CN109670025A - Dialogue management method and device - Google Patents
Dialogue management method and device Download PDFInfo
- Publication number
- CN109670025A CN109670025A CN201811566830.5A CN201811566830A CN109670025A CN 109670025 A CN109670025 A CN 109670025A CN 201811566830 A CN201811566830 A CN 201811566830A CN 109670025 A CN109670025 A CN 109670025A
- Authority
- CN
- China
- Prior art keywords
- dialogue
- semantic information
- state
- user semantic
- jumping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The disclosure is directed to dialogue management method and devices.This method comprises: determining current user semantic information；According to the current user semantic information, determine that is be directed to applies APP context；By user's current dialogue states, the user semantic information, the APP context of determination and the historical operation record input state machine that prestores, determine that is met jumps the corresponding Next dialog states of condition, and jumped；Wherein, the dialogue state after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps, the condition that jumps includes the APP context and historical operation record that user semantic information, the user semantic information are directed to.The technical solution can greatly simplify state machine architecture, and state machine is made to be easier to design and safeguard.
Description
Technical field
This disclosure relates to natural language processing technique field more particularly to dialogue management method and device.
Background technique
With the development of artificial intelligence technology, there are more and more man-machine conversational systems, which can
So that user can be interacted by natural language and computer, interaction flow are as follows: the voice of reception user input first
Signal, and be converted into text by speech recognition, then semantic and context is extracted by semantic understanding, then by it is semantic with
Context determines the return information provided, then generates natural-sounding by language generation and speech synthesis and play back.
Summary of the invention
The embodiment of the present disclosure provides a kind of dialogue management method and device.The technical solution is as follows:
According to the first aspect of the embodiments of the present disclosure, a kind of dialogue management method is provided, comprising:
Determine current user semantic information；
According to the current user semantic information, determine that is be directed to applies APP context；
By user's current dialogue states, the user semantic information, determination APP context and prestore history behaviour
It notes down input state machine, determines that is met jumps the corresponding Next dialog states of condition, and jumped；
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and historical operation note that user semantic information, the user semantic are directed to
Record.
In one embodiment, after being jumped, the method also includes:
According to the Next dialog states and the current user semantic information, Xiang Suoshu APP sending action data, and
Export response data.
In one embodiment, the method also includes:
Read the configuration information in configuration file；
Wherein, the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state after turning, the condition that jumps includes user semantic information, APP context and historical operation record；
The state machine is initialized according to the configuration information.
In one embodiment, the method also includes:
This jump information for jumping to Next dialog states from the current dialogue states is stored as a history behaviour
It notes down；
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
In one embodiment, the method also includes:
It controls the APP and executes the corresponding operation of the action data.
According to the second aspect of an embodiment of the present disclosure, a kind of dialogue management device is provided, comprising:
First determining module, for determining current user semantic information；
Second determining module, for according to the current user semantic information, determining that is be directed to applies APP context；
Jump module, for by user's current dialogue states, the user semantic information, determination APP context and
The historical operation record input state machine prestored determines that is met jumps the corresponding Next dialog states of condition, and is jumped；
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and historical operation note that user semantic information, the user semantic are directed to
Record.
In one embodiment, described device further include:
Output module, for according to the Next dialog states and the current user semantic information, Xiang Suoshu APP hair
Action data is sent, and exports response data.
In one embodiment, described device further include:
Read module, for reading the configuration information in configuration file；
Wherein, the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state after turning, the condition that jumps includes user semantic information, APP context and historical operation record；
Initialization module, for initializing the state machine according to the configuration information.
In one embodiment, described device further include:
Memory module, for storing this jump information for jumping to Next dialog states from the current dialogue states
For a historical operation record；
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
In one embodiment, described device further include:
Control module executes the corresponding operation of the action data for controlling the APP.
According to the third aspect of an embodiment of the present disclosure, a kind of dialogue management device is provided, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing the step in the above method.
According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, computer is stored with and refers to
It enables, the step in the above method is realized when the computer instruction is executed by processor.
The technical scheme provided by this disclosed embodiment can include the following benefits: the present embodiment can determine currently
User semantic information；According to the current user semantic information, determine that is be directed to applies APP context；User is current
Dialogue state, the user semantic information, the APP context of determination and the historical operation record input state machine that prestores, really
Surely what is met jumps the corresponding Next dialog states of condition, and is jumped；The state machine considers people, terminal and third party
Tripartite's interaction of APP, and state transition and historical operation record before, APP context-sensitive, can use simpler network
Structure realizes same complicated condition managing, greatly simplifies the structure of state machine, and the state corresponding A PP's of state machine is upper and lower
Text makes the state of APP be easier to be tracked by conversational system.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of flow chart of dialogue management method shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of dialogue management method shown according to an exemplary embodiment.
Fig. 3 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Fig. 4 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Fig. 6 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Fig. 7 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Fig. 8 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Currently, dialogue management is mainly based upon the dialogue management of tree or state machine, which usually models dialogue
To pass through the path of tree or finite state machine.This method has merged context, can use one group of limited information exchange template
To complete the modeling of dialogue.Dialog procedure is regarded as the process jumped in finite state, each state have corresponding dynamic
Make and reply, if can smoothly circulate from start node to terminal node, task is just completed.But the finite state machine
Taken into consideration only people and dialogue two side of machine interaction, and use finite state machine status jump only it is related with preceding state,
If historical information is stored in one stage structure of state machine, state machine can be made to be difficult to design and safeguard；Each state is corresponding
Be a reply language, reply that language meaning is close to be also required to design different states even if different, state machine architecture is complicated.
The present embodiment to solve the above-mentioned problems, can configure new state machine, be provided in the state machine and jump every time
When, dialogue state before jumping, jump condition and jump after dialogue state, it is described jump condition include user semantic information,
APP context and historical operation record；In this way, terminal is in acquisition user semantic information and and according to the user semantic information
After determining the application APP context being directed to, so that it may the historical operation record based on state machine and storage, from current dialogue states
Jump to Next dialog states；The dialog procedure considers tripartite's interaction of user, terminal and third party APP, and state machine
Each state transition it is related with historical operation record, the structure of state machine can be greatly simplified.
Fig. 1 is a kind of flow chart of dialogue management method shown according to an exemplary embodiment, as shown in Figure 1, this is right
Session managing method is for including the following steps 101-103 in terminal:
In a step 101, current user semantic information is determined.
Here, when human-computer dialogue starts, user can receive the voice of user to terminal input speech signal, terminal
After signal, speech recognition can be carried out to the voice signal, convert text for the voice signal, and language is carried out to the text
Justice analysis, determines current user semantic information.
In a step 102, according to the current user semantic information, determine that is be directed to applies APP context.
Here, after terminal determines current user semantic information, the application that the user semantic information is directed to can be determined, into
And the corresponding context using APP of the user semantic information can be obtained out of the APP memory space, such as user semantic
Information is directed to wechat application, then terminal needs to obtain the context of wechat application.
In step 103, by user's current dialogue states, the user semantic information, determination APP context and
The historical operation record input state machine prestored determines that is met jumps the corresponding Next dialog states of condition, and is jumped.
Here, pair after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Speech phase, the condition that jumps includes the APP context and historical operation that user semantic information, the user semantic information are directed to
Record.Therefore terminal is after getting the APP context that user semantic information and the user semantic information are directed to, so that it may will
The user semantic information, APP context and the historical operation record stored before such as history human-computer dialogue information and dialog history
State transition procedure inputs the state machine, which can determine therefrom that the condition that jumps of satisfaction completes a state transition,
Next dialog states are jumped to from current dialogue states.
It is exemplary, user when being given bonus by human-computer dialogue to Zhang San's wechat, current dialogue states be wechat enter with
The state of the communication interface of Zhang San's communication, obtaining user semantic information is " giving bonus ", at this point, the state machine is according to user semantic
Information " gives bonus ", the context of wechat application, and the historical operation record stored before is (when such as user and progress wechat give bonus
Human-computer dialogue information and dialog history state transition procedure), Next dialog states can be jumped to from current dialogue states i.e.
Wechat enters the state at the red packet interface to give bonus to Zhang San.In this way, realizing a state transition.
What needs to be explained here is that the historical operation record may include the N wheel dialogue carried out between user and terminal
History, i.e. the response that N takes turns instruction and corresponding terminal that user issues operates, which is more than or equal to 0, i.e., is talking with initial N
0, in the subsequent progress with dialogue, N is gradually increased；The initial state of the state machine one and only one, last termination shape
State at least one, the voice that user can input different semantemes jumps to different final states.
The present embodiment can configure new state machine, when being provided with each jump in the state machine, the dialogue shape before jumping
State, jump condition and jump after dialogue state, it is described jump condition include user semantic information, APP context and history behaviour
It notes down；In this way, terminal is obtaining user semantic information and and is determining that is be directed to applies APP according to the user semantic information
After context, so that it may which the historical operation record based on state machine and storage jumps to Next dialog shape from current dialogue states
State；The dialog procedure consider user, terminal and third party APP tripartite interaction, and each state transition of state machine with
Historical operation record is related, can greatly simplify the structure of state machine.
In a kind of possible embodiment, after being jumped, above-mentioned dialogue management method can also include following
Step A1.
In step A1, according to the Next dialog states and the current user semantic information, Xiang Suoshu APP is sent
Action data, and export response data.
Here, after which carries out state transition, terminal can be according to the Next dialog states and the user semantic
Information generates the APP and executes action data required for the user semantic information.Still according to above-mentioned example, state machine from
Current dialogue states jump to after Next dialog states i.e. wechat enters the state at the red packet interface to give bonus to Zhang San, and terminal can
To enter the state and user semantic information " giving bonus " at the red packet interface to give bonus to Zhang San according to the wechat, generates wechat and answer
Action data is that wechat applies the action data for entering the red packet interface to give bonus to Zhang San.
Here, terminal can also generate the response to the user according to the Next dialog states and the user semantic information
Data, still taking the above example as an example, terminal can be generated response data and " prepare to send out wechat red packet to Zhang San, please input red packet gold
Volume " etc..The terminal can also can show the response data etc. in the user interface of application with the voice output response data
Deng in this way, completing a dialog procedure between user and terminal.
The present embodiment can remove the generation of response data from state machine, can also greatly simplify state machine architecture,
State machine is set to be easier to design and safeguard.
In a kind of possible embodiment, above-mentioned dialogue management method can also include the following steps A2 to A3.
In step A2, the configuration information in configuration file is read.
In step A3, the state machine is initialized according to the configuration information.
Here, developer can store the configuration information of the state machine in the configuration file of terminal in advance, described to match
Confidence breath include dialogue state in state machine when jumping every time, before jumping, jump condition and jump after dialogue state, it is described
The condition of jumping includes user semantic information, APP context and historical operation record, and exemplary, which can use adjoining
The structure of the formal definition state machine of table, as shown in table 1 below:
Table 1
Here, the Command Line Parsing device in terminal reads this table line by line, all dialogue shapes for jumping condition, jumping front and back
State is stored in the data structure of state machine, initializes the state machine.
The present embodiment can read the configuration information in configuration file, initialize the state machine according to the configuration information,
The condition that jumps of the configuration information contains historical operation record and APP context, in this way, simpler network structure can be used
It realizes same complicated condition managing, the physical state of APP can also be tracked by APP context.
In a kind of possible embodiment, above-mentioned dialogue management method can also include the following steps B1.
In step bl is determined, this jump information for jumping to Next dialog states from the current dialogue states is stored as
Historical operation record.
Here, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping；In this way, terminal can by state transition each in history and user and
Dialogue between terminal is stored in historical operation record；To facilitate succeeding state machine to be remembered according to the historical operation of preset times
Record jump next time.
The present embodiment can by jumped to from the current dialogue states Next dialog states dialog history state transition,
The user semantic information and the response data are stored in the historical operation record, can be convenient state machine at subsequent
Jump next time according to the historical operation record.
In a kind of possible embodiment, above-mentioned dialogue management method can also include the following steps C1.
In step C1, controls the APP and execute the corresponding operation of the action data.
Here, the APP can execute the corresponding operation of the action data, still according to upper after receiving action data
Example is stated, the action data that terminal generates wechat application is that wechat applies the movement number for entering the red packet interface to give bonus to Zhang San
According to rear, so that it may control APP and execute the corresponding operation of the action data, into the red packet interface to give bonus to Zhang San.
The present embodiment can control APP and execute the corresponding operation of the action data, complete after receiving action data
Execution to user semantic information.
Realization process is discussed in detail below by several embodiments.
Fig. 2 is a kind of flow chart of dialogue management method shown according to an exemplary embodiment, as shown in Fig. 2, this is right
Session managing method can be realized by equipment such as terminals, including step 201-206.
In step 201, the configuration information in configuration file is read.
Wherein, the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state after turning, the condition that jumps includes user semantic information, APP context and historical operation record；
In step 202, the state machine is initialized according to the configuration information.
In step 203, current user semantic information is determined.
In step 204, according to the current user semantic information, determine that is be directed to applies APP context.
In step 205, by user's current dialogue states, the user semantic information, determination APP context and
The historical operation record input state machine prestored determines that is met jumps the corresponding Next dialog states of condition, and is jumped.
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and history behaviour that user semantic information, the user semantic information are directed to
It notes down.
In step 206, according to the Next dialog states and the current user semantic information, Xiang Suoshu APP hair
Action data is sent, and exports response data.
In step 207, this jump information that Next dialog states are jumped to from the current dialogue states is stored
For a historical operation record.
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
In a step 208, it controls the APP and executes the corresponding operation of the action data.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.
Fig. 3 is a kind of block diagram of dialogue management device shown according to an exemplary embodiment, which can be by soft
Part, hardware or both are implemented in combination with as some or all of of electronic equipment.As shown in figure 3, the dialogue management device
Include:
First determining module 301, for determining current user semantic information；
Second determining module 302, for according to the current user semantic information, determining that is be directed to applies APP or more
Text；
Jump module 303, for by the APP context of user's current dialogue states, the user semantic information, determination with
And the historical operation record input state machine prestored, determine that is met jumps the corresponding Next dialog states of condition, and jumped
Turn；
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and historical operation note that user semantic information, the user semantic are directed to
Record.
As a kind of possible embodiment, Fig. 4 is a kind of dialogue management device shown according to an exemplary embodiment
Block diagram, as shown in figure 4, dialogue management device disclosed above can be configured to include output module 304, in which:
Output module 304, for according to the Next dialog states and the current user semantic information, Xiang Suoshu
APP sending action data, and export response data.
As a kind of possible embodiment, Fig. 5 is a kind of dialogue management device shown according to an exemplary embodiment
Block diagram, as shown in figure 5, dialogue management device disclosed above can be configured to include read module 305 and initialization mould
Block 306, in which:
Read module 305, for reading the configuration information in configuration file；Wherein, the configuration information includes state machine
In when jumping every time, dialogue state before jumping, jump condition and jump after dialogue state, the condition that jumps includes user
Semantic information, APP context and historical operation record；
Initialization module 306, for initializing the state machine according to the configuration information.
As a kind of possible embodiment, Fig. 6 is a kind of dialogue management device shown according to an exemplary embodiment
Block diagram, as shown in fig. 6, dialogue management device disclosed above can be configured to include memory module 307, in which:
Memory module 307, for this jump information of Next dialog states will to be jumped to from the current dialogue states
It is stored as a historical operation record；
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
As a kind of possible embodiment, Fig. 7 is a kind of dialogue management device shown according to an exemplary embodiment
Block diagram, as shown in fig. 7, dialogue management device disclosed above can be configured to include control module 308, in which:
Control module 308 executes the corresponding operation of the action data for controlling the APP.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 8 is a kind of block diagram for dialogue management device shown according to an exemplary embodiment, which is suitable for
Terminal device.For example, device 800 can be mobile phone, game console, computer, tablet device, personal digital assistant etc..
Device 800 may include following one or more components: processing component 801, memory 802, power supply module 803,
Multimedia component 804, audio component 805, input/output (I/O) interface 806, sensor module 807 and communication component
808。
The integrated operation of the usual control device 800 of processing component 801, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 801 may include that one or more processors 820 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 801 may include one or more modules, just
Interaction between processing component 801 and other assemblies.For example, processing component 801 may include multi-media module, it is more to facilitate
Interaction between media component 804 and processing component 801.
Memory 802 is configured as storing various types of data to support the operation in device 800.These data are shown
Example includes the instruction of any application or method for operating on device 800, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 802 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 803 provides electric power for the various assemblies of device 800.Power supply module 803 may include power management system
System, one or more power supplys and other with for device 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 804 includes the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 804 includes a front camera and/or rear camera.When device 800 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 805 is configured as output and/or input audio signal.For example, audio component 805 includes a Mike
Wind (MIC), when device 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 802 or via communication set
Part 808 is sent.In some embodiments, audio component 805 further includes a loudspeaker, is used for output audio signal.
The interface 806 of I/O provides interface, above-mentioned peripheral interface module between processing component 801 and peripheral interface module
It can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and
Locking press button.
Sensor module 807 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor module 807 can detecte the state that opens/closes of device 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor module 807 can be with 800 1 components of detection device 800 or device
Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800
Temperature change.Sensor module 807 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 807 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 808 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 808 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 808 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 802 of instruction, above-metioned instruction can be executed by the processor 820 of device 800 to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of device 800
When device executes, so that device 800 is able to carry out above-mentioned dialogue management method, which comprises
Determine current user semantic information；
According to the current user semantic information, determine that is be directed to applies APP context；
By user's current dialogue states, the user semantic information, determination APP context and prestore history behaviour
It notes down input state machine, determines that is met jumps the corresponding Next dialog states of condition, and jumped；
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and history behaviour that user semantic information, the user semantic information are directed to
It notes down.
In one embodiment, after being jumped, the method also includes:
According to the Next dialog states and the current user semantic information, Xiang Suoshu APP sending action data, and
Export response data.
In one embodiment, the method also includes:
Read the configuration information in configuration file；
Wherein, the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state after turning, the condition that jumps includes user semantic information, APP context and historical operation record；
The state machine is initialized according to the configuration information.
In one embodiment, the method also includes:
This jump information for jumping to Next dialog states from the current dialogue states is stored as a history behaviour
It notes down；
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
In one embodiment, the method also includes:
It controls the APP and executes the corresponding operation of the action data.
The present embodiment additionally provides a kind of dialogue management device, comprising:
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
Determine current user semantic information；
According to the current user semantic information, determine that is be directed to applies APP context；
By user's current dialogue states, the user semantic information, determination APP context and prestore history behaviour
It notes down input state machine, determines that is met jumps the corresponding Next dialog states of condition, and jumped；
Wherein, after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
Dialogue state, the condition that jumps includes the APP context and history behaviour that user semantic information, the user semantic information are directed to
It notes down.
In one embodiment, above-mentioned processor can be additionally configured to:
After being jumped, the method also includes:
According to the Next dialog states and the current user semantic information, Xiang Suoshu APP sending action data, and
Export response data.
In one embodiment, above-mentioned processor can be additionally configured to:
The method also includes:
Read the configuration information in configuration file；
Wherein, the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state after turning, the condition that jumps includes user semantic information, APP context and historical operation record；
The state machine is initialized according to the configuration information.
In one embodiment, above-mentioned processor can be additionally configured to:
The method also includes:
This jump information for jumping to Next dialog states from the current dialogue states is stored as a history behaviour
It notes down；
Wherein, this described jump information include: dialogue state before this is jumped, it is the user semantic information, described
Response data and the dialogue state after jumping.
In one embodiment, above-mentioned processor can be additionally configured to:
The method also includes:
It controls the APP and executes the corresponding operation of the action data.
Those skilled in the art will readily occur to its of the disclosure after considering specification and practicing disclosure disclosed herein
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (12)
1. a kind of dialogue management method characterized by comprising
Determine current user semantic information；
According to the current user semantic information, determine that is be directed to applies APP context；
By user's current dialogue states, the user semantic information, determination APP context and prestore historical operation note
Input state machine is recorded, determines that is met jumps the corresponding Next dialog states of condition, and jumped；
Wherein, the dialogue after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
State, the condition that jumps includes the APP context and historical operation note that user semantic information, the user semantic information are directed to
Record.
2. the method according to claim 1, wherein after being jumped, the method also includes:
According to the Next dialog states and the current user semantic information, Xiang Suoshu APP sending action data, and export
Response data.
3. the method according to claim 1, wherein the method also includes:
Read the configuration information in configuration file；
Wherein, after the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state, the condition that jumps includes user semantic information, APP context and historical operation record；
The state machine is initialized according to the configuration information.
4. according to the method described in claim 2, it is characterized in that, the method also includes:
This jump information for jumping to Next dialog states from the current dialogue states is stored as a historical operation note
Record；
Wherein, this described jump information includes: dialogue state, the user semantic information, the response before this is jumped
Data and the dialogue state after jumping.
5. according to the method described in claim 2, it is characterized in that, the method also includes:
It controls the APP and executes the corresponding operation of the action data.
6. a kind of dialogue management device characterized by comprising
First determining module, for determining current user semantic information；
Second determining module, for according to the current user semantic information, determining that is be directed to applies APP context；
Jump module, for by user's current dialogue states, the user semantic information, determination APP context and prestore
Historical operation record input state machine, determine that is met jumps the corresponding Next dialog states of condition, and jumped；
Wherein, the dialogue after the dialogue state every time when jumping, before jumping is provided in the state machine, condition is jumped and jumps
State, the condition that jumps includes the APP context and historical operation record that user semantic information, the user semantic are directed to.
7. device according to claim 6, which is characterized in that described device further include:
Output module, for according to the Next dialog states and the current user semantic information, Xiang Suoshu APP to send dynamic
Make data, and exports response data.
8. device according to claim 6, which is characterized in that described device further include:
Read module, for reading the configuration information in configuration file；
Wherein, after the configuration information includes dialogue state when jumping every time in state machine, before jumping, jumps condition and jump
Dialogue state, the condition that jumps includes user semantic information, APP context and historical operation record；
Initialization module, for initializing the state machine according to the configuration information.
9. device according to claim 7, which is characterized in that described device further include:
Memory module, for this jump information for jumping to Next dialog states from the current dialogue states to be stored as one
Secondary historical operation record；
Wherein, this described jump information includes: dialogue state, the user semantic information, the response before this is jumped
Data and the dialogue state after jumping.
10. device according to claim 7, which is characterized in that described device further include:
Control module executes the corresponding operation of the action data for controlling the APP.
11. a kind of dialogue management device characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to perform claim requires the step in any one of 1 to 5 the method.
12. a kind of computer readable storage medium, is stored with computer instruction, which is characterized in that the computer instruction is located
Manage the step realized in any one of claim 1 to 5 the method when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811566830.5A CN109670025B (en) | 2018-12-19 | 2018-12-19 | Dialogue management method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811566830.5A CN109670025B (en) | 2018-12-19 | 2018-12-19 | Dialogue management method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109670025A true CN109670025A (en) | 2019-04-23 |
| CN109670025B CN109670025B (en) | 2023-06-16 |
Family
ID=66145059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811566830.5A Active CN109670025B (en) | 2018-12-19 | 2018-12-19 | Dialogue management method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109670025B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104502A (en) * | 2019-12-24 | 2020-05-05 | 携程计算机技术（上海）有限公司 | Dialogue management method, system, electronic device and storage medium for outbound system |
| CN111652001A (en) * | 2020-06-04 | 2020-09-11 | 联想(北京)有限公司 | Data processing method and device |
| CN113779214A (en) * | 2021-08-17 | 2021-12-10 | 深圳市人马互动科技有限公司 | Automatic generation method and device of jump condition, computer equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020133355A1 (en) * | 2001-01-12 | 2002-09-19 | International Business Machines Corporation | Method and apparatus for performing dialog management in a computer conversational interface |
| CN105589848A (en) * | 2015-12-28 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Dialog management method and device |
| CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
| US20160294771A1 (en) * | 2014-01-22 | 2016-10-06 | Tencent Technology (Shenzhen) Company Limited | Apparatus, Method, And Client For Synchronizing Jump Context |
| CN106575396A (en) * | 2014-08-15 | 2017-04-19 | 微软技术许可有限责任公司 | Quick navigation of message conversation history |
| CN106874259A (en) * | 2017-02-23 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of semantic analysis method and device, equipment based on state machine |
| CN106911812A (en) * | 2017-05-05 | 2017-06-30 | 腾讯科技（上海）有限公司 | A kind of processing method of session information, server and computer-readable recording medium |
| CN108846030A (en) * | 2018-05-28 | 2018-11-20 | 苏州思必驰信息科技有限公司 | Access method, system, electronic equipment and the storage medium of official website |
-
2018
- 2018-12-19 CN CN201811566830.5A patent/CN109670025B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020133355A1 (en) * | 2001-01-12 | 2002-09-19 | International Business Machines Corporation | Method and apparatus for performing dialog management in a computer conversational interface |
| US20160294771A1 (en) * | 2014-01-22 | 2016-10-06 | Tencent Technology (Shenzhen) Company Limited | Apparatus, Method, And Client For Synchronizing Jump Context |
| CN106575396A (en) * | 2014-08-15 | 2017-04-19 | 微软技术许可有限责任公司 | Quick navigation of message conversation history |
| CN105589848A (en) * | 2015-12-28 | 2016-05-18 | 百度在线网络技术（北京）有限公司 | Dialog management method and device |
| CN105845137A (en) * | 2016-03-18 | 2016-08-10 | 中国科学院声学研究所 | Voice communication management system |
| CN106874259A (en) * | 2017-02-23 | 2017-06-20 | 腾讯科技（深圳）有限公司 | A kind of semantic analysis method and device, equipment based on state machine |
| CN106911812A (en) * | 2017-05-05 | 2017-06-30 | 腾讯科技（上海）有限公司 | A kind of processing method of session information, server and computer-readable recording medium |
| CN108846030A (en) * | 2018-05-28 | 2018-11-20 | 苏州思必驰信息科技有限公司 | Access method, system, electronic equipment and the storage medium of official website |
Non-Patent Citations (1)
| Title |
|---|
| 王菁华,钟义信,王枞,刘建毅: "口语对话管理综述", 计算机应用研究 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104502A (en) * | 2019-12-24 | 2020-05-05 | 携程计算机技术（上海）有限公司 | Dialogue management method, system, electronic device and storage medium for outbound system |
| CN111652001A (en) * | 2020-06-04 | 2020-09-11 | 联想(北京)有限公司 | Data processing method and device |
| CN113779214A (en) * | 2021-08-17 | 2021-12-10 | 深圳市人马互动科技有限公司 | Automatic generation method and device of jump condition, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109670025B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6811758B2 (en) | Voice interaction methods, devices, devices and storage media | |
| CN110634483B (en) | Man-machine interaction method and device, electronic equipment and storage medium | |
| CN110224901A (en) | Intelligent device interaction, device and storage medium | |
| CN108538291A (en) | Sound control method, terminal device, cloud server and system | |
| CN105975156B (en) | Application interface display methods and device | |
| CN104951335B (en) | The processing method and processing device of application program installation kit | |
| CN105389304B (en) | Event Distillation method and device | |
| CN113168227A (en) | Method of performing function of electronic device and electronic device using the same | |
| CN107945806B (en) | User identification method and device based on sound characteristics | |
| CN106791921A (en) | The processing method and processing device of net cast | |
| CN110619873A (en) | Audio processing method, device and storage medium | |
| CN105516485B (en) | The way of recording and device | |
| CN109670025A (en) | Dialogue management method and device | |
| CN104539871B (en) | Multimedia session method and device | |
| CN109445879A (en) | Method, storage medium and the equipment of monitor video are shown with suspended window | |
| CN108710791A (en) | The method and device of voice control | |
| CN110349578A (en) | Equipment wakes up processing method and processing device | |
| CN106990812A (en) | USB connector and terminal device | |
| CN115273831A (en) | Voice conversion model training method, voice conversion method and device | |
| CN109036404A (en) | Voice interactive method and device | |
| JP7240445B2 (en) | AUDIO PROCESSING METHOD, APPARATUS, TERMINAL AND STORAGE MEDIUM | |
| CN105323383B (en) | The method of adjustment and device of mobile phone bell volume | |
| WO2023040658A1 (en) | Speech interaction method and electronic device | |
| CN109451135A (en) | Contact person's creation method and device | |
| CN110012359A (en) | Answer reminding method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |