CN111026932A - Man-machine conversation interaction method and device, electronic equipment and storage medium - Google Patents
Man-machine conversation interaction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111026932A CN111026932A CN201911334965.3A CN201911334965A CN111026932A CN 111026932 A CN111026932 A CN 111026932A CN 201911334965 A CN201911334965 A CN 201911334965A CN 111026932 A CN111026932 A CN 111026932A
- Authority
- CN
- China
- Prior art keywords
- conversation
- user
- scene
- determining
- candidate
- 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.)
- Granted
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
- G06F16/90—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 conversation interaction method, a man-machine conversation interaction device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: receiving a dialogue statement input by a user; determining that the active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information; determining a current conversation scene according to the current conversation environment information; determining a plurality of candidate topics from a preset scene graph according to a current conversation scene; obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation 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 obtained based on the user interests, and a plurality of conversation contents are actively recommended to the user based on the topics, so that the conversation efficiency and effect are improved, and the user experience is improved.
Description
Technical Field
The present application relates to the field of artificial intelligence in computer technologies, and in particular, to a human-computer interaction method and apparatus, an electronic device, and a storage medium.
Background
With the continuous development of artificial intelligence technology, meeting the user's needs by interacting with an intelligent device is an interaction mode that is more and more common in the user's life.
In the related art, the user is asked by selecting a suitable question to select a target content from the candidate contents and provide the target content to the user, thereby resulting in a technical problem of poor conversation effect and efficiency.
Disclosure of Invention
A first object of the present application is to provide a man-machine interaction method.
A second objective of the present application is to provide a human-computer interaction device.
A third object of the present application is to provide an electronic device.
A fourth object of the present application is to propose a non-transitory computer readable storage medium storing computer instructions.
In order to achieve the above object, an embodiment of a first aspect of the present application provides a human-computer interaction method, including the following steps:
receiving a dialogue statement input by a user;
determining that an active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information;
determining a current conversation scene according to the current conversation environment information;
determining a plurality of candidate topics from a preset scene graph according to the current conversation scene;
obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy.
To achieve the above object, a second aspect of the present application provides a human-computer interaction device, including:
the receiving module is used for receiving the dialogue sentences input by the user;
the first determining module is used for determining that the active recommendation condition is met according to the conversation statement;
the first acquisition module is used for acquiring the current conversation environment information;
the second determining module is used for determining the current conversation scene according to the current conversation environment information;
the third determining module is used for determining a plurality of candidate topics from a preset scene graph according to the current conversation scene;
the obtaining and determining module is used for obtaining interest information of the user and determining a target topic from the candidate topics according to the interest information;
the second acquisition module is used for acquiring a plurality of candidate conversation contents corresponding to the target topic;
and the recommending module is used for recommending the candidate conversation contents to the user according to a preset recommending strategy.
To achieve the above object, 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, the instructions being executable by the at least one processor to enable the at least one processor to perform the human-computer interaction method described in the above embodiments.
To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the human-computer interaction method described in the above embodiments.
One embodiment in the above application has the following advantages or benefits:
receiving a dialogue statement input by a user; determining that the active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information; determining a current conversation scene according to the current conversation environment information; determining a plurality of candidate topics from a preset scene graph according to a current conversation scene; obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy. Therefore, the technical problem that conversation effect and efficiency are poor due to passive conversation recommendation in the prior art is solved, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are obtained based on the user interest, a plurality of conversation contents are actively recommended to the user based on the topics, the conversation scene requirements are met, conversation efficiency and effect are improved, and user experience is improved.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a flow chart of a human-machine dialog interaction method according to a first embodiment of the present application;
FIG. 2 is a flow chart of a method of human-machine dialog interaction according to a second embodiment of the present application;
FIG. 3 is a flow chart of a human-machine dialog interaction method according to a third embodiment of the present application;
FIG. 4 is a schematic structural diagram of a human-computer dialog interaction device according to a fourth embodiment of the present application;
FIG. 5 is a schematic structural diagram of a human-computer conversation interaction apparatus according to a fifth embodiment of the present application
Fig. 6 is a block diagram of an electronic device for implementing a man-machine interaction method according to an embodiment of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those 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 man-machine conversation interaction method, apparatus, electronic device, and storage medium according to the embodiments of the present application are described below with reference to the accompanying drawings.
In order to solve the technical problem that conversation effect and efficiency are poor due to passive conversation recommendation in the prior art, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are obtained based on the user interests, and a plurality of conversation contents are actively recommended to the user based on the topics, so that the conversation scene requirements are met, the conversation efficiency and effect are improved, and the user experience is improved.
Specifically, fig. 1 is a flowchart of a human-computer dialog interaction method according to a first embodiment of the present application.
As shown in fig. 1, the method includes:
And 102, determining that the active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information.
In practical application, the intelligent device can be awakened through modes such as voice or manual operation, so that the intelligent device can receive information such as text and voice, and a user can input dialogue sentences according to the requirement of practical application to carry out dialogue interaction with the intelligent device.
It is understood that the dialog sentence input by the user has many forms, such as an inquiry sentence, an instruction sentence, etc., and it may be determined that the dialog sentence is not the instruction sentence, etc. after performing the sentence analysis on the dialog sentence, that is, it is not necessary for the smart device to perform corresponding operations on the dialog sentence, for example, a scene such as controlling the television to be turned on is determined to satisfy the active recommendation condition, for example, the user and the smart device are just performing a cold talk or a short talk, or a command (for example, asking weather/question time, etc.) initiated by the user to initiate a non-immersive scene is determined to satisfy the active recommendation condition, wherein the immersive scene command is similar to listening to a song/listening to a story, and therefore is not suitable for interrupting the user to perform the active recommendation.
Further acquiring current conversation environment information, wherein there are many ways to acquire current conversation scene information, for example, as follows:
in a first example, the current session time information is obtained by invoking the smart device local system.
In a second example, the current dialog position information is obtained by calling an intelligent device positioning system, or the current dialog position information is obtained by communicating with a terminal device, or the current position information is obtained from a dialog statement.
In a third example, behavior and action information of a user, such as behavior and action information of running, reading, and the like, is acquired through a camera, an infrared sensor, and the like of the smart device.
And 103, determining the current conversation scene according to the current conversation environment information.
Specifically, after obtaining the current dialog environment information, the current dialog scenario may be determined according to the current dialog environment information, which is illustrated as follows:
in a first example, the current session scene is determined according to the current time information and the current session position information, such as eight morning spots and the user living address information a, which are determined as the morning getting-up scene.
In a second example, a current conversation scene is determined according to current conversation position information and behavior action information of a user, such as user office address information B and a user computer-in-use determined as a work scene.
And 104, determining a plurality of candidate topics from a preset scene graph according to the current conversation scene.
It can be understood that a scene graph is preset before conversation content recommendation is performed, and each scene in the scene graph corresponds to one topic.
As one possible implementation manner, a plurality of historical dialogue data are acquired, a plurality of dialogue scenes and a plurality of topics corresponding to each dialogue scene are determined according to the plurality of historical dialogue data, a connection relationship of the plurality of dialogue scenes is constructed, and a preset scene graph is generated according to the connection relationship of each dialogue scene and the topics corresponding to each dialogue scene.
That is, in the preset scene graph, an edge between two scene nodes indicates a logical connection between different scenes, such as jumping from a morning getting-up scene to a trip scene, and an edge between each scene node and a plurality of topic nodes indicates that the topics belong to the scene, such as the morning getting-up scene including weather forecast content, news content, and the like.
Therefore, the scene node of the current conversation scene can be found in the preset scene graph, and a plurality of topic nodes under the scene node are obtained as a plurality of candidate topics.
And 105, acquiring interest information of the user, and determining a target topic from a plurality of candidate topics according to the interest information.
And 106, acquiring a plurality of candidate conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy.
It can be understood that the interest information of the user, i.e., the user preference information, can be analyzed to obtain the interest information of the user in each dialog scenario based on the historical dialog content, and it should be noted that if the new user can actively ask and record the interest information of the user, it is only necessary to call the new user when actively recommending dialogues.
Further, a target topic is determined from the multiple candidate topics according to the interest information, for example, a news topic is determined as the target topic, so that multiple candidate conversation contents corresponding to the target topic, such as sports news, current affair news and the like, are obtained, and finally, the multiple candidate conversation contents are recommended to the user according to a preset recommendation strategy.
As an example, a plurality of candidate dialog contents are weighted based on the recommendation heat, the dialog content generation time and the user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate dialog contents, and the target dialog contents are determined according to the plurality of recommendation score values and recommended to the user.
It should be noted that, recommendation can be stopped when a certain termination condition is met (for example, the user proposes a termination dialog, or the number of rounds of dialogs between two parties reaches a certain maximum value), so that active multiple-time recommendation in a dialog manner is realized, and the experience of the user using the intelligent voice assistant is improved.
In summary, the man-machine conversation interaction method of the embodiment of the application receives a conversation sentence input by a user; determining that the active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information; determining a current conversation scene according to the current conversation environment information; determining a plurality of candidate topics from a preset scene graph according to a current conversation scene; obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy. Therefore, the technical problem that conversation effect and efficiency are poor due to passive conversation recommendation in the prior art is solved, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are obtained based on the user interest, a plurality of conversation contents are actively recommended to the user based on the topics, the conversation scene requirements are met, conversation efficiency and effect are improved, and user experience is improved.
To implement the above embodiments, fig. 2 is a flowchart of a human-computer conversation interaction method according to a second embodiment of the present application.
It can be understood that the dialog sentences input by the user have many forms, such as query sentences, instruction sentences, and the like, and it can be determined that the dialog sentences are not the instruction sentences and the like after the dialog sentences are subjected to sentence analysis, that is, the intelligent device is not required to perform corresponding operations on the dialog sentences, such as controlling a television to be turned on and the like, and determining that the active recommendation conditions are satisfied.
And step 203, determining the current conversation scene according to the current conversation time information, the current conversation position information and the behavior and action information of the user.
Specifically, the current conversation time information is acquired by calling a local system of the intelligent device, the current conversation position information is acquired by calling a positioning system of the intelligent device, or the current conversation position information is acquired by communicating with the terminal device, or the current position information is acquired from a conversation sentence, and the behavior and action information of the user, such as the behavior and action information of running, reading and the like, is acquired through a camera, an infrared sensor and the like of the intelligent device.
Further, a current conversation scene is determined according to the current time information and the current conversation position information, for example, eight morning spots and the user living address information A are determined as a morning getting-up scene, or the current conversation scene is determined according to the current conversation position information and the user behavior action information, for example, the user office address information B and the user computer are determined as a work scene.
It can be understood that a scene graph is preset before conversation content recommendation is performed, and each scene in the scene graph corresponds to one topic.
As one possible implementation manner, a plurality of historical dialogue data are acquired, a plurality of dialogue scenes and a plurality of topics corresponding to each dialogue scene are determined according to the plurality of historical dialogue data, a connection relationship of the plurality of dialogue scenes is constructed, and a preset scene graph is generated according to the connection relationship of each dialogue scene and the topics corresponding to each dialogue scene.
That is, in the preset scene graph, an edge between two scene nodes indicates a logical connection between different scenes, such as jumping from a morning getting-up scene to a trip scene, and an edge between each scene node and a plurality of topic nodes indicates that the topics belong to the scene, such as the morning getting-up scene including weather forecast content, news content, and the like.
Therefore, the scene node of the current conversation scene can be found in the preset scene graph, and a plurality of topic nodes under the scene node are obtained as a plurality of candidate topics.
It can be understood that the interest information of the user, i.e., the user preference information, can be analyzed to obtain the interest information of the user in each dialog scenario based on the historical dialog content, and it should be noted that if the new user can actively ask and record the interest information of the user, it is only necessary to call the new user when actively recommending dialogues.
Further, a target topic is determined from the plurality of candidate topics according to the interest information, for example, a news topic is determined as the target topic.
And step 206, determining the target conversation content to recommend to the user according to the plurality of recommendation score values.
Specifically, for example, the user may be more interested in the dialog content with a higher recommendation popularity and may be given a higher weight, it may be understood that the weights corresponding to the recommendation popularity, the dialog content generation time, and the user preference information may all be adjusted and set according to actual application needs, after the calculation, each candidate dialog content has a corresponding recommendation score value, and the corresponding target dialog content may be directly recommended to the user from high to low according to the recommendation score value.
And step 207, receiving a feedback statement input by the user, and determining whether a preset switching condition is met according to the feedback statement.
And step 208, recommending the updated conversation content to the user if the preset switching condition is met according to the feedback statement.
It can be understood that after the active recommendation is performed, 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 changed, the update dialog 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, an 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 conversation content is selected from the candidate conversation contents and recommended to the user, for example, the target recommended content is female news, and the user feedback statement determines that the user is not interested and can switch current news and recommend current news 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 use requirement and improve the user use experience.
To sum up, the man-machine conversation interaction method of the embodiment of the application receives conversation sentences input by a user, determines to meet active recommendation conditions according to the conversation sentences, acquires current conversation time information, acquires current conversation position information and acquires behavior action information of the user, determines a current conversation scene according to the current conversation time information, the current conversation position information and the behavior action information of the user, determines a plurality of candidate topics from a preset scene map according to the current conversation scene, acquires interest information of the user, determines a target topic from the plurality of candidate topics according to the interest information, acquires a plurality of candidate conversation contents corresponding to the target topic, performs weighting processing on the plurality of candidate conversation contents based on recommendation heat, conversation content generation time and user preference information to generate a plurality of recommendation score values corresponding to the plurality of candidate conversation contents, and determining that the target conversation content is recommended to the user according to the plurality of recommendation score values, receiving a feedback statement input by the user, determining whether a preset switching condition is met according to the feedback statement, and recommending the updated conversation content to the user if the preset switching condition is met according to the feedback statement. Therefore, the technical problem that conversation effect and efficiency are poor due to passive conversation recommendation in the prior art is solved, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are obtained based on the interest of the user, a plurality of conversation contents are actively recommended to the user based on the topics, the conversation scene requirements are met, conversation efficiency and effect are improved, user use experience is improved, in addition, recommendation content switching can be carried out in real time, conversation efficiency and effect are further improved, and 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, and the like are satisfied, so as to update the dialog content and recommend the dialog content to the user, and how to update the dialog content and recommend the dialog content to the user after scene switching is described in detail below with reference to fig. 3.
Fig. 3 is a flowchart of a human-computer dialog interaction method according to a third embodiment of the present application, as shown in fig. 3, including:
Step 302, determining a plurality of updating candidate topics from a preset scene graph according to the updating conversation scene.
Specifically, for example, in a learning scene of a user at night, if the feedback statement is received, it is determined that the user is sleeping, so that the scene switching condition is satisfied, and it is determined from each scene connection point of the learning scene in a preset scene graph that the user jumps to an updated dialogue scene to prepare for a sleeping scene.
Further, a plurality of updating candidate topics are determined from the preset scene graph according to the updating dialogue scene, that is, a plurality of topic nodes under the node of the scene ready to sleep are obtained as a plurality of updating candidate topics, such as music playing, pre-sleep story playing and the like.
Therefore, the updating topic is determined from the plurality of updating candidate topics according to the interest information, for example, the story topic of the child is determined to be the updating topic, so that a plurality of updating candidate conversation contents corresponding to the updating topic are obtained, and finally the plurality of updating candidate conversation contents are recommended to the user according to a preset recommendation strategy.
In summary, according to the man-machine conversation interaction method provided by the embodiment of the application, if it is determined that the preset scene switching condition is met according to the feedback statement, the updated conversation scene is determined from the preset scene graph according to the feedback statement, the plurality of update candidate topics are determined from the preset scene graph according to the updated conversation scene, the update topic is determined from the plurality of update candidate topics according to the interest information, the plurality of update candidate conversation contents corresponding to the update topic are obtained, the update conversation contents are determined from the plurality of update candidate conversation contents, and the update conversation contents are recommended to the user.
Based on the description of the above embodiments, by triggering a certain scenario, further triggering recommendation of related content/entities, so as to support active multiple recommendations, for example, a user requests a song to trigger an entertainment scenario, may trigger a system to perform multiple recommendations of other music/movies, a child triggers a learning scenario for a question of a certain knowledge point, may trigger a system to perform multiple recommendations of story/encyclopedic knowledge, and the following gives specific dialog examples to make it more clear to those skilled in the art that the application of man-machine dialog interaction in the present application:
example one:
bot morning good! Now eight am.
Wa, all eight points, I should go out today!
The bots are all eight-dot cheer, and the local weather is as follows: cloudy and northern wind, the highest temperature is 13 ℃, and the lowest temperature is 5 ℃. The words after going out are coupled.
User, good, thanks you, i want to get up to wash
A bot, washing while listening to a small music for broadcasting news: according to the website message of Focus-5 in the United states, the gunshot case occurs 19 days and a night in the United states of America, Washington, Columbia, and the local police are currently investigating.
User, news of girl?
bot, the world of the female, the Zhan Binsheng, in the competition of the home team of the Dongdao Advance of China who finishes 19 days later, the home team of China was fighting with 3 to 0 major rancidity. After the match, the first-stage match is ended by the female in China with the achievement of the five-battle win without losing one round, and the female in China is high in the top of the world cup point list.
User, the girl in the year returns to the Lala!
Let a bot be really exciting!
User is not chatting, I want to go out!
And Bot: turning to!
Example two:
user is how long the dinosaur can live?
bots-long neck vegetarian dinosaurs may have a longer life than other dinosaurs. If they are hot, they may live to one hundred years; if it is cold, it may live to two hundred years or more. However, tyrannosaurus has a particularly short life span, which is only 16.6 years on average.
User, Wa, not Braille!
Dinosaurs are a class of animals that live approximately 2 hundred million 3500 to 6500 million years ago and walk upright with hind limbs supporting the body, dominating the global terrestrial ecosystem for over 1 million 6 million years. Most dinosaurs have died, but the offspring of dinosaurs, birds, survive and multiply.
The dinosaur suddenly disappears all the time when the chalk period finishes in 6500 ten thousand years, and becomes a riddle in the earth's biological evolution history, and the riddle can not be solved.
Dinosaurs are of many types and vary in shape and habit, with the largest fragile double chamber dinosaurs being likely to exceed 50 meters, and the smallest hummingbirds being likely to be less than 10 centimeters. In terms of food habits, there are warm and smooth grass eaters, fierce meat eaters, and omnivorous dinosaurs which are eaten by both meat and vegetables. Governs the earth about 8000 ten thousand years (1.44 hundred million years ago-6500 ten thousand years ago).
User thanks recommendation, i learned much dinosaur knowledge again.
Does Bot want to listen to dinosaur-related stories?
User, good, i like listening to dinosaur story.
Bot is big dinosaur who is afraid of cold.
The natural cold, one big dinosaur coming to honest "sneeze, the sneeze dinosaur said: "true cold, remove warm and warm! "
Girls see a shout: ' I have warm air in our home, come in warm and warm the bar! The dinosaur stretches the neck and the head bag is inserted into the dinosaur, so that the dinosaur can stay outside and feel cold.
The dinosaur can strike the body more severely when the dinosaur sneezes. The old milk sees, say: "how do you don't wear your clothing for a poor child? "
Everybody has come, they have taken off the cotton-padded clothes and covered the dinosaur, but only the fingers of the dinosaur are covered, and the quilt is covered on the dinosaur, but the dinosaur still feels cold. Everybody has got up the fiery beside the dinosaur, can still be cold, and at this moment, a group of children see dinosaur, tremble directly, yell: to do exercises together. Thus, the dinosaur thrown away the cotton-padded clothes and quilt, and played with a child. He is he! Dinosaurs also sweat on their bodies.
Do not chat, i want to go out and play.
Therefore, the content which is interesting to the user (such as a certain movie/song/a certain news) is recommended under the condition that the user does not have an explicit requirement on the recommended content type, or the associated content recommendation is triggered based on the current requirement of the user so as to be distinguished from passive recommendation (namely the user actively finds the intelligent device to inquire the content to be recommended), the content which is interesting to the user can be continuously recommended, and the chatting time of the user is prolonged.
In order to implement the foregoing embodiments, the present application further provides a human-computer interaction device, and fig. 4 is a schematic structural diagram of a human-computer interaction device according to a fourth embodiment of the present application, as shown in fig. 4, the human-computer 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,
a receiving module 401, configured to receive a dialog statement input by a user.
A first determining module 402, configured to determine that an active recommendation condition is satisfied according to the dialog statement.
A first obtaining module 403, configured to obtain current dialog environment information.
A second determining module 404, configured to determine a current dialog scenario according to the current dialog environment information.
A third determining module 405, configured to determine a plurality of candidate topics from a preset scene graph according to the current dialog scene.
An obtaining and determining module 406, configured to obtain 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 candidate session contents to the user according to a preset recommending policy.
In an embodiment of the present application, the first obtaining module 403 is specifically configured to:
acquiring time information of a current conversation; and/or acquiring the position information of the current conversation; and/or acquiring the behavior and action information of the user.
In an embodiment of the present application, as shown in fig. 5, on the basis of fig. 4, the method further includes: a third obtaining module 409, a fourth determining module 410 and a generating 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 a connection relationship between the multiple dialog scenes, and a connection relationship between each dialog scene and multiple topics corresponding to each dialog scene to generate the preset scene graph.
In this embodiment, the recommending module 408 is specifically configured to: and performing weighting processing on the candidate conversation contents based on the recommendation heat, the conversation content generation time and the user preference information to generate a plurality of recommendation score values corresponding to the candidate conversation contents, and determining the target conversation contents to be recommended to the user according to the recommendation score values.
In an embodiment of the present application, the receiving module 401 is further configured to receive a 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 the updated dialog content to the user if it is determined that the preset switching condition is met according to the feedback statement.
In an embodiment of the present application, the recommending module 408 is specifically configured to: if the preset scene switching condition is determined to be met according to the feedback statement, an updating conversation scene is determined from a preset scene map according to the feedback statement, a plurality of updating candidate topics are determined from the preset scene map according to the updating conversation scene, the updating topics are determined from the updating candidate topics according to the interest information, a plurality of updating candidate conversation contents corresponding to the updating topics are obtained, the updating conversation contents are determined from the updating candidate conversation contents, and the updating conversation contents are recommended to the user.
In an embodiment of the present application, the recommending module 408 is specifically configured to: if the preset content switching condition is met according to the feedback statement, selecting the updated conversation content from the candidate conversation contents and recommending the updated conversation content to the user, for example, the target recommended content is female news, and the user feedback statement determines that the user is not interested and can switch current news and recommend the current news to the user.
It should be noted that the 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 is not described herein again.
In summary, the man-machine conversation interaction device of the embodiment of the application receives a conversation sentence input by a user; determining that the active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information; determining a current conversation scene according to the current conversation environment information; determining a plurality of candidate topics from a preset scene graph according to a current conversation scene; obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy. Therefore, the technical problem that conversation effect and efficiency are poor due to passive conversation recommendation in the prior art is solved, the conversation scene is determined according to the conversation environment information, topics corresponding to the conversation scene are obtained based on the user interest, a plurality of conversation contents are actively recommended to the user based on the topics, the conversation scene requirements are met, conversation efficiency and effect are improved, and user experience is improved.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 6 is a block diagram of an electronic device 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 phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 6, the electronic apparatus includes: one or more processors 601, memory 602, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. 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 for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 6, one processor 601 is taken as an example.
The memory 602 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the methods provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the human-computer dialog interaction method provided by the present application.
The memory 602 is used as a non-transitory computer readable storage medium and may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the method for identifying the validity of parking space data in the embodiment of the present application (for example, 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). 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, that is, implementing the man-machine interaction method in the above 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, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, 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, the memory 602 optionally includes memory located remotely from the 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 recognizing validity of parking space data may further include: an input device 603 and an output device 604. The processor 601, the memory 602, the input device 603 and the output device 604 may be connected by a bus or other means, and fig. 6 illustrates the connection by a bus as an example.
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 apparatus, such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or other input device. The output devices 604 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. 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 can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. 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 a pointing device (e.g., a mouse or a 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 can 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, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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 clients and servers. A client and server are generally 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 understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (16)
1. A human-computer dialogue interaction method is characterized by comprising the following steps:
receiving a dialogue statement input by a user;
determining that an active recommendation condition is met according to the conversation statement, and acquiring current conversation environment information;
determining a current conversation scene according to the current conversation environment information;
determining a plurality of candidate topics from a preset scene graph according to the current conversation scene;
obtaining 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 conversation contents corresponding to the target topic, and recommending the candidate conversation contents to the user according to a preset recommendation strategy.
2. The method of claim 1, wherein the obtaining current dialog context information comprises:
acquiring current conversation time information; and/or the presence of a gas in the gas,
acquiring current conversation position information; and/or the presence of a gas in the gas,
and acquiring the behavior and action information of the user.
3. The method as recited in claim 1, further comprising, prior to said determining a plurality of candidate topics from a preset scene graph as a function of said current conversation scene:
acquiring a plurality of historical dialogue data;
determining a plurality of dialogue scenes according to the historical dialogue data and a plurality of topics corresponding to each dialogue scene;
and constructing the connection relation of the plurality of conversation scenes and the connection relation of each conversation scene and a plurality of topics corresponding to each conversation scene to generate the preset scene graph.
4. The method of claim 1, wherein recommending the plurality of candidate conversation contents to the user according to a preset recommendation strategy comprises:
weighting the candidate conversation contents based on recommendation heat, conversation content generation time and user preference information to generate a plurality of recommendation score values corresponding to the candidate conversation contents;
and determining the target conversation content to be recommended to the user according to the plurality of recommendation score values.
5. The method of claim 1, wherein after said recommending the plurality of candidate conversation contents to the user according to a preset recommendation strategy, further comprising:
receiving a feedback statement input by the user;
determining whether a preset switching condition is met according to the feedback statement;
and recommending the updated conversation content to the user if the preset switching condition is determined to be met according to the feedback statement.
6. The method of claim 5, wherein recommending updated dialog content to the user if it is determined that the preset switching condition is satisfied according to the feedback statement comprises:
if the preset scene switching condition is determined to be met according to the feedback statement, determining an updated dialog scene from the preset scene map according to the feedback statement;
determining a plurality of updating candidate topics from a preset scene graph according to the updating dialogue scene;
determining an updating topic from the plurality of updating candidate topics according to the interest information, and acquiring a plurality of updating candidate conversation contents corresponding to the updating topic;
determining an update dialog content from the plurality of update candidate dialog contents, and recommending the update dialog content to the user.
7. The method of claim 5, wherein recommending updated dialog content to the user if it is determined that the preset switching condition is satisfied according to the feedback statement comprises:
and if the preset content switching condition is determined to be met according to the feedback statement, selecting updated conversation content from the candidate conversation contents and recommending the updated conversation content to the user.
8. A human-computer dialog interaction device, comprising:
the receiving module is used for receiving the dialogue sentences input by the user;
the first determining module is used for determining that the active recommendation condition is met according to the conversation statement;
the first acquisition module is used for acquiring the current conversation environment information;
the second determining module is used for determining the current conversation scene according to the current conversation environment information;
the third determining module is used for determining a plurality of candidate topics from a preset scene graph according to the current conversation scene;
the obtaining and determining module is used for obtaining interest information of the user and determining a target topic from the candidate topics according to the interest information;
the second acquisition module is used for acquiring a plurality of candidate conversation contents corresponding to the target topic;
and the recommending module is used for recommending the candidate conversation contents to the user according to a preset recommending strategy.
9. The apparatus of claim 8, wherein the first obtaining module is specifically configured to:
acquiring time information of a current conversation; and/or the presence of a gas in the gas,
acquiring the position information of the current conversation; and/or the presence of a gas in the gas,
and acquiring the behavior and action information of the user.
10. The apparatus of claim 8, further comprising:
the third acquisition module is used for acquiring a plurality of historical dialogue data;
a fourth determining module, configured to determine, according to the historical conversation data, a plurality of conversation scenes and a plurality of topics corresponding to each conversation scene;
and the generating module is used for constructing the connection relationship of the plurality of conversation scenes and the connection relationship of each conversation scene and a plurality of topics corresponding to each conversation scene to generate the preset scene map.
11. The apparatus of claim 8, wherein the recommendation module is specifically configured to:
weighting the candidate conversation contents based on recommendation heat, conversation content generation time and user preference information to generate a plurality of recommendation score values corresponding to the candidate conversation contents;
and determining the target conversation content to be recommended to the user according to the plurality of recommendation score values.
12. The apparatus of claim 8, further comprising:
the receiving module is further configured to receive a 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 conversation content to the user if the preset switching condition is determined to be met according to the feedback statement.
13. The apparatus of claim 12, wherein the recommendation module is further specifically configured to:
if the preset scene switching condition is determined to be met according to the feedback statement, determining an updated dialog scene from the preset scene map according to the feedback statement;
determining a plurality of updating candidate topics from a preset scene graph according to the updating dialogue scene;
determining an updating topic from the plurality of updating candidate topics according to the interest information, and acquiring a plurality of updating candidate conversation contents corresponding to the updating topic;
determining an update dialog content from the plurality of update candidate dialog contents, and recommending the update dialog content to the user.
14. The apparatus of claim 12, wherein the recommendation module is further specifically configured to:
and if the preset content switching condition is determined to be met according to the feedback statement, selecting updated conversation content from the candidate conversation contents and recommending the updated conversation content to the user.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
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 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
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 true CN111026932A (en) | 2020-04-17 |
| CN111026932B 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) |
Cited By (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 |
| 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 |
| 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 |
| CN112000781A (en) * | 2020-07-20 | 2020-11-27 | 北京百度网讯科技有限公司 | Information processing method and device in user conversation, electronic equipment and storage medium |
| CN112015881A (en) * | 2020-10-23 | 2020-12-01 | 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 |
| 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 |
| 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 |
| CN112836098A (en) * | 2021-02-01 | 2021-05-25 | 三星电子（中国）研发中心 | Multi-role-based conversation assistance method and device |
| CN112883170A (en) * | 2021-01-20 | 2021-06-01 | 中国人民大学 | User feedback guided self-adaptive conversation recommendation method and system |
| CN112988994A (en) * | 2021-03-04 | 2021-06-18 | 网易（杭州）网络有限公司 | Conversation processing method and device and electronic equipment |
| CN113535926A (en) * | 2021-07-26 | 2021-10-22 | 深圳市优必选科技股份有限公司 | Active dialogue method, device and voice terminal |
| CN113688220A (en) * | 2021-09-02 | 2021-11-23 | 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 |
| WO2022188534A1 (en) * | 2021-03-11 | 2022-09-15 | 北京沃东天骏信息技术有限公司 | Information pushing method and apparatus |
| CN115424624A (en) * | 2022-11-04 | 2022-12-02 | 深圳市人马互动科技有限公司 | Man-machine interaction service processing method and device and related equipment |
| 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 |
| CN115809669A (en) * | 2022-12-30 | 2023-03-17 | 联通智网科技股份有限公司 | Conversation 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 (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN108037905A (en) * | 2017-11-21 | 2018-05-15 | 北京光年无限科技有限公司 | A kind of interaction output method and intelligent robot for 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 (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN108037905A (en) * | 2017-11-21 | 2018-05-15 | 北京光年无限科技有限公司 | A kind of interaction output method and intelligent robot for 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 |
Non-Patent Citations (1)
| Title |
|---|
| 管业鹏: "复杂人机交互场景下的指势用户对象识别", 《电子学报》 * |
Cited By (23)
| 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 |
| CN112000781A (en) * | 2020-07-20 | 2020-11-27 | 北京百度网讯科技有限公司 | Information processing method and device in user conversation, electronic 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 |
| CN112015881A (en) * | 2020-10-23 | 2020-12-01 | 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 |
| CN112883170A (en) * | 2021-01-20 | 2021-06-01 | 中国人民大学 | User feedback guided self-adaptive conversation recommendation method and system |
| CN112883170B (en) * | 2021-01-20 | 2023-08-18 | 中国人民大学 | User feedback guided self-adaptive dialogue recommendation method and system |
| CN112836098A (en) * | 2021-02-01 | 2021-05-25 | 三星电子（中国）研发中心 | Multi-role-based conversation assistance method and device |
| CN112988994A (en) * | 2021-03-04 | 2021-06-18 | 网易（杭州）网络有限公司 | Conversation processing method and device and electronic equipment |
| WO2022188534A1 (en) * | 2021-03-11 | 2022-09-15 | 北京沃东天骏信息技术有限公司 | Information pushing method and apparatus |
| CN113535926A (en) * | 2021-07-26 | 2021-10-22 | 深圳市优必选科技股份有限公司 | Active dialogue method, device and voice terminal |
| 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 |
| CN113688220A (en) * | 2021-09-02 | 2021-11-23 | 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 |
| CN115424624A (en) * | 2022-11-04 | 2022-12-02 | 深圳市人马互动科技有限公司 | Man-machine interaction service processing method and device and related 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 |
| CN115809669A (en) * | 2022-12-30 | 2023-03-17 | 联通智网科技股份有限公司 | Conversation management method and electronic 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111026932B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111026932A (en) | Man-machine conversation interaction method and device, electronic equipment and storage medium | |
| CN111953763B (en) | Business data pushing method and device and storage medium | |
| CN108762843A (en) | Preloading method, apparatus, storage medium and the intelligent terminal of application program | |
| CN113018848B (en) | Game picture display method, related device, equipment and storage medium | |
| CN105204886B (en) | A kind of method, user terminal and server activating application program | |
| JP2021096886A (en) | Method, apparatus, device, medium, and program for information recommendation based on fusion relation network | |
| US11267121B2 (en) | Conversation output system, conversation output method, and non-transitory recording medium | |
| CN109643325A (en) | The recommending friends in automatic chatting | |
| US20210141862A1 (en) | Cognitive orchestration of multi-task dialogue system | |
| WO2022242260A1 (en) | Interaction method, apparatus and device in game, and storage medium | |
| CN109154948B (en) | Method and apparatus for providing content | |
| CN110781421B (en) | Virtual resource display method and related device | |
| CN111565143A (en) | Instant messaging method, equipment and computer readable storage medium | |
| US10133464B2 (en) | Selectively reenabling an interactive element for the collection of user feedback | |
| CN114344906A (en) | Method, device, equipment and storage medium for controlling partner object in virtual scene | |
| CN110841296B (en) | Game character skill generation method and device, electronic equipment and storage medium | |
| CN110674338B (en) | Voice skill recommendation method, device, equipment and storage medium | |
| CN112328776A (en) | Dialog generation method and device, electronic equipment and storage medium | |
| CN112562641B (en) | Voice interaction satisfaction evaluation method, device, equipment and storage medium | |
| CN112822558A (en) | Information broadcasting method, device, equipment and medium based on online platform | |
| Pardo et al. | Goal-oriented trajectories for efficient exploration | |
| CN112138410B (en) | Interaction method of virtual objects and related device | |
| CN117899478B (en) | Virtual character control method and related device | |
| JP2020014715A (en) | Video game processing program and video game processing system | |
| CN110704595B (en) | Dialogue processing method and device, electronic equipment and readable storage medium |
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 |