CN111382241A - Session scene switching method and device - Google Patents
Session scene switching method and device Download PDFInfo
- Publication number
- CN111382241A CN111382241A CN201811626785.8A CN201811626785A CN111382241A CN 111382241 A CN111382241 A CN 111382241A CN 201811626785 A CN201811626785 A CN 201811626785A CN 111382241 A CN111382241 A CN 111382241A
- Authority
- CN
- China
- Prior art keywords
- intention
- user
- conversation
- session
- scene
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a conversation scene switching method and a conversation scene switching device. Based on the method and the device, different conversation scenes can be switched according to different conversation intentions of the user in the multi-turn conversation process, and the quality and the user experience of the multi-turn conversation are improved.
Description
Technical Field
The invention relates to the technical field of multi-turn conversation, in particular to a conversation scene switching method and device.
Background
Artificial intelligence is an application for natural language processing. With the development of artificial intelligence technology, a human-computer interaction system with the function of multi-round conversation between an artificial intelligence robot and a real person has been realized.
Currently, the following strategies are generally adopted for the functional implementation of multiple rounds of sessions: firstly, obtaining information input by a user, then, carrying out natural language processing to obtain intrinsic information and implicit information, meanwhile, carrying out conversation intention judgment and conversation scene modeling by utilizing context information, and then, realizing multiple rounds of conversations under the established conversation scene.
However, in the prior art, multiple rounds of conversations cannot be switched to different conversation scenes according to different conversation intentions of users, so that the quality and the user experience of the multiple rounds of conversations are greatly influenced.
Disclosure of Invention
In view of the above, the present invention is proposed to provide a session scene switching method and apparatus that overcomes or at least partially solves the above problems. The specific scheme is as follows:
a method of session context switching, the method comprising:
acquiring a first message input by a user;
identifying a first intent of the user from the first message;
enabling a session with the user based on a first session scene corresponding to the first intention;
acquiring a second message input by a user in the first session scene;
identifying a second intent of the user from the second message;
and judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene.
Optionally, the implementing a session with the user based on a second session scene corresponding to the second intention includes:
acquiring a third message input by the user in the second session scene;
identifying a third intent of the user from the third message;
when the third intent is the same as the first intent, suspending the second session scenario and resuming the first session scenario; enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the first intention, judging whether the third intention is the same as the second intention, and when the third intention is the same as the second intention, sending preset guiding dialect information to a user to guide the user to input a message corresponding to the first intention;
receiving a fourth message input by the user;
identifying a fourth intent of the user from the fourth message;
the fourth intention is the same as the first intention, suspending the second session scenario and resuming the first session scenario;
enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the second intention, a conversation with the user is realized based on a third conversation scene corresponding to the third intention, and the second conversation scene is suspended.
Optionally, the method further comprises:
when the fourth intention is not the same as the first intention, judging whether the fourth intention is the same as the second intention;
when the fourth intent is the same as the second intent, enabling a conversation with the user based on the second conversation scenario;
when the fourth intention is different from the second intention, a conversation with the user is realized based on a fourth conversation scene corresponding to the fourth intention, and the second conversation scene is suspended.
Optionally, before suspending the first session scenario, the method further comprises:
and recording the session state between the user and the first session scene.
Optionally, the sending preset guidance session information to the user includes:
searching target guide conversation information corresponding to the recorded conversation state between the first conversation scene and the user;
and sending the target guide dialect information to a user.
A session scenario switching apparatus, the apparatus comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first message input by a user;
an intention identifying unit for identifying a first intention of the user according to the first message;
a conversation unit, configured to implement a conversation with the user based on a first conversation scene corresponding to the first intention;
the acquiring unit is further configured to acquire a second message input by the user in the first session scene;
the intention identification unit is further used for identifying a second intention of the user according to the second message;
the conversation unit is further configured to determine whether the second intention is the same as the first intention, and if the second intention is different from the first intention, implement a conversation with the user based on a second conversation scene corresponding to the second intention, and suspend the first conversation scene.
A storage medium having stored thereon a program which, when executed by a processor, implements the session scene switching method as described above.
An electronic device comprising a memory for storing a program and a processor for executing the program, wherein the program executes to perform the session context switching method as described above.
By means of the technical scheme, when the conversation between the user and the first conversation scene is achieved based on the first intention, the conversation scene switching method and the conversation scene switching device, provided by the invention, obtain the second message input by the user in the first conversation scene, identify the second intention of the user according to the second message, achieve the conversation between the user and the second conversation scene based on the second intention when the second intention is different from the first intention, and suspend the first conversation scene. Based on the method and the device, different conversation scenes can be switched according to different conversation intentions of the user in the multi-turn conversation process, and the quality and the user experience of the multi-turn conversation are improved.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flow chart of a session scene switching method disclosed in an embodiment of the present invention;
fig. 2 is a schematic flowchart of another session scene switching method disclosed in the embodiment of the present invention;
fig. 3 is a schematic flowchart of another session scene switching method disclosed in the embodiment of the present invention;
fig. 4 is a schematic structural diagram of a session scene switching apparatus according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, fig. 1 is a schematic flow chart of a session scene switching method according to an embodiment of the present invention, where the method includes:
step S101: acquiring a first message input by a user;
the first message input by the user may be a natural language message in various formats, such as a picture format, a text format, a voice format, and the like. The content of the message differs from session context to session context. For example, in the automobile field, the first message input by the user may be a message related to a car buying or a car renting.
Step S102: identifying a first intent of the user from the first message;
after acquiring the first message, the intention of the user may be recognized by using an existing intention recognition algorithm, and this embodiment is not limited in any way.
Step S103: enabling a session with the user based on a first session scene corresponding to the first intention;
in one possible implementation, conversation scenes corresponding to different intentions can be established in advance, and after a first intention of the user is determined, a first conversation scene corresponding to the first intention can be called to realize a conversation with the user. As an exemplary description, the session scenario in the present embodiment may include four scenarios of car selling, car renting, camp renting, and touring.
Step S104: acquiring a second message input by a user in the first session scene;
in one possible embodiment, the second message is a message input by the user after the first message, and the second message and the first message may be two adjacent messages.
Step S105: identifying a second intent of the user from the second message;
in an implementation manner, after the second message is obtained, the intention of the user may be recognized by using an existing intention recognition algorithm, and this embodiment is not limited in any way.
Step S106: and judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene.
In one possible implementation, conversation scenes corresponding to different intentions can be established in advance, and after a second intention of the user is determined, a second conversation scene corresponding to the second intention can be called to realize a conversation with the user, and the first conversation scene is suspended.
According to the conversation scene switching method provided by the embodiment, when a conversation between the user and the first conversation scene corresponding to the first intention is realized, the second message input by the user in the first conversation scene is obtained, the second intention of the user is identified according to the second message, when the second intention is different from the first intention, the conversation between the user and the second conversation scene corresponding to the second intention is realized, and the first conversation scene is suspended. Based on the method, different conversation scenes can be switched according to different conversation intentions of the user in the multi-turn conversation process, and the quality and the user experience of the multi-turn conversation are improved.
Referring to fig. 2, fig. 2 is a schematic flow chart of another session scene switching method disclosed in the embodiment of the present invention, where the method includes:
step S201: acquiring a first message input by a user;
step S202: identifying a first intent of the user from the first message;
step S203: enabling a session with the user based on a first session scene corresponding to the first intention;
step S204: acquiring a second message input by a user in the first session scene;
step S205: identifying a second intent of the user from the second message;
step S206: judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene;
it should be noted that steps S201 to S206 are the same as steps S101 to S106 in the previous embodiment, and specific implementation may refer to related descriptions in the previous embodiment, which is not described again in this embodiment.
Step S207: acquiring a third message input by the user in the second session scene;
step S208: identifying a third intent of the user from the third message;
step S209: when the third intent is the same as the first intent, suspending the second session scenario and resuming the first session scenario; enabling a session with the user based on the first session scenario.
Based on the embodiment, in a second conversation scene, performing intention identification on each message input by a user, judging whether the intention of the user is the same as the first intention, if so, suspending the second conversation scene, and recovering the first conversation scene; and realizing the session with the user based on the first session scene, thereby realizing the purpose of returning to the initial session scene.
In one embodiment, if the user does not input the same message as the first intention within the preset time, the purpose of returning to the initial session scene is achieved in a guiding manner, which can be described in detail by the following embodiments.
Referring to fig. 3, fig. 3 is a schematic flow chart of another session scene switching method disclosed in the embodiment of the present invention, where the method is implemented on the basis of the session scene switching method shown in fig. 2, and specifically includes:
step S301: when the third intention is different from the first intention, judging whether the third intention is the same as the second intention, and when the third intention is the same as the second intention, sending preset guiding dialect information to a user to guide the user to input a message corresponding to the first intention;
in one possible implementation, before suspending a first session scenario, a session state with the user in the first session scenario is recorded. Sending preset guiding dialect information to the user, wherein the preset guiding dialect information comprises the following steps: searching target guide conversation information corresponding to the recorded conversation state between the first conversation scene and the user; and sending the target guide dialect information to a user.
In one possible implementation, each suspended session scenario records the session state with the user in the session scenario, so that the boot session information corresponding to the session scenario can be acquired when the session scenario is resumed.
Step S302: receiving a fourth message input by the user;
step S303: identifying a fourth intent of the user from the fourth message;
step S304: the fourth intention is the same as the first intention, suspending the second session scenario and resuming the first session scenario;
step S305: enabling a session with the user based on the first session scenario.
The above embodiment describes a specific implementation manner for successfully achieving the purpose of returning to the initial session scenario in a boot manner.
In yet another possible implementation, when the third intention is different from the second intention, a session with the user is implemented based on a third session scenario corresponding to the third intention, and the second session scenario is suspended. This embodiment describes an embodiment in which the session scene is switched again according to the information input by the user.
In yet another possible implementation, when the fourth intention is not the same as the first intention, determining whether the fourth intention is the same as the second intention;
when the fourth intent is the same as the second intent, enabling a conversation with the user based on the second conversation scenario;
when the fourth intention is different from the second intention, a conversation with the user is realized based on a fourth conversation scene corresponding to the fourth intention, and the second conversation scene is suspended. The embodiment describes a specific processing mode in which the purpose of returning to the initial session scenario is not successfully achieved by adopting a guidance mode, and the specific processing mode includes continuing to adopt the current session scenario and switching to other session scenarios.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a session scene switching apparatus according to an embodiment of the present invention, where the apparatus includes:
an obtaining unit 41, configured to obtain a first message input by a user;
an intention identifying unit 42 for identifying a first intention of the user from the first message;
a conversation unit 43, configured to implement a conversation with the user based on a first conversation scene corresponding to the first intention;
the obtaining unit 41 is further configured to obtain a second message input by the user in the first session scenario;
the intention identifying unit 42 is further configured to identify a second intention of the user according to the second message;
the conversation unit 43 is further configured to determine whether the second intention is the same as the first intention, and if the second intention is different from the first intention, implement a conversation with the user based on a second conversation scenario corresponding to the second intention, and suspend the first conversation scenario.
It should be noted that specific function implementation of each unit is already described in detail in the method embodiment, and this embodiment is not described again.
The conversation scene switching device comprises a processor and a memory, wherein the acquisition unit, the intention identification unit, the conversation unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, different conversation scenes are switched according to different conversation intents of the user by adjusting kernel parameters, and the quality and the user experience of multiple rounds of conversations are improved.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a storage medium, on which a program is stored, and the program, when executed by a processor, implements the session scene switching method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the session scene switching method is executed when the program runs.
The embodiment of the invention provides electronic equipment, which comprises a processor, a memory and a program which is stored on the memory and can be operated on the processor, wherein the processor executes the program and realizes the following steps:
acquiring a first message input by a user;
identifying a first intent of the user from the first message;
enabling a session with the user based on a first session scene corresponding to the first intention;
acquiring a second message input by a user in the first session scene;
identifying a second intent of the user from the second message;
and judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene.
Optionally, the implementing a session with the user based on a second session scene corresponding to the second intention includes:
acquiring a third message input by the user in the second session scene;
identifying a third intent of the user from the third message;
when the third intent is the same as the first intent, suspending the second session scenario and resuming the first session scenario; enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the first intention, judging whether the third intention is the same as the second intention, and when the third intention is the same as the second intention, sending preset guiding dialect information to a user to guide the user to input a message corresponding to the first intention;
receiving a fourth message input by the user;
identifying a fourth intent of the user from the fourth message;
the fourth intention is the same as the first intention, suspending the second session scenario and resuming the first session scenario;
enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the second intention, a conversation with the user is realized based on a third conversation scene corresponding to the third intention, and the second conversation scene is suspended.
Optionally, the method further comprises:
when the fourth intention is not the same as the first intention, judging whether the fourth intention is the same as the second intention;
when the fourth intent is the same as the second intent, enabling a conversation with the user based on the second conversation scenario;
when the fourth intention is different from the second intention, a conversation with the user is realized based on a fourth conversation scene corresponding to the fourth intention, and the second conversation scene is suspended.
Optionally, before suspending the first session scenario, the method further comprises:
and recording the session state between the user and the first session scene.
Optionally, the sending preset guidance session information to the user includes:
searching target guide conversation information corresponding to the recorded conversation state between the first conversation scene and the user;
and sending the target guide dialect information to a user.
The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
acquiring a first message input by a user;
identifying a first intent of the user from the first message;
enabling a session with the user based on a first session scene corresponding to the first intention;
acquiring a second message input by a user in the first session scene;
identifying a second intent of the user from the second message;
and judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene.
Optionally, the implementing a session with the user based on a second session scene corresponding to the second intention includes:
acquiring a third message input by the user in the second session scene;
identifying a third intent of the user from the third message;
when the third intent is the same as the first intent, suspending the second session scenario and resuming the first session scenario; enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the first intention, judging whether the third intention is the same as the second intention, and when the third intention is the same as the second intention, sending preset guiding dialect information to a user to guide the user to input a message corresponding to the first intention;
receiving a fourth message input by the user;
identifying a fourth intent of the user from the fourth message;
the fourth intention is the same as the first intention, suspending the second session scenario and resuming the first session scenario;
enabling a session with the user based on the first session scenario.
Optionally, the method further comprises:
when the third intention is different from the second intention, a conversation with the user is realized based on a third conversation scene corresponding to the third intention, and the second conversation scene is suspended.
Optionally, the method further comprises:
when the fourth intention is not the same as the first intention, judging whether the fourth intention is the same as the second intention;
when the fourth intent is the same as the second intent, enabling a conversation with the user based on the second conversation scenario;
when the fourth intention is different from the second intention, a conversation with the user is realized based on a fourth conversation scene corresponding to the fourth intention, and the second conversation scene is suspended.
Optionally, before suspending the first session scenario, the method further comprises:
and recording the session state between the user and the first session scene.
Optionally, the sending preset guidance session information to the user includes:
searching target guide conversation information corresponding to the recorded conversation state between the first conversation scene and the user;
and sending the target guide dialect information to a user.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, 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. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that 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 an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for switching session scenes, the method comprising:
acquiring a first message input by a user;
identifying a first intent of the user from the first message;
enabling a session with the user based on a first session scene corresponding to the first intention;
acquiring a second message input by a user in the first session scene;
identifying a second intent of the user from the second message;
and judging whether the second intention is the same as the first intention or not, if so, realizing the conversation with the user based on a second conversation scene corresponding to the second intention, and suspending the first conversation scene.
2. The method of claim 1, wherein the enabling of the session with the user based on the second session scenario corresponding to the second intent comprises:
acquiring a third message input by the user in the second session scene;
identifying a third intent of the user from the third message;
when the third intent is the same as the first intent, suspending the second session scenario and resuming the first session scenario; enabling a session with the user based on the first session scenario.
3. The method of claim 2, further comprising:
when the third intention is different from the first intention, judging whether the third intention is the same as the second intention, and when the third intention is the same as the second intention, sending preset guiding dialect information to a user to guide the user to input a message corresponding to the first intention;
receiving a fourth message input by the user;
identifying a fourth intent of the user from the fourth message;
the fourth intention is the same as the first intention, suspending the second session scenario and resuming the first session scenario;
enabling a session with the user based on the first session scenario.
4. The method of claim 3, further comprising:
when the third intention is different from the second intention, a conversation with the user is realized based on a third conversation scene corresponding to the third intention, and the second conversation scene is suspended.
5. The method of claim 3, further comprising:
when the fourth intention is not the same as the first intention, judging whether the fourth intention is the same as the second intention;
when the fourth intent is the same as the second intent, enabling a conversation with the user based on the second conversation scenario;
when the fourth intention is different from the second intention, a conversation with the user is realized based on a fourth conversation scene corresponding to the fourth intention, and the second conversation scene is suspended.
6. The method of any of claims 1-5, wherein prior to suspending the first session scenario, the method further comprises:
and recording the session state between the user and the first session scene.
7. The method of claim 6, wherein sending the preset guide dialect information to the user comprises:
searching target guide conversation information corresponding to the recorded conversation state between the first conversation scene and the user;
and sending the target guide dialect information to a user.
8. A session scene switching apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a first message input by a user;
an intention identifying unit for identifying a first intention of the user according to the first message;
a conversation unit, configured to implement a conversation with the user based on a first conversation scene corresponding to the first intention;
the acquiring unit is further configured to acquire a second message input by the user in the first session scene;
the intention identification unit is further used for identifying a second intention of the user according to the second message;
the conversation unit is further configured to determine whether the second intention is the same as the first intention, and if the second intention is different from the first intention, implement a conversation with the user based on a second conversation scene corresponding to the second intention, and suspend the first conversation scene.
9. A storage medium having stored thereon a program which, when executed by a processor, implements the session scene switching method according to any one of claims 1 to 7.
10. An electronic device comprising a memory for storing a program and a processor for executing the program, wherein the program when executed performs the session context switching method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626785.8A CN111382241A (en) | 2018-12-28 | 2018-12-28 | Session scene switching method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626785.8A CN111382241A (en) | 2018-12-28 | 2018-12-28 | Session scene switching method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111382241A true CN111382241A (en) | 2020-07-07 |
Family
ID=71216358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811626785.8A Pending CN111382241A (en) | 2018-12-28 | 2018-12-28 | Session scene switching method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382241A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010255A (en) * | 2021-03-24 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Interaction method and device based on binding session group and computer equipment |
| CN114095330A (en) * | 2020-07-29 | 2022-02-25 | 华为技术有限公司 | Intention negotiation method and device |
| WO2022060029A1 (en) * | 2020-09-16 | 2022-03-24 | 삼성전자 주식회사 | Electronic device providing information about reason why response was changed, and operation method therefor |
| CN114663114A (en) * | 2022-03-22 | 2022-06-24 | 平安科技（深圳）有限公司 | Session management method, computer and storage medium |
| CN114722171A (en) * | 2022-03-28 | 2022-07-08 | 北京百度网讯科技有限公司 | Multi-turn conversation processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN107292696A (en) * | 2017-04-27 | 2017-10-24 | 深圳虫门科技有限公司 | A kind of automobile intelligent purchase guiding system and implementation method |
| CN108197191A (en) * | 2017-12-27 | 2018-06-22 | 神思电子技术股份有限公司 | A kind of scene of more wheel dialogues is intended to interrupt method |
| CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
-
2018
- 2018-12-28 CN CN201811626785.8A patent/CN111382241A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292696A (en) * | 2017-04-27 | 2017-10-24 | 深圳虫门科技有限公司 | A kind of automobile intelligent purchase guiding system and implementation method |
| CN107247726A (en) * | 2017-04-28 | 2017-10-13 | 北京神州泰岳软件股份有限公司 | Suitable for the implementation method and device of the intelligent robot of multi-service scene |
| CN108197191A (en) * | 2017-12-27 | 2018-06-22 | 神思电子技术股份有限公司 | A kind of scene of more wheel dialogues is intended to interrupt method |
| CN108376144A (en) * | 2018-01-12 | 2018-08-07 | 上海大学 | Man-machine more wheel dialogue methods that scene based on deep neural network automatically switches |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114095330A (en) * | 2020-07-29 | 2022-02-25 | 华为技术有限公司 | Intention negotiation method and device |
| US11909600B2 (en) | 2020-07-29 | 2024-02-20 | Huawei Technologies Co., Ltd. | Intent negotiation method and apparatus |
| WO2022060029A1 (en) * | 2020-09-16 | 2022-03-24 | 삼성전자 주식회사 | Electronic device providing information about reason why response was changed, and operation method therefor |
| CN113010255A (en) * | 2021-03-24 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Interaction method and device based on binding session group and computer equipment |
| CN113010255B (en) * | 2021-03-24 | 2022-09-09 | 腾讯科技（深圳）有限公司 | Interaction method and device based on binding session group and computer equipment |
| CN114663114A (en) * | 2022-03-22 | 2022-06-24 | 平安科技（深圳）有限公司 | Session management method, computer and storage medium |
| CN114722171A (en) * | 2022-03-28 | 2022-07-08 | 北京百度网讯科技有限公司 | Multi-turn conversation processing method and device, electronic equipment and storage medium |
| CN114722171B (en) * | 2022-03-28 | 2023-10-24 | 北京百度网讯科技有限公司 | Multi-round dialogue processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111382241A (en) | Session scene switching method and device | |
| CN107610695B (en) | Dynamic adjustment method for driver voice awakening instruction word weight | |
| CN106658129B (en) | Terminal control method and device based on emotion and terminal | |
| CN109065044B (en) | Awakening word recognition method and device, electronic equipment and computer readable storage medium | |
| CN104113576A (en) | Method and device for updating client | |
| CN113990354B (en) | Audio control method, device, equipment and storage medium based on Linux | |
| CN103577516A (en) | Method and device for displaying contents | |
| CN107729897B (en) | Text operation method, device and terminal | |
| CN104933134A (en) | User feature analysis method and user feature analysis device | |
| US20190333514A1 (en) | Method and apparatus for dialoguing based on a mood of a user | |
| CN109376363A (en) | A kind of real-time voice interpretation method and device based on earphone | |
| CN109766422A (en) | Information processing method, apparatus and system, storage medium, terminal | |
| CN112735407A (en) | Conversation processing method and device | |
| CN115952272A (en) | Method, device and equipment for generating dialogue information and readable storage medium | |
| CN107957687B (en) | Method and device for controlling functions of interconnection equipment | |
| CN104063284B (en) | The method and apparatus running application program | |
| CN114373472A (en) | Audio noise reduction method, device and system and storage medium | |
| CN115545002A (en) | Method, device, storage medium and equipment for model training and business processing | |
| CN112749299A (en) | Method and device for determining video type, electronic equipment and readable storage medium | |
| CN111292725B (en) | Voice decoding method and device | |
| CN112053699A (en) | Method and device for processing game card voice change | |
| CN110941603A (en) | Data expansion method and device, storage medium and electronic equipment | |
| CN115171735A (en) | Voice activity detection method, storage medium and electronic equipment | |
| CN108922547B (en) | Identity identification method and device and electronic equipment | |
| CN112786016B (en) | Voice recognition method, device, medium and equipment |
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 |