CN111612482A - Conversation management method, device and equipment - Google Patents
Conversation management method, device and equipment Download PDFInfo
- Publication number
- CN111612482A CN111612482A CN202010444389.4A CN202010444389A CN111612482A CN 111612482 A CN111612482 A CN 111612482A CN 202010444389 A CN202010444389 A CN 202010444389A CN 111612482 A CN111612482 A CN 111612482A
- Authority
- CN
- China
- Prior art keywords
- information
- current
- previous
- node
- conversation
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 107
- 230000008569 process Effects 0.000 claims abstract description 90
- 230000004044 response Effects 0.000 claims abstract description 28
- 230000001419 dependent effect Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides a conversation management method, a device and equipment, wherein the method comprises the following steps: analyzing the received current conversation information to obtain current intention understanding information of the current conversation information, and determining current slot position information of the current intention understanding information; determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node; generating response information corresponding to the target intention node based on a preset information generation rule of the target intention node; and outputting response information corresponding to the target intention node. According to the technical scheme, the target intention node is dynamically determined in the process of the conversation between the user and the intelligent customer service system, so that node skipping is performed according to the input information of the user in the process of the conversation between the user and the intelligent customer service system, and the efficiency of human-computer interaction is improved and lower.
Description
Technical Field
The invention relates to the technical field of intelligent customer service, in particular to a conversation management method, a conversation management device and conversation management equipment.
Background
In the intelligent customer service system, after a user inputs dialogue information such as natural sentences, pictures and the like, the automatic response of the intelligent customer service system is obtained immediately. The Dialog Management (DM) controls the process of man-machine Dialog in the intelligent customer service system, and the DM determines the reaction to the user at this moment according to the Dialog history information, which is the core part in the artificial intelligent Dialog.
In the prior art, the dialogue management belongs to a semantic Understanding (NUL) service, and after the NUL service obtains a dialogue intention of a user, a dialogue flow is sequentially executed according to a preset intention node corresponding to the dialogue intention, that is, in a dialogue process between the user and an intelligent customer service system, the dialogue management can only guide the user to input corresponding input information step by step according to the preset intention node, so that the human-computer interaction efficiency is low.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method, an apparatus and a device for session management, so as to solve the problem of low human-computer interaction efficiency in the prior art.
Based on the above object, the present invention provides a dialog management method, including:
analyzing the received current conversation information to obtain current intention understanding information of the current conversation information, and determining current slot position information of the current intention understanding information;
determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node;
generating response information corresponding to the target intention node based on a preset information generation rule of the target intention node;
and outputting response information corresponding to the target intention node.
Further, in the above-mentioned dialog management method, before analyzing the received current dialog information to obtain current intention understanding information of the current dialog information and determining slot position information of the current intention understanding information, the method further includes:
responding to user configuration operation, and respectively configuring an intention understanding process and a conversation management process;
the intention understanding process is used for sending the current intention understanding information and the slot position information to the conversation management process after obtaining the current intention understanding information and the slot position information;
and the conversation management process is used for carrying out conversation management according to the slot position information.
Further, in the above dialog management method, determining slot information of the current intention understanding information includes:
and determining the slot position information according to the existing conversation content of the user and the current conversation information.
Further, the above-mentioned dialog management method further includes:
judging whether the current intention understanding information is the same as the previous intention understanding information;
if the current intention understanding information is different from the previous intention understanding information, switching to a current conversation process corresponding to the current intention understanding information, and pausing the previous conversation process corresponding to the previous intention understanding information;
and returning to the last conversation process when the current conversation process is detected to be finished.
Further, in the dialog management method described above, the switching to the current dialog flow corresponding to the current intention understanding information and pausing the previous dialog flow corresponding to the previous intention understanding information includes:
respectively and sequentially stacking the previous dialogue node corresponding to the previous dialogue process and the current dialogue node corresponding to the current dialogue process;
wherein, the stacking sequence of the last dialogue node is the stacking sequence of the current dialogue node;
the pop sequence of the last dialog node is the pop sequence of the current dialog node.
Further, the above-mentioned dialog management method further includes:
and if the fact that the dependent conversation node contained in the current conversation process exists in the stack is detected, carrying out invalidation processing on the dependent conversation node, so that the dependent conversation node does not output response information corresponding to the dependent conversation node when the dependent conversation node meets the pop condition.
Further, in the above dialog management method, before switching to a current dialog flow corresponding to the current intention understanding information and pausing a previous dialog flow corresponding to the previous intention understanding information, the method further includes:
judging whether the current identity information corresponding to the current dialogue information is matched with the previous identity information corresponding to the previous dialogue input information;
correspondingly, the switching to the current conversation process corresponding to the current intention understanding information and pausing the previous conversation process corresponding to the previous intention understanding information includes:
and if the current identity information is matched with the previous identity information, switching to a current conversation process corresponding to the current intention understanding information, and pausing a previous conversation process corresponding to the previous intention understanding information.
Further, in the above dialog management method, the current dialog information and the previous dialog input information are both voice;
the determining whether the current identity information corresponding to the current dialog information matches the previous identity information corresponding to the previous dialog input information includes:
respectively determining current characteristic information corresponding to the current voice and previous characteristic information corresponding to the previous voice;
judging whether the current characteristic information is matched with the previous characteristic information;
if the current characteristic information is matched with the previous characteristic information, determining that the current identity information is matched with the previous identity information;
and if the current characteristic information is not matched with the previous characteristic information, determining that the current identity information is not matched with the previous identity information.
The present invention also provides a session management apparatus, comprising:
the analysis module is used for analyzing the received current conversation information to obtain current intention understanding information of the current conversation information and determining current slot position information of the current intention understanding information;
the determining module is used for determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node;
the generating module is used for generating response information corresponding to the target intention node based on a preset information generating rule of the target intention node;
and the output module is used for outputting the response information corresponding to the target intention node.
The invention also provides a dialog management device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method as claimed in any one of the above when executing the program.
As can be seen from the above, the dialog management method, apparatus, and device provided by the present invention analyze the received current dialog information to obtain the current intention understanding information of the current dialog information and the current slot position information of the current intention understanding information; and determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node, dynamically determining the target intention node in the conversation process of the user and the intelligent customer service system, generating and outputting response information corresponding to the target intention node based on the information generation rule of the preset target intention node, further realizing node skip according to the input information of the user in the conversation process of the user and the intelligent customer service system, and improving the low efficiency of human-computer interaction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a session management method embodiment of the present invention;
FIG. 2 is a schematic diagram of a session flow switching between different intention nodes;
FIG. 3 is another schematic diagram of a session flow switching between different intent nodes;
FIG. 4 is a schematic structural diagram of a session management apparatus according to a first embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a second session management apparatus according to a second embodiment of the present invention;
fig. 6 is a schematic structural diagram of an embodiment of a session management device of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It is to be noted that technical terms or scientific terms used in the embodiments of the present invention should have the ordinary meanings as understood by those having ordinary skill in the art to which the present disclosure belongs, unless otherwise defined. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
Fig. 1 is a flowchart of an embodiment of a session management method of the present invention, and as shown in fig. 1, the session management method of this embodiment may specifically include the following steps:
100. analyzing the received current conversation information to obtain current intention understanding information of the current conversation information, and determining current slot position information of the current intention understanding information;
in a specific implementation process, current dialogue information input by a user can be received, the current dialogue information input by the user is analyzed, current intention understanding information of the current dialogue information is obtained, and current slot position information of the current intention understanding information is determined. For example, the current dialog information input by the user may include speech, user-recognized text, touch events, graphical images, and the like.
Specifically, the current dialog information of the user may be converted into recognizable characters, then, the NLU model is used to perform semantic analysis, and finally, the current intention understanding information of the current dialog information is obtained, and keywords are extracted from the converted recognizable characters, so that the current slot position information of the current intention understanding information is obtained.
For example, the current dialogue information of the user may be "how much weather is available in tomorrow", "look up weather in tomorrow in beijing", and the like. At this time, the current intention understanding information may be analyzed as "query weather", and the slot corresponding to the query weather is "date" or "place". And extracting key data from the specific content of the current session information so as to obtain current slot position information of the current intention understanding information. For example, if the current session information of the user is "how much the weather is tomorrow", the extracted key data is "tomorrow", the slot position information corresponding to the slot position of the "date" that the user intends to understand the information is "tomorrow", and the slot position information corresponding to the slot position of the "place" is empty. If the current conversation information is 'looking up the weather of Beijing tomorrow', the extracted key data are 'Beijing' and 'tomorrow', the slot position information corresponding to the slot position of 'time' and 'place' of the current intention understanding information can be obtained as 'tomorrow', and the slot position information corresponding to the slot position of 'place' is 'Beijing'.
For another example, the user inputs "get up 10 tomorrow", "set 10 alarm clock", and the like, and at this time, the current intention understanding information may be analyzed as "set alarm clock", and the slot corresponding to the alarm clock may be set as "date", "time", "event", and the like. If the user inputs '10 o' clock getting up in tomorrow 'to know, the slot position information of' date 'is' tomorrow ', the' time 'is' 10 o 'clock', and the 'event' is 'getting up'. The user inputs 'an alarm clock with 10 points', 'slot information of date' is empty, 'time' is '10 points' and 'event' is empty.
In addition, in this embodiment, in order to improve the accuracy of the slot position information, the slot position information may be determined according to the existing session content and the current session information of the user. For example, the user has already completed the air ticket ordering process and subsequently enters the weather checking process, and although the address in the current session information is null, the address can be acquired according to the destination of the user in the air ticket ordering process, so that the address can be directly added.
101. Determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node;
in a specific implementation process, in a process of a conversation between a user and an intelligent customer service system, the user can obtain information desired by the user as soon as possible, or the intelligent customer service system can obtain information of the user and the like quickly, if the user and the intelligent customer service system perform the conversation, corresponding input information can be input step by step only according to guidance of conversation management, and therefore human-computer interaction efficiency is low.
For example, the user may input dialog information including key data of time, location, and the like, so as to quickly acquire the weather of the location at the time, but the user may only input the time, and thus, the intelligent customer service system needs to perform next guidance and query on the user to determine the location that the user needs to query, so that it is inefficient for the user to obtain the information that the user wants.
For another example, in order to prevent people from contacting with each other during an epidemic situation, a conversation can be performed between people by using an intelligent customer service system, so that the entrance and exit detection of a user can be realized. If the user is in a conversation process with the intelligent customer service system, if the intelligent customer service system can already obtain the information required by the user according to the historical conversation information and the current conversation information, but the current conversation information is not the content required for finishing the conversation process, the intelligent customer service system still needs to execute the subsequent intention node, and therefore the efficiency of obtaining the information of the user by the intelligent customer service system is low.
Therefore, in order to solve the above technical problem, in this embodiment, a skip condition of each intention node may be set in advance according to different slot position information, so that the slot position information and the intention node may be associated to obtain an association relationship between the slot position information and the intention node, and after determining the current slot position information of the current intention understanding information, a target intention node corresponding to the current slot position information may be determined according to a preset association relationship between the slot position information and the intention node. For example: in the weather checking process, when the user does not speak the date, the target intention node can be determined as the automatic addition node. In the process of setting the alarm clock, if the alarm clock setting time is earlier than the current time, the target intention node is determined to be an abnormal processing node.
102. Generating response information corresponding to a target intention node based on a preset information generation rule of the target intention node;
specifically, in this embodiment, a corresponding information generation rule may be set for each intention node, so that after a target intention node corresponding to the current slot position information is determined, response information corresponding to the target intention node may be generated based on a preset information generation rule of the target intention node.
For example, if the current slot information includes all the required information and does not belong to the constraint of the target intended node, the response information including all the required information may be directly generated.
If the current slot position information contains part of required information and does not belong to the constraint condition of the target intention node, other required information can be automatically added, and response information containing all the required information is generated so as to be convenient for a user to confirm. For example, in the weather checking process, when the user does not speak the date, the date of the day may be defaulted for active addition, or the date at which the user may arrive at a certain place is obtained from a third-party database, and the date at which the user may arrive at the certain place is actively added.
If the current slot position information contains part or all of the required information but belongs to the constraint condition of the target intention node, in the process of setting the alarm clock, if the set time of the alarm clock is earlier than the current time, the method can skip to an exception handling node and output exception prompt information such as setting errors. For example, in an epidemic situation detection process, if the body temperature of the user reaches a preset temperature, the user can jump to an exception handling node to alarm.
103. And outputting response information corresponding to the target intention node.
After generating the response information corresponding to the target intention node, the response information corresponding to the target intention node may be output.
In the dialog management method of this embodiment, the current intention understanding information of the current dialog information and the current slot position information of the current intention understanding information are obtained by analyzing the received current dialog information; and determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node, dynamically determining the target intention node in the conversation process of the user and the intelligent customer service system, generating and outputting response information corresponding to the target intention node based on the information generation rule of the preset target intention node, further realizing node skip according to the input information of the user in the conversation process of the user and the intelligent customer service system, and improving the low efficiency of human-computer interaction.
In a specific implementation process, before analyzing received current conversation information to obtain current intention understanding information of the current conversation information and determining slot position information of the current intention understanding information, an intention understanding process and a conversation management process can be respectively configured in response to user configuration operation, so that the intention understanding process and the conversation management process are decoupled and separated; therefore, the current intention understanding information and the slot position information are obtained only by the intention understanding process and then are sent to the conversation management process, and then the conversation management process carries out conversation management according to the slot position information.
In practical application, since a user may suddenly think of a certain event when performing a certain conversation process, and the user needs to switch to another conversation process, in the prior art, the user must enter another conversation process only when the user finishes executing the current conversation process or the user actively says to exit, and when the user finishes another conversation process and wants to do the previous conversation process, the user must start to do from the beginning, so that the interaction is relatively inflexible, and the user experience is relatively poor.
In this embodiment, after obtaining the current intention understanding information of the current dialog information, it may be determined whether the current intention understanding information is the same as the previous intention understanding information, and if the current intention understanding information is not the same as the previous intention understanding information, switch to the current dialog flow corresponding to the current intention understanding information, and pause the previous dialog flow corresponding to the previous intention understanding information; and returning to the last conversation process when the current conversation process is detected to be finished.
In practical application, based on the stack principle, the current dialog flow corresponding to the current intention understanding information may be switched to, and the previous dialog flow corresponding to the previous intention understanding information may be paused. Specifically, a previous dialogue node corresponding to a previous dialogue process and a current dialogue node corresponding to a current dialogue process are sequentially subjected to stacking processing and unstacking processing; wherein, the stacking sequence of the previous dialogue node is the stacking sequence of the current dialogue node; the pop sequence of the last dialog node is the pop sequence of the current dialog node.
For example, fig. 2 is a schematic diagram illustrating switching of conversation flows of different intention nodes, as shown in fig. 2, when a user has a conversation with an intelligent customer service system to an intention node a2, the user suddenly jumps to the flow of the intention B, the intention node a2 may be put on the stack, and then each required intention node of the intention B may be put on the stack, such as the intention node B2 of fig. 3, so that the intention node B2 is located above the intention node a2, the pop sequence of the intention node B2 takes precedence over the intention node a2, so that the user may switch to the flow corresponding to the intention B, and after the flow of the intention B is finished, the intention node a2 is at the top of the stack, and at this time, the intention node a2 may be put on the stack, so that the intention a may temporarily stop the conversation, and after the intention B is finished, the conversation flow of the intention a may be resumed.
In addition, although the user switches the session flow, the user may switch the original session flow when performing another session flow, so in this embodiment, if it is detected that the dependent session node included in the current session flow already exists in the stack, the dependent session node is invalidated, so that the dependent session node does not output the response information corresponding to the dependent session node when the pop condition is satisfied.
For example, fig. 3 is another schematic diagram illustrating switching of the session flows of different intention nodes, for example, after the user switches from the intention a to the intention B, the intention B executes a part of the session, and then the user switches back to the intention a, so that in order to avoid repeatedly executing the session flow of the intention a because the session flow of the intention a is in a suspended state, in this embodiment, the intention node a may be invalidated, and when the intention node a is located at the top of the stack, the subsequent session flow of the intention a may not be executed any more.
In this embodiment, when the user switches to the intention a again, the dialog flow corresponding to the existing intention a may be output, and the dialog flow corresponding to the intention a is restarted, or the dialog flow corresponding to the existing intention a is directly performed according to the existing dialog flow, so as to prevent the user from repeatedly executing the dialog flow corresponding to the intention a because the user forgets to perform the dialog flow corresponding to the intention a before, and further ensure efficient service.
In practical application, a user may be interfered with some interference during a conversation process with the intelligent customer service system, so that the front intention understanding information and the rear intention understanding information are inconsistent, and a conversation process is switched.
Specifically, before switching to the current dialogue process corresponding to the current intention understanding information and pausing the previous dialogue process corresponding to the previous intention understanding information, it may be further determined whether the current identity information corresponding to the current dialogue information matches the previous identity information corresponding to the previous dialogue input information. In this way, if the current identity information is matched with the previous identity information, the current conversation process corresponding to the current intention understanding information is switched to, and the previous conversation process corresponding to the previous intention understanding information is suspended, otherwise, if the current identity information is not matched with the previous identity information, the original conversation process is maintained.
In practical application, the current dialog information and the previous dialog input information are both voice, so that whether the current identity information corresponding to the current dialog information is matched with the previous identity information corresponding to the previous dialog input information is judged, and the method can be executed according to the following operations:
respectively determining current characteristic information corresponding to the current voice and previous characteristic information corresponding to the previous voice; judging whether the current characteristic information is matched with the previous characteristic information; if the current characteristic information is matched with the previous characteristic information, determining that the current identity information is matched with the previous identity information; and if the current characteristic information is not matched with the previous characteristic information, determining that the current identity information is not matched with the previous identity information.
Specifically, the current characteristic information includes a current sound source position and a voiceprint of the current sound source, and the previous characteristic information includes a previous sound source position and a voiceprint of the previous sound source, so that if the current sound source position matches the previous sound source position and the voiceprint of the current sound source matches the voiceprint of the previous sound source, it is indicated that the current identity information matches the previous identity information. Otherwise, if the current sound source position is not matched with the previous sound source position and/or the voiceprint of the current sound source is not matched with the voiceprint of the previous sound source, it is indicated that the current identity information is not matched with the previous identity information.
It should be noted that the method of the embodiment of the present invention may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In the case of such a distributed scenario, one device of the multiple devices may only perform one or more steps of the method according to the embodiment of the present invention, and the multiple devices interact with each other to complete the method.
Fig. 4 is a schematic structural diagram of a first embodiment of a session management device of the present invention, and as shown in fig. 4, the passing device of the present embodiment includes an analyzing module 40, a determining module 41, a generating module 42, and an output module 43.
The analysis module 40 is configured to analyze the received current session information to obtain current intention understanding information of the current session information, and determine current slot position information of the current intention understanding information;
for example, the slot information may be determined according to the existing session content of the user and the current session information.
A determining module 41, configured to determine a target intended node corresponding to current slot information according to a preset association relationship between the slot information and the intended node;
a generating module 42, configured to generate response information corresponding to the target intention node based on a preset information generating rule of the target intention node;
and an output module 43, configured to output response information corresponding to the target intention node.
The dialog management device of this embodiment obtains current intention understanding information of current dialog information and current slot position information of the current intention understanding information by analyzing the received current dialog information; and determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node, dynamically determining the target intention node in the conversation process of the user and the intelligent customer service system, generating and outputting response information corresponding to the target intention node based on the information generation rule of the preset target intention node, further realizing node skip according to the input information of the user in the conversation process of the user and the intelligent customer service system, and improving the low efficiency of human-computer interaction.
Fig. 5 is a schematic structural diagram of a second session management apparatus according to an embodiment of the present invention, and as shown in fig. 5, the session management apparatus of this embodiment may further include a configuration module 44 on the basis of the above embodiment:
a configuration module 44, configured to respond to a user configuration operation, and respectively configure an intention understanding process and a dialogue management process; the intention understanding process is used for obtaining current intention understanding information and slot position information and then sending the current intention understanding information and the slot position information to the conversation management process; and the conversation management flow is used for carrying out conversation management according to the slot position information.
Further, as shown in fig. 5, the dialog management device of this embodiment may further include a judging module 45 and a switching module 46.
A judging module 45, configured to judge whether the current intention understanding information is the same as the previous intention understanding information;
a switching module 46, configured to switch to a current conversation process corresponding to the current intention understanding information and pause a previous conversation process corresponding to the previous intention understanding information if the current intention understanding information is different from the previous intention understanding information; and returning to the last conversation process when the current conversation process is detected to be finished.
Specifically, the previous dialog node corresponding to the previous dialog flow and the current dialog node corresponding to the current dialog flow may be sequentially subjected to stacking processing and popping processing; wherein, the stacking sequence of the last dialogue node is the stacking sequence of the current dialogue node; the pop sequence of the last dialog node is the pop sequence of the current dialog node.
Further, the switching module 46 is further configured to, if it is detected that a dependent session node included in the current session flow exists in the stack, perform invalidation processing on the dependent session node, so that the dependent session node does not output response information corresponding to the dependent session node any more when the dependent session node meets the pop condition.
Further, in the above embodiment, the determining module 45 is further configured to determine whether the current identity information corresponding to the current dialog information matches with the previous identity information corresponding to the previous dialog input information;
correspondingly, if the current identity information is matched with the previous identity information, switching to the current conversation process corresponding to the current intention understanding information, and pausing the previous conversation process corresponding to the previous intention understanding information.
In the embodiment, the current dialogue information and the last dialogue input information are preferably voice;
the judging module 45 is further configured to determine current feature information corresponding to the current voice and previous feature information corresponding to the previous voice respectively; judging whether the current characteristic information is matched with the previous characteristic information; if the current characteristic information is matched with the previous characteristic information, determining that the current identity information is matched with the previous identity information; and if the current characteristic information is not matched with the previous characteristic information, determining that the current identity information is not matched with the previous identity information.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Fig. 6 is a schematic structural diagram of an embodiment of a session management device of the present invention, and as shown in fig. 6, the passing device of this embodiment may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The present invention also provides a storage medium characterized in that the storage medium stores computer instructions for causing the computer to execute the dialog management method of the above-described embodiment.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A dialog management method, comprising:
analyzing the received current conversation information to obtain current intention understanding information of the current conversation information, and determining current slot position information of the current intention understanding information;
determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node;
generating response information corresponding to the target intention node based on a preset information generation rule of the target intention node;
and outputting response information corresponding to the target intention node.
2. The session management method according to claim 1, wherein before analyzing the received current session information to obtain current intention understanding information of the current session information and determining slot position information of the current intention understanding information, the method further comprises:
responding to user configuration operation, and respectively configuring an intention understanding process and a conversation management process;
the intention understanding process is used for sending the current intention understanding information and the slot position information to the conversation management process after obtaining the current intention understanding information and the slot position information;
and the conversation management process is used for carrying out conversation management according to the slot position information.
3. The dialog management method of claim 1 wherein determining slot information for the current intent understanding information comprises:
and determining the slot position information according to the existing conversation content of the user and the current conversation information.
4. The dialog management method of claim 1 further comprising:
judging whether the current intention understanding information is the same as the previous intention understanding information;
if the current intention understanding information is different from the previous intention understanding information, switching to a current conversation process corresponding to the current intention understanding information, and pausing the previous conversation process corresponding to the previous intention understanding information;
and returning to the last conversation process when the current conversation process is detected to be finished.
5. The dialog management method according to claim 4, wherein the switching to a current dialog flow corresponding to the current intention understanding information and pausing a previous dialog flow corresponding to the previous intention understanding information comprises:
respectively and sequentially stacking the previous dialogue node corresponding to the previous dialogue process and the current dialogue node corresponding to the current dialogue process;
wherein, the stacking sequence of the last dialogue node is the stacking sequence of the current dialogue node;
the pop sequence of the last dialog node is the pop sequence of the current dialog node.
6. The dialog management method of claim 5 further comprising:
and if the fact that the dependent conversation node contained in the current conversation process exists in the stack is detected, carrying out invalidation processing on the dependent conversation node, so that the dependent conversation node does not output response information corresponding to the dependent conversation node when the dependent conversation node meets the pop condition.
7. The dialog management method according to claim 4, wherein before switching to a current dialog flow corresponding to the current intention understanding information and suspending a previous dialog flow corresponding to the previous intention understanding information, the method further comprises:
judging whether the current identity information corresponding to the current dialogue information is matched with the previous identity information corresponding to the previous dialogue input information;
correspondingly, the switching to the current conversation process corresponding to the current intention understanding information and pausing the previous conversation process corresponding to the previous intention understanding information includes:
and if the current identity information is matched with the previous identity information, switching to a current conversation process corresponding to the current intention understanding information, and pausing a previous conversation process corresponding to the previous intention understanding information.
8. The dialog management method of claim 7 wherein the current dialog information and the last dialog input information are both speech;
the determining whether the current identity information corresponding to the current dialog information matches the previous identity information corresponding to the previous dialog input information includes:
respectively determining current characteristic information corresponding to the current voice and previous characteristic information corresponding to the previous voice;
judging whether the current characteristic information is matched with the previous characteristic information;
if the current characteristic information is matched with the previous characteristic information, determining that the current identity information is matched with the previous identity information;
and if the current characteristic information is not matched with the previous characteristic information, determining that the current identity information is not matched with the previous identity information.
9. A dialog management device, comprising:
the analysis module is used for analyzing the received current conversation information to obtain current intention understanding information of the current conversation information and determining current slot position information of the current intention understanding information;
the determining module is used for determining a target intention node corresponding to the current slot position information according to the incidence relation between the preset slot position information and the intention node;
the generating module is used for generating response information corresponding to the target intention node based on a preset information generating rule of the target intention node;
and the output module is used for outputting the response information corresponding to the target intention node.
10. A dialog management device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010444389.4A CN111612482A (en) | 2020-05-22 | 2020-05-22 | Conversation management method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010444389.4A CN111612482A (en) | 2020-05-22 | 2020-05-22 | Conversation management method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612482A true CN111612482A (en) | 2020-09-01 |
Family
ID=72196199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010444389.4A Pending CN111612482A (en) | 2020-05-22 | 2020-05-22 | Conversation management method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612482A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112015880A (en) * | 2020-10-23 | 2020-12-01 | 和美（深圳）信息技术股份有限公司 | Automatic transfer method and system for man-machine conversation process of intelligent robot |
| CN112735411A (en) * | 2020-12-25 | 2021-04-30 | 广州橙行智动汽车科技有限公司 | Control method, client, vehicle, voice system, and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153322A1 (en) * | 2009-12-23 | 2011-06-23 | Samsung Electronics Co., Ltd. | Dialog management system and method for processing information-seeking dialogue |
| CN104360897A (en) * | 2014-10-29 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Conversation processing method and conversation management system |
| CN107886948A (en) * | 2017-11-16 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device, terminal, server and readable storage medium storing program for executing |
| CN109101545A (en) * | 2018-06-29 | 2018-12-28 | 北京百度网讯科技有限公司 | Natural language processing method, apparatus, equipment and medium based on human-computer interaction |
| US20190013017A1 (en) * | 2017-07-04 | 2019-01-10 | Samsung Sds Co., Ltd. | Method, apparatus and system for processing task using chatbot |
| CN109446307A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of method for realizing dialogue management in Intelligent dialogue |
| CN109829036A (en) * | 2019-02-12 | 2019-05-31 | 浙江核新同花顺网络信息股份有限公司 | A kind of dialogue management method and relevant apparatus |
| CN109871129A (en) * | 2019-03-22 | 2019-06-11 | 深圳追一科技有限公司 | Man-machine interaction method, device, customer service equipment and storage medium |
| CN110096191A (en) * | 2019-04-24 | 2019-08-06 | 北京百度网讯科技有限公司 | A kind of interactive method, device and electronic equipment |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| EP3557501A1 (en) * | 2018-04-20 | 2019-10-23 | Facebook, Inc. | Assisting users with personalized and contextual communication content |
| CN110377716A (en) * | 2019-07-23 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | Exchange method, device and the computer readable storage medium of dialogue |
| CN110460654A (en) * | 2019-02-26 | 2019-11-15 | 北京蓦然认知科技有限公司 | The method for down loading and device of interactive engine in a kind of intelligent interaction platform |
| US20190385611A1 (en) * | 2018-06-18 | 2019-12-19 | Sas Institute Inc. | System for determining user intent from text |
| CN110704594A (en) * | 2019-09-27 | 2020-01-17 | 北京百度网讯科技有限公司 | Task type dialogue interaction processing method and device based on artificial intelligence |
| CN110785763A (en) * | 2017-10-03 | 2020-02-11 | 谷歌有限责任公司 | User programmable automated assistant |
| CN111046150A (en) * | 2018-10-15 | 2020-04-21 | 阿里巴巴集团控股有限公司 | Human-computer interaction processing system and method, storage medium and electronic device |
| CN111090728A (en) * | 2019-12-13 | 2020-05-01 | 车智互联（北京）科技有限公司 | Conversation state tracking method and device and computing equipment |
| CN111128154A (en) * | 2019-12-03 | 2020-05-08 | 北京蓦然认知科技有限公司 | Method and device for forming interaction engine cluster by aggregation |
-
2020
- 2020-05-22 CN CN202010444389.4A patent/CN111612482A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110153322A1 (en) * | 2009-12-23 | 2011-06-23 | Samsung Electronics Co., Ltd. | Dialog management system and method for processing information-seeking dialogue |
| CN104360897A (en) * | 2014-10-29 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Conversation processing method and conversation management system |
| US20190013017A1 (en) * | 2017-07-04 | 2019-01-10 | Samsung Sds Co., Ltd. | Method, apparatus and system for processing task using chatbot |
| CN110785763A (en) * | 2017-10-03 | 2020-02-11 | 谷歌有限责任公司 | User programmable automated assistant |
| CN107886948A (en) * | 2017-11-16 | 2018-04-06 | 百度在线网络技术（北京）有限公司 | Voice interactive method and device, terminal, server and readable storage medium storing program for executing |
| EP3557501A1 (en) * | 2018-04-20 | 2019-10-23 | Facebook, Inc. | Assisting users with personalized and contextual communication content |
| US20190385611A1 (en) * | 2018-06-18 | 2019-12-19 | Sas Institute Inc. | System for determining user intent from text |
| CN109101545A (en) * | 2018-06-29 | 2018-12-28 | 北京百度网讯科技有限公司 | Natural language processing method, apparatus, equipment and medium based on human-computer interaction |
| CN111046150A (en) * | 2018-10-15 | 2020-04-21 | 阿里巴巴集团控股有限公司 | Human-computer interaction processing system and method, storage medium and electronic device |
| CN109446307A (en) * | 2018-10-16 | 2019-03-08 | 浪潮软件股份有限公司 | A kind of method for realizing dialogue management in Intelligent dialogue |
| CN109829036A (en) * | 2019-02-12 | 2019-05-31 | 浙江核新同花顺网络信息股份有限公司 | A kind of dialogue management method and relevant apparatus |
| CN110460654A (en) * | 2019-02-26 | 2019-11-15 | 北京蓦然认知科技有限公司 | The method for down loading and device of interactive engine in a kind of intelligent interaction platform |
| CN109871129A (en) * | 2019-03-22 | 2019-06-11 | 深圳追一科技有限公司 | Man-machine interaction method, device, customer service equipment and storage medium |
| CN110096191A (en) * | 2019-04-24 | 2019-08-06 | 北京百度网讯科技有限公司 | A kind of interactive method, device and electronic equipment |
| CN110321472A (en) * | 2019-06-12 | 2019-10-11 | 中国电子科技集团公司第二十八研究所 | Public sentiment based on intelligent answer technology monitors system |
| CN110377716A (en) * | 2019-07-23 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | Exchange method, device and the computer readable storage medium of dialogue |
| CN110704594A (en) * | 2019-09-27 | 2020-01-17 | 北京百度网讯科技有限公司 | Task type dialogue interaction processing method and device based on artificial intelligence |
| CN111128154A (en) * | 2019-12-03 | 2020-05-08 | 北京蓦然认知科技有限公司 | Method and device for forming interaction engine cluster by aggregation |
| CN111090728A (en) * | 2019-12-13 | 2020-05-01 | 车智互联（北京）科技有限公司 | Conversation state tracking method and device and computing equipment |
Non-Patent Citations (2)
| Title |
|---|
| 黄民烈等: "对话管理中基于槽特征有限状态自动机的方法研究", 《计算机学报》 * |
| 黄民烈等: "对话管理中基于槽特征有限状态自动机的方法研究", 《计算机学报》, no. 08, 12 August 2004 (2004-08-12) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112015880A (en) * | 2020-10-23 | 2020-12-01 | 和美（深圳）信息技术股份有限公司 | Automatic transfer method and system for man-machine conversation process of intelligent robot |
| CN112015881B (en) * | 2020-10-23 | 2021-02-19 | 和美（深圳）信息技术股份有限公司 | Automatic switching method and system for man-machine conversation process of intelligent robot |
| CN112015880B (en) * | 2020-10-23 | 2021-03-30 | 和美（深圳）信息技术股份有限公司 | Automatic transfer method and system for man-machine conversation process of intelligent robot |
| CN112735411A (en) * | 2020-12-25 | 2021-04-30 | 广州橙行智动汽车科技有限公司 | Control method, client, vehicle, voice system, and storage medium |
| WO2022135492A1 (en) * | 2020-12-25 | 2022-06-30 | 广州橙行智动汽车科技有限公司 | Control method, client, vehicle, voice system, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109002510B (en) | Dialogue processing method, device, equipment and medium | |
| US10656909B2 (en) | Learning intended user actions | |
| CN111612482A (en) | Conversation management method, device and equipment | |
| US11151995B2 (en) | Electronic device for mapping an invoke word to a sequence of inputs for generating a personalized command | |
| CN112286485B (en) | Method and device for controlling application through voice, electronic equipment and storage medium | |
| KR20210098397A (en) | Response speed test method, apparatus, device and storage medium of vehicle device | |
| US8868419B2 (en) | Generalizing text content summary from speech content | |
| KR20200011198A (en) | Method, apparatus and computer program for providing interaction message | |
| CN111816192A (en) | Voice equipment and control method, device and equipment thereof | |
| US10950221B2 (en) | Keyword confirmation method and apparatus | |
| CN111640429A (en) | Method of providing voice recognition service and electronic device for the same | |
| CN112767916A (en) | Voice interaction method, device, equipment, medium and product of intelligent voice equipment | |
| US20190214013A1 (en) | Speech-to-text conversion based on user interface state awareness | |
| KR20190021136A (en) | System and device for generating TTS model | |
| KR20210042520A (en) | An electronic apparatus and Method for controlling the electronic apparatus thereof | |
| CN114661287A (en) | Component linkage rendering method and device, electronic equipment, storage medium and product | |
| US20190026074A1 (en) | Electronic device and method for expressing natural language | |
| CN109446078A (en) | Code test method and device, storage medium, electronic equipment | |
| CN112863496B (en) | Voice endpoint detection method and device | |
| CN112199470A (en) | Session-based customer complaint service method, intelligent terminal and storage medium | |
| KR20220057249A (en) | Electronic apparatus for processing user utterance and controlling method thereof | |
| CN110716867A (en) | Method, device and equipment for detecting multi-page jump pressure | |
| CN114299955B (en) | Voice interaction method and device, electronic equipment and storage medium | |
| CN115798469A (en) | Voice control method and device, electronic equipment and computer readable storage medium | |
| CN111967273B (en) | Dialog management system, method and rule engine device |
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: 20200901 |
|
| RJ01 | Rejection of invention patent application after publication |