CN110196927A - It is a kind of to take turns interactive method, device and equipment more - Google Patents
It is a kind of to take turns interactive method, device and equipment more Download PDFInfo
- Publication number
- CN110196927A CN110196927A CN201910383367.9A CN201910383367A CN110196927A CN 110196927 A CN110196927 A CN 110196927A CN 201910383367 A CN201910383367 A CN 201910383367A CN 110196927 A CN110196927 A CN 110196927A
- Authority
- CN
- China
- Prior art keywords
- user
- reply data
- instruction
- client
- server
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Telephonic Communication Services (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The embodiment of the invention discloses one kind to take turns interactive method, device and equipment more, this method comprises: client obtains user's interactive voice that user inputs under current session round, and parses to be analyzed the instruction;The client is if it is determined that be that return instruction, then acquisition and the message identification of the matched upper level machine reply data of machine reply data of the current session round are sent to server;The client receives the confirmation returning response of the server, and the upper level machine reply data of storage is presented to the user.The technical solution of the embodiment of the present invention, when client parsing user's interactive voice is return instruction, by sending message identification and obtaining the confirmation returning response of server, corresponding machine reply data is transferred to be presented to the user, realize more wheels dialogue between man-machine, user experience is improved, while reducing the data bandwidth of client occupancy, saves server resource.
Description
Technical field
The present embodiments relate to human-computer interaction technique field, more particularly to a kind of more wheel interactive methods, device and
Equipment.
Background technique
With being constantly progressive for software technology, various application programs (Application, abbreviation APP) are appeared in
In the people visual field, voice interactive function has become as an invisible tie between user and application program using journey
A particularly important component part in sequence exploitation.
The application program developed at present is all using single-wheel session, for example, user exists in the conversation procedure of interactive voice
Say " nearby have what nice ", what voice interactive function returned is cuisines list, user it may be said that dining room name or column
The index number of table, such as " first ", into the details interface to the dining room, when user does not like the dining room or wants to check
When other dining rooms, then user needs to re-enter " nearby having anything to be fond of eating ".
Such interactive voice mode is needed logically there are larger defect, the especially relevance between shortage context
Server is wanted repeatedly to provide identical session content, especially when the level of user conversation is more, user generally requires frequently defeated
Enter the same problem, after repeatedly screening, gets to the dialogue level needed, considerably increase interaction times, extend
Session duration.
Summary of the invention
Take turns interactive method, device and equipment the embodiment of the invention provides one kind realizes more wheels between man-machine more
Dialogue ensure that the accuracy that data are presented, and avoids client and repeats to obtain identical data content, saves server money
Source.
In a first aspect, the embodiment of the invention provides one kind to take turns interactive method more, comprising:
Client obtains user's interactive voice that user inputs under current session round, and to user's interactive voice
Instruction parsing is carried out, is analyzed the instruction;
The client then obtains the machine with the current session round if it is determined that described analyze the instruction as return instruction
The message identification of the matched upper level machine reply data of reply data is sent to server;
The client determines institute according to the server feedback and the message identification matched confirmation returning response
It states user's interactive voice and meets historical machine reply data request condition, and be in by the upper level machine reply data of storage
Now give user.
Second aspect, the embodiment of the invention provides one kind to take turns interactive method more, comprising:
Server receives user's interactive voice that the user that client is sent inputs under current session round;
The server is if it is determined that user's interactive voice is return instruction, then acquisition and the current session round
The message identification of the matched upper level machine reply data of machine reply data, and feed back and the matched confirmation of the message identification
Returning response determines that user's interactive voice meets historical machine reply data request condition;
The server is using the upper level machine reply data as current machine reply data, so that the server
Keep data synchronous with the client.
The third aspect, the embodiment of the invention provides one kind to take turns human-computer dialogue device more, is applied in client, comprising:
Command analysis module, the user's interactive voice inputted under current session round for obtaining user, and to described
User's interactive voice carries out instruction parsing, is analyzed the instruction;
Message identification obtains module, for if it is determined that described analyze the instruction as return instruction, then obtain with it is described currently right
The message identification for talking about the matched upper level machine reply data of machine reply data of round is sent to server;
Module is presented in machine reply data, for according to the server feedback and the message identification matched confirmation
Returning response determines that user's interactive voice meets historical machine reply data request condition, and by described upper the one of storage
Grade machine reply data is presented to the user.
Fourth aspect, the embodiment of the invention provides one kind to take turns human-computer dialogue device more, is applied in server, comprising:
User's interactive voice obtains module, the use that the user for receiving client transmission inputs under current session round
Family interactive voice;
Instruct respond module, be used for if it is determined that user's interactive voice be return instruction, then obtain with it is described currently it is right
The message identification of the matched upper level machine reply data of machine reply data of round is talked about, and is fed back and the message identification
The confirmation returning response matched determines that user's interactive voice meets historical machine reply data request condition;
First data simultaneous module, for using the upper level machine reply data as current machine reply data, with
The server is set to keep data synchronous with the client.
5th aspect, the embodiment of the invention provides a kind of equipment, the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes more wheel interactive methods described in any embodiment of that present invention.
6th aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes more wheel interactive methods described in any embodiment of that present invention when the program is executed by processor.
The technical solution of the embodiment of the present invention parses user's interactive voice by client, in user's interaction language
When sound is return instruction, the message identification of storage is sent to server, and after receiving the confirmation returning response of server, this
Ground is transferred corresponding machine reply data and is presented to the user, and realizes more wheels dialogue between man-machine, improves user experience, and
By demonstrating the validity of message identification, the accuracy that data are presented ensure that, meanwhile, reduce the data of client occupancy
Bandwidth avoids and repeats to obtain identical data content from server, saves server resource.
Detailed description of the invention
Figure 1A is the flow chart for more wheel interactive methods that the embodiment of the present invention one provides;
Figure 1B is the data flowchart for more wheel interactive methods that the embodiment of the present invention one provides;
Fig. 2A is the flow chart of more wheel interactive methods provided by Embodiment 2 of the present invention;
Fig. 2 B is the data flowchart of more wheel interactive methods provided by Embodiment 2 of the present invention;
Fig. 3 is the structural block diagram for more wheel human-computer dialogue devices that the embodiment of the present invention three provides;
Fig. 4 is the structural block diagram for more wheel human-computer dialogue devices that the embodiment of the present invention four provides;
Fig. 5 is the structural block diagram for the equipment that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Figure 1A is the flow chart for the more wheel interactive methods of one kind that the embodiment of the present invention one provides, and the present embodiment is applicable
Carry out the case where taking turns human-computer dialogue in user and client, this method can be by more wheel human-computer dialogues in the embodiment of the present invention more
Device executes, which can be by software and or hardware realization, and generally can integrate and to provide human-computer interaction function
In client, it is used cooperatively with the server for providing machine reply data, typically, can integrate in vehicle mounted guidance client
In, this method specifically comprises the following steps:
S110, client obtain user's interactive voice that user inputs under current session round, and hand over the user
Mutual voice carries out instruction parsing, is analyzed the instruction.
Client (Client) is that the application program of local service is provided for user, is mounted in the client computer of user, example
Such as, it is mounted in the electronic equipments such as mobile phone and computer;It is mounted in the communication device of the vehicles such as automobile, train and aircraft.
Client includes diversified forms, for example, browsing the browser and various types of application programs that webpage uses
(Application, APP) etc..Optionally, in embodiments of the present invention, to the type of client and client is installed
Client type is not especially limited.
Client in the embodiment of the present invention is that have the client of human-computer interaction function, the interaction language of available user
Sound.In current session, client carries out instruction parsing when getting user's interactive voice, to user's interactive voice,
It is analyzed the instruction.Optionally, in embodiments of the present invention, automatic speech recognition (Automatic Speech is utilized
Recognition, abbreviation ASR) and technology and/or natural language understanding (Natural Language Understanding, referred to as
NLU) technology carries out instruction parsing to user's interactive voice, is analyzed the instruction.ASR is will be in the vocabulary in human speech
Appearance is converted to computer-readable input, such as key, binary coding or character string etc..NLU is then to focus on text
Semanteme, i.e., content of text is converted into text semantic, the precise meaning of word is not important in text, it is important that text pass
The semantic information reached.
S120, the client then obtain and the current session round if it is determined that described analyze the instruction as return instruction
The message identification of the matched upper level machine reply data of machine reply data be sent to server.
Client is according to the instruction after parsing, if it is confirmed that being return instruction;The return instruction is looking into for user's sending
Take a fancy to the instruction of level-one machine reply data;If the machine reply data of current session round is based on another machine answer number
What the relevant information in obtained, then the machine reply data of the current session round is answered as another described machine
The next stage machine reply data of answer evidence, another described machine reply data are then used as the machine response of current session round
The upper level machine reply data of data;For example, identifying includes keys such as " returns ", " upper level " or " gravity treatment " in instruction
Word then assert that the instruction is return instruction, then client obtains the machine reply data with the current session round at this time
The message identification of matched upper level machine reply data is simultaneously sent to server.For example, user is " attached by issuing voice messaging
Close cuisines ", client provide corresponding " cuisines list ", are somebody's turn to do " cuisines list " and are used as first order machine reply data;?
Under the dialogue, user again by issue voice messaging selection " cuisines list " in " cuisines title " or " index number " with
The details of one of cuisines are checked, then the details for the cuisines that client provides then are used as second level machine to answer
Answer evidence, first order machine reply data are the upper level machine reply data of second level machine reply data.Each machine
Device reply data can all generate a matching and unique message identification, when generating for indicating the machine response
Data, therefore, client is under the machine reply data of current session round namely under the dialogue of the details of the cuisines,
When getting return instruction, then search the corresponding message identification of machine reply data of upper level, i.e., " cuisines list " it is corresponding
Message identification, and it is sent to server.
S130, the client according to the server feedback and the message identification matched confirmation returning response,
Determine that user's interactive voice meets historical machine reply data request condition, and by the upper level machine response of storage
Data are presented to the user.
If client gets the confirmation returning response of server feedback, illustrate that the message identification is effective, for example, above-mentioned
" cuisines list " corresponding message identification has determined that user's interactive voice meets historical machine reply data request item
Part, client will be stored in the upper level machine reply data of local current machine reply data, the i.e. detailed letter of the cuisines
The upper level machine reply data " cuisines list " of breath is presented to the user.Particularly, machine reply data can with voice and/or
The mode of textual list is presented to the user, and can also be presented to the user in other ways, in embodiments of the present invention, optionally,
The presentation mode of machine reply data is not especially limited.
If client gets the message identification illegal command of server feedback or does not receive service within the set time
The confirmation returning response of device feedback, then notify user's return instruction invalid in the form of voice and/or text, so that user's weight
It is new to carry out interactive voice.
Optionally, in embodiments of the present invention, the use that user inputs under current session round is obtained in the client
Family interactive voice, and instruction parsing is carried out to user's interactive voice, after being analyzed the instruction, the client if it is determined that
It is described to analyze the instruction as irrevocable instruction, then described analyze the instruction is sent to server, so that the server is searched and institute
It states and analyzes the instruction matched machine reply data and generate and the matched message identification of machine reply data;It is described irrevocable
Instruction, is other user instructions in addition to return instruction;Particularly, if identify in user instruction do not include " return ", " on
The keywords such as level-one " and " gravity treatment " will the user instruction be considered as irrevocable instruction, for example, the dialogue of current round is client root
" the cuisines list " provided according to the voice messaging " cuisines of attachment " that user issues, the voice messaging that user issues again are
" neighbouring supermarket ", client confirm that this is analyzed the instruction as irrevocable instruction according to the instruction after parsing, then at this time will parsing
Instruction is sent to server so that the server search with " neighbouring supermarket " matched " supermarket's list " and generate with it is " super
The matched message identification of city's list ";If client get as the server send described in " supermarket's list " and with institute
" supermarket's list " matched message identification is stated, then is locally stored, and by described in " supermarket's list " is presented to the user.
The technical solution of the embodiment of the present invention parses user's interactive voice by client, in user's interaction language
When sound is return instruction, the message identification of storage is sent to server, and after receiving the confirmation returning response of server, this
Ground is transferred corresponding machine reply data and is presented to the user, and realizes more wheels dialogue between man-machine, improves user experience, and
By demonstrating the validity of message identification, the accuracy that data are presented ensure that, meanwhile, reduce the data of client occupancy
Bandwidth avoids and repeats to obtain identical data content from server, saves server resource.
Concrete application scene one
Figure 1B is the more wheel human-computer dialogues of one kind that concrete application scene one of the present invention provides on the basis of the above embodiments
The data flowchart of method, the data flow are as follows:
Client obtains user's interactive voice that user inputs under current session round and parses;Client determines parsing
Instruction afterwards is return instruction;Client obtains the matched upper level machine of machine reply data with the current session round
The message identification of reply data;The message identification is sent to server by client;Server receives the letter that client is sent
Breath mark;Message identification described in server authentication is effective;Server generates and the matched confirmation returning response of the message identification,
And current machine reply data is updated, it is synchronous with the data of client to guarantee;Server sends the confirmation returning response
To client;Client receives the confirmation returning response that server is sent;Client determines that user's interactive voice meets history machine
Device reply data request condition;The upper level machine reply data of storage is presented to the user by client.
The technical solution of the embodiment of the present invention parses user's interactive voice by client, in user's interaction language
When sound is return instruction, the message identification of storage is sent to server, and after receiving the confirmation returning response of server, this
Ground is transferred corresponding machine reply data and is presented to the user, and realizes more wheels dialogue between man-machine, improves user experience, and
By demonstrating the validity of message identification, the accuracy that data are presented ensure that, meanwhile, reduce the data of client occupancy
Bandwidth avoids and repeats to obtain identical data content from server, saves server resource.
Embodiment two
Fig. 2A is a kind of flow chart of more wheel interactive methods provided by Embodiment 2 of the present invention, and the present embodiment is applicable
Carry out the case where taking turns human-computer dialogue in user and client, this method can be by more wheel human-computer dialogues in the embodiment of the present invention more
Device executes, which can be by software and or hardware realization, and generally can integrate and to handle function with human-computer dialogue
In the server of energy, it is used cooperatively with the client for obtaining user's interactive voice, typically, can integrate in vehicle mounted guidance service
In device, this method specifically comprises the following steps:
S210, server receive user's interactive voice that the user that client is sent inputs under current session round.
S220, the server are if it is determined that user's interactive voice is return instruction, then acquisition and the current session
The message identification of the matched upper level machine reply data of the machine reply data of round, and feed back and matched with the message identification
Confirmation returning response, determine that user's interactive voice meets historical machine reply data request condition.
Optionally, in embodiments of the present invention, server determines user's interactive voice according to ASR technology and/or NLU technology
It whether is return instruction;If server determines that user's interactive voice is return instruction, obtain and the current session round
The message identification of the matched upper level machine reply data of machine reply data;If the message identification can be got, prove
The return instruction is effective, then confirmation returning response is sent to client, so that the return instruction of client end response user;If cannot
The message identification is got, then proves that the return instruction is invalid, sends invalid returning response to client, so that client is logical
Know that user's return instruction is invalid.
Optionally, in embodiments of the present invention, the effective time that can be identified with set information, server is within effective time
The message identification is saved, more than deleting the message identification after effective time, namely the message identification, the information can not be inquired again
Indicating failure;For example, using the machine reply data of current session round in above-described embodiment as the detailed data of cuisines, and information
The effective time of mark be ten minutes for, if server at a time determine user's interactive voice be return instruction,
The difference time if the moment and upper level machine reply data, i.e., between the generation time of the message identification of " cuisines list "
Less than or equal to ten minutes, then the message identification still saves in the server, server is available to arrive the message identification,
I.e. the message identification is effective.The different message identification holding times can also be set according to the level of user, for example, VIP
User sets the longer message identification holding time, and ordinary user sets the shorter message identification holding time.
Optionally, the message identification includes cryptographic Hash;Cryptographic Hash is by certain hash algorithm, such as MD5 message
Digest algorithm (MD5Message-Digest Algorithm) and secure hash algorithm 1 (Secure Hash Algorithm 1,
Abbreviation SHA-1) etc., one section of longer data is mapped as the process compared with short data, the relatively short data after mapping is exactly this compared with long number
According to cryptographic Hash.In embodiments of the present invention, the algorithm for obtaining cryptographic Hash use is not especially limited.Particularly, for same
The user of one time identical content requests, for example, same time different user issues same interactive voice " neighbouring cuisines ",
Due to user present position and the difference of hierarchy of users, the machine reply data for inquiring acquisition is not also identical, i.e., data source is not
Together, thus also not identical according to the cryptographic Hash of machine reply data generation, therefore, having uniqueness using cryptographic Hash, this is special
Point can accurately distinguish different machine reply datas using cryptographic Hash as message identification.
Server feedback confirmation returning response corresponding with message identification, had both been utilized the uniqueness of message identification, guaranteed
The accuracy of response, while in turn avoiding sending same machine reply data to client again, reduce client and accounts for
Data bandwidth saves server communication resource.
S230, the server are using the upper level machine reply data as current machine reply data, so that described
Server keeps data synchronous with the client.
Server is while sending confirmation returning response to client, using the upper level machine reply data as working as
Preceding machine reply data, so that the server keeps data synchronous with the client.
Optionally, in embodiments of the present invention, the user of client transmission is received under current session round in server
After user's interactive voice of input, the server if it is determined that user's interactive voice be irrevocable instruction, then obtain with
The matched machine reply data of user's interactive voice, generation and the matched message identification of machine reply data, by institute
It states machine reply data and the message identification feeds back to the client, so that the client is by the machine reply data
It is presented to the user;For example, the voice messaging that current round dialogue is server parsing user is " cuisines of attachment ", and then provide
" cuisines list " is used as current machine reply data, and server obtains the interactive voice of the user again, and resolve to " near
Supermarket " when, it is determined that this is analyzed the instruction as irrevocable instruction, then obtain it is matched " supermarket's list " with " neighbouring supermarket ",
And generate with " supermarket's list " matched message identification, server by " supermarket's list " and with " supermarket's list " matched information
Mark is sent to client, so that " supermarket's list " is presented to the user by client, meanwhile, server is by " supermarket's list " conduct
Current machine reply data, it is synchronous with the data of client to guarantee.
The technical solution of the embodiment of the present invention parses user's interactive voice by server, in user's interaction language
When sound is return instruction, according to message identification transmission confirmation returning response to client, and current machine reply data is updated, with
It keeps synchronous with the data of client, realizes more wheels dialogue between man-machine, improve user experience, and by demonstrating letter
The validity for ceasing mark ensure that the data between accuracy and client and server that data are presented are synchronous, meanwhile, it keeps away
Exempt from server to repeat to send identical data content to same client, saves the communication resource.
Concrete application scene two
Fig. 2 B is the more wheel human-computer dialogues of one kind that concrete application scene two of the present invention provides on the basis of the above embodiments
The data flowchart of method, the data flow are as follows:
Client obtains user's interactive voice that user inputs under current session round;Client is interactive by the user
Voice is sent to server;Server receives user's interactive voice that client is sent, and parses;Server determines the user
Interactive voice is return instruction;Server obtains the matched upper level machine of machine reply data with the current session round
The message identification of reply data;Server generates and the matched confirmation returning response of the message identification, and updates current machine
Reply data;Server will be sent to client with the matched confirmation returning response of the message identification;Client receives service
The confirmation returning response that device is sent;The upper level machine reply data of storage is presented to the user by client.
The technical solution of the embodiment of the present invention parses user's interactive voice by server, in user's interaction language
When sound is return instruction, according to message identification transmission confirmation returning response to client, and current machine reply data is updated, with
It keeps synchronous with the data of client, realizes more wheels dialogue between man-machine, improve user experience, and by demonstrating letter
The validity for ceasing mark ensure that the data between accuracy and client and server that data are presented are synchronous, meanwhile, it keeps away
Exempt from server to repeat to send identical data content to same client, saves the communication resource.
Embodiment three
Fig. 3 is the structural block diagram of the more wheel human-computer dialogue devices of one kind provided by the embodiment of the present invention three, the device application
In client, specifically include: command analysis module 310, message identification obtain module 320 and module is presented in machine reply data
330。
Command analysis module 310, the user's interactive voice inputted under current session round for obtaining user, and to institute
It states user's interactive voice and carries out instruction parsing, analyzed the instruction;
Message identification obtains module 320, for if it is determined that described analyze the instruction as return instruction, then obtain with it is described current
The message identification of the matched upper level machine reply data of the machine reply data of dialog turns is sent to server;
Module 330 is presented in machine reply data, for according to the matched with the message identification of the server feedback
Confirm returning response, determines that user's interactive voice meets historical machine reply data request condition, and will be described in storage
Upper level machine reply data is presented to the user.
The technical solution of the embodiment of the present invention parses user's interactive voice by client, in user's interaction language
When sound is return instruction, the message identification of storage is sent to server, and after receiving the confirmation returning response of server, this
Ground is transferred corresponding machine reply data and is presented to the user, and realizes more wheels dialogue between man-machine, improves user experience, and
By demonstrating the validity of message identification, the accuracy that data are presented ensure that, meanwhile, reduce the data of client occupancy
Bandwidth avoids and repeats to obtain identical data content from server, saves server resource.
It is optionally, take turns human-computer dialogue device on the basis of the various embodiments described above more, further includes:
Irrevocable instruction determining module, for if it is determined that described analyze the instruction as irrevocable instruction, then referring to the parsing
Order is sent to server so that the server search with it is described analyze the instruction matched machine reply data and generation with it is described
The matched message identification of machine reply data;
Module is locally stored, if for get the machine reply data sent by the server and with it is described
The matched message identification of machine reply data, then be locally stored, and the machine reply data is presented to the user.
Optionally, on the basis of the various embodiments described above, command analysis module 310 is specifically used for:
Instruction solution is carried out to user's interactive voice using automatic speech recognition technology and/or natural language understanding technology
Analysis, is analyzed the instruction.
More wheel interactive methods provided by any embodiment of the invention can be performed in above-mentioned apparatus, have execution method phase
The functional module and beneficial effect answered.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is arbitrarily implemented
The method that example provides.
Example IV
Fig. 4 is the structural block diagram of the more wheel human-computer dialogue devices of one kind provided by the embodiment of the present invention four, the device application
In server, specifically include: user's interactive voice obtains module 410, instruction respond module 420 and the first data simultaneous module
430。
User's interactive voice obtains module 410, and the user for receiving client transmission inputs under current session round
User's interactive voice;
Instruct respond module 420, be used for if it is determined that user's interactive voice is return instruction, then obtain with it is described current
The message identification of the matched upper level machine reply data of the machine reply data of dialog turns, and feed back and the message identification
Matched confirmation returning response determines that user's interactive voice meets historical machine reply data request condition;
First data simultaneous module 430, for using the upper level machine reply data as current machine reply data,
So that the server keeps data synchronous with the client.
The technical solution of the embodiment of the present invention parses user's interactive voice by server, in user's interaction language
When sound is return instruction, according to message identification transmission confirmation returning response to client, and current machine reply data is updated, with
It keeps synchronous with the data of client, realizes more wheels dialogue between man-machine, improve user experience, and by demonstrating letter
The validity for ceasing mark ensure that the data between accuracy and client and server that data are presented are synchronous, meanwhile, it keeps away
Exempt from server to repeat to send identical data content to same client, saves the communication resource.
It is optionally, take turns human-computer dialogue device on the basis of the various embodiments described above more, further includes:
Machine reply data sending module, be used for if it is determined that user's interactive voice be irrevocable instruction, then obtain with
The matched machine reply data of user's interactive voice, generation and the matched message identification of machine reply data, by institute
It states machine reply data and the message identification feeds back to the client, so that the client is by the machine reply data
It is presented to the user;
Second data simultaneous module is used for using the machine reply data as current machine reply data, so that described
Server keeps data synchronous with the client.
Optionally, on the basis of the various embodiments described above, the message identification includes cryptographic Hash.
More wheel interactive methods provided by any embodiment of the invention can be performed in above-mentioned apparatus, have execution method phase
The functional module and beneficial effect answered.The not technical detail of detailed description in the present embodiment, reference can be made to the present invention is arbitrarily implemented
The method that example provides.
Embodiment five
Fig. 5 is the structural schematic diagram for more wheel man-machine dialogue equipments that the embodiment of the present invention five provides, as shown in figure 5, this sets
Standby includes processor 50, memory 51, input unit 52 and output device 53;The quantity of processor 50 can be one in equipment
Or it is multiple, in Fig. 5 by taking a processor 50 as an example;Device handler 50, memory 51, input unit 52 and output device 53 can
To be connected by bus or other modes, in Fig. 5 for being connected by bus.
Memory 51 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, such as the corresponding module of more wheel human-computer dialogue devices (the instruction solution by client executing in the embodiment of the present invention
Analyse module 310, message identification obtains module 320 and module 330 is presented in machine reply data).Alternatively, as in the embodiment of the present invention
(user's interactive voice obtains module 410, instruction respond module to the corresponding module of more wheel human-computer dialogue devices executed by server
420 and first data simultaneous module 430) processor 50 be stored in memory 51 by operation software program, instruction and
Module realizes above-mentioned more wheel interactive methods thereby executing the various function application and data processing of equipment.
Memory 51 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 51 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 51 can be further
Including the memory remotely located relative to processor 50, these remote memories can pass through network connection to equipment.It is above-mentioned
The example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 52 can be used for receiving the number or character information of input, and generate with the user setting of equipment and
The related key signals input of function control.Output device 53 may include that display screen etc. shows equipment.
Embodiment six
The embodiment of the present invention six additionally provides a kind of computer readable storage medium, and the computer readable storage medium exists
For executing more wheel interactive methods when being executed by computer processor, this method comprises:
Client obtains user's interactive voice that user inputs under current session round, and to user's interactive voice
Instruction parsing is carried out, is analyzed the instruction;
The client then obtains the machine with the current session round if it is determined that described analyze the instruction as return instruction
The message identification of the matched upper level machine reply data of reply data is sent to server;
The client determines institute according to the server feedback and the message identification matched confirmation returning response
It states user's interactive voice and meets historical machine reply data request condition, and be in by the upper level machine reply data of storage
Now give user.
Alternatively, the computer readable storage medium by computer processor when being executed for executing more wheel human-computer dialogues
Method, this method comprises:
Server receives user's interactive voice that the user that client is sent inputs under current session round;
The server is if it is determined that user's interactive voice is return instruction, then acquisition and the current session round
The message identification of the matched upper level machine reply data of machine reply data, and feed back and the matched confirmation of the message identification
Returning response determines that user's interactive voice meets historical machine reply data request condition;
The server is using the upper level machine reply data as current machine reply data, so that the server
Keep data synchronous with the client.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
It is man-machine that more wheels provided by any embodiment of the invention can also be performed in the method operation that executable instruction is not limited to the described above
Relevant operation in dialogue method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of above-mentioned more wheel human-computer dialogue device, included modules only according to
What function logic was divided, but be not limited to the above division, as long as corresponding functions can be realized;In addition, each
The specific name of functional module is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (12)
1. a kind of more wheel interactive methods characterized by comprising
Client obtains user's interactive voice that user inputs under current session round, and carries out to user's interactive voice
Instruction parsing, is analyzed the instruction;
The client is if it is determined that described analyze the instruction as return instruction, then the machine response of acquisition and the current session round
The message identification of the upper level machine reply data of Data Matching is sent to server;
The client determines the use according to the server feedback and the message identification matched confirmation returning response
Family interactive voice meets historical machine reply data request condition, and the upper level machine reply data of storage is presented to
User.
2. the method according to claim 1, wherein obtaining user under current session round in the client
User's interactive voice of input, and instruction parsing is carried out to user's interactive voice, after being analyzed the instruction, comprising:
Described analyze the instruction then is sent to server if it is determined that described analyze the instruction as irrevocable instruction by the client, with
It searches the server and analyzes the instruction matched machine reply data and generation is matched with the machine reply data with described
Message identification;
If the client get the machine reply data sent by the server and with the machine answer number
It according to matched message identification, is then locally stored, and the machine reply data is presented to the user.
3. method according to claim 1 or 2, which is characterized in that described to carry out instruction solution to user's interactive voice
Analysis, is analyzed the instruction, comprising: using automatic speech recognition technology and/or natural language understanding technology to user interaction
Voice carries out instruction parsing, is analyzed the instruction.
4. a kind of more wheel interactive methods characterized by comprising
Server receives user's interactive voice that the user that client is sent inputs under current session round;
The server then obtains and the machine of the current session round if it is determined that user's interactive voice is return instruction
The message identification of the matched upper level machine reply data of reply data, and feed back and returned with the matched confirmation of the message identification
Response, determines that user's interactive voice meets historical machine reply data request condition;
The server is using the upper level machine reply data as current machine reply data, so that the server and institute
Stating client keeps data synchronous.
5. according to the method described in claim 4, it is characterized in that, receiving the user of client transmission current right in server
After the user's interactive voice inputted under words round, comprising:
The server is if it is determined that user's interactive voice is irrevocable instruction, then acquisition is matched with user's interactive voice
Machine reply data, generate with the matched message identification of machine reply data, by the machine reply data and described
Message identification feeds back to the client, so that the machine reply data is presented to the user by the client;
The server is using the machine reply data as current machine reply data, so that the server and the client
End keeps data synchronous.
6. according to the method described in claim 4, it is characterized in that, the message identification includes cryptographic Hash.
7. a kind of more wheel human-computer dialogue devices, are applied in client characterized by comprising
Command analysis module, the user's interactive voice inputted under current session round for obtaining user, and to the user
Interactive voice carries out instruction parsing, is analyzed the instruction;
Message identification obtains module, for if it is determined that described analyze the instruction as return instruction, then obtaining and the current session wheel
The message identification of the matched upper level machine reply data of secondary machine reply data is sent to server;
Module is presented in machine reply data, for returning with the matched confirmation of the message identification according to the server feedback
Response determines that user's interactive voice meets historical machine reply data request condition, and by the upper level machine of storage
Device reply data is presented to the user.
8. device according to claim 7, which is characterized in that more wheel human-computer dialogue devices further include:
Irrevocable instruction determining module, for if it is determined that described analyze the instruction as irrevocable instruction, then analyzing the instruction hair for described
Send to server so that the server search with it is described analyze the instruction matched machine reply data and generate with the machine
The matched message identification of reply data;
Module is locally stored, if for get the machine reply data sent by the server and with the machine
The matched message identification of reply data, then be locally stored, and the machine reply data is presented to the user.
9. device according to claim 7 or 8, which is characterized in that described instruction parsing module is specifically used for:
Instruction parsing is carried out to user's interactive voice using automatic speech recognition technology and/or natural language understanding technology,
It is analyzed the instruction.
10. a kind of more wheel human-computer dialogue devices, are applied in server characterized by comprising
User's interactive voice obtains module, and the user that the user for receiving client transmission inputs under current session round hands over
Mutual voice;
Respond module is instructed, is used for if it is determined that user's interactive voice is return instruction, then acquisition and the current session wheel
The message identification of the matched upper level machine reply data of secondary machine reply data, and feed back matched with the message identification
Confirm returning response, determines that user's interactive voice meets historical machine reply data request condition;
First data simultaneous module is used for using the upper level machine reply data as current machine reply data, so that institute
It states server and keeps data synchronous with the client.
11. device according to claim 10, which is characterized in that more wheel human-computer dialogue devices further include:
Machine reply data sending module, be used for if it is determined that user's interactive voice be irrevocable instruction, then obtain with it is described
The matched machine reply data of user's interactive voice, generation and the matched message identification of machine reply data, by the machine
Device reply data and the message identification feed back to the client, so that the machine reply data is presented in the client
To user;
Second data simultaneous module is used for using the machine reply data as current machine reply data, so that the service
Device keeps data synchronous with the client.
12. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as more wheel interactive methods as claimed in any one of claims 1-3, or more wheel people as described in any in claim 4-6
Machine dialogue method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910383367.9A CN110196927B (en) | 2019-05-09 | 2019-05-09 | Multi-round man-machine conversation method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910383367.9A CN110196927B (en) | 2019-05-09 | 2019-05-09 | Multi-round man-machine conversation method, device and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110196927A true CN110196927A (en) | 2019-09-03 |
CN110196927B CN110196927B (en) | 2021-09-10 |
Family
ID=67752607
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910383367.9A Active CN110196927B (en) | 2019-05-09 | 2019-05-09 | Multi-round man-machine conversation method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110196927B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110737765A (en) * | 2019-10-25 | 2020-01-31 | 上海喜马拉雅科技有限公司 | Dialogue data processing method for multi-turn dialogue and related device |
CN110941693A (en) * | 2019-10-09 | 2020-03-31 | 深圳软通动力信息技术有限公司 | Task-based man-machine conversation method, system, electronic equipment and storage medium |
CN112417109A (en) * | 2020-10-26 | 2021-02-26 | 出门问问(苏州)信息科技有限公司 | Method and device for testing man-machine conversation system |
CN113079400A (en) * | 2021-03-25 | 2021-07-06 | 海信视像科技股份有限公司 | Display device, server and voice interaction method |
CN113656562A (en) * | 2020-11-27 | 2021-11-16 | 话媒(广州)科技有限公司 | Multi-round man-machine psychological interaction method and device |
CN116521841A (en) * | 2023-04-18 | 2023-08-01 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and medium for generating reply information |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103927006A (en) * | 2014-04-08 | 2014-07-16 | 弗徕威智能机器人科技(上海)有限公司 | Robot based information interaction system and method |
US20140278403A1 (en) * | 2013-03-14 | 2014-09-18 | Toytalk, Inc. | Systems and methods for interactive synthetic character dialogue |
CN106095568A (en) * | 2016-06-01 | 2016-11-09 | 努比亚技术有限公司 | Memory management device, mobile terminal and method |
CN107053208A (en) * | 2017-05-24 | 2017-08-18 | 北京无忧创新科技有限公司 | A kind of method of active dialog interaction robot system and the system active interlocution |
US20180004729A1 (en) * | 2016-06-29 | 2018-01-04 | Shenzhen Gowild Robotics Co., Ltd. | State machine based context-sensitive system for managing multi-round dialog |
CN108366281A (en) * | 2018-02-05 | 2018-08-03 | 山东浪潮商用***有限公司 | A kind of full voice exchange method applied to set-top box |
CN109151063A (en) * | 2018-10-10 | 2019-01-04 | 小雅智能平台(深圳)有限公司 | A kind of method and system controlling intelligent robot |
-
2019
- 2019-05-09 CN CN201910383367.9A patent/CN110196927B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140278403A1 (en) * | 2013-03-14 | 2014-09-18 | Toytalk, Inc. | Systems and methods for interactive synthetic character dialogue |
CN103927006A (en) * | 2014-04-08 | 2014-07-16 | 弗徕威智能机器人科技(上海)有限公司 | Robot based information interaction system and method |
CN106095568A (en) * | 2016-06-01 | 2016-11-09 | 努比亚技术有限公司 | Memory management device, mobile terminal and method |
US20180004729A1 (en) * | 2016-06-29 | 2018-01-04 | Shenzhen Gowild Robotics Co., Ltd. | State machine based context-sensitive system for managing multi-round dialog |
CN107053208A (en) * | 2017-05-24 | 2017-08-18 | 北京无忧创新科技有限公司 | A kind of method of active dialog interaction robot system and the system active interlocution |
CN108366281A (en) * | 2018-02-05 | 2018-08-03 | 山东浪潮商用***有限公司 | A kind of full voice exchange method applied to set-top box |
CN109151063A (en) * | 2018-10-10 | 2019-01-04 | 小雅智能平台(深圳)有限公司 | A kind of method and system controlling intelligent robot |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110941693A (en) * | 2019-10-09 | 2020-03-31 | 深圳软通动力信息技术有限公司 | Task-based man-machine conversation method, system, electronic equipment and storage medium |
CN110737765A (en) * | 2019-10-25 | 2020-01-31 | 上海喜马拉雅科技有限公司 | Dialogue data processing method for multi-turn dialogue and related device |
CN112417109A (en) * | 2020-10-26 | 2021-02-26 | 出门问问(苏州)信息科技有限公司 | Method and device for testing man-machine conversation system |
CN112417109B (en) * | 2020-10-26 | 2023-08-01 | 问问智能信息科技有限公司 | Method and device for testing man-machine dialogue system |
CN113656562A (en) * | 2020-11-27 | 2021-11-16 | 话媒(广州)科技有限公司 | Multi-round man-machine psychological interaction method and device |
CN113079400A (en) * | 2021-03-25 | 2021-07-06 | 海信视像科技股份有限公司 | Display device, server and voice interaction method |
CN116521841A (en) * | 2023-04-18 | 2023-08-01 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and medium for generating reply information |
CN116521841B (en) * | 2023-04-18 | 2024-05-14 | 百度在线网络技术(北京)有限公司 | Method, device, equipment and medium for generating reply information |
Also Published As
Publication number | Publication date |
---|---|
CN110196927B (en) | 2021-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110196927A (en) | It is a kind of to take turns interactive method, device and equipment more | |
US10733983B2 (en) | Parameter collection and automatic dialog generation in dialog systems | |
US10679622B2 (en) | Dependency graph generation in a networked system | |
US20180277115A1 (en) | Generating dialog recommendations for chat information systems based on user interaction and environmental data | |
CN102737104B (en) | Task driven user intents | |
US9177551B2 (en) | System and method of providing speech processing in user interface | |
JP2019144598A (en) | Developer voice actions system | |
US9373322B2 (en) | System and method for determining query intent | |
CN103365833B (en) | A kind of input candidate word reminding method based on context and system | |
JP2019503526A5 (en) | ||
WO2016004763A1 (en) | Service recommendation method and device having intelligent assistant | |
US20160048500A1 (en) | Concept Identification and Capture | |
CN104239459A (en) | Voice search method, voice search device and voice search system | |
US9898455B2 (en) | Natural language understanding cache | |
WO2015014122A1 (en) | Voice interaction method and system and interaction terminal | |
US20180213062A1 (en) | Speed and accuracy of computers when resolving client queries by using graph database model | |
US20230169102A1 (en) | Determining responsive content for a compound query based on a set of generated sub-queries | |
CN110970021A (en) | Question-answering control method, device and system | |
CN111213136A (en) | Generation of domain-specific models in networked systems | |
CN110692040A (en) | Activating remote devices in a network system | |
KR20190109498A (en) | Establish audio-based network sessions using unregistered resources | |
CN114596854A (en) | Voice processing method and system based on full-duplex communication protocol and computer equipment | |
CN117235235A (en) | Information processing method, device, equipment and medium based on cloud platform | |
CN111881253A (en) | Method and device for determining synonymy entity pair |
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 |