CN113488047A - Man-machine conversation interruption method, electronic device and computer readable storage medium - Google Patents
Man-machine conversation interruption method, electronic device and computer readable storage mediumDownload PDFInfo
- Publication number
- CN113488047A CN113488047ACN202110761273.8ACN202110761273ACN113488047ACN 113488047 ACN113488047 ACN 113488047ACN 202110761273 ACN202110761273 ACN 202110761273ACN 113488047 ACN113488047 ACN 113488047A
- Authority
- CN
- China
- Prior art keywords
- dialog
- new
- intention
- intent
- space
- 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
- 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
- G10L15/222—Barge in, i.e. overridable guidance for interrupting prompts
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The present invention relates to the field of human-computer conversation technologies, and in particular, to a human-computer conversation interruption method, an electronic device, and a computer-readable storage medium.
Background
In the existing man-machine conversation, whether voice exists can be monitored simultaneously in the broadcasting process of the electronic equipment for users, and whether the current broadcasting is interrupted or not to respond is determined according to the monitoring result. The methods generally adopted in the prior art are as follows: judging whether the user speaks or finishes speaking by using voice VAD (voice Activity detection) technology through the strength or pause time of the voice signal; or whether the user is speaking is judged through a rejection model.
The voice input of a user is monitored while the machine broadcasts through the VAD judging method, whether voice exists or not is judged from a voice layer, and if the voice exists, the user is considered to speak.
The 'rejection model' is divided into two types, one type judges whether the input sound is background noise by training an audio classifier, such as the speaking sound of surrounding people, and the rejection function is to filter out invalid voice; another is semantic rejection: and establishing a two-classification model based on the text of the current words of the user and the text of the historical words of the user, and learning whether to reject through the model. The idea has a precondition hypothesis that the texts of the words "speak with the robot" and "speak with the robot" of the user are different in semantic space and are essentially a two-classification classifier.
However, rejection by VAD tends to cause the machine to stop broadcasting due to background sounds or noise; it is also easy for the machine to think that the user is finished because of a short pause in the user's speaking. The voice rejection is equivalent to the strengthened VAD, and classifiers for voice training such as background voice, noise and the like are added in the VAD judgment process. Whether or not it should be rejected is learned by some characteristic of the noise. However, because only the voice signal is used as the basis, it cannot be determined whether the user only utters some linguistic words or really wants to speak. In addition, it is impossible to determine whether the user is actually finished speaking or just pausing briefly.
Semantic rejection it is now common practice to train a two-class semantic classifier, but this approach has the assumption that the text of the user "speaking with the robot" and "not speaking with the robot" is different in semantic space. However, it is difficult to make a correct judgment that the actual user is talking to a nearby person or that a nearby person is chatting, which makes sense.
Disclosure of Invention
An embodiment of the present invention provides a man-machine conversation interruption method, an electronic device, and a computer-readable storage medium, which are used for solving at least one of the above technical problems.
In a first aspect, an embodiment of the present invention provides a man-machine conversation interruption method, which is applied to an electronic device, and includes:
determining a dialog intention space from the completed dialog;
when a new dialogue statement is detected, determining a new dialogue intention according to the new dialogue statement;
determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space.
In a second aspect, the present invention provides a computer-readable storage medium, in which one or more programs including execution instructions are stored, where the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform any one of the above man-machine conversation interruption methods of the present invention.
In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to perform any of the human-machine conversation interruption methods of the present invention described above.
In a fourth aspect, the present invention further provides a computer program product, which includes a computer program stored on a storage medium, the computer program including program instructions, which when executed by a computer, cause the computer to execute any one of the man-machine conversation interruption methods described above.
In the embodiment of the invention, when the new dialogue intention is determined to belong to the preset dialogue intention space, the new dialogue sentence is indicated to be related to the completed dialogue, so that the detected new dialogue sentence is determined to be not noise, and the response is made to the new dialogue sentence, thereby avoiding the mistaken interruption of the man-machine dialogue in noise.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of one embodiment of a human-machine conversation interruption method of the present invention;
FIG. 2 is a flow chart of another embodiment of a human-machine conversation interruption method of the present invention;
FIG. 3 is a waveform diagram illustrating a human-machine conversation interruption method according to the present invention;
FIG. 4 is a flow chart of another embodiment of a human-machine conversation interruption method of the present invention;
FIG. 5 is a flow chart of another embodiment of a human-machine conversation interruption method of the present invention;
fig. 6 is a schematic structural diagram of an embodiment of an electronic device according to the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
As used in this disclosure, "module," "device," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes based on a signal having one or more data packets, e.g., from a data packet interacting with another element in a local system, distributed system, and/or across a network in the internet with other systems by way of the signal.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The man-machine conversation interruption method is applied to electronic equipment, which can be a smart sound box with man-machine function, a smart robot (such as a doorphone robot, an inquiry robot, etc.), a smart phone, a tablet computer, a car machine, etc., and the invention is not limited thereto.
Fig. 1 shows a man-machine conversation interruption method provided by an embodiment of the present invention, which is applied to an electronic device, and the method includes:
and S10, determining a dialog intention space according to the completed dialog.
Illustratively, a completed conversation may be one or more rounds of conversations that the electronic device has completed with the user. The electronic equipment determines a plurality of dialogue intentions to form a dialogue intention space according to the completed dialogue turns in the process of man-machine dialogue with a user. The plurality of dialog intents may include a user's dialog intention determined from a dialog turn that has been completed and may also include a machine dialog intention communicated to the user by the electronic device determined from a dialog turn that has been completed.
And S20, when a new dialogue statement is detected, determining a new dialogue intention according to the new dialogue statement.
Illustratively, the new dialog statements detected by the electronic device may be from the user in the previous round of the human-machine dialog, and may also be from other users. And the new dialog sentence may be a control instruction of the user to the electronic device (is a continuation of the previous dialog or a start of a new dialog), or may be merely a dialog sentence between the user and another person (there is no correlation with the previous dialog).
Illustratively, after determining a new dialog intention of a new dialog statement, it is determined whether the new dialog intention belongs to the dialog intention space as a basis for whether to respond to the new dialog intention.
S30, determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space.
Illustratively, when it is determined that the new dialog intention belongs to the predetermined dialog intention space, it is indicated that the new dialog sentence is associated with a dialog that has been completed, so that it can be determined that the detected new dialog sentence is not noise, and a response is made to the new dialog sentence, avoiding a false interruption of the human-machine dialog in noise.
In some embodiments, the dialog intent space includes a current dialog intent and an associated dialog intent. Fig. 2 is a flow chart of another embodiment of the man-machine conversation interruption method of the present invention, in which the determining of the conversation intention space according to the completed conversation includes:
s11, determining the current conversation intention according to the completed conversation;
and S12, determining the associated dialog intention associated with the current dialog intention.
In the present embodiment, the dialog intention space includes not only the current dialog intention but also the associated dialog intention associated with the current dialog intention, so that the detected new dialog intention corresponding to the new dialog sentence will not directly regard the new dialog sentence as noise even if the new dialog intention is not in accordance with the current dialog intention. If the new dialogue intention is determined to accord with the associated dialogue intention, the new dialogue statement can also be determined to be non-noise, so that the problem that the target user cannot obtain the response of the electronic equipment when the new dialogue intention corresponding to the dialogue statement of the target user cannot completely accord with the current dialogue intention is avoided.
The above current dialog intention and associated dialog intention may be understood as a desired intention that fits the current dialog expectation, being a possible intention space for the user to speak when the current dialog node is present, for example:
a. the current dialog intent may be the intent of the current node: for example, in the process of registering and sending an express, the robot asks the user what the address of the user is, and the expected intention of the current node is the address.
b. The associated dialog intent may be a possible intent of the current scene: this node user may also express the intent that i don't register, complain, i ask for express delivery fee first, etc.
In some embodiments, the dialog intent space also includes dialog intents for switching dialog tasks. Illustratively, the conversation intent to switch conversation tasks may be an intent or encyclopedia knowledge across scenes that triggers other conversation tasks, such as how much tomorrow is, how many kilometers beijing is to shanghai, and so on.
The above dialog intents (the current dialog intention and/or the associated dialog intention and/or the dialog intention switching the dialog task) constitute the desired intention of the current dialog context. If the detected new dialogue intention corresponding to the new dialogue statement is not in the expected intention range, in this case, even if the signal such as voice indicates that a person is speaking, intelligent interruption does not interrupt the current machine broadcasting. Thereby effectively avoiding the error interruption.
In some embodiments, a completed conversation may include: the above answers, the current question, the current scene, domain, etc. And the factors considered in determining the dialog intent space may include, in addition to the dialog that has been completed, speech signal features, speech noise features, speech confidence features, real-time user image features, descriptive way features in the user representation, and the like.
In some embodiments, before detecting the new conversational sentence, further comprising: and broadcasting the broadcasting content corresponding to the current conversation intention. Illustratively, during the man-machine conversation, full-duplex communication can be realized between the electronic device and the user, and the electronic device can broadcast the determined broadcast content and simultaneously detect whether a new user statement exists.
In some embodiments, step S30, determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space, includes: interrupting the announcement and determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space.
For example, determining reply content corresponding to the new dialog intent after interrupting the announcement of the electronic device may include: judging whether the new dialog intention is complete, and if so, determining reply content corresponding to the new dialog intention; if not, it is continuously detected whether the user is speaking continuously, if so, the previous new dialogue intention is updated according to the continuously detected user sentence, and the reply content is determined.
As shown in fig. 3, which is a waveform diagram of the man-machine conversation interruption method of the present invention, in this embodiment, a waveform of machine broadcast audio and a waveform of ambient audio and user speaking audio are displayed. In this embodiment the user statement is "i want to look up yesterday that express". Before the user speaks, the electronic equipment detects the noise while broadcasting. When the user speaks, and the electronic device determines the corresponding conversation intention compound expectation intention according to the conversation sentence detected in real time when the user speaks 'i want to find down', but further judges that the conversation intention is incomplete, so that the detection is further continued until a complete conversation intention is obtained, and then response content is determined according to the complete conversation intention.
In some embodiments, before detecting the new conversational sentence, further comprising: broadcasting broadcast content corresponding to the current conversation intention; the man-machine conversation interruption method of the embodiment further comprises the following steps: determining whether the broadcast content is a forced broadcast content;
fig. 4 is a flow chart of another embodiment of the human-machine dialog interruption method of the present invention, in which the determining of the reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space includes:
s31, when the broadcast content is the non-mandatory broadcast content and the new dialogue intention belongs to the dialogue intention space, interrupting the play of the non-mandatory broadcast content and determining reply content corresponding to the new dialogue intention;
and S32, when the broadcast content is a forced broadcast content and the new dialog intention belongs to the dialog intention space, determining reply content corresponding to the new dialog intention after the forced broadcast content is completed.
Illustratively, the broadcast content may be set to an attribute according to the service requirement, for example, the broadcast content may be set to be broadcast forcibly or broadcast non-forcibly. For example, some broadcast contents which are helpful to improve the communication efficiency can be set as forced broadcast contents, and interruption is not allowed in the broadcast process; some irrelevant additional introduction contents can be set to be non-compulsory broadcast contents, and the broadcast process can be interrupted at any time.
In this embodiment, it is determined that the detected new dialog statement expresses an intention related to the current node, but the current node is performing broadcasting of necessary service notification, intelligent interruption may not interrupt continuous broadcasting, but simultaneously records an intention expressed by the user, and after the broadcasting is completed, the unprocessed intention is sent to dialog management for processing, so as to delay response to the intention of the user.
As shown in fig. 5, which is a flowchart of another embodiment of the man-machine conversation interruption method of the present invention, the embodiment further includes:
s41, when the new dialogue intention is determined not to belong to the dialogue intention space, inquiring whether the new dialogue intention appears once;
s42, if not, recording the new dialogue intention;
s43, if yes, determining reply content corresponding to the new dialog intention.
Another key module of intelligent interruption is an interruption fault-tolerant mechanism, which is implemented by interrupting a context. For example, in practical applications, when an intention space is constructed, it is often not possible to incorporate all the intention-most income intention spaces that should be included (e.g., missing conversation intention a), resulting in incomplete intentions. Thus, when the dialog intention a is determined from the detected user sentence, the electronic device determines that the dialog intention a does not belong to the intention space, that is, is not within the desired range without interruption, because the intention space is incomplete, and then the user may further emphasize or repeat his or her own problem. The embodiment of the invention just gives the behavior habit to the user, and the method of the embodiment is set, so that the states of nodes, time and the like of each interruption in history are recorded, and intelligent interruption judges that the response to the user is required to be interrupted even if the current intention is not in the expected intention range and exists in the record according to the above and the current speech semantics.
In some embodiments, before detecting the new conversational sentence, further comprising: broadcasting broadcast content corresponding to the current conversation intention; the man-machine conversation interrupting method further comprises the following steps: judging whether the interruption times in the preset time exceed the preset times or not before interrupting the broadcast; if yes, continuing to finish broadcasting; if not, interrupting the broadcast.
The man-machine conversation interruption method can prevent the broadcasting of the electronic equipment from being interrupted frequently, and avoid influencing normal and smooth man-machine conversation. In the embodiment, another situation that a fault-tolerant mechanism is needed is provided, if the current same node is frequently interrupted, a conversation is difficult to continue, for example, if the current same node is interrupted just before 1 second, the conversation is interrupted again immediately, even if various characteristics judge that interruption is needed, the conversation is not interrupted temporarily but continuously broadcasted, and whether interruption is needed is comprehensively evaluated after the next judgment that interruption is needed is waited.
In the embodiment of the man-machine conversation interruption method, the robot monitors the words spoken by the user simultaneously in the speaking process and judges whether the user speaks to the robot, if the user speaks to the robot (namely, non-noise), the robot stops broadcasting and finishes hearing the words spoken by the user, and then the response is made according to the semantic meaning spoken by the user.
In the embodiment of the man-machine conversation interruption method, if the user finishes speaking, the robot can judge that the user finishes speaking in time, and does not need to start speaking after the user stops for a period of time to confirm that the user finishes speaking from the voice signal.
It should be noted that for simplicity of explanation, the foregoing method embodiments are described as a series of acts or combination of acts, but those skilled in the art will appreciate that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention. In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In some embodiments, the present invention provides a computer-readable storage medium, in which one or more programs including execution instructions are stored, and the execution instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform any of the above man-machine conversation interruption methods of the present invention.
In some embodiments, the present invention further provides a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform any of the human-machine conversation interruption methods described above.
In some embodiments, an embodiment of the present invention further provides an electronic device, which includes: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a human-machine conversation breaking method.
Fig. 6 is a schematic hardware structure diagram of an electronic device for performing a man-machine conversation interruption method according to another embodiment of the present application, where as shown in fig. 6, the device includes:
one ormore processors 610 and amemory 620, with oneprocessor 610 being an example in fig. 6.
The apparatus for performing the man-machine conversation interruption method may further include: aninput device 630 and anoutput device 640.
Theprocessor 610, thememory 620, theinput device 630, and theoutput device 640 may be connected by a bus or other means, such as the bus connection in fig. 6.
Thememory 620, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the man-machine conversation interruption method in the embodiments of the present application. Theprocessor 610 executes various functional applications of the server and data processing by running nonvolatile software programs, instructions and modules stored in thememory 620, namely, implements the human-machine conversation interruption method of the above-described method embodiment.
Thememory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the stored data area may store data created from use of the human-machine conversation interrupting apparatus, and the like. Further, thememory 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments,memory 620 optionally includes memory located remotely fromprocessor 610, which may be connected to the human conversation interruption device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Theinput device 630 may receive entered numeric or character information and generate signals related to user settings and function controls of the human-machine dialog interrupting device. Theoutput device 640 may include a display device such as a display screen.
The one or more modules are stored in thememory 620 and, when executed by the one ormore processors 610, perform the human-machine conversation interruption method of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as ipads.
(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, as well as smart toys and portable car navigation devices.
(4) And other electronic devices with data interaction functions.
The above-described embodiments of the apparatus are merely illustrative, and 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, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions substantially or contributing to the related art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A man-machine conversation interruption method is applied to an electronic device, and comprises the following steps:
determining a dialog intention space from the completed dialog;
when a new dialogue statement is detected, determining a new dialogue intention according to the new dialogue statement;
determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space.
2. The method of claim 1, wherein the dialog intent space includes a current dialog intent and an associated dialog intent, and wherein determining a dialog intent space from a completed dialog comprises:
determining a current dialog intention according to the completed dialog;
an associated dialog intent associated with the current dialog intent is determined.
3. The method of claim 2, wherein the dialog intent space further comprises dialog intents for switching dialog tasks.
4. The method of claim 1, further comprising, prior to detecting a new conversational sentence: broadcasting broadcast content corresponding to the current conversation intention;
determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space, including:
interrupting the announcement and determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space.
5. The method of claim 1, further comprising, prior to detecting a new conversational sentence: broadcasting broadcast content corresponding to the current conversation intention;
the method further comprises the following steps: determining whether the broadcast content is a forced broadcast content;
determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space, comprising:
and when the broadcast content is the non-mandatory broadcast content and the new conversation intention belongs to the conversation intention space, interrupting the play of the non-mandatory broadcast content and determining reply content corresponding to the new conversation intention.
6. The method of claim 5, wherein determining reply content corresponding to the new dialog intent at least when the new dialog intent belongs to the dialog intent space comprises:
when the broadcast content is a forced broadcast content and the new dialog intention belongs to the dialog intention space, determining reply content corresponding to the new dialog intention after the forced broadcast content is completed.
7. The method of any one of claims 1-6, further comprising:
querying whether the new dialog intent has ever appeared when it is determined that the new dialog intent does not belong to the dialog intent space;
if not, recording the new dialogue intention;
if so, the reply content corresponding to the new dialog intent is determined.
8. The method of claim 1, further comprising, prior to detecting a new conversational sentence: broadcasting broadcast content corresponding to the current conversation intention;
the method further comprises the following steps:
judging whether the interruption times in the preset time exceed the preset times or not before interrupting the broadcast; if yes, continuing to finish broadcasting; if not, interrupting the broadcast.
9. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any one of claims 1-8.
10. A computer-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 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110761273.8ACN113488047A (en) | 2021-07-06 | 2021-07-06 | Man-machine conversation interruption method, electronic device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110761273.8ACN113488047A (en) | 2021-07-06 | 2021-07-06 | Man-machine conversation interruption method, electronic device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113488047Atrue CN113488047A (en) | 2021-10-08 |
Family
ID=77941150
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110761273.8APendingCN113488047A (en) | 2021-07-06 | 2021-07-06 | Man-machine conversation interruption method, electronic device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113488047A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457945A (en)* | 2022-11-10 | 2022-12-09 | 广州小鹏汽车科技有限公司 | Voice interaction method, server and storage medium |
| CN119694304A (en)* | 2025-02-24 | 2025-03-25 | 科大讯飞股份有限公司 | Streaming voice interaction method and related device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190013017A1 (en)* | 2017-07-04 | 2019-01-10 | Samsung Sds Co., Ltd. | Method, apparatus and system for processing task using chatbot |
| CN111508474A (en)* | 2019-08-08 | 2020-08-07 | 马上消费金融股份有限公司 | Voice interruption method, electronic equipment and storage device |
| CN112100339A (en)* | 2020-11-04 | 2020-12-18 | 北京淇瑀信息科技有限公司 | User intention recognition method and device for intelligent voice robot and electronic equipment |
| CN112614491A (en)* | 2020-12-11 | 2021-04-06 | 广州橙行智动汽车科技有限公司 | Vehicle-mounted voice interaction method and device, vehicle and readable medium |
- 2021
- 2021-07-06CNCN202110761273.8Apatent/CN113488047A/enactivePending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190013017A1 (en)* | 2017-07-04 | 2019-01-10 | Samsung Sds Co., Ltd. | Method, apparatus and system for processing task using chatbot |
| CN111508474A (en)* | 2019-08-08 | 2020-08-07 | 马上消费金融股份有限公司 | Voice interruption method, electronic equipment and storage device |
| CN112100339A (en)* | 2020-11-04 | 2020-12-18 | 北京淇瑀信息科技有限公司 | User intention recognition method and device for intelligent voice robot and electronic equipment |
| CN112614491A (en)* | 2020-12-11 | 2021-04-06 | 广州橙行智动汽车科技有限公司 | Vehicle-mounted voice interaction method and device, vehicle and readable medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457945A (en)* | 2022-11-10 | 2022-12-09 | 广州小鹏汽车科技有限公司 | Voice interaction method, server and storage medium |
| CN119694304A (en)* | 2025-02-24 | 2025-03-25 | 科大讯飞股份有限公司 | Streaming voice interaction method and related device, equipment and storage medium |
| CN119694304B (en)* | 2025-02-24 | 2025-06-17 | 科大讯飞股份有限公司 | Streaming voice interaction method, related device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108538298B (en) | Voice wake-up method and device | |
| US12131735B2 (en) | Man-machine dialogue mode switching method | |
| CN112700767B (en) | Man-machine conversation interruption method and device | |
| JP7516571B2 (en) | Hotword threshold auto-tuning | |
| CN108962262A (en) | Voice data processing method and device | |
| CN111506292B (en) | Voice skill skipping method for man-machine conversation, electronic device and storage medium | |
| JP2023515897A (en) | Correction method and apparatus for voice dialogue | |
| US11721328B2 (en) | Method and apparatus for awakening skills by speech | |
| CN113488047A (en) | Man-machine conversation interruption method, electronic device and computer readable storage medium | |
| CN113779208A (en) | Method and apparatus for human-machine dialogue | |
| US12118993B2 (en) | Full-duplex voice dialogue method | |
| US11817093B2 (en) | Method and system for processing user spoken utterance | |
| CN118782027A (en) | Voice interaction method, device, robot, electronic device and storage medium | |
| CN112786031B (en) | Man-machine conversation method and system | |
| CN114743546B (en) | Method and device for reducing false wake-up rate of intelligent voice, and electronic device | |
| CN117711392A (en) | Voice interaction method, system, equipment and storage medium | |
| CN110675856A (en) | Man-machine conversation method and device for call center | |
| CN115762505A (en) | Voice interaction method, electronic device and storage medium | |
| CN115188377A (en) | Voice interaction method, electronic device and storage medium | |
| CN113590207A (en) | Method and device for improving awakening effect | |
| WO2025130156A1 (en) | Question-answer method and related apparatus | |
| CN119479634A (en) | Voice control method, device, storage medium and electronic device | |
| CN120340504A (en) | Voice wake-up method, system and electronic device based on noise reduction separation | |
| CN115631747A (en) | Voice wake-up method, system, electronic device and storage medium | |
| CN120071923A (en) | Interaction method, system, medium, product and terminal of dialogue robot |
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:20211008 | |
| RJ01 | Rejection of invention patent application after publication |