topic a and the topic B is the highest according to whether the two topics appear simultaneously in one session of the user, for example, the topic a and the topic B appear simultaneously in one session of the user, and the strength of the topic a and the topic C is a certain fixed value if the topic a and the topic C appear in several sessions of the user respectively; and then updating the topic map according to the intensity.
Specifically, the embodiment exemplifies the updating of the topic map:
for example, if the topic A and the topic B appear in the n-wheel conversation, the intensity i of the two topics is updated to be equal to the original intensity multiplied by a value larger than 1, and max (1, i) is taken to improve the intensity between the two topics. And multiplying the rest of the topic points connected with the topic A by a value smaller than 1 to reduce the strength.
The topic map is updated by calculating the strength between every two topics, so that the topic map can be optimized, the answer given by the robot is more accurate, and the individual characteristics of the user are better met.
Specifically, in step S3, the topic map is updated by a machine learning method, specifically:
calculating a frequency value of common appearance between every two topics in the plurality of topics;
and updating the topic map according to the frequency value.
The frequency value of the common occurrence between every two topics in the multiple topics refers to the frequency of the common occurrence between the topics discovered from all the user data, for example, how many probabilities are after the topic a is spoken, the topic B is spoken again, the probabilities are sorted from large to small according to the probability of the common occurrence between the topic a and the topic a, and the probability is higher and is multiplied by the higher intensity.
Through the big data of all the users chatting, the frequency of the common occurrence between every two topics can be automatically calculated, and the frequency is used as the basis for updating the topic map. By the method, the topic map is updated, so that the topic map can be optimized, the answer given by the robot is more accurate, and the method is more in line with the personal characteristics of the user.
FIG. 2 is a diagram illustrating a system for topic detection based user representation modeling in text dialog according to an embodiment of the present invention; as shown in fig. 2, a user portrait modeling system 10 based on topic detection in text dialog according to an embodiment of the present invention includes:
the topic acquisition module 101 is configured to acquire, by a topic identification system, multiple topics of a text input by a user, where the multiple topics include a main topic and a secondary topic;
the topic map establishing module 102 is configured to map a plurality of topics into a topic relation map with a graph structure to form a topic map;
and the user portrait module 103 is used for updating the topic map through a logic rule or a machine learning method to obtain the user portrait of the user.
The invention provides a topic detection-based user portrait modeling system 10 in text dialogue, which adopts the technical scheme that: the topic acquisition module 101 is used for acquiring multiple topics of a text input by a user through a topic identification system, wherein the multiple topics include a main topic and a secondary topic; then, the topic map establishing module 102 is used for mapping a plurality of topics into a topic relation map with a graph structure to form a topic map; finally, the user portrait module 103 is used for updating the topic map through logic rules or machine learning methods to obtain the user portrait of the user.
The topic detection-based user portrait modeling system 10 in the character dialogue divides topics in a user dialogue text into main topics and secondary topics, establishes topic maps for the main topics and the secondary topics, updates the topic maps according to topics contained in dialogue contents of each user to obtain user portraits of the user, and considers user individuality factors in a man-machine dialogue process according to the user portraits to enable artificial intelligent dialogue to be more like a real person and understand topics interesting to the user so as to achieve personalization and more natural man-machine interaction.
Specifically, the topic acquisition module 101 is specifically configured to:
obtaining a text input by a user;
detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
The main topic is a large range to which the content of the text representing the input belongs, and the secondary topic represents a smaller range relative to the main topic, such as "i like eating banana", the main topic is "food", and the secondary topic is "fruit", so that the content of the text is divided into the main topic and the secondary topic, which is convenient for classification and establishment of relationship.
Preferably, the detection of topics is performed by logic rules and machine learning methods.
The topic detection is carried out according to a certain logic rule or a machine learning method, so that the speed and the accuracy of the detection can be increased.
Specifically, the topic map establishing module 102 is specifically configured to:
according to a main topic and a secondary topic contained in a plurality of topics, the main topic and the secondary topic are represented in a point form, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topics and the points of the secondary topics according to the correlation strength between the main topics and the secondary topics to obtain a plurality of connecting lines;
and forming a topic map according to the plurality of points and the plurality of connecting lines.
The topic itself is represented in a point form, and a connecting line between the points represents the degree of association between the two topics, so that the representation form is simple and clear and is easier to understand; for example, the correlation degree between the topic "food" and the topic "fruit" is large, the correlation degree between the topic "tree" and the topic "ginkgo tree" is large, and the correlation degree between the topic "fruit" and the topic "ginkgo tree" is small, so that according to the relationship between the main topic and the secondary topic, and in combination with the correlation degree between the topics, the topics contained in the text content can be quickly searched and updated, and a more personalized user map is obtained.
In particular, user representation module 103 is specifically configured to:
calculating topic map strength between every two topics in the plurality of topics, wherein the topic map strength represents the association strength between every two topics in the plurality of topics;
and updating the topic map according to the topic map strength.
The topic map strength is predefined and represents the strength of association between every two topics in a plurality of topics, specifically, the strength of the topic a and the topic B is the highest according to whether the two topics appear simultaneously in one session of the user, for example, the topic a and the topic B appear simultaneously in one session of the user, and the strength of the topic a and the topic C is a certain fixed value if the topic a and the topic C appear in several sessions of the user respectively; and then updating the topic map according to the intensity.
Specifically, the embodiment exemplifies the updating of the topic map:
for example, if the topic A and the topic B appear in the n-wheel conversation, the intensity i of the two topics is updated to be equal to the original intensity multiplied by a value larger than 1, and max (1, i) is taken to improve the intensity between the two topics. And multiplying the rest of the topic points connected with the topic A by a value smaller than 1 to reduce the strength.
The topic map is updated by calculating the strength between every two topics, so that the topic map can be optimized, the answer given by the robot is more accurate, and the individual characteristics of the user are better met.
In particular, user representation module 103 is specifically configured to:
calculating a frequency value of common appearance between every two topics in the plurality of topics;
and updating the topic map according to the frequency value.
The frequency value of the common occurrence between every two topics in the multiple topics refers to the frequency of the common occurrence between the topics discovered from all the user data, for example, how many probabilities are after the topic a is spoken, the topic B is spoken again, the probabilities are sorted from large to small according to the probability of the common occurrence between the topic a and the topic a, and the probability is higher and is multiplied by the higher intensity.
Through the big data of all the users chatting, the frequency of the common occurrence between every two topics can be automatically calculated, and the frequency is used as the basis for updating the topic map. By the method, the topic map is updated, so that the topic map can be optimized, the answer given by the robot is more accurate, and the method is more in line with the personal characteristics of the user.
Example two
The user portrait modeling method based on topic detection in the text dialogue and the user portrait modeling system 10 based on topic detection in the text dialogue, which are provided by the embodiment of the invention, are applied to a human-computer dialogue system, and the specific processes are as follows:
the user enters a text sentence, for example: news of royal fevers?
Detecting topics in the sentence spoken by the user by a topic identification system, for example, the main topic in the previous sentence is "artist", and the secondary topic is "singer";
mapping the main topic 'artist' and the secondary topic 'singer' into a topic map;
according to logic rules or machine learning algorithm, the personalized map (topic map) is updated, the preference degree of the individual to different topics can be known through the topic map, and intelligent answers are given.
By the user portrait modeling method and system based on topic detection in text conversation, according to the user portrait, in the man-machine conversation process, the individual factors of the user are considered, so that the artificial intelligent conversation is more like a real person, the topics which are interesting to the user are understood, and personalized and more natural man-machine interaction is achieved.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (6)
1. A user portrait modeling method based on topic detection in text conversation is characterized by comprising the following steps:
step S1, obtaining a plurality of topics of the text input by the user through a topic identification system, wherein the topics comprise a main topic and a secondary topic;
step S2, mapping the multiple topics into a topic relation graph with a graph structure to form a topic map;
step S3, updating the topic map through logic rules or machine learning method to obtain the user portrait of the user;
the step S2 specifically includes:
according to a main topic and a secondary topic contained in the plurality of topics, the main topic and the secondary topic are represented in the form of points, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topic and the secondary topic according to the association strength between the main topic and the secondary topic to obtain a plurality of connecting lines;
forming a topic map according to the plurality of points and the plurality of connecting lines;
in the step S3, the topic map is updated by a method of logic rules, specifically:
calculating topic map strength between two of the plurality of topics, the topic map strength representing the strength of association between two of the plurality of topics;
and updating the topic map according to the topic map strength.
2. The method as claimed in claim 1, wherein the topic detection-based user representation modeling method is applied to a text dialog,
the step S1 specifically includes:
obtaining a text input by a user;
and detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
3. The method as claimed in claim 1, wherein the topic detection-based user representation modeling method is applied to a text dialog,
in step S3, the topic map is updated by a machine learning method, specifically:
calculating a frequency value of common occurrence between every two of the plurality of topics;
and updating the topic map according to the frequency value.
4. A topic detection-based user portrait modeling system in text dialogue, comprising:
the topic acquisition module is used for acquiring a plurality of topics of the text input by the user through a topic identification system, wherein the topics comprise main topics and secondary topics;
the topic map establishing module is used for mapping the topics into a topic relation map with a graph structure to form a topic map;
the user portrait module is used for updating the topic map through a logic rule or a machine learning method to obtain a user portrait of the user;
the topic map establishing module is specifically used for:
according to a main topic and a secondary topic contained in the plurality of topics, the main topic and the secondary topic are represented in the form of points, and a plurality of points are obtained, wherein one point represents one main topic or one secondary topic;
connecting the points of the main topic and the secondary topic according to the association strength between the main topic and the secondary topic to obtain a plurality of connecting lines;
forming a topic map according to the plurality of points and the plurality of connecting lines;
the user profile module is specifically configured to:
calculating topic map strength between two of the plurality of topics, the topic map strength representing the strength of association between two of the plurality of topics;
and updating the topic map according to the topic map strength.
5. The system of claim 4, wherein the topic detection-based user representation modeling system further comprises a topic detection module,
the topic acquisition module is specifically configured to:
obtaining a text input by a user;
and detecting topics according to the content of the text input by the user to obtain a plurality of topics, wherein the topics comprise main topics and secondary topics.
6. The system of claim 4, wherein the topic detection-based user representation modeling system further comprises a topic detection module,
the user profile module is specifically configured to:
calculating a frequency value of common occurrence between every two of the plurality of topics;
and updating the topic map according to the frequency value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710217263.1A CN107066567B (en) | 2017-04-05 | 2017-04-05 | Topic detection-based user portrait modeling method and system in text conversation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710217263.1A CN107066567B (en) | 2017-04-05 | 2017-04-05 | Topic detection-based user portrait modeling method and system in text conversation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107066567A CN107066567A (en) | 2017-08-18 |
| CN107066567B true CN107066567B (en) | 2021-08-31 |
Family
ID=59601589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710217263.1A Active CN107066567B (en) | 2017-04-05 | 2017-04-05 | Topic detection-based user portrait modeling method and system in text conversation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107066567B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108415932B (en) * | 2018-01-23 | 2023-12-22 | 思必驰科技股份有限公司 | Man-machine conversation method and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662956A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | Method for identifying opinion leaders in social network based on topic link behaviors of users |
| CN103294818A (en) * | 2013-06-12 | 2013-09-11 | 北京航空航天大学 | Multi-information fusion microblog hot topic detection method |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN106448670A (en) * | 2016-10-21 | 2017-02-22 | 竹间智能科技（上海）有限公司 | Dialogue automatic reply system based on deep learning and reinforcement learning |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7685199B2 (en) * | 2006-07-31 | 2010-03-23 | Microsoft Corporation | Presenting information related to topics extracted from event classes |
| US8032510B2 (en) * | 2008-03-03 | 2011-10-04 | Yahoo! Inc. | Social aspects of content aggregation, syndication, sharing, and updating |
| US8438229B2 (en) * | 2007-03-07 | 2013-05-07 | True Engineering Technology, Llc | System and method of supporting constructive discourse on computers and mobile devices |
| US20130275182A1 (en) * | 2012-02-02 | 2013-10-17 | Compass Labs, Inc. | Social audience analysis |
| CN103226569A (en) * | 2013-03-21 | 2013-07-31 | 天脉聚源(北京)传媒科技有限公司 | Video providing method, device and system |
| CN104298765B (en) * | 2014-10-24 | 2017-09-15 | 福州大学 | The Dynamic Recognition and method for tracing of a kind of internet public feelings topic |
| US10157350B2 (en) * | 2015-03-26 | 2018-12-18 | Tata Consultancy Services Limited | Context based conversation system |
| CN105488195A (en) * | 2015-12-07 | 2016-04-13 | 中国人民大学 | Search result diversification ordering method based on hierarchical structure subtopic |
| CN105808695A (en) * | 2016-03-03 | 2016-07-27 | 陈包容 | Method and device for obtaining chat reply contents |
-
2017
- 2017-04-05 CN CN201710217263.1A patent/CN107066567B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662956A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | Method for identifying opinion leaders in social network based on topic link behaviors of users |
| CN103294818A (en) * | 2013-06-12 | 2013-09-11 | 北京航空航天大学 | Multi-information fusion microblog hot topic detection method |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN106448670A (en) * | 2016-10-21 | 2017-02-22 | 竹间智能科技（上海）有限公司 | Dialogue automatic reply system based on deep learning and reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107066567A (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108000526B (en) | Dialogue interaction method and system for intelligent robot | |
| CN107291783B (en) | Semantic matching method and intelligent equipment | |
| CN106202476B (en) | A kind of interactive method and device of knowledge based collection of illustrative plates | |
| WO2019084810A1 (en) | Information processing method and terminal, and computer storage medium | |
| CN112507706B (en) | Training method and device for knowledge pre-training model and electronic equipment | |
| CN110209897A (en) | Intelligent dialogue method, apparatus, storage medium and equipment | |
| WO2020155619A1 (en) | Method and apparatus for chatting with machine with sentiment, computer device and storage medium | |
| CN112434139A (en) | Information interaction method and device, electronic equipment and storage medium | |
| CN112632244A (en) | Man-machine conversation optimization method and device, computer equipment and storage medium | |
| CN109635080A (en) | Acknowledgment strategy generation method and device | |
| CN107704612A (en) | Dialogue exchange method and system for intelligent robot | |
| CN111813910A (en) | Method, system, terminal device and computer storage medium for updating customer service problem | |
| CN112632242A (en) | Intelligent conversation method and device and electronic equipment | |
| CN106649410B (en) | Method and device for obtaining chat reply content | |
| CN111161726B (en) | Intelligent voice interaction method, device, medium and system | |
| CN111191463A (en) | Sentiment analysis method, device, electronic device and storage medium | |
| CN117421398A (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN117171310A (en) | Digital person interaction method and device, electronic equipment and storage medium | |
| CN107977676A (en) | Text similarity computing method and device | |
| CN111625636B (en) | Method, device, equipment and medium for rejecting man-machine conversation | |
| CN106776557B (en) | Emotional state memory identification method and device of emotional robot | |
| CN116955529A (en) | Data processing method and device and electronic equipment | |
| CN112860995B (en) | Interaction method, device, client, server and storage medium | |
| CN115438170A (en) | Dialog model generation method, dialog model application method, dialog model generation system, dialog model application system, dialog model generation equipment and dialog model application equipment | |
| CN113111664B (en) | Text generation method and device, storage medium and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |