CN111026932B - Man-machine dialogue interaction method and device, electronic equipment and storage medium - Google Patents
Man-machine dialogue interaction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111026932B CN111026932B CN201911334965.3A CN201911334965A CN111026932B CN 111026932 B CN111026932 B CN 111026932B CN 201911334965 A CN201911334965 A CN 201911334965A CN 111026932 B CN111026932 B CN 111026932B
- Authority
- CN
- China
- Prior art keywords
- dialogue
- user
- scene
- candidate
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000003993 interaction Effects 0.000 title claims abstract description 37
- 230000015654 memory Effects 0.000 claims description 19
- 230000009471 action Effects 0.000 claims description 13
- 230000006399 behavior Effects 0.000 claims description 13
- 230000000694 effects Effects 0.000 abstract description 15
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 241000086550 Dinosauria Species 0.000 description 27
- 238000010586 diagram Methods 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 244000062645 predators Species 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 241001164374 Calyx Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000086571 Tyrannosaurus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000147 hypnotic effect Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000004243 sweat Anatomy 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a man-machine dialogue interaction method, a man-machine dialogue interaction device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, wherein the man-machine dialogue interaction method comprises the following steps: receiving dialogue sentences input by a user; determining that the active recommendation condition is met according to the dialogue statement, and acquiring current dialogue environment information; determining a current dialogue scene according to the current dialogue environment information; determining a plurality of candidate topics from a preset scene map according to the current dialogue scene; acquiring interest information of a user, and determining a target topic from a plurality of candidate topics according to the interest information; and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy. Therefore, the technical problem that the conversation effect and efficiency are poor is solved, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are acquired based on user interests, a plurality of conversation contents are actively recommended to the user based on the topics, conversation efficiency and effect are improved, and user experience is improved.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence in computer technology, and in particular, to a method and apparatus for man-machine interaction, an electronic device, and a storage medium.
Background
With the continuous development of artificial intelligence technology, meeting user requirements by talking with intelligent devices is an interactive way that is more and more common in the life of users.
In the related art, a user is queried by selecting an appropriate question so as to select a target content from candidate contents to be provided to the user, thereby resulting in a dialogue effect and a technical problem of poor efficiency.
Disclosure of Invention
A first object of the present application is to provide a human-machine interaction method.
A second object of the present application is to provide a human-machine interaction device.
A third object of the present application is to propose an electronic device.
A fourth object of the present application is to propose a non-transitory computer readable storage medium storing computer instructions.
To achieve the above objective, an embodiment of a first aspect of the present application provides a human-machine interaction method, which includes the following steps:
receiving dialogue sentences input by a user;
acquiring current dialogue environment information according to the dialogue statement determining that the active recommendation condition is met;
Determining a current dialogue scene according to the current dialogue environment information;
determining a plurality of candidate topics from a preset scene map according to the current dialogue scene;
acquiring interest information of the user, and determining a target topic from the candidate topics according to the interest information;
and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy.
To achieve the above object, an embodiment of a second aspect of the present application provides a human-machine interaction device, including:
the receiving module is used for receiving dialogue sentences input by a user;
the first determining module is used for determining that the active recommendation condition is met according to the dialogue statement;
the first acquisition module is used for acquiring current dialogue environment information;
the second determining module is used for determining a current dialogue scene according to the current dialogue environment information;
the third determining module is used for determining a plurality of candidate topics from a preset scene map according to the current dialogue scene;
the acquisition determining module is used for acquiring interest information of the user and determining target topics from the candidate topics according to the interest information;
The second acquisition module is used for acquiring a plurality of candidate dialogue contents corresponding to the target topics;
and the recommending module is used for recommending the plurality of candidate dialogue contents to the user according to a preset recommending strategy.
To achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the human-machine interaction method described in the above embodiments.
To achieve the above object, an embodiment of a fourth aspect of the present application proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the man-machine interaction method described in the above embodiment.
One embodiment of the above application has the following advantages or benefits:
receiving dialogue sentences input by a user; acquiring current dialogue environment information according to the dialogue statement to confirm that the active recommendation condition is met; determining a current dialogue scene according to the current dialogue environment information; determining a plurality of candidate topics from a preset scene map according to the current dialogue scene; acquiring interest information of a user, and determining a target topic from a plurality of candidate topics according to the interest information; and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy. Therefore, the technical problems of poor dialogue effect and poor efficiency caused by passive dialogue recommendation in the prior art are solved, the dialogue scene is determined according to dialogue environment information, topics corresponding to the dialogue scene are acquired based on user interests, a plurality of dialogue contents are actively recommended to the user based on the topics, the dialogue scene requirements are met, the dialogue efficiency and effect are improved, and the user experience is improved.
Other effects of the above alternative will be described below in connection with specific embodiments.
Drawings
The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:
FIG. 1 is a flow chart of a human-machine interactive method according to a first embodiment of the present application;
FIG. 2 is a flow chart of a human-machine interactive method according to a second embodiment of the present application;
FIG. 3 is a flow chart of a human-machine interaction method according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a man-machine interactive device according to a fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of a man-machine interactive device according to a fifth embodiment of the present application
Fig. 6 is a block diagram of an electronic device for implementing a human-machine conversation interaction method of an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The following describes a man-machine dialogue interaction method, a man-machine dialogue interaction device, an electronic device and a storage medium according to the embodiments of the application with reference to the accompanying drawings.
In order to solve the technical problems of poor dialogue effect and poor efficiency caused by passive dialogue recommendation in the prior art, the technical scheme is characterized in that dialogue scenes are determined according to dialogue environment information, topics corresponding to the dialogue scenes are acquired based on user interests, a plurality of dialogue contents are actively recommended to users based on the topics, dialogue scene requirements are met, dialogue efficiency and effect are improved, and user experience is improved.
Specifically, fig. 1 is a flowchart of a man-machine conversation interaction method according to a first embodiment of the present application.
As shown in fig. 1, the method includes:
And 102, acquiring current dialogue environment information according to the dialogue statement to determine that the active recommendation condition is met.
In practical application, the intelligent device can be awakened by voice or manual operation and the like, so that the intelligent device can receive information such as text and voice, and a user can input dialogue sentences according to the practical application requirement to perform dialogue interaction with the intelligent device.
It can be understood that the dialogue sentence input by the user has various forms, such as an inquiry sentence, an instruction sentence and the like, and it can be determined that the dialogue sentence is not an instruction sentence or the like after the sentence analysis is performed on the dialogue sentence, that is, the intelligent device is not required to perform corresponding operations on the dialogue sentence, for example, the intelligent device is controlled to turn on to determine that the active recommendation condition is met, for example, the user and the intelligent device are only performing a cold or chatting, or a command (for example, asking weather/question time and the like) of initiating a non-immersive scene is determined to meet the active recommendation condition, wherein the immersive scene command is similar to a song/story listening, so that the user is not suitable for being interrupted to perform active recommendation.
Further, the current dialogue environment information is obtained, wherein, various ways of obtaining the current dialogue scene information are as follows:
in a first example, current session time information is obtained by invoking a smart device local system.
In a second example, the current dialogue location information is obtained by calling the intelligent device positioning system, or the current dialogue location information is obtained by communicating with the terminal device, or the current location information is obtained from dialogue sentences.
In a third example, behavior and action information of a user, such as running, reading, etc., is obtained through a camera, an infrared sensor, etc., of the smart device.
Specifically, after the current dialog environment information is acquired, the current dialog scene may be determined according to the current dialog environment information, for example as follows:
in a first example, a current dialog scenario is determined from current time information and current dialog location information, such as eight morning points and user residence address information a is determined as a morning wake scenario.
In a second example, the current dialogue scene is determined according to the current dialogue position information and the behavior action information of the user, such as the office address information B of the user and the working scene determined by the user on a computer.
It can be understood that the scene graph and the corresponding topic of each scene in the scene graph are preset before the dialog content recommendation is performed.
As one possible implementation manner, a plurality of historical dialogue data are acquired, a plurality of dialogue scenes are determined according to the plurality of historical dialogue data, a plurality of topics corresponding to each dialogue scene are constructed, connection relations of the plurality of dialogue scenes are constructed, and a preset scene map is generated according to the connection relations of each dialogue scene and the plurality of topics corresponding to each dialogue scene.
That is, in the preset scene graph, edges between two scene nodes indicate logical links between different scenes, such as jumping from an early morning getting-up scene to a travel scene, and edges between each scene node and a plurality of topic nodes indicate that the topics belong to the scene, such as the early morning getting-up scene including weather forecast content, news content, and the like.
Therefore, the scene node of the current dialogue scene can be found in the preset scene map, and a plurality of topic nodes under the scene node are obtained to serve as a plurality of candidate topics.
And 106, acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy.
It can be understood that the interest information of the user, namely the user preference information, can be analyzed based on the historical dialogue content to obtain the interest information of the user in each dialogue scene, and it should be noted that if the interest information of the user can be actively inquired and recorded for a new user, the interest information can be called when the active dialogue is recommended.
Further, determining a target topic from the plurality of candidate topics according to the interest information, for example, determining a news topic as the target topic, thereby acquiring a plurality of candidate dialogue contents corresponding to the target topic, for example, sports news, newsletter, and the like, and finally recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy.
As an example, the plurality of candidate dialogue contents are weighted based on the recommendation heat, the dialogue content generation time and the user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate dialogue contents, and the target dialogue content is determined to be recommended to the user according to the plurality of recommendation score values.
It should be noted that, a certain termination condition (for example, the user proposes to terminate the dialogue, or the number of rounds of the dialogues reaches a certain maximum value) may be met to stop the recommendation, so as to realize the active multi-time recommendation of the dialogue, and improve the experience of the user using the intelligent voice assistant.
In summary, according to the man-machine conversation interaction method, conversation sentences input by a user are received; acquiring current dialogue environment information according to the dialogue statement to confirm that the active recommendation condition is met; determining a current dialogue scene according to the current dialogue environment information; determining a plurality of candidate topics from a preset scene map according to the current dialogue scene; acquiring interest information of a user, and determining a target topic from a plurality of candidate topics according to the interest information; and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy. Therefore, the technical problems of poor dialogue effect and poor efficiency caused by passive dialogue recommendation in the prior art are solved, the dialogue scene is determined according to dialogue environment information, topics corresponding to the dialogue scene are acquired based on user interests, a plurality of dialogue contents are actively recommended to the user based on the topics, the dialogue scene requirements are met, the dialogue efficiency and effect are improved, and the user experience is improved.
To implement the above embodiment, fig. 2 is a flowchart of a man-machine conversation interaction method according to a second embodiment of the present application.
In step 201, a dialogue sentence input by a user is received, and it is determined that an active recommendation condition is satisfied according to the dialogue sentence.
It can be understood that the dialogue sentence input by the user has various forms, such as an inquiry sentence, an instruction sentence and the like, and after the dialogue sentence is analyzed, it can be determined that the dialogue sentence is not the instruction sentence and the like, that is, the intelligent device is not required to execute corresponding operations on the dialogue sentence, for example, controlling the television to be turned on and other scenes, so as to determine that the active recommendation condition is met.
Specifically, the current dialogue time information is obtained by calling the local system of the intelligent device, the current dialogue position information is obtained by calling the positioning system of the intelligent device, or the current dialogue position information is obtained by communicating with the terminal device, or the current position information is obtained from dialogue sentences, and the behavior action information of the user, such as running, reading and the like, is obtained by a camera, an infrared sensor and the like of the intelligent device.
Further, the current dialogue scene is determined according to the current time information and the current dialogue position information, such as the morning eighth point and the user residence address information A, or the current dialogue scene is determined according to the current dialogue position information and the behavior action information of the user, such as the user office address information B and the user in-use computer, as the working scene.
It can be understood that the scene graph and the corresponding topic of each scene in the scene graph are preset before the dialog content recommendation is performed.
As one possible implementation manner, a plurality of historical dialogue data are acquired, a plurality of dialogue scenes are determined according to the plurality of historical dialogue data, a plurality of topics corresponding to each dialogue scene are constructed, connection relations of the plurality of dialogue scenes are constructed, and a preset scene map is generated according to the connection relations of each dialogue scene and the plurality of topics corresponding to each dialogue scene.
That is, in the preset scene graph, edges between two scene nodes indicate logical links between different scenes, such as jumping from an early morning getting-up scene to a travel scene, and edges between each scene node and a plurality of topic nodes indicate that the topics belong to the scene, such as the early morning getting-up scene including weather forecast content, news content, and the like.
Therefore, the scene node of the current dialogue scene can be found in the preset scene map, and a plurality of topic nodes under the scene node are obtained to serve as a plurality of candidate topics.
It can be understood that the interest information of the user, namely the user preference information, can be analyzed based on the historical dialogue content to obtain the interest information of the user in each dialogue scene, and it should be noted that if the interest information of the user can be actively inquired and recorded for a new user, the interest information can be called when the active dialogue is recommended.
Further, a target topic is determined from a plurality of candidate topics according to the interest information, for example, a news topic is determined to be the target topic.
In step 205, a plurality of candidate dialogue contents corresponding to the target topic are acquired, and a plurality of recommendation score values corresponding to the plurality of candidate dialogue contents are generated after the plurality of candidate dialogue contents are weighted based on the recommendation heat, the dialogue content generation time and the user preference information.
At step 206, determining a recommendation for the target session content to the user based on the plurality of recommendation score values.
Specifically, for example, the user may give a higher weight to the dialogue content with higher recommendation heat, it may be understood that the recommendation heat, the dialogue content generation time and the weight corresponding to the user preference information may be adjusted and set according to the actual application requirement, and after calculation, each candidate dialogue content has a corresponding recommendation score value, and the corresponding target dialogue content may be recommended to the user directly according to the recommendation score value from high to low.
And step 208, if the preset switching condition is met according to the feedback statement, recommending the updated dialogue content to the user.
It can be appreciated that after the active recommendation, whether the user is interested or not can be determined according to the feedback statement input by the user, if the user is interested, the recommendation of the content can be continued, and if the user is not interested or the scene has been changed, the updated dialogue content can be recommended to the user, for example, as follows:
in a first example, if it is determined that the preset scene switching condition is satisfied according to the feedback statement, an update dialog scene is determined from a preset scene graph according to the feedback statement, a plurality of update candidate topics are determined from the preset scene graph according to the update dialog scene, the update topic is determined from the plurality of update candidate topics according to the interest information, a plurality of update candidate dialog contents corresponding to the update topic are obtained, the update dialog contents are determined from the plurality of update candidate dialog contents, and the update dialog contents are recommended to the user.
In a second example, if it is determined that the preset content switching condition is met according to the feedback statement, the updated dialogue content is selected from the plurality of candidate dialogue contents to be recommended to the user, for example, the target recommended content is the news for lading, the user feedback statement determines that the user is not interested, and the news for newsletter can be recommended to the user.
It should be noted that, after the active recommendation is performed, the user preference information can be continuously analyzed and stored and updated, so as to further meet the user requirement and improve the user experience.
In summary, according to the man-machine conversation interaction method of the embodiment of the application, conversation sentences input by a user are received, active recommendation conditions are determined to be met according to the conversation sentences, current conversation time information is acquired, current conversation position information is acquired, behavior action information of the user is acquired, a current conversation scene is determined according to the current conversation time information, the current conversation position information is acquired, the behavior action information of the user is acquired, a plurality of candidate topics are determined from a preset scene map according to the current conversation scene, interest information of the user is acquired, target topics are determined according to the interest information, a plurality of candidate conversation contents corresponding to the target topics are acquired, a plurality of recommendation score values corresponding to the candidate conversation contents are generated after weighting processing is performed on the basis of recommendation heat, conversation content generation time and user preference information, the target conversation contents are determined to be recommended to the user according to the recommendation score values, whether preset switching conditions are met or not is determined according to the feedback statement, and updated conversation contents are recommended to the user if the preset switching conditions are determined to be met according to the feedback statement. Therefore, the technical problems of poor dialogue effect and efficiency caused by passive dialogue recommendation in the prior art are solved, the dialogue scene is determined according to dialogue environment information, topics corresponding to the dialogue scene are acquired based on user interests, a plurality of dialogue contents are actively recommended to a user based on the topics, the dialogue scene requirements are met, the dialogue efficiency and effect are improved, the user use experience is improved, in addition, the recommended content switching can be carried out in real time, the dialogue efficiency and effect are further improved, and the user use experience is improved.
Based on the description of the above embodiment, according to the user feedback statement, it may be determined whether the preset scene switching condition, the preset content switching condition, etc. are satisfied, so as to update the dialogue content for recommending to the user, and how to update the dialogue content for recommending to the user after the scene switching is described in detail below with reference to fig. 3.
Fig. 3 is a flowchart of a man-machine conversation interaction method according to a third embodiment of the present application, as shown in fig. 3, including:
Step 302, determining a plurality of update candidate topics from a preset scene map according to the update dialogue scene.
Specifically, for example, in a study scene of a user at night, whether a feedback statement is received is determined to be the sleeping state, so that the scene switching condition is determined to be met, and a jump to an updated dialogue scene from each scene connection point of the study scene in a preset scene map is determined to be a preparation sleeping scene.
Further, a plurality of candidate topics for updating are determined from a preset scene map according to the updated dialogue scene, namely a plurality of topic nodes under the nodes of the scene to sleep are obtained as a plurality of candidate topics for updating, such as hypnotic music playing, pre-sleep story playing and the like.
And finally recommending the plurality of the update candidate dialogue contents to the user according to a preset recommendation strategy.
In summary, according to the man-machine conversation interaction method of the embodiment of the application, if the preset scene switching condition is met according to the feedback statement, an updated conversation scene is determined from the preset scene map according to the feedback statement, a plurality of updated candidate topics are determined from the preset scene map according to the updated conversation scene, updated topics are determined from the updated candidate topics according to the interest information, a plurality of updated candidate conversation contents corresponding to the updated topics are obtained, the updated conversation contents are determined from the updated candidate conversation contents, and the updated conversation contents are recommended to the user, so that the recommended contents can be switched in real time, conversation efficiency and effect are further improved, and user experience is improved.
Based on the description of the above embodiment, by triggering a certain scene, further triggering the recommendation of related content/entity to support active multiple recommendation, for example, the user requests songs to trigger entertainment scenes, the system can be triggered to make multiple recommendation of other music/movies, the children can trigger learning scenes for questions of a certain knowledge point, the system can be triggered to make multiple recommendation of story/encyclopedia knowledge, and the following specific dialogue examples are given to enable the application of man-machine dialogue interaction of the application to be more clear to the person skilled in the art:
example one:
bot good morning-! Now eight am.
User, java, eight-point pressing, I't go out of the tweed today-!
bot, eight cheers, local weather: cloudy, north wind, maximum air temperature of 13 ℃ and minimum air temperature of 5 ℃. The user remembers to add clothes when going out.
User, thank you for you, I want to get up and wash her face and rinse her mouth
bot, listening to your news bar with little hearing while washing, and broadcasting: [ world Wide Web express ] according to the U.S. "Focus-5" Web site message, local time 19 days later, the Washington Columbia zone of U.S. developed a gun shot, and local police were currently investigating.
User, news of female rank?
bot, female's world cup and land area, in the race of the main Japanese team of the Chinese female's team at the end of 19 days later, the Chinese female's team is battle with 3 to 0 Dapatu Japanese team. After the competition, the Chinese woman finishes the competition in the first stage with the battle of five battles without losing the score of one game, and the woman in the first stage has a top of the world cup score list of the woman in the first cause.
User that the current year's girl returns to cheer-!
Bot is o, really is exciting the mind-!
User is boring, I want to go out-!
Bot: bye-!
Example two:
user how long the dinosaur can live o?
bot, a vegetarian dinosaur with a long neck may have a longer life than other dinosaurs. If they are hot, they may live to one hundred years old; if cold, it may live to a couple of hundred years or longer. However, the lifetimes of tyrannosaurus are extremely short, on average only 16.6 years old.
User, java, do not run-!
bot dinosaur is a class of animals living in about 2 hundred million 3500 to 6500 tens of thousands of years ago that can walk upright with hind limbs supporting the body, governing the global terrestrial ecosystem for over 1 hundred million and 6 tens of millions of years. Most dinosaurs have been extincted, but the offspring of dinosaurs, birds, survive and reproduce.
Dinosaur suddenly disappears completely at the end of the chalky period 6500 years ago, becoming a riddle on the biological evolutionary history of the earth, which is still not solved by people.
Dinosaur is of a wide variety, and has large differences in shape and habit, with the largest fragile double chambered dragon being more than 50 meters and the smallest buzzes being less than 10 cm. In terms of feeding, there are warm and smooth predators and inland predators, and also omnivorous dinosaurs which are eaten by both meat and vegetables. The earth is dominated by about 8000 trillion years (1.44 hundred million years ago- -6500 trillion years ago).
User, thank for recommendation, i learn the knowledge of many dinosaurs.
What do Bot want to listen to dinosaur related stories?
User, o, i prefer to listen to the story of dinosaur.
Bot, cold-afraid dinosaur.
In nature, a dinosaur goes to Chengli sneeze and sneeze dinosaur says that: "really cold, remove the warmth and warmth-! "
The calyx girls see the shout: "I have a warm in home, come in and warm the bar-! "dinosaur stretches the neck and the brain is gone into, but the body is outside, dinosaur still feels cold.
Sneeze is a greater degree of dinosaur collision. The foremilk sees, say: "poor children, how do you don't wear clothes? "
Everyone gets off the cotton-padded trousers, covers the dinosaur, covers the fingers of the dinosaur, and covers the dinosaur with the quilt, and the dinosaur feels cold. When people put a fire at the side of dinosaur, the dinosaur can be still cold, and a group of children can see the dinosaur to be megaly and shout busy: "from, everything moves together. "the dinosaur then throws away the cotton-padded quilt and the child plays away. He/she is he-! Dinosaur also sweats.
Not boring, i want to go out to play.
Thus, if the user does not have an explicit need to recommend the content type, the user can be recommended to interested content (such as a certain movie/song/a certain news), or the user can be continuously recommended to interested content based on the current need of the user by triggering the associated content recommendation to be distinguished from passive recommendation (i.e. the user actively searches for the content to be recommended by the intelligent device), so that the chat duration of the user can be prolonged.
In order to achieve the foregoing embodiments, the present application further provides a man-machine interaction device, and fig. 4 is a schematic structural diagram of a man-machine interaction device according to a fourth embodiment of the present application, as shown in fig. 4, where the man-machine interaction device includes: a receiving module 401, a first determining module 402, a first obtaining module 403, a second determining module 404, a third determining module 405, an obtaining determining module 406, a second obtaining module 407, and a recommending module 408, wherein,
the receiving module 401 is configured to receive a dialogue sentence input by a user.
A first determining module 402, configured to determine that an active recommendation condition is satisfied according to the dialogue sentence.
A first obtaining module 403, configured to obtain current session context information.
A second determining module 404, configured to determine a current dialog scene according to the current dialog environment information.
A third determining module 405, configured to determine a plurality of candidate topics from a preset scene map according to the current dialog scene.
The acquiring determining module 406 is configured to acquire interest information of the user, and determine a target topic from the multiple candidate topics according to the interest information.
A second obtaining module 407, configured to obtain a plurality of candidate conversation contents corresponding to the target topic;
and a recommending module 408, configured to recommend the plurality of candidate dialog contents to the user according to a preset recommending policy.
In one embodiment of the present application, the first obtaining module 403 is specifically configured to:
acquiring time information of a current dialogue; and/or, obtaining the position information of the current dialogue; and/or acquiring behavior action information of the user.
In one embodiment of the present application, as shown in fig. 5, on the basis of fig. 4, the method further includes: a third acquisition module 409, a fourth determination module 410 and a generation module 411.
A third obtaining module 409, configured to obtain a plurality of historical dialogue data.
A fourth determining module 410, configured to determine a plurality of dialog scenarios and a plurality of topics corresponding to each dialog scenario according to the plurality of historical dialog data.
The generating module 411 is configured to construct connection relations of the multiple dialog scenes, and generate the preset scene map according to connection relations of each dialog scene and multiple topics corresponding to each dialog scene.
In this embodiment, the recommendation module 408 is specifically configured to: and weighting the plurality of candidate dialogue contents based on recommendation heat, dialogue content generation time and user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate dialogue contents, and determining a target dialogue content recommendation to the user according to the plurality of recommendation score values.
In one embodiment of the present application, the receiving module 401 is further configured to receive the feedback statement input by the user.
The first determining module 402 is further configured to determine whether a preset switching condition is met according to the feedback statement.
The recommending module 408 is further configured to recommend updated dialogue content to the user if it is determined that the preset switching condition is met according to the feedback statement.
In one embodiment of the present application, the recommendation module 408 is specifically configured to: if the feedback statement determines that the preset scene switching condition is met, determining an update dialogue scene from a preset scene graph according to the feedback statement, determining a plurality of update candidate topics from the preset scene graph according to the update dialogue scene, determining the update topics from the plurality of update candidate topics according to the interest information, acquiring a plurality of update candidate dialogue contents corresponding to the update topics, determining the update dialogue contents from the plurality of update candidate dialogue contents, and recommending the update dialogue contents to a user.
In one embodiment of the present application, the recommendation module 408 is specifically configured to: if the preset content switching condition is met according to the feedback statement, selecting and updating dialogue content from a plurality of candidate dialogue contents to recommend to the user, for example, the target recommended content is the news of the female, and the user feedback statement determines that the user is not interested, so that the current news recommendation can be switched to the user.
The foregoing explanation of the man-machine interaction method is also applicable to the man-machine interaction device according to the embodiment of the present invention, and the implementation principle is similar and will not be repeated here.
In summary, the man-machine dialogue interaction device of the embodiment of the application receives dialogue sentences input by a user; acquiring current dialogue environment information according to the dialogue statement to confirm that the active recommendation condition is met; determining a current dialogue scene according to the current dialogue environment information; determining a plurality of candidate topics from a preset scene map according to the current dialogue scene; acquiring interest information of a user, and determining a target topic from a plurality of candidate topics according to the interest information; and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy. Therefore, the technical problems of poor dialogue effect and poor efficiency caused by passive dialogue recommendation in the prior art are solved, the dialogue scene is determined according to dialogue environment information, topics corresponding to the dialogue scene are acquired based on user interests, a plurality of dialogue contents are actively recommended to the user based on the topics, the dialogue scene requirements are met, the dialogue efficiency and effect are improved, and the user experience is improved.
According to embodiments of the present application, an electronic device and a readable storage medium are also provided.
As shown in fig. 6, a block diagram of an electronic device is provided for a method of human-machine interaction according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.
As shown in fig. 6, the electronic device includes: one or more processors 601, memory 602, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 601 is illustrated in fig. 6.
The memory 602 is used as a non-transitory computer readable storage medium, and may be used to store a non-transitory software program, a non-transitory computer executable program, and program instructions/modules (e.g., the receiving module 401, the first determining module 402, the first obtaining module 403, the second determining module 404, the third determining module 405, the obtaining determining module 406, the second obtaining module 407, and the recommending module 408 shown in fig. 4) corresponding to a method for identifying validity of parking space data in an embodiment of the present application. The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 602, i.e., implements the human-machine interaction method in the above-described method embodiments.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the electronic device, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 602 may optionally include memory located remotely from processor 601, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device performing the method of validity identification of parking space data may further include: an input device 603 and an output device 604. The processor 601, memory 602, input device 603 and output device 604 may be connected by a bus or otherwise, for example in fig. 6.
The input device 603 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, trackpad, touchpad, pointer stick, one or more mouse buttons, trackball, joystick, and like input devices. The output means 604 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.
The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.
Claims (14)
1. A human-machine interaction method, comprising:
receiving dialogue sentences input by a user;
Acquiring current dialogue environment information according to the dialogue statement, wherein the current dialogue environment information comprises current dialogue time information and/or current dialogue position information and/or behavior action information of the user, the current dialogue time information is acquired by calling a local system of the intelligent equipment, the current dialogue position information is acquired by calling a positioning system of the intelligent equipment, and/or is acquired by communicating with terminal equipment and/or is acquired from the dialogue statement, and the behavior action information of the user is acquired by a camera or an infrared sensor of the intelligent equipment;
determining a current dialogue scene according to the current dialogue environment information;
determining a plurality of candidate topics from a preset scene map according to the current dialogue scene;
acquiring interest information of the user, and determining a target topic from the candidate topics according to the interest information;
and acquiring a plurality of candidate dialogue contents corresponding to the target topics, and recommending the plurality of candidate dialogue contents to the user according to a preset recommendation strategy.
2. The method of claim 1, further comprising, prior to said determining a plurality of candidate topics from a preset scene graph based on the current dialog scene:
Acquiring a plurality of historical dialogue data;
determining a plurality of dialogue scenes and a plurality of topics corresponding to each dialogue scene according to the plurality of historical dialogue data;
and constructing connection relations of the plurality of dialogue scenes, and generating the preset scene map by the connection relation of each dialogue scene and the topics corresponding to each dialogue scene.
3. The method of claim 1, wherein recommending the plurality of candidate conversation content to the user according to a preset recommendation policy comprises:
weighting the plurality of candidate dialogue contents based on recommendation heat, dialogue content generation time and user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate dialogue contents;
and determining the recommendation of the target dialogue content to the user according to the plurality of recommendation score values.
4. The method of claim 1, further comprising, after said recommending said plurality of candidate conversation content to said user according to a preset recommendation policy:
receiving a feedback statement input by the user;
determining whether a preset switching condition is met according to the feedback statement;
and if the preset switching condition is met according to the feedback statement, recommending the updated dialogue content to the user.
5. The method of claim 4, wherein recommending updated dialog content to the user if the preset switching condition is determined to be satisfied based on the feedback statement, comprising:
if the feedback statement is determined to meet the preset scene switching condition, determining an updated dialogue scene from the preset scene graph according to the feedback statement;
determining a plurality of update candidate topics from a preset scene map according to the update dialogue scene;
determining an updated topic from the plurality of updated candidate topics according to the interest information, and acquiring a plurality of updated candidate dialogue contents corresponding to the updated topic;
determining updated dialogue content from the plurality of updated candidate dialogue content and recommending the updated dialogue content to the user.
6. The method of claim 4, wherein recommending updated dialog content to the user if the preset switching condition is determined to be satisfied based on the feedback statement, comprising:
and if the preset content switching condition is met according to the feedback statement, selecting updated dialogue content from the plurality of candidate dialogue contents and recommending the updated dialogue content to the user.
7. A human-machine interaction device, comprising:
The receiving module is used for receiving dialogue sentences input by a user;
the first determining module is used for determining that the active recommendation condition is met according to the dialogue statement;
the first acquisition module is used for acquiring current dialogue environment information, wherein the current dialogue environment information comprises current dialogue time information and/or current dialogue position information and/or behavior action information of the user, the current dialogue time information is acquired by calling a local system of the intelligent equipment, the current dialogue position information is acquired by calling a positioning system of the intelligent equipment and/or is acquired by communicating with terminal equipment and/or is acquired from dialogue sentences, and the behavior action information of the user is acquired by a camera or an infrared sensor of the intelligent equipment;
the second determining module is used for determining a current dialogue scene according to the current dialogue environment information;
the third determining module is used for determining a plurality of candidate topics from a preset scene map according to the current dialogue scene;
the acquisition determining module is used for acquiring interest information of the user and determining target topics from the candidate topics according to the interest information;
the second acquisition module is used for acquiring a plurality of candidate dialogue contents corresponding to the target topics;
And the recommending module is used for recommending the plurality of candidate dialogue contents to the user according to a preset recommending strategy.
8. The apparatus as recited in claim 7, further comprising:
the third acquisition module is used for acquiring a plurality of historical dialogue data;
a fourth determining module, configured to determine a plurality of dialog scenes and a plurality of topics corresponding to each dialog scene according to the plurality of historical dialog data;
the generation module is used for constructing connection relations of the plurality of dialogue scenes and generating the preset scene map according to the connection relations of each dialogue scene and the topics corresponding to each dialogue scene.
9. The apparatus of claim 7, wherein the recommendation module is specifically configured to:
weighting the plurality of candidate dialogue contents based on recommendation heat, dialogue content generation time and user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate dialogue contents;
and determining the recommendation of the target dialogue content to the user according to the plurality of recommendation score values.
10. The apparatus as recited in claim 7, further comprising:
the receiving module is further used for receiving the feedback statement input by the user;
The first determining module is further configured to determine whether a preset switching condition is met according to the feedback statement;
and the recommending module is further used for recommending the updated dialogue content to the user if the preset switching condition is met according to the feedback statement.
11. The apparatus of claim 10, wherein the recommendation module is further specifically configured to:
if the feedback statement is determined to meet the preset scene switching condition, determining an updated dialogue scene from the preset scene graph according to the feedback statement;
determining a plurality of update candidate topics from a preset scene map according to the update dialogue scene;
determining an updated topic from the plurality of updated candidate topics according to the interest information, and acquiring a plurality of updated candidate dialogue contents corresponding to the updated topic;
determining updated dialogue content from the plurality of updated candidate dialogue content and recommending the updated dialogue content to the user.
12. The apparatus of claim 10, wherein the recommendation module is further specifically configured to:
and if the preset content switching condition is met according to the feedback statement, selecting updated dialogue content from the plurality of candidate dialogue contents and recommending the updated dialogue content to the user.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.
14. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911334965.3A CN111026932B (en) | 2019-12-20 | 2019-12-20 | Man-machine dialogue interaction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911334965.3A CN111026932B (en) | 2019-12-20 | 2019-12-20 | Man-machine dialogue interaction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111026932A CN111026932A (en) | 2020-04-17 |
| CN111026932B true CN111026932B (en) | 2023-05-26 |
Family
ID=70212595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911334965.3A Active CN111026932B (en) | 2019-12-20 | 2019-12-20 | Man-machine dialogue interaction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111026932B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737411A (en) * | 2020-05-20 | 2020-10-02 | 华为技术有限公司 | Response method in man-machine conversation, conversation system and storage medium |
| CN111881254A (en) * | 2020-06-10 | 2020-11-03 | 百度在线网络技术（北京）有限公司 | Method and device for generating dialogs, electronic equipment and storage medium |
| CN111813912A (en) * | 2020-06-29 | 2020-10-23 | 北京百度网讯科技有限公司 | Man-machine conversation method, device, equipment and storage medium |
| CN112000781B (en) * | 2020-07-20 | 2023-07-21 | 北京百度网讯科技有限公司 | Information processing method and device in user dialogue, electronic equipment and storage medium |
| CN112100491A (en) * | 2020-09-08 | 2020-12-18 | 中国平安人寿保险股份有限公司 | Information recommendation method, device and equipment based on user data and storage medium |
| CN112015881B (en) * | 2020-10-23 | 2021-02-19 | 和美（深圳）信息技术股份有限公司 | Automatic switching method and system for man-machine conversation process of intelligent robot |
| CN112732951A (en) * | 2020-12-30 | 2021-04-30 | 青岛海信智慧生活科技股份有限公司 | Man-machine interaction method and device |
| CN112883170B (en) * | 2021-01-20 | 2023-08-18 | 中国人民大学 | User feedback guided self-adaptive dialogue recommendation method and system |
| CN112836098B (en) * | 2021-02-01 | 2023-07-07 | 三星电子（中国）研发中心 | Multi-role-based conversation assistance method and device |
| CN112988994B (en) * | 2021-03-04 | 2023-03-21 | 网易（杭州）网络有限公司 | Conversation processing method and device and electronic equipment |
| CN114119123A (en) * | 2021-03-11 | 2022-03-01 | 北京沃东天骏信息技术有限公司 | Information pushing method and device |
| CN113535926B (en) * | 2021-07-26 | 2023-11-10 | 深圳市优必选科技股份有限公司 | Active dialogue method and device and voice terminal |
| WO2023019517A1 (en) * | 2021-08-19 | 2023-02-23 | 阿波罗智联(北京)科技有限公司 | Instruction recommendation method and apparatus |
| CN113688220B (en) * | 2021-09-02 | 2022-05-24 | 国家电网有限公司客户服务中心 | Text robot dialogue method and system based on semantic understanding |
| CN114003826A (en) * | 2021-12-31 | 2022-02-01 | 思创数码科技股份有限公司 | Resource directory recommendation method and device, readable storage medium and electronic equipment |
| CN115424624B (en) * | 2022-11-04 | 2023-01-24 | 深圳市人马互动科技有限公司 | Man-machine interaction service processing method and device and related equipment |
| CN115809669B (en) * | 2022-12-30 | 2024-03-29 | 联通智网科技股份有限公司 | Dialogue management method and electronic equipment |
| CN117408708A (en) * | 2023-11-09 | 2024-01-16 | 南方电网储能股份有限公司信息通信分公司 | Customer service center dispatching system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407425A (en) * | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| CN107728780A (en) * | 2017-09-18 | 2018-02-23 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device based on virtual robot |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN108000526A (en) * | 2017-11-21 | 2018-05-08 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105068661B (en) * | 2015-09-07 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method based on artificial intelligence and system |
| CN106020488A (en) * | 2016-06-03 | 2016-10-12 | 北京光年无限科技有限公司 | Man-machine interaction method and device for conversation system |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN108037905B (en) * | 2017-11-21 | 2021-12-21 | 北京光年无限科技有限公司 | Interactive output method for intelligent robot and intelligent robot |
| CN109977216A (en) * | 2019-04-01 | 2019-07-05 | 苏州思必驰信息科技有限公司 | Dialogue recommended method and system based on scene |
-
2019
- 2019-12-20 CN CN201911334965.3A patent/CN111026932B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407425A (en) * | 2016-09-27 | 2017-02-15 | 北京百度网讯科技有限公司 | A method and a device for information push based on artificial intelligence |
| CN107728780A (en) * | 2017-09-18 | 2018-02-23 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device based on virtual robot |
| CN107832433A (en) * | 2017-11-15 | 2018-03-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, server and storage medium based on dialogue interaction |
| CN108000526A (en) * | 2017-11-21 | 2018-05-08 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
Non-Patent Citations (1)
| Title |
|---|
| 复杂人机交互场景下的指势用户对象识别;管业鹏;《电子学报》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026932A (en) | 2020-04-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026932B (en) | Man-machine dialogue interaction method and device, electronic equipment and storage medium | |
| CN111953763B (en) | Business data pushing method and device and storage medium | |
| McRae | Flesh Made Word: Sex, Text and the Vikeual Body | |
| KR101959368B1 (en) | Determining an active persona of a user device | |
| US9908051B2 (en) | Techniques for creating dynamic game activities for games | |
| CN108919669A (en) | A kind of smart home dynamic decision method, apparatus and service terminal | |
| CN109643325B (en) | Recommending friends in automatic chat | |
| US11423235B2 (en) | Cognitive orchestration of multi-task dialogue system | |
| CN113018848B (en) | Game picture display method, related device, equipment and storage medium | |
| US11267121B2 (en) | Conversation output system, conversation output method, and non-transitory recording medium | |
| CN111538862B (en) | Method and device for explaining video | |
| CN109154948B (en) | Method and apparatus for providing content | |
| WO2018033066A1 (en) | Robot control method and companion robot | |
| US11397601B2 (en) | Interface and interruption management | |
| CN117085314A (en) | Auxiliary control method and device for cloud game, storage medium and electronic equipment | |
| CN116943220A (en) | Game artificial intelligence control method, device, equipment and storage medium | |
| CN109313638B (en) | Application recommendation | |
| CN112562641B (en) | Voice interaction satisfaction evaluation method, device, equipment and storage medium | |
| Bird | Flash mobs and zombie shuffles: Play in the augmented city | |
| Rehn et al. | Trendspotting-The Basics | |
| Hingston et al. | Mobile games with intelligence: A killer application? | |
| CN113144606A (en) | Skill triggering method of virtual object and related equipment | |
| CN111773736B (en) | Behavior generation method and device for virtual roles | |
| CN112138410B (en) | Interaction method of virtual objects and related device | |
| JP7331349B2 (en) | Conversation output system, server, conversation output method and program |
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 |