CN112989014A - Dialogue processing method and device, electronic equipment and readable storage medium - Google Patents
Dialogue processing method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN112989014A CN112989014A CN202110479880.5A CN202110479880A CN112989014A CN 112989014 A CN112989014 A CN 112989014A CN 202110479880 A CN202110479880 A CN 202110479880A CN 112989014 A CN112989014 A CN 112989014A
- Authority
- CN
- China
- Prior art keywords
- current
- user
- topic
- conversation
- electronic device
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0005—Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Mathematical Physics (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a conversation processing method, a device, electronic equipment and a readable storage medium, wherein the method is applied to the electronic equipment with a conversation function and comprises the following steps: judging whether the current conversation user is interested in the current topic or not in the process of carrying out conversation between the electronic equipment and the current conversation user based on the current topic; determining a relative relationship between the electronic device and the current conversing user based on the current topic; and generating a question sentence of the electronic equipment based on the judgment result and the relative relation, and actively asking a question to the current dialogue user based on the question sentence.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and an apparatus for processing a dialog, an electronic device, and a readable storage medium.
Background
With the development of human-computer interaction technology, more and more intelligent products based on human-computer interaction technology are produced, such as chat robots (chat bots) and the like. These smart products can chat with the user and generate answer information based on the user's questions. The existing chat robot usually carries out conversation with a user according to a fixed question-answer mode, and the chat mode is mechanical and boring, cannot well adapt to different requirements of the user, and causes poor experience of the user.
Disclosure of Invention
In view of the above, the main objective of the present invention is to provide a conversation processing method, device, electronic device and readable storage medium, which can actively ask a question to a user by determining a relationship between a conversation robot and the user and determining whether the user is interested in topics discussed by the conversation robot and the user, so as to enable the conversation robot to actively climb up according to the determination result, and further guide or grasp the initiative right in the chat process, so as to create a more active chat atmosphere, so that the user is more willing to converse with the conversation robot, or more willing to spend more time chatting with the conversation robot.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a dialog processing method, which is applied to an electronic device including a dialog function, where the method includes:
judging whether the current conversation user is interested in the current topic or not in the process of carrying out conversation between the electronic equipment and the current conversation user based on the current topic; determining a relative relationship between the electronic device and the current conversing user based on the current topic;
and generating a question sentence of the electronic equipment based on the judgment result and the relative relation, and actively asking a question to the current dialogue user based on the question sentence.
In the above scheme, the determining whether the current dialog user is interested in the current topic includes:
obtaining a dialogue sentence between the electronic equipment and a current dialogue user; the conversational sentence is associated with the current topic;
analyzing and processing the dialogue sentences to obtain an analysis result;
and judging whether the current dialog user is interested in the current topic or not based on the analysis result.
In the above scheme, the analyzing the conversational sentence to obtain an analysis result includes at least one of:
analyzing the feedback speed of the reply sentences in the dialogue sentences to obtain a first analysis result;
analyzing the words of the reply sentences in the dialogue sentences to obtain a second analysis result;
analyzing the semantics of the reply sentences in the dialogue sentences to obtain a third analysis result;
correspondingly, the determining whether the current dialog user is interested in the current topic based on the analysis result includes:
judging whether the current dialog user is interested in the current topic based on at least one of the first analysis result, the second analysis result and the third analysis result;
wherein the reply sentence is a reply of the current dialog user to the question asked by the electronic device.
In the above solution, the determining a relative relationship between the electronic device and the current dialog user based on the current topic includes:
acquiring keywords contained in the current topic;
accessing a third-party database and/or a self database based on the keywords to obtain an access result; determining a relative relationship between the electronic device and the current dialog user based on the access result;
the self database is a database of the electronic equipment; the third-party database is a database which can be linked by the electronic equipment through a network.
In the above solution, in a case that the access result is that the keyword is contained in the third-party database and/or the self database, the determining, based on the access result, a relative relationship between the electronic device and the current conversation user includes: determining that the relative relationship between the electronic device and the current dialog user is: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user;
in a case that the access result is that the keyword is not contained in the third-party database and/or the self-database, the determining, based on the access result, a relative relationship between the electronic device and the current conversation user includes: determining that the relative relationship between the electronic device and the current dialog user is: a second relationship; and the relative relationship in the second relationship is that the electronic equipment is in the second relationship, the current conversation user is guided to ask more questions, information related to the current topic is obtained, and the third-party database is accessed based on the information so as to feed back the questions of the current conversation user.
In the foregoing solution, the generating a question sentence of the electronic device based on the determination result and the relative relationship includes:
generating a first question statement under the condition that the judgment result is that the current conversation user is interested in the current topic and the relative relationship is that the electronic equipment is in a first relationship; the first question sentence is used for correcting the error of the current dialog user and/or providing consultation;
and generating a second question sentence under the condition that the judgment result is that the current dialogue user is interested in the current topic and the relative relationship is that the electronic equipment is in a second relationship, wherein the second question sentence is used for guiding the current dialogue user to ask more questions.
In the above aspect, the method further includes:
under the condition that the current conversation user is not interested in the current topic, the topic is replaced, and whether the current conversation user is interested in the replaced topic is judged again; re-determining a relative relationship between the electronic device and the current conversing user based on the replaced topic; until the number of times of changing the topics which are interesting to the current conversation user is larger than a preset threshold value.
In the above aspect, the method further includes:
in the process that the electronic equipment and a current conversation user carry out conversation based on a current topic, sensing the occurrence time of the conversation; generating a sentence of interest based on the occurrence time; wherein, the concern sentence contains a keyword for representing the concern of the current dialogue user.
In a second aspect, an embodiment of the present invention further provides a dialog processing apparatus applied to an electronic device including a dialog function, where the dialog processing apparatus includes a determining unit, a generating unit, and a questioning unit,
the judging unit is used for judging whether the current conversation user is interested in the current topic or not in the process that the electronic equipment and the current conversation user have a conversation based on the current topic;
the determining unit is used for determining the relative relationship between the electronic equipment and the current conversation user based on the current topic;
the generating unit is used for generating question sentences of the electronic equipment based on the judgment result and the relative relation;
and the question asking unit is used for actively asking questions of the current dialogue user based on the question sentences.
In the above scheme, the determining unit includes a first obtaining subunit, an analyzing subunit, and a determining subunit, wherein,
the first obtaining subunit is configured to obtain a dialog statement between the electronic device and a current dialog user; the conversational sentence is associated with the current topic;
the analysis subunit is configured to perform analysis processing on the dialog statement to obtain an analysis result;
and the judging subunit is used for judging whether the current conversation user is interested in the current topic or not based on the analysis result.
In the foregoing scheme, the analysis subunit is specifically configured to: including at least one of:
analyzing the feedback speed of the reply sentences in the dialogue sentences to obtain a first analysis result;
analyzing the words of the reply sentences in the dialogue sentences to obtain a second analysis result;
analyzing the semantics of the reply sentences in the dialogue sentences to obtain a third analysis result;
the judging subunit is specifically configured to: judging whether the current dialog user is interested in the current topic based on at least one of the first analysis result, the second analysis result and the third analysis result;
wherein the reply sentence is a reply of the current dialog user to the question asked by the electronic device.
In the above solution, the determining unit includes a second obtaining subunit and an accessing subunit, wherein,
the second obtaining subunit is configured to obtain a keyword included in the current topic;
the access subunit is used for accessing a third-party database and/or a self database based on the keywords to obtain an access result;
the determining subunit is configured to determine, based on the access result, a relative relationship between the electronic device and the current conversation user;
the self database is a database of the electronic equipment; the third-party database is a database which can be linked by the electronic equipment through a network.
In the foregoing solution, the determining subunit is specifically configured to: determining the relative relationship between the electronic equipment and the current conversation user as follows under the condition that the access result is that the keyword is contained in the third-party database and/or the self database: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user;
or, the determining subunit is specifically configured to: determining that the relative relationship between the electronic device and the current conversation user is: a second relationship; and the relative relationship in the second relationship is that the electronic equipment is in the second relationship, the current conversation user is guided to ask more questions, information related to the current topic is obtained, and the third-party database is accessed based on the information so as to feed back the questions of the current conversation user.
In the foregoing solution, the generating unit is specifically configured to: generating a first question statement under the condition that the judgment result is that the current conversation user is interested in the current topic and the relative relationship is that the electronic equipment is in a first relationship; the first question sentence is used for correcting the error of the current dialog user and/or providing consultation;
or, the generating unit is specifically configured to: and generating a second question sentence under the condition that the judgment result is that the current dialogue user is interested in the current topic and the relative relationship is that the electronic equipment is in a second relationship, wherein the second question sentence is used for guiding the current dialogue user to ask more questions.
In the above aspect, the conversation processing apparatus further includes a replacement unit configured to, in a case where it is determined that the current conversation user is not interested in the current topic, replace the topic, and newly determine whether the current conversation user is interested in the replaced topic; re-determining a relative relationship between the electronic device and the current conversing user based on the replaced topic; until the number of times of changing the topics which are interesting to the current conversation user is larger than a preset threshold value.
In the foregoing aspect, the dialog processing apparatus further includes: the sensing unit is used for sensing the occurrence time of the conversation in the process that the electronic equipment and the current conversation user carry out the conversation based on the current topic;
the generating unit is further used for generating a concern statement based on the occurrence time; wherein, the concern sentence contains a keyword for representing the concern of the current dialogue user.
In a third aspect, the present invention further provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method described above.
In a fourth aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method when executing the computer program.
The embodiment of the invention provides a conversation processing method, a conversation processing device, electronic equipment and a readable storage medium. The method is applied to the electronic equipment containing the conversation function, and comprises the following steps: judging whether the current conversation user is interested in the current topic or not in the process of carrying out conversation between the electronic equipment and the current conversation user based on the current topic; determining a relative relationship between the electronic device and the current conversing user based on the current topic; and generating a question sentence of the electronic equipment based on the judgment result and the relative relation, and actively asking a question to the current dialogue user based on the question sentence. The method judges the relationship between the electronic equipment with the conversation function and the user and judges whether the user is interested in the topic discussed by the electronic equipment and the user, and then actively asks questions to the user according to the two judgment results, so that the electronic equipment actively climbs the conversation to guide or master the initiative in the chat process, and creates a more active chat atmosphere, so that the user is more willing to have conversation with the electronic equipment or spend more time chatting with the electronic equipment.
Drawings
Fig. 1 is a schematic flow chart of a dialog processing method according to an embodiment of the present invention;
fig. 2A is a schematic flowchart of a dialog processing method provided by an embodiment of the present invention in a chat scenario between a chat robot and a user;
fig. 2B is a schematic flowchart of a conversation processing method provided by the embodiment of the present invention in a scene where the chat robot and the user have a definite purpose;
fig. 3 is a schematic structural diagram of a session processing apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the following describes specific technical solutions of the present invention in further detail with reference to the accompanying drawings in the embodiments of the present invention. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a schematic flowchart of a dialog processing method according to an embodiment of the present invention. As shown in fig. 1, the method is applied to an electronic device including a dialog function, and includes the following specific steps:
s101: judging whether the current conversation user is interested in the current topic or not in the process of carrying out conversation between the electronic equipment and the current conversation user based on the current topic;
s102: determining a relative relationship between the electronic device and the current conversing user based on the current topic;
s103: and generating a question sentence of the electronic equipment based on the judgment result and the relative relation, and actively asking a question to the current dialogue user based on the question sentence.
It should be noted that the conversation processing method may be started at any time during the conversation process between the electronic device and the current conversation user based on the current topic, that is, the electronic device starts to judge whether the user likes the topic and the relative relationship between the two under the topic at any time during the whole conversation process, so as to actively negotiate with the user based on the judgment result and dominate the whole conversation process.
In practical applications, the determining in S101 whether the current dialog user is interested in the current topic may include:
s1011: obtaining a dialogue sentence between the electronic equipment and a current dialogue user; the conversational sentence is associated with the current topic;
s1012: analyzing and processing the dialogue sentences to obtain an analysis result;
s1013: and judging whether the current dialog user is interested in the current topic or not based on the analysis result.
Here, said conversation sentence is associated with said current topic, that is, what is obtained is conversation content between said electronic device and said current conversation user on said current topic. It should be understood that the electronic device may retrieve the dialog statements based on the current topic from its own self database.
In some embodiments, for S1012, may include: including at least one of:
analyzing the feedback speed of the reply sentences in the dialogue sentences to obtain a first analysis result;
analyzing the words of the reply sentences in the dialogue sentences to obtain a second analysis result;
analyzing the semantics of the reply sentences in the dialogue sentences to obtain a third analysis result;
correspondingly, S1013 may include: judging whether the current dialog user is interested in the current topic based on at least one of the first analysis result, the second analysis result and the third analysis result;
wherein the reply sentence is a reply of the current dialog user to the question asked by the electronic device.
It should be noted that the feedback speed is used to indicate whether the current dialog user desires to have a dialog on the current topic, and may be measured by a time interval at which the electronic device receives a reply sentence of the current dialog user after sending a question sentence, and then, obtaining the first analysis result may be to obtain a time interval at which the electronic device receives the reply sentence of the current dialog user after sending the question sentence based on the current topic. In order to determine whether the conversation desire of the current conversation user for the current topic is urgent, in a normal case, a set time interval may be set according to experience, the acquired time interval is compared with the set time interval, and in a case that the acquired time interval is not greater than the set time interval, the conversation desire of the current conversation user for the current topic is urgent; and under the condition that the acquired time interval is greater than the set time interval, the conversation desire of the current conversation user on the current topic is not urgent.
Here, the term is used to represent an emotion or emotion of the current conversational user, and may be measured by a word representing a mood of the current conversational user in a reply sentence of the current conversational user, or a intonation of the current conversational user speaking, and the like, and then the second analysis result may be to obtain the word representing the mood or the intonation of the current conversational user in the reply sentence, for example, a mood word or an intonation of a exclamation point in the sentence replied by the current conversational user, and then the current conversational user may be less anxious at this time.
Here, the semantic meaning may be an object or a requirement expressed by a reply sentence of the current dialogue user, for example, the sentence replied by the current dialogue user includes a flight that can be quickly checked for a meeting, where the meeting flight is the meaning expressed by the dialogue sentence. Based on this, the third analysis result is the purpose or requirement expressed by the reply sentence of the current dialog user.
Based on the foregoing description, the analysis of the conversational sentence may include at least one of at least three analysis results when determining whether the current conversational user is interested in the current topic.
Specifically, when the first analysis result is adopted to judge whether the current conversation user is interested in the current topic, the time interval in the first analysis result is compared with a set time interval, whether the conversation desire of the current conversation user on the current topic is urgent or not is judged based on the comparison result, and if the conversation desire is urgent, the current conversation user is judged to be interested in the current topic; and if the current topic is not eager, judging that the current conversation user is not interested in the current topic.
Judging whether the current conversation user is interested in the current topic according to the acquired words representing the tone of the current conversation user or the tone of the current conversation user when judging whether the current conversation user is interested in the current topic by adopting a second analysis result, and judging that the current conversation user is interested in the current topic if the preset tone or tone of the current conversation user is easy and pleasant; and if the preset tone or tone of the current conversation user is impatient and impatient, judging that the current conversation user is uninterested in the current topic.
When the third analysis result is adopted to judge whether the current dialog user is interested in the current topic, the judgment can be directly carried out according to the meaning expressed by the current dialog user, and when the reply sentence of the current dialog user contains the meanings that I likes the topic and can specifically chat one chat, then the current dialog user is judged to be interested in the current topic; when the reply sentence of the current conversation user contains meanings that I does not like the topic, I wants to change the topic and the like, then the current conversation user is judged not to be interested in the current topic.
It should be noted that, it may also be determined whether the current topic is interested by the current dialog user according to the three analysis results, that is, when the current dialog user is in an urgent and pleasant state and wants to discuss further, it is determined that the current topic is interested by the current dialog user; when the current conversation user is not eagerly presented, low in mood and does not want to discuss further, it is determined that the current conversation user is interested in the current topic.
In some embodiments, for S102, may include:
s1021: acquiring keywords contained in the current topic;
s1022: accessing a third-party database and/or a self database based on the keywords to obtain an access result;
s1023: determining a relative relationship between the electronic device and the current dialog user based on the access result;
the self database is a database of the electronic equipment; the third-party database is a database which can be linked by the electronic equipment through a network.
Specifically, in the case that the access result is that the keyword is contained in the third party database and/or the self database, the S1023 may include: determining that the relative relationship between the electronic device and the current dialog user is: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user;
in the case that the access result is that the keyword is not included in the third party database and/or the self database, for S1023, the method may include: determining that the relative relationship between the electronic device and the current dialog user is: a second relationship; and the relative relationship in the second relationship is that the electronic equipment is in the second relationship, the current conversation user is guided to ask more questions, information related to the current topic is obtained, and the third-party database is accessed based on the information so as to feed back the questions of the current conversation user.
It should be noted that the keywords included in the current topic described here can be obtained by performing word segmentation and semantic recognition on the obtained conversation sentence.
In practical applications, no matter the current dialog user has a definite purpose or wants to chat, that is, no matter what scene, the relative relationship between the electronic device and the current dialog user can be roughly divided into two types: one is that the electronic device is good at the current topic, can correct the deficiency for the current dialog user, or provide consultation; the other type is that the electronic equipment is not good at the current topic, the electronic equipment guides the current dialog user to ask more questions and speak more knowledge in the current topic so as to obtain more information about the current topic, and then the third database can be accessed based on the more information to feed back the questions of the current dialog user.
In order to determine whether the electronic device is good at the current topic, a keyword contained in the current topic is used as a search engine, the third-party database and/or the self database are searched for obtaining an access result, and if the access result is that the keyword is contained in the third-party database and/or the self database, the electronic device is good at the current topic, then the relative relationship between the electronic device and the current dialog user is determined as follows: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user; in the case that the access result is that the keyword is not contained in the third-party database and/or the self database, and the electronic device is not good at the current topic, determining that the relative relationship between the electronic device and the current dialog user is: a second relationship; the relative relationship in the second relationship is that the electronic device is in the second relationship, the current dialogue user is guided to ask more questions and teach more knowledge in the current topic so as to acquire more information about the current topic, and then the third database can be accessed based on the information to feed back the question of the current dialogue user.
It should be noted that, according to the switching of different topic scenes, the relative relationship between the electronic device and the current dialog user dynamically changes. Furthermore, the relative relationship between the electronic device and the current dialog user may form an opponent, a debate, and so on, according to different division modes.
It should be noted that, in practical application, there is no strict sequence for determining the relative relationship and determining whether the current topic is interested, in other words, the foregoing S101 and S102 do not have a sequence.
After determining whether the current conversing user is interested in the current topic and determining the relative relationship between the electronic device and the current conversing user under the current topic, in some embodiments, generating the question statement of the electronic device based on the determination result and the relative relationship in S103 may include:
s1031: generating a first question statement under the condition that the judgment result is that the current conversation user is interested in the current topic and the relative relationship is that the electronic equipment is in a first relationship; the first question sentence is used for correcting the error of the current dialog user and/or providing consultation;
s1032: and generating a second question sentence under the condition that the judgment result is that the current dialogue user is interested in the current topic and the relative relationship is that the electronic equipment is in a second relationship, wherein the second question sentence is used for guiding the current dialogue user to ask more questions.
It should be noted that, two steps in S103 are substantially question sentences that can be actively provided by the electronic device to the current dialogue user when the current dialogue user is interested in the current topic, when the electronic device is good at the current topic, and when the electronic device is not good at the current topic.
Specifically, when the electronic device is good at the current topic, the electronic device provides a first question and sentence for correcting errors of the current dialog user and/or providing a consultation, for example, assuming that the current topic is the latest price of an iphone, and the electronic device can learn the prices of different regions in China through a third party database and a self database and can also acquire the prices of different countries, that is, the electronic device knows the topic very much, and the electronic device can actively provide the question and sentence for consultation to the current dialog user.
When the electronic device is not good at the current topic, the electronic device provides a second question sentence for guiding the current conversational user to ask more questions, such as the aforementioned latest price of the iphone, and the electronic device feels that the scope is too wide and not a good answer. At this time, the electronic device may pass an allegorical sentence (e.g., which area you say is the latest price of the iphone in that area
) Further, more information is known, so that accurate feedback can be given to the current conversation user, or some suggestions can be provided instead of mechanically answering unknown, unclear and other words of cold ice, so that words of cold ice can be givenThe user has a more comfortable experience.
It should be understood that the method may also include another situation:
under the condition that the current conversation user is not interested in the current topic, the topic is replaced, and whether the current conversation user is interested in the replaced topic is judged again; re-determining a relative relationship between the electronic device and the current conversing user based on the replaced topic; until the number of times of changing the topics which are interesting to the current conversation user is larger than a preset threshold value.
That is, when the currently conversing user does not like the current topic, the electronic device may change topics for the currently conversing user, which generally occurs when the currently conversing user is boring, and at this time, the electronic device may initiate an active conversation from an open personality question, such as asking places where people live, and will travel, or current hot news, or messages related to the current place, and so on, and then, according to the feedback of the currently conversing user, re-determine the relative relationship between the two and whether the currently conversing user likes the changed topics, and then actively provide corresponding services to the currently conversing user.
It should be understood that, in the practical application process, the electronic device may not infinitely change topics for the current dialog user, and therefore, the electronic device needs to stop changing after the number of times of changing reaches a preset threshold value, so as to satisfactorily remind the user that an interested topic can be provided.
In some embodiments, the method further comprises: judging the correlation degree of the current topic and the historical hotspot/conflict event; if the degree of correlation is high, after completing the conversation based on the current topic, initiating an active inquiry to the historical hotspot/conflict event, such as a belief that you are looking at the historical hotspot/conflict event, or whether you are satisfied with the processing of the historical hotspot/conflict event, etc. Then, the iteration continues to interact with the user in accordance with the user's feedback to the active query. In this way, determining how relevant a current topic is to historical hotspots/conflict events not only may the electronic device be able to somewhat extend the current topic, but converse with the current conversational user from a different perspective based on the current topic, which not only may not make the current conversational user somewhat obtrusive, but may also prefer to converse with the electronic device. For example, if the electronic device talks about the current topic of a star with the current topic of the dialog user, the electronic device may actively ask questions about historical hotspots/conflict events related to the star according to the topic of the star's octagram and historical hotspots/conflict events related to the star stored in the electronic device itself.
It should be noted that, here, the determining the degree of correlation between the current topic and the historical hotspot/conflict event may include: extracting each keyword in a dialogue sentence between the electronic equipment and the current dialogue user; the conversation sentences are sentences of the conversation between the electronic equipment and the current conversation users based on the current topics; then, the degree of correlation between the current topic and the historical hotspot/conflict event is judged according to the participle or Euclidean distance on the basis of each keyword. Wherein the historical hotspot/conflict event is data acquired by the electronic device before talking with the current conversation user, wherein the data may include but is not limited to: hot events that occurred over a period of time in the past, professional technological progress, books, movies read over a period of time in the past, and the like; the acquisition mode may include, but is not limited to: and the user terminal can talk with other users to obtain the data, or periodically connect with a third-party data platform to obtain the data, and the like.
Explaining by taking a scene, in this scene, the electronic device is a chat robot, the current topic is a certain hotcast movie, and a conversation process between a current conversation user and the chat robot is as follows:
the current dialog user: does you know XXX movies
The chat robot comprises: it is known.
The current dialog user: bother you say what the specific narration of a XXX movie is
The chat robot comprises: good, XXX movies teach … … primarily.
At this time, the chat robot knows that the current dialogue user wants to know the XXX movie and is very interested in the current topic according to the dialogue sentences provided by the current dialogue user, and at this time, the chat robot also stores information about scores of the XXX movie on a certain platform, comments of some famous film evaluators on the movie, and the like. After the chat robot finishes the complete event of the XXX movie, extracting the XXX movie keyword, and determining the degree of correlation with the historical hotspot/salient event (i.e. the rating of the XXX movie on a certain platform, the comments of some famous film evaluators on the movie), wherein the degree of correlation is relatively high, and it should be noted that the determinations are all determined by the chat robot in the background.
The chat robot actively inquires: do you want to know the rating of XXX movies on a certain platform
Alternatively, the chat robot actively asks: do you want to know the comment of the famous film rater XX on the film
And so on.
In this way, the chat robot can talk to the current conversation user from different angles based on the current topic, which not only is not obtrusive to the current conversation user, but may be more willing to talk to the electronic device.
In some embodiments, the method further comprises:
in the process that the electronic equipment and a current conversation user carry out conversation based on a current topic, sensing the occurrence time of the conversation;
generating a sentence of interest based on the occurrence time; wherein, the concern sentence contains a keyword for representing the concern of the current dialogue user.
It should be noted that, as an implementable manner, the sensing of the occurrence time of the current dialog may be performed by analyzing the dialog statement, extracting time information, and determining the occurrence time of the current dialog based on the time information.
As another practical manner, the sensing of the occurrence time of the current dialog may further obtain the current time from a time system of the electronic device when the electronic device has a dialog with a current dialog user, and use the current time as the occurrence time of the current dialog.
For example, when the electronic device senses that the occurrence time of the current conversation is late at night, the current conversation user wants to chat, and at this time, because the current conversation is late at night, the electronic device can actively negotiate with the current conversation user by using an interest sentence including keywords related to "not early, should sleep" or "should sleep early and get up early, develop good habits" and the like, so as to show the interest of the current conversation user.
According to the conversation processing method provided by the embodiment of the invention, the relation between the electronic equipment with the conversation function and the user is judged, whether the user is interested in the topic discussed by the electronic equipment and the user is judged, and then the question is actively asked to the user according to the two judgment results, so that the electronic equipment actively climbs the conversation to guide or master the initiative in the chat process, a more positive chat atmosphere is created, and the user is more willing to have a conversation with the electronic equipment or spend more time in chatting with the electronic equipment.
For understanding the embodiment of the present invention, as shown in fig. 2, it is a schematic flow chart of a dialog processing method provided by the embodiment of the present invention for a specific scenario. In fig. 2A, the application scenario includes: the specific chat flow of a certain user and a chat robot which are chatting comprises the following steps:
S201-A: the chat robot starts chatting with a user based on a topic;
S202-A: the chat robot chats with the user according to the set chat style and acquires conversation sentences between the chat robot and the user;
S203-A: at a certain moment in the chat process, the chat robot judges whether the user likes the current topic according to the conversation sentences, and determines the relative relationship between the chat robot and the user based on the topic;
S204-A: generating a first question sentence for correcting the error of the current dialogue user and/or providing consultation under the condition that the topic is interested in the user and the relative relation is a first relation; generating a second question sentence guiding the current dialogue user to question more if the topic is interested by the user and the relative relation is a second relation;
S205-A: under the condition that the topic is not interested by the user, rapidly switching the topic, and judging whether the user is interested in the replaced topic again; re-determining a relative relationship between the chat robot and the user based on the replaced topic; until the number of times of changing the topics in which the user is interested or changing the topics is greater than a preset threshold value;
S206-A: and acquiring a first reply sentence of the user corresponding to the first question sentence, and continuing interactive dialogue based on the first reply sentence until the chat is ended, or acquiring a second reply sentence of the user corresponding to the second question sentence, and continuing interactive dialogue based on the second reply sentence until the chat is ended.
It should be noted that, in this scenario, the chat robot should create topics as much as possible, and open or select questions to find the interest points of the interlocutors, and determine whether the interest points are in the domain where the chat robot is good at, to determine the relative relationship between the chat robot and the user in the topics where the two perform conversation, so as to provide corresponding services.
In fig. 2B, a user and a chat robot, both of which are chatting on a professional topic, may include:
S201-B: the chat robot and the user start chatting based on the professional topic;
S202-B: the chat robot chats with the user according to the set chat style and acquires conversation sentences between the chat robot and the user;
S203-B: at a certain moment in the chat process, the chat robot judges whether the user likes the professional topic according to the conversation sentences, and determines the relative relationship between the chat robot and the user based on the professional topic;
S204-B: generating a first question sentence for correcting the error of the user and/or providing consultation if the relative relation is a first relation and the user is interested in the professional topic; generating a second question sentence guiding the user to ask more questions if the relative relation is a second relation and the user is interested in the professional topic;
S205-B: and acquiring a first reply sentence of the user corresponding to the first question sentence, and continuing interactive dialogue based on the first reply sentence until the chat is ended, or acquiring a second reply sentence of the user corresponding to the second question sentence, and continuing interactive dialogue based on the second reply sentence until the chat is ended.
In this scenario, the chat robot determines that the chat is performed on a professional topic, which is the topic that the user wants to know, in other words, when performing professional topic chat, the user generally has a relatively clear purpose, and the professional should be one of the key points. The keywords contained in the topics are contained in the third-party database and/or the self database, and the database formed by the third-party database and the self database is rich enough, so that the chat robot can judge that the chat robot is more professional when the chat robot is used for the purpose of conversation, the chat robot can optionally play the role of an expert, the defects of the user are corrected, or the consultation is provided. The keywords contained in the topic are not contained in the third-party database and/or the self-database, so that the response of the user feedback under the topic is usually super-outline to the chat robot, or the data information of the related destination in the local database of the chat robot is less, so that the chat robot needs to be used as a weaker listener or learner to guide the user to speak and teach more and acquire more information so as to dynamically query the data to interactively feed back by means of online access to the third-party database.
Based on the same inventive concept, an embodiment of the present invention further provides a dialog processing apparatus as shown in fig. 3. In fig. 3, the dialog processing device 30 is applied to an electronic device with a dialog function, and specifically includes a judging unit 301, a determining unit 302, a generating unit 303, and a questioning unit 304, wherein,
the judging unit is used for judging whether the current conversation user is interested in the current topic or not in the process that the electronic equipment and the current conversation user have a conversation based on the current topic;
the determining unit is used for determining the relative relationship between the electronic equipment and the current conversation user based on the current topic;
the generating unit is used for generating question sentences of the electronic equipment based on the judgment result and the relative relation;
and the question asking unit is used for actively asking questions of the current dialogue user based on the question sentences.
In some embodiments, the determining unit includes a first acquiring subunit, an analyzing subunit, and a determining subunit, wherein,
the first obtaining subunit is configured to obtain a dialog statement between the electronic device and a current dialog user; the conversational sentence is associated with the current topic;
the analysis subunit is configured to perform analysis processing on the dialog statement to obtain an analysis result;
and the judging subunit is used for judging whether the current conversation user is interested in the current topic or not based on the analysis result.
In some embodiments, the analysis subunit is specifically configured to: including at least one of:
analyzing the feedback speed of the reply sentences in the dialogue sentences to obtain a first analysis result;
analyzing the words of the reply sentences in the dialogue sentences to obtain a second analysis result;
analyzing the semantics of the reply sentences in the dialogue sentences to obtain a third analysis result;
the judging subunit is specifically configured to: judging whether the current dialog user is interested in the current topic based on at least one of the first analysis result, the second analysis result and the third analysis result;
wherein the reply sentence is a reply of the current dialog user to the question asked by the electronic device.
In some embodiments, the determining unit comprises a second acquiring subunit and an accessing subunit, wherein,
the second obtaining subunit is configured to obtain a keyword included in the current topic;
the access subunit is used for accessing a third-party database and/or a self database based on the keywords to obtain an access result;
the determining subunit is configured to determine, based on the access result, a relative relationship between the electronic device and the current conversation user;
the self database is a database of the electronic equipment; the third-party database is a database which can be linked by the electronic equipment through a network.
In some embodiments, the determining subunit is specifically configured to: determining the relative relationship between the electronic equipment and the current conversation user as follows under the condition that the access result is that the keyword is contained in the third-party database and/or the self database: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user;
or, the determining subunit is specifically configured to: determining that the relative relationship between the electronic device and the current conversation user is: a second relationship; and the relative relationship in the second relationship is that the electronic equipment is in the second relationship, the current conversation user is guided to ask more questions, information related to the current topic is obtained, and the third-party database is accessed based on the information so as to feed back the questions of the current conversation user.
In some embodiments, the generating unit is specifically configured to: generating a first question statement under the condition that the judgment result is that the current conversation user is interested in the current topic and the relative relationship is that the electronic equipment is in a first relationship; the first question sentence is used for correcting the error of the current dialog user and/or providing consultation;
or, the generating unit is specifically configured to: and generating a second question sentence under the condition that the judgment result is that the current dialogue user is interested in the current topic and the relative relationship is that the electronic equipment is in a second relationship, wherein the second question sentence is used for guiding the current dialogue user to ask more questions.
In some embodiments, the conversation processing apparatus further includes a replacement unit configured to, in a case where it is determined that the current conversation user is not interested in the current topic, replace the topic, and newly determine whether the current conversation user is interested in the replaced topic; re-determining a relative relationship between the electronic device and the current conversing user based on the replaced topic; until the number of times of changing the topics which are interesting to the current conversation user is larger than a preset threshold value.
In some embodiments, the dialog processing device further comprises: the sensing unit is used for sensing the occurrence time of the conversation in the process that the electronic equipment and the current conversation user carry out the conversation based on the current topic; the generating unit is further used for generating a concern statement based on the occurrence time; wherein, the concern sentence contains a keyword for representing the concern of the current dialogue user.
The dialog processing device provided by the embodiment of the invention is based on the same inventive concept as the dialog processing method, and the terms appearing here are clearly described in the method, and are not described again here.
Embodiments of the present invention further provide a readable storage medium, on which a computer program is stored, where the computer program processor implements the steps of the foregoing method embodiments when executed by a processor, and the foregoing storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. The readable storage medium is a computer readable storage medium.
An embodiment of the present invention further provides an electronic device, where the electronic device includes: a processor and a memory for storing a computer program capable of running on the processor, wherein the processor is configured to execute the steps of the above-described method embodiments stored in the memory when running the computer program.
Fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention, where the electronic device 40 includes: the at least one processor 401, the memory 402, and optionally the electronic device 40 may further include at least one communication interface 403, and the various components in the electronic device 40 are coupled together by a bus system 404, it being understood that the bus system 404 is used to implement connection communication between these components. The bus system 404 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 404 in FIG. 4.
It will be appreciated that the memory 402 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. Among them, the nonvolatile Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a magnetic Random access Memory (FRAM), a magnetic Random access Memory (Flash Memory), a magnetic surface Memory, an optical disk, or a Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced DRAM), Synchronous Dynamic Random Access Memory (SLDRAM), Direct Memory (DRmb Access), and Random Access Memory (DRAM). The memory 402 described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The memory 402 in embodiments of the present invention is used to store various types of data to support the operation of the electronic device 40. Examples of such data include: any computer program for operating on the electronic device 40, such as an implementation of determining a decision pattern matching the first bit based on the forward decision result and the backward decision result, etc., may be embodied in the memory 402 for implementing a method according to an embodiment of the present invention.
The method disclosed in the above embodiments of the present invention may be applied to the processor 401, or implemented by the processor 401. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The processor may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium having a memory and a processor reading the information in the memory and combining the hardware to perform the steps of the method.
In an exemplary embodiment, the electronic Device 40 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, Micro Controllers (MCUs), microprocessors (microprocessors), or other electronic components for performing the above-described methods.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A dialog processing method applied to an electronic device including a dialog function, the method comprising:
judging whether the current conversation user is interested in the current topic or not in the process of carrying out conversation between the electronic equipment and the current conversation user based on the current topic;
determining a relative relationship between the electronic device and the current conversing user based on the current topic;
and generating a question sentence of the electronic equipment based on the judgment result and the relative relation, and actively asking a question to the current dialogue user based on the question sentence.
2. The method of claim 1, wherein said determining whether the currently conversing user is interested in a current topic comprises:
obtaining a dialogue sentence between the electronic equipment and a current dialogue user; the conversational sentence is associated with the current topic;
analyzing and processing the dialogue sentences to obtain an analysis result;
judging whether the current dialog user is interested in the current topic based on the analysis result;
wherein, the analyzing the dialogue statement to obtain an analysis result includes at least one of the following:
analyzing the feedback speed of the reply sentences in the dialogue sentences to obtain a first analysis result;
analyzing the words of the reply sentences in the dialogue sentences to obtain a second analysis result;
analyzing the semantics of the reply sentences in the dialogue sentences to obtain a third analysis result;
correspondingly, the determining whether the current dialog user is interested in the current topic based on the analysis result includes: judging whether the current dialog user is interested in the current topic based on at least one of the first analysis result, the second analysis result and the third analysis result; wherein the reply sentence is a reply of the current dialog user to the question asked by the electronic device.
3. The method of claim 2, wherein the determining a relative relationship between the electronic device and the current conversing user based on the current topic comprises:
acquiring keywords contained in the current topic;
accessing a third-party database and/or a self database based on the keywords to obtain an access result;
determining a relative relationship between the electronic device and the current dialog user based on the access result;
the self database is a database of the electronic equipment; the third-party database is a database which can be linked by the electronic equipment through a network.
4. The method according to claim 3, wherein in the case that the access result is that the keyword is contained in the third-party database and/or the self database, the determining the relative relationship between the electronic device and the current conversation user based on the access result comprises: determining that the relative relationship between the electronic device and the current dialog user is: a first relationship; in the first relation, the electronic equipment is in an expert role and corrects errors and/or provides consultation for the current conversation user;
in a case that the access result is that the keyword is not contained in the third-party database and/or the self-database, the determining, based on the access result, a relative relationship between the electronic device and the current conversation user includes: determining that the relative relationship between the electronic device and the current dialog user is: a second relationship; and the relative relationship in the second relationship is that the electronic equipment is in the second relationship, the current conversation user is guided to ask more questions, information related to the current topic is obtained, and the third-party database is accessed based on the information so as to feed back the questions of the current conversation user.
5. The method of claim 4, wherein generating the question statement for the electronic device based on the determination result and the relative relationship comprises:
generating a first question statement under the condition that the judgment result is that the current conversation user is interested in the current topic and the relative relationship is that the electronic equipment is in a first relationship; the first question sentence is used for correcting the error of the current dialog user and/or providing consultation;
and generating a second question sentence under the condition that the judgment result is that the current dialogue user is interested in the current topic and the relative relationship is that the electronic equipment is in a second relationship, wherein the second question sentence is used for guiding the current dialogue user to ask more questions.
6. The method of claim 1, further comprising:
under the condition that the current conversation user is not interested in the current topic, the topic is replaced, and whether the current conversation user is interested in the replaced topic is judged again; re-determining a relative relationship between the electronic device and the current conversing user based on the replaced topic; until the number of times of changing the topics which are interesting to the current conversation user is larger than a preset threshold value.
7. The method of claim 1, further comprising:
in the process that the electronic equipment and a current conversation user carry out conversation based on a current topic, sensing the occurrence time of the conversation;
generating a sentence of interest based on the occurrence time; wherein, the concern sentence contains a keyword for representing the concern of the current dialogue user.
8. A dialogue processing apparatus applied to an electronic device including a dialogue function, the dialogue processing apparatus including a judgment unit, a determination unit, a generation unit, and a question unit,
the judging unit is used for judging whether the current conversation user is interested in the current topic or not in the process that the electronic equipment and the current conversation user have a conversation based on the current topic;
the determining unit is used for determining the relative relationship between the electronic equipment and the current conversation user based on the current topic;
the generating unit is used for generating question sentences of the electronic equipment based on the judgment result and the relative relation;
and the question asking unit is used for actively asking questions of the current dialogue user based on the question sentences.
9. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
10. An electronic device, characterized in that the electronic device comprises: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of any of claims 1 to 7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110479880.5A CN112989014A (en) | 2021-04-30 | 2021-04-30 | Dialogue processing method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110479880.5A CN112989014A (en) | 2021-04-30 | 2021-04-30 | Dialogue processing method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112989014A true CN112989014A (en) | 2021-06-18 |
Family
ID=76336869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110479880.5A Pending CN112989014A (en) | 2021-04-30 | 2021-04-30 | Dialogue processing method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112989014A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113535920A (en) * | 2021-07-19 | 2021-10-22 | 安徽淘云科技股份有限公司 | Guiding learning method, guiding learning robot, storage medium, and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150356142A1 (en) * | 2014-06-06 | 2015-12-10 | Xerox Corporation | Question answering system adapted to style of user requests |
| CN106354815A (en) * | 2016-08-30 | 2017-01-25 | 北京光年无限科技有限公司 | Topic processing method for conversational system |
| CN107977415A (en) * | 2017-11-22 | 2018-05-01 | 北京寻领科技有限公司 | Automatic question-answering method and device |
| CN108073600A (en) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of intelligent answer exchange method, device and electronic equipment |
| CN109885810A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium based on semanteme parsing |
-
2021
- 2021-04-30 CN CN202110479880.5A patent/CN112989014A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150356142A1 (en) * | 2014-06-06 | 2015-12-10 | Xerox Corporation | Question answering system adapted to style of user requests |
| CN106354815A (en) * | 2016-08-30 | 2017-01-25 | 北京光年无限科技有限公司 | Topic processing method for conversational system |
| CN108073600A (en) * | 2016-11-11 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of intelligent answer exchange method, device and electronic equipment |
| CN107977415A (en) * | 2017-11-22 | 2018-05-01 | 北京寻领科技有限公司 | Automatic question-answering method and device |
| CN109885810A (en) * | 2019-01-17 | 2019-06-14 | 平安城市建设科技(深圳)有限公司 | Nan-machine interrogation's method, apparatus, equipment and storage medium based on semanteme parsing |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113535920A (en) * | 2021-07-19 | 2021-10-22 | 安徽淘云科技股份有限公司 | Guiding learning method, guiding learning robot, storage medium, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536802B (en) | Interaction method and device based on child emotion | |
| CN110288985B (en) | Voice data processing method and device, electronic equipment and storage medium | |
| KR102580322B1 (en) | Automated assistants with conference capabilities | |
| Doyle et al. | Mapping perceptions of humanness in intelligent personal assistant interaction | |
| CN107943998B (en) | Man-machine conversation control system and method based on knowledge graph | |
| JP6704525B2 (en) | Facilitate the generation and playback of voice recorded by users | |
| US8374859B2 (en) | Automatic answering device, automatic answering system, conversation scenario editing device, conversation server, and automatic answering method | |
| US11314944B2 (en) | Transitioning between prior dialog contexts with automated assistants | |
| US9380017B2 (en) | Human assisted chat information system | |
| US20100049513A1 (en) | Automatic conversation system and conversation scenario editing device | |
| JP7300435B2 (en) | Methods, apparatus, electronics, and computer-readable storage media for voice interaction | |
| Fang et al. | Sounding board–university of washington’s alexa prize submission | |
| Baron | Shall we talk? Conversing with humans and robots | |
| CN113468894B (en) | Dialogue interaction method and device, electronic equipment and computer readable storage medium | |
| US10770068B2 (en) | Dialog agent, reply sentence generation method, and non-transitory computer-readable recording medium | |
| CN117253478A (en) | Voice interaction method and related device | |
| CN112989014A (en) | Dialogue processing method and device, electronic equipment and readable storage medium | |
| Inaba et al. | Collection and analysis of travel agency task dialogues with age-diverse speakers | |
| Ward et al. | Using dialog-activity similarity for spoken information retrieval. | |
| Ghosh | “Can You Search for Me?”: Understanding and Improving User‐System Dialogues for Complex Search Tasks | |
| CN110136719B (en) | Method, device and system for realizing intelligent voice conversation | |
| CN112989012B (en) | Information updating method and device, electronic equipment and readable storage medium | |
| CN111161706A (en) | Interaction method, device, equipment and system | |
| Wang et al. | Understanding differences between human language processing and natural language processing by the synchronized model | |
| JP7368335B2 (en) | Programs, devices and methods for interacting with positive parroting responses |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |