CN109462546A - A kind of voice dialogue history message recording method, apparatus and system - Google Patents
A kind of voice dialogue history message recording method, apparatus and system Download PDFInfo
- Publication number
- CN109462546A CN109462546A CN201811624245.6A CN201811624245A CN109462546A CN 109462546 A CN109462546 A CN 109462546A CN 201811624245 A CN201811624245 A CN 201811624245A CN 109462546 A CN109462546 A CN 109462546A
- Authority
- CN
- China
- Prior art keywords
- message
- voice
- user speech
- answer
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 230000002452 interceptive effect Effects 0.000 claims abstract description 75
- 230000008569 process Effects 0.000 claims abstract description 21
- 230000003993 interaction Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/07—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail characterised by the inclusion of specific contents
- H04L51/10—Multimedia information
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/52—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail for supporting social networking services
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention discloses a kind of voice dialogue history message recording method, apparatus and system, wherein, this method disclosed by the invention is by carrying out parsing identification to the user speech audio-frequency information received, obtain user speech content, and according to the voice content, after organizing corresponding answer information, by the user speech content, the answer is formatted and is transmitted in message queue, and the user speech content is taken out from the message queue, the answer, and it stores into table storage, realize the generation from voice dialogue history message, transmission, storage, and when user consults voice dialogue history message, by receiving and consulting request according to the dialog information from interactive voice terminal, the history message to be consulted of user is filtered out from table storage, for users to use.This recording mode to the generation of history message, transmission, storage, not will increase the overloading generated in interactive voice service process.
Description
Technical field
The present invention relates to technical field of voice interaction more particularly to a kind of voice dialogue history message recording methods, device
And system.
Background technique
Instant messaging application on the market at present all includes usually history message function, but is only limitted in text and audio
Hold, and the content of speech recognition interaction can not be saved.The message of instant messaging application is initiated by each terminal, is associated with account number,
Message can store while sending to cloud.Recent news can also be stored in local simultaneously.Do not have when user will check locally
When some history messages, application can request cloud to pull.Cloud is filtered and returns according to user and user message object.This
The transmission process of kind information determines that instant messaging application is not suitable for man machine language's interaction, and under non-speech recognition scene,
Historical content only has message content, without more detailed information, the features such as not meeting the parsing in speech recognition process, synthesize.
In addition, the application of similar man machine language's interaction, such as cell phone intelligent assistant software.Applying for this kind of interactive voice makes
With in the process, human-computer dialogue content is stored in local, can not check the session log of history, more it is even more impossible to be made by historical record
Use, although and mobile phone assistant software the recognition result of showing interface user speech is provided upon awakening, and displaying is to every
The answer of Duan Yuyin, but after user terminates this application interaction, voice dialogue record is without saving.
In view of the above-mentioned problems, general settling mode is to send the audio to cloud to be identified and handled, processed
Voice input is needed in journey, retains the information such as recognition result, is then stored, but this processing mode makes speech message
Save, transmission, using very big to service impact, need to rebuild project and carry out special disposal.
Summary of the invention
The embodiment of the present invention provides recording method and the device of a kind of voice dialogue history message, above-mentioned at least solving
One of technical problem.
In a first aspect, the embodiment of the present invention provides a kind of voice dialogue history message recording method, this method comprises: receiving
User speech audio-frequency information from interactive voice terminal；Parsing identification is carried out to the user speech audio-frequency information, is used
Family voice content, and according to the voice content, organize answer corresponding with the user speech content；By the user speech
After content, the answer format, it is transmitted in message queue；Taken out from the message queue user speech content,
The answer, and store into table storage.
In some possible embodiments, described by after the user speech content, answer formatting, it is transmitted to
Step in message queue, including by after the user speech content, answer formatting, be transmitted to and disappear in asynchronous task
It ceases in queue.
In some possible embodiments, the user speech content, described taken out from the message queue
The step answered, and stored into table storage, including the user speech content, described time are taken out from the message queue
It answers, and is stored according to the major key preset to the user speech content, the answer into table storage.
In some possible embodiments, in described the step of formatting the user speech content, the answer
Before, the method also includes the answer is sent to the interactive voice terminal to be shown.
In some possible embodiments, the method also includes: receive the dialog information from interactive voice terminal
Consult request；It is consulted and is requested according to the dialog information, filter out the target dialogue message to be consulted from table storage；By institute
Target dialogue message is stated to be sent to from voice interactive terminal.
In some possible embodiments, the dialog information consults the equipment that request includes the interactive voice terminal
Number and User ID.
In some possible embodiments, described consulted according to the dialog information is requested, and is screened from table storage
The step of target dialogue message to be consulted out, including consulted and requested according to the dialog information, the basis from table storage
Sequence ID and number sieve select the target dialogue message to be consulted.
Second aspect, the embodiment of the present invention also provides a kind of voice dialogue history message recording device, above-mentioned for executing
Either method, the device include:
Input/output module, for receiving the user speech audio-frequency information from interactive voice terminal；
Interaction process module obtains user speech content for carrying out parsing identification to the user speech audio-frequency information,
And according to the voice content, answer corresponding with the user speech content is organized；
Processing module is formatted, after formatting the user speech content, the answer, is transmitted to message queue
In；
Message storage module for taking out the user speech content, the answer from the message queue, and stores
Into table storage.
In some possible embodiments, the formatting processing module is by the user speech content, the answer
After formatting, it is transmitted in message queue in asynchronous task.
In some possible embodiments, the message storage module takes out user's language from the message queue
Sound content, the answer, and stored according to the major key preset to the user speech content, the answer into table storage.
In some possible embodiments, the input/output module is also used to the answer being sent to the voice
Interactive terminal is shown.
In some possible embodiments, described device further includes that message consults module；The input/output module is also
Request is consulted for receiving the dialog information from interactive voice terminal；The message is consulted module and is looked into according to the dialog information
Request is read, filters out the target dialogue message to be consulted from table storage；The input/output module is by the target dialogue
Message is sent to from voice interactive terminal.
In some possible embodiments, the dialog information consults the equipment that request includes the interactive voice terminal
Number and User ID.
In some possible embodiments, the message consults module and consults request according to the dialog information, from table
The target dialogue message to be consulted is selected according to Sequence ID and number sieve in lattice storage.
The third aspect, the embodiment of the present invention also provide a kind of electronic equipment comprising: at least one processor, Yi Jiyu
The memory of at least one processor communication connection, wherein the memory is stored with can be by least one described processing
The instruction that device executes, described instruction is executed by least one described processor, so that at least one described processor is able to carry out
The step of any one the method provided in first aspect.
Fourth aspect, the embodiment of the present invention also provide a kind of storage medium, are stored thereon with computer program, and feature exists
In, when which is executed by processor realize first aspect in provide any one the method the step of.
5th aspect, the embodiment of the present invention also provide a kind of voice dialogue history message record system, which includes: cloud
Hold server, interactive voice terminal；The cloud server includes that voice dialogue described in any one of claim 8-14 is gone through
History Message Record device；
The dialogic voice for receiving the dialogic voice of user's input, and is converted into user's language by interactive voice terminal
Sound audio-frequency information；
The voice dialogue history message recording device, for carrying out parsing identification to the user speech audio-frequency information,
User speech content is obtained, and according to the voice content, organizes answer corresponding with the user speech content；And by institute
After stating user speech content, answer formatting, it is transmitted in message queue；And described in being taken out from the message queue
User speech content, the answer, and store into table storage.
In some possible embodiments, the interactive voice terminal is also used to receive the access voice of user's input,
And the access voice is converted into dialog information and consults request；The voice dialogue history message recording device is according to described right
It talks about information and consults request, the target dialogue message to be consulted is filtered out from table storage, and the target dialogue message is sent out
It send to from voice interactive terminal.
The beneficial effect of the embodiment of the present invention is: the user speech audio-frequency information received by basis, to the use
Family speech audio information carries out parsing identification, obtains user speech content, and according to the voice content, tissue and the user
The user speech content, the answer are formatted later and are transmitted in message queue by the corresponding answer of voice content, with
And the user speech content, the answer are taken out from the message queue, and store into table storage, it realizes from voice
Generation, transmission, the storage of conversation history message, in case it is subsequent when user consults voice dialogue history message, filter out user
The history message to be consulted, for users to use.And this recording mode to the generation of history message, transmission, storage, it will not
Increase the overloading generated in interactive voice service process.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment
Attached drawing be briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, for this field
For those of ordinary skill, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart for voice dialogue history message recording method that the embodiment of the present invention one provides；
Fig. 2 is stream of the embodiment of the present invention two based on Fig. 1 another voice dialogue history message recording method provided
Cheng Tu；
Fig. 3 is a kind of structural block diagram for voice dialogue history message recording device that the embodiment of the present invention three provides；
Fig. 4 is a kind of structural block diagram for voice dialogue history message record system that the embodiment of the present invention four provides；
Fig. 5 is execution flow chart when system shown in Figure 4 executes method shown in Fig. 1 about dialog information storage；
Fig. 6 is that system shown in Figure 4 executes the execution flow chart consulted when method shown in Fig. 2 about message.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.
The present invention can describe in the general context of computer-executable instructions executed by a computer, such as program
Module.Generally, program module includes routines performing specific tasks or implementing specific abstract data types, programs, objects, member
Part, data structure etc..The present invention can also be practiced in a distributed computing environment, in these distributed computing environments, by
Task is executed by the connected remote processing devices of communication network.In a distributed computing environment, program module can be with
In the local and remote computer storage media including storage equipment.
In the present invention, the fingers such as " module ", " device ", " system " are applied to the related entities of computer, such as hardware, hardware
Combination, software or software in execution with software etc..In detail, for example, element can with but be not limited to run on processing
Process, processor, object, executable element, execution thread, program and/or the computer of device.In addition, running on server
Application program or shell script, server can be element.One or more elements can be in the process and/or thread of execution
In, and element can be localized and/or be distributed between two or multiple stage computers on one computer, and can be by each
Kind computer-readable medium operation.Element can also according to the signal with one or more data packets, for example, from one with
Another element interacts in local system, distributed system, and/or the network in internet passes through signal and other system interactions
The signals of data communicated by locally and/or remotely process.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise", not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or equipment institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence " including ... ", it is not excluded that including described want
There is also other identical elements in the process, method, article or equipment of element.
Fig. 1 is a kind of flow chart for voice dialogue history message recording method that the embodiment of the present invention one provides.The party
Method can be used for cloud server.As shown in Figure 1, method includes the following steps:
S101: the user speech audio-frequency information from interactive voice terminal is received.
Specifically, the interactive voice terminal (terminal that such as mobile phone, iPad, vehicle device have intelligent sound interactive function.) quilt
After user inputs wake up instruction wake-up, interactive voice terminal is initially located in the state of user session voice to be received.When user is defeated
When entering dialogic voice, user session voice is converted into user speech audio-frequency information by interactive voice terminal.
S102: carrying out parsing identification to the user speech audio-frequency information, obtains user speech content, and according to institute's predicate
Sound content organizes answer corresponding with the user speech content.
Specifically, the user speech audio-frequency information parsed, identified, obtain the conversation content of user, and according to
The conversation content of user carries out appointment voice technical ability, and (voice technical ability cooperates this novel human-machine interaction form of voice and uses
Third-party application.Under the conditions of interacting with touch-control, these software applications are integrated into the application program shop under operation system of software, example
Such as Google Play, Apple Store etc..Voice technical ability market is the collection of third-party application under the conditions of interactive voice
It closes, mainly there is the voice technical ability under the mainstreams SDK development platforms such as Alexa Skills Kit, Action on Google to answer at present
With).Voice technical ability is organized corresponding with the user speech content (i.e. user speech audio-frequency information) according to the conversation content of user
Answer.The voice technical ability can accordingly answer information to be used to generate according to voice input in existing voice interaction technique
Technology does not do auspicious state herein.
Optionally, the answer can be sent to interactive voice terminal to be shown, so that user can check and accept friendship immediately
Answer information in mutually.
S103: it after the user speech content, the answer are formatted, is transmitted in message queue.
Specifically, after the user speech content, the answer being formatted, message queue is transmitted in asynchronous task
In.In the present embodiment, convenient for recycling after dialog information (i.e. user speech content, answer format) formats, voice pair
Words message not only will record conversation content, the intention of dialogue, and dialogue result, operating result for parsing etc. should all be remembered
Record, therefore formatting processing has been carried out to user speech content and answer.In addition, in the present embodiment, using asynchronous system
Reason is: the storing process of message should not influence the normal session operational scenarios of user, and user's human-computer dialogue should be one complete
Freely without the process of intervention, message stores only a wherein derivative subtask for rectification, and talks with result independent of dialogue storage
Whether succeed, therefore, by the way of asynchronous task processing, messaging list is written into conversation message, so that storing process not shadow
The normal session operational scenarios of user are rung, create a complete smooth interactive process without intervention for user's human-computer dialogue.
S104: taking out the user speech content, the answer from the message queue, and stores to table and store
In.
Specifically, the user speech content, the answer are taken out from the message queue, and according to the user
The preset major key of voice content, the answer is stored into table storage.It optionally, can be to the use before step S101
Family voice content, the answer preset major key set in advance.It is provided by the way of table storage in the present embodiment
A kind of storage scheme (the table storage that Ali's cloud provides), can promote the real-time of voice dialogue historical information record, and just
In extension.In the present embodiment, by the user session information obtained after formatting the user speech content, the answer
Store message queue in, buffer function can be played, so as to for by user session information be added table store before pre- place
Reason is raced against time, and preventing message from overstocking causes system load excessively high.
In the present embodiment one, the user speech audio-frequency information received by basis, to the user speech audio-frequency information
Parsing identification is carried out, user speech content is obtained, and according to the voice content, is organized corresponding with the user speech content
It answers, by the user speech content, answers formatting and is transmitted in message queue later, and from the message team
The user speech content, the answer are taken out in column, and is stored into table storage, are realized from voice dialogue history message
It generates, transmission, storage, in case it is subsequent when user consults voice dialogue history message, filter out the history to be consulted of user
Message, for users to use.And this recording mode to the generation of history message, transmission, storage, it not will increase interactive voice clothes
The overloading generated during business.
Fig. 2 is a kind of voice dialogue history message recording method that the embodiment of the present invention two is provided based on embodiment one
Flow chart.As shown in Fig. 2, the method that the embodiment two provides increases following steps after the step 104 of embodiment one:
S105: it receives the dialog information from interactive voice terminal and consults request.
It specifically, (is including the dialogue of user speech content, answer information etc. by the human-computer interaction dialog information of user
Information) storage after (i.e. after step 104), user can first wake up the voice interactive function of interactive voice terminal, and request to consult
Voice dialogue historical information.When user inputs the phonetic order for consulting voice dialogue historical information, interactive voice terminal
The phonetic order is converted into dialog information and consults request.It may include the interactive voice terminal that the dialog information, which consults request,
Device number and User ID.
S106: consulting according to the dialog information and request, and filters out the target dialogue message to be consulted from table storage；
Specifically, the device number and User ID that the interactive voice terminal in request is consulted according to dialog information, identify and ask
The terminal device for consulting voice dialogue historical information and user are asked, and according to Sequence ID and number sieve from table storage
Select the target dialogue message to be consulted (i.e. the voice dialogue historical information to be consulted of user).Illustratively, Sequence ID
Refer to the sequence number of message, mark is which message, such as the feelings that Sequence ID is 10 and Sequence ID is 100
Condition, expression take 100 articles of message since the 10th article of message.
S107: the target dialogue message is sent to from voice interactive terminal.
Specifically, the device number and User ID that the interactive voice terminal in request is consulted according to dialog information, determine request
After the terminal device and the user that consult voice dialogue historical information, target dialogue message is sent to corresponding to the device number
Interactive voice terminal, for User ID, corresponding user is used.
In the present embodiment two provided by the invention, receives the dialog information from interactive voice terminal and consult request, according to
Dialog information consults the device number and User ID of the interactive voice terminal in request, identifies that voice dialogue history letter is consulted in request
The terminal device of breath and user, and the target dialogue to be consulted is selected according to Sequence ID and number sieve from table storage
Message, and it is sent to interactive voice terminal, for users to use, and then the generation from conversation message, transmission, storage, use, it realizes
The utilization of conversation message, and generation, transmission, storage, the use of conversation message be associated with user and apparatus bound, realizes voice
Accurate positionin, secure storage, the convenient use of conversation history message.
Fig. 3 is a kind of structural block diagram for voice dialogue history message recording device that the embodiment of the present invention three provides.It should
Device is for executing Fig. 1 or method shown in Fig. 2.As shown in figure 3, the device includes:
Input/output module 201, for receiving the user speech audio-frequency information from interactive voice terminal.
Interaction process module 202 obtains in user speech for carrying out parsing identification to the user speech audio-frequency information
Hold, and according to the voice content, organizes answer corresponding with the user speech content.
Processing module 203 is formatted, after formatting the user speech content, the answer, is transmitted to message
In queue.
Message storage module 204, for taking out the user speech content, the answer from the message queue, and
It stores into table storage.
Message consult module 205, for receive dialog information consult request in the case where, according to the dialog information
Request is consulted, filters out the target dialogue message to be consulted from table storage.
Further, device shown in Fig. 3 execute method shown in FIG. 1 process it is as follows:
Processing module 203 is formatted by the received user speech audio-frequency information of input/output module 201, interaction process module
After the answer that 202 tissues generate formats, it is transmitted in message queue in asynchronous task.Message storage module 204 is from message
The user speech content, the answer are taken out in queue, and according to the master preset to the user speech content, the answer
Key is stored into table storage, in case it is subsequent when user consults voice dialogue history message, user is filtered out from table storage
The history message to be consulted, for users to use.Optionally, input/output module 201 can be used for the answer being sent to language
Sound interactive terminal is shown, so that user checks use.Device shown in Fig. 3 to the detailed implementation of method shown in Fig. 1,
It can refer to the detail of method and step shown in FIG. 1, details are not described herein again.
Further, device shown in Fig. 3 execute method shown in Fig. 2 process it is as follows:
Input/output module 201 receives the dialog information from interactive voice terminal and consults request；The dialog information is looked into
Read the device number and User ID that request includes the interactive voice terminal.Interaction process module 202 consults the dialog information
After request carries out parsing identification, module 205 is consulted by message, request is consulted according to the dialog information, screened from table storage
The target dialogue message to be consulted out, i.e. message consult module 204 and consult request according to the dialog information, from table storage
The target dialogue message to be consulted is selected according to Sequence ID and number sieve.Input/output module 201 is by the target dialogue
Message is sent to from voice interactive terminal.Device shown in Fig. 3 can refer to Fig. 2 institute to the detailed implementation of method shown in Fig. 2
The detail of the method and step shown, details are not described herein again.
In some embodiments, the embodiment of the present invention also provides a kind of electronic equipment comprising: at least one processing
Device, and the memory being connect at least one described processor communication, wherein the memory be stored with can by it is described at least
The instruction that one processor executes, described instruction is executed by least one described processor, so that at least one described processor
The step of being able to carry out method shown in Fig. 1 or Fig. 2.
In some embodiments, the embodiment of the present invention also provides a kind of storage medium, is stored thereon with computer program,
The program realizes the step of method shown in Fig. 1 or Fig. 2 when being executed by processor.
Fig. 4 is a kind of structural block diagram for voice dialogue history message record system that the embodiment of the present invention four provides.Such as
Shown in Fig. 4, which includes: interactive voice terminal 301, cloud server 302；(both including) is run on cloud server 302
Voice dialogue history message recording device shown in Fig. 3；
The dialogic voice for receiving the dialogic voice of user's input, and is converted into user by interactive voice terminal 301
Speech audio information.
The voice dialogue history message recording device, for carrying out parsing identification to the user speech audio-frequency information,
User speech content is obtained, and according to the voice content, organizes answer corresponding with the user speech content；And by institute
After stating user speech content, answer formatting, it is transmitted in message queue；And described in being taken out from the message queue
User speech content, the answer, and store into table storage.As an example, Fig. 5 show system shown in Figure 4 and holds
One example of method shown in row Fig. 1, the i.e. storing process of dialog information.As shown in figure 5, specific as follows:
User wakes up interactive voice terminal by input voice, and starts to talk with interactive voice terminal.Interactive voice is whole
The dialogic voice that user inputs is converted into speech audio information and is sent to cloud server by end.Cloud server (i.e. voice pair
Talk about history message recording device) the speech audio information received is parsed into identification, conversation content intention is obtained, and according to parsing
Obtained content selects the voice technical ability of content hit.The voice technical ability tissue obtain with the speech audio (and dialogue in
Hold) corresponding answer.Cloud server conversation content and obtained answer are formatted after generate conversation message (and dialogue
Information), and messaging list is written.Cloud server is deposited after obtaining formatted conversation message in messaging list
Into table storage, dialog information storage terminates for storage.In addition, cloud server when handling each speech audio information, is used
Family can continue to carry out interactive voice with interactive voice terminal, until completing whole wheel dialogue.When user needs to carry out next round pair
Then restart a new round dialogue when words, otherwise terminates to talk with.
Further, interactive voice terminal 301 is also used to receive the access voice of user's input, and by the access voice
It is converted into dialog information and consults request；The voice dialogue history message recording device is consulted according to the dialog information and is requested,
The target dialogue message to be consulted is filtered out from table storage, and the target dialogue message was sent to from interactive voice end
End 301.Optionally, the voice dialogue history message recording device carries out parsing identification to the user speech audio-frequency information,
Obtain user speech content, and according to the voice content, it, can will be with after organizing answer corresponding with the user speech content
The corresponding answer of the user speech content (i.e. user speech audio-frequency information) is sent to interactive voice terminal 301 and is shown.
As an example, Fig. 6 show system shown in Figure 4 and executes the example that message is consulted in method shown in Fig. 2.Such as Fig. 6 institute
Show, specific as follows:
Interactive voice terminal consults voice after being waken up, when user issues, when voice dialogue historical information is consulted in request,
Interactive voice terminal is converted into access voice to carry the interactive voice terminal device number and the dialog information access of User ID is asked
It asks, is sent to cloud server.Conversation message in cloud server Sequence ID and item number position-table, and filter out
The target dialogue message to be consulted simultaneously is sent to interactive voice terminal after formatting, is shown by interactive voice terminal.It is optional
, the target dialogue message filtered out is sent to interactive voice terminal after being formatted, and is opened up by interactive voice terminal
Show.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Movement merge, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
The electronic equipment of the embodiment of the present application/terminal with intelligent sound interactive function exists in a variety of forms, including
But it is not limited to:
(1) mobile communication equipment: the characteristics of this kind of equipment is that have mobile communication function, and to provide speech, data
Communication is main target.This Terminal Type includes: smart phone (such as iPhone), multimedia handset, functional mobile phone and low
Hold mobile phone etc..
(2) super mobile personal computer equipment: this kind of equipment belongs to the scope of personal computer, there is calculating and processing function
Can, generally also have mobile Internet access characteristic.This Terminal Type includes: PDA, MID and UMPC equipment etc., such as iPad.
(3) portable entertainment device: this kind of equipment can show and play multimedia content.Such equipment include: audio,
Video player (such as iPod), handheld device, e-book and intelligent toy and portable car-mounted navigation equipment.
(4) server: providing the equipment of the service of calculating, and the composition of server includes that processor, hard disk, memory, system are total
Line etc., server is similar with general computer architecture, but due to needing to provide highly reliable service, in processing energy
Power, stability, reliability, safety, scalability, manageability etc. are more demanding.
(5) other are with/the electronic device with intelligent sound interactive function.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, above-mentioned technology
Scheme substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute, the computer
Software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions to
So that computer equipment (can be personal computer, server or the network equipment etc.) execute each embodiment or
Method described in certain parts of embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (17)
1. a kind of voice dialogue history message recording method, which is characterized in that the described method includes:
Receive the user speech audio-frequency information from interactive voice terminal；
Parsing identification is carried out to the user speech audio-frequency information, obtains user speech content, and according in the user speech
Hold, organizes answer corresponding with the user speech content；
After the user speech content, the answer are formatted, it is transmitted in message queue；
The user speech content, the answer are taken out from the message queue, and are stored into table storage.
2. the method according to claim 1, wherein described by the user speech content, the answer format
After change, the step that is transmitted in message queue, comprising:
After the user speech content, the answer are formatted, it is transmitted in message queue in asynchronous task.
3. the method according to claim 1, wherein described take out the user speech from the message queue
Content, the answer, and the step stored into table storage, comprising:
The user speech content, the answer are taken out from the message queue, and according to the user speech content, institute
The preset major key of answer is stated to store into table storage.
4. the method according to claim 1, wherein described by the user speech content, the answer lattice
Before the step of formula, the method also includes:
The answer is sent to the interactive voice terminal to be shown.
5. the method according to claim 1, wherein the method also includes:
It receives the dialog information from interactive voice terminal and consults request；
It is consulted and is requested according to the dialog information, filter out the target dialogue message to be consulted from table storage；
The target dialogue message is sent to from voice interactive terminal.
6. according to the method described in claim 5, it is characterized in that, it includes the interactive voice that the dialog information, which consults request,
The device number and User ID of terminal.
7. according to the method described in claim 5, it is characterized in that, described consulted according to the dialog information is requested, from table
The step of target dialogue message to be consulted is filtered out in storage, comprising:
It is consulted and is requested according to the dialog information, selected from table storage according to Sequence ID and number sieve to be consulted
Target dialogue message.
8. a kind of voice dialogue history message recording device, which is characterized in that described device includes:
Input/output module (201), for receiving the user speech audio-frequency information from interactive voice terminal；
Interaction process module (202) obtains in user speech for carrying out parsing identification to the user speech audio-frequency information
Hold, and according to the voice content, organizes answer corresponding with the user speech content；
It formats processing module (203), after formatting the user speech content, the answer, is transmitted to message team
In column；
Message storage module (204) for taking out the user speech content, the answer from the message queue, and is deposited
Storage is into table storage.
9. device according to claim 8, which is characterized in that the formatting processing module (203) is by user's language
After sound content, the answer format, it is transmitted in message queue in asynchronous task.
10. device according to claim 8, which is characterized in that the message storage module (204) is from the message queue
It is middle to take out the user speech content, the answer, and deposited according to the major key preset to the user speech content, the answer
Storage is into table storage.
11. device according to claim 8, which is characterized in that described device further includes that message consults module (205)；Institute
It states input/output module and is also used to receive the dialog information access request from interactive voice terminal；The message consults module
(205) it is consulted and is requested according to the dialog information, filter out the target dialogue message to be consulted from table storage；The input
The target dialogue message is sent to from voice interactive terminal by output module.
12. device according to claim 11, which is characterized in that the dialog information is consulted request and handed over comprising the voice
The device number and User ID of mutual terminal.
13. device according to claim 11, which is characterized in that the message consults module (205) according to the dialogue
Information consults request, selects the target dialogue message to be consulted according to Sequence ID and number sieve from table storage.
14. a kind of electronic equipment comprising: at least one processor, and connect at least one described processor communication
Memory, wherein the memory be stored with can by least one described processor execute instruction, described instruction by it is described extremely
A few processor executes, so that at least one described processor is able to carry out any one of claim 1-7 the method
The step of.
15. a kind of storage medium, is stored thereon with computer program, which is characterized in that the realization when program is executed by processor
The step of any one of claim 1-7 the method.
16. a kind of voice dialogue history message records system, which is characterized in that the system comprises: interactive voice terminal
(301), cloud server (302)；The cloud server (302) includes voice pair described in any one of claim 8-14
Talk about history message recording device；
The dialogic voice for receiving the dialogic voice of user's input, and is converted into user's language by interactive voice terminal (301)
Sound audio-frequency information；
The voice dialogue history message recording device is obtained for carrying out parsing identification to the user speech audio-frequency information
User speech content, and according to the voice content, organize answer corresponding with the user speech content；And by the use
After family voice content, the answer format, it is transmitted in message queue；And the user is taken out from the message queue
Voice content, the answer, and store into table storage.
17. system according to claim 16, which is characterized in that the interactive voice terminal (301) is also used to receive use
The access voice of family input, and the access voice is converted into dialog information and consults request；The voice dialogue history message
Recording device is consulted according to the dialog information and is requested, and the target dialogue message to be consulted is filtered out from table storage, and will
The target dialogue message is sent to from voice interactive terminal (301).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624245.6A CN109462546A (en) | 2018-12-28 | 2018-12-28 | A kind of voice dialogue history message recording method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624245.6A CN109462546A (en) | 2018-12-28 | 2018-12-28 | A kind of voice dialogue history message recording method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109462546A true CN109462546A (en) | 2019-03-12 |
Family
ID=65615420
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811624245.6A Pending CN109462546A (en) | 2018-12-28 | 2018-12-28 | A kind of voice dialogue history message recording method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109462546A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781034A (en) * | 2019-10-29 | 2020-02-11 | 成都中航信虹科技股份有限公司 | Distributed supervision method and system |
| CN111125055A (en) * | 2019-11-22 | 2020-05-08 | 北京理工大学 | Retrospective hearing-impaired person auxiliary dialogue system |
| CN111459686A (en) * | 2020-03-17 | 2020-07-28 | 无锡华云数据技术服务有限公司 | Queue message storing and forwarding method and system and computer device with operating system |
| CN112714057A (en) * | 2020-12-22 | 2021-04-27 | 北京北信源软件股份有限公司 | Instant message processing method, device, equipment and storage medium |
| CN114338573A (en) * | 2020-09-30 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Interactive data processing method and device and computer readable storage medium |
| CN114706969A (en) * | 2022-05-31 | 2022-07-05 | 深圳追一科技有限公司 | Attention content acquisition method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133231A (en) * | 2016-02-29 | 2017-09-05 | 中移(苏州)软件技术有限公司 | A kind of data capture method and device |
| US20180276201A1 (en) * | 2017-03-23 | 2018-09-27 | Samsung Electronics Co., Ltd. | Electronic apparatus, controlling method of thereof and non-transitory computer readable recording medium |
| CN108920639A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108962233A (en) * | 2018-07-26 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Voice dialogue processing method and system for voice dialogue platform |
| CN109005276A (en) * | 2018-09-21 | 2018-12-14 | 马鑫 | Intelligent dialogue robot, dialog control method, computer equipment and storage medium |
-
2018
- 2018-12-28 CN CN201811624245.6A patent/CN109462546A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133231A (en) * | 2016-02-29 | 2017-09-05 | 中移(苏州)软件技术有限公司 | A kind of data capture method and device |
| US20180276201A1 (en) * | 2017-03-23 | 2018-09-27 | Samsung Electronics Co., Ltd. | Electronic apparatus, controlling method of thereof and non-transitory computer readable recording medium |
| CN108920639A (en) * | 2018-07-02 | 2018-11-30 | 北京百度网讯科技有限公司 | Context acquisition methods and equipment based on interactive voice |
| CN108962233A (en) * | 2018-07-26 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Voice dialogue processing method and system for voice dialogue platform |
| CN109005276A (en) * | 2018-09-21 | 2018-12-14 | 马鑫 | Intelligent dialogue robot, dialog control method, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 花开半夏: ""米家新品：两种玩法，语音控制智能家居，售价不到2百元，6不6?"", 《HTTPS://WWW.JIAHEU.COM/TOPIC/299441.HTML》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781034A (en) * | 2019-10-29 | 2020-02-11 | 成都中航信虹科技股份有限公司 | Distributed supervision method and system |
| CN110781034B (en) * | 2019-10-29 | 2022-11-29 | 成都中航信虹科技股份有限公司 | Distributed supervision method and system |
| CN111125055A (en) * | 2019-11-22 | 2020-05-08 | 北京理工大学 | Retrospective hearing-impaired person auxiliary dialogue system |
| CN111459686A (en) * | 2020-03-17 | 2020-07-28 | 无锡华云数据技术服务有限公司 | Queue message storing and forwarding method and system and computer device with operating system |
| CN111459686B (en) * | 2020-03-17 | 2023-06-27 | 华云数据控股集团有限公司 | Queue message storing and forwarding method, system and computer device with operating system |
| CN114338573A (en) * | 2020-09-30 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Interactive data processing method and device and computer readable storage medium |
| CN114338573B (en) * | 2020-09-30 | 2023-10-20 | 腾讯科技（深圳）有限公司 | Interactive data processing method and device and computer readable storage medium |
| CN112714057A (en) * | 2020-12-22 | 2021-04-27 | 北京北信源软件股份有限公司 | Instant message processing method, device, equipment and storage medium |
| CN114706969A (en) * | 2022-05-31 | 2022-07-05 | 深圳追一科技有限公司 | Attention content acquisition method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109462546A (en) | A kind of voice dialogue history message recording method, apparatus and system | |
| CN111192591B (en) | Awakening method and device of intelligent equipment, intelligent sound box and storage medium | |
| TW202016693A (en) | Human-computer interaction processing system, method, storage medium and electronic device | |
| US10956480B2 (en) | System and method for generating dialogue graphs | |
| JP2023504777A (en) | Systems and methods for managing interactions between contact center systems and their users | |
| US20150254061A1 (en) | Method for user training of information dialogue system | |
| CN108564966B (en) | Voice test method and device with storage function | |
| CN110459222A (en) | Sound control method, phonetic controller and terminal device | |
| CN108470034A (en) | A kind of smart machine service providing method and system | |
| JP7331044B2 (en) | Information processing method, device, system, electronic device, storage medium and computer program | |
| WO2021050159A1 (en) | Dynamic contextual dialog session extension | |
| CN109448694A (en) | A kind of method and device of rapid synthesis TTS voice | |
| CN111177453A (en) | Method, device and equipment for controlling audio playing and computer readable storage medium | |
| CN110519472A (en) | The method and device of dialogue service is provided for client | |
| CN109727592A (en) | O&M instruction executing method, medium and terminal based on natural language speech interaction | |
| JP7436077B2 (en) | Skill voice wake-up method and device | |
| CN105244042A (en) | FSA (Finite State Automaton) based voice emotion interaction device and method | |
| CN114244821B (en) | Data processing method, device, equipment, electronic equipment and storage medium | |
| WO2021077528A1 (en) | Method for interrupting human-machine conversation | |
| CN105335466A (en) | Audio data retrieval method and apparatus | |
| CN104702758B (en) | A kind of terminal and its method for managing multimedia notepad | |
| CN111933118B (en) | Method and device for optimizing voice recognition and intelligent voice dialogue system applying same | |
| CN112259076A (en) | Voice interaction method and device, electronic equipment and computer readable storage medium | |
| WO2021042584A1 (en) | Full duplex voice chatting method | |
| CN110442698A (en) | Conversation content generation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |