Voice interactive method, apparatus and systemTechnical fieldThis application involves speech recognition technologies, such as are related to a kind of voice interactive method, apparatus and system.
Background techniqueWith advances in technology and the demand of people's life, the intelligent robot product for company successively come out.
The voice system of company robot combination artificial intelligence in the related technology, realizes the function of robot chat, realizes the company to people.However, the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, more services cannot be provided for user.
Summary of the invention
The application provides a kind of voice interactive method, apparatus and system, provides more services by the artificial user of intelligence machine to realize.
In a first aspect, the embodiment of the present application provides a kind of voice interactive method, it is applied to intelligent robot, comprising:
The voice data that will acquire is sent to server；
Receive the feedback data that server is sent；And
According to the feedback data, interactive information is shown.
Optionally, according to the feedback data, show that interactive information includes:
According to the feedback data, corresponding voice is played, corresponding robot limb movement is executed and/or shows corresponding content on a display screen.
Optionally, the feedback data includes:
Related service index and/or feedback language data.
Second aspect, the embodiment of the present application provide a kind of voice interactive method, are applied to server, comprising:
Receive the voice data that intelligent robot is sent；
Speech recognition and semantic parsing are carried out to the voice data, generative semantics analyze result；
Feedback data is determined according to the semantic analysis result；And
The feedback data is sent to intelligent robot.
Optionally, speech recognition and semantic parsing are carried out to the voice data, generative semantics analysis result includes:
Speech recognition is carried out to the voice data, generates text；
The text is segmented, and near synonym replacement is carried out to participle, generates participle replacement text；And
Text is replaced according to the participle and default semantic base carries out semantic matches, determines semantic analysis result.
Optionally, determine that feedback data includes according to the semantic analysis result:
Feedback voice data is determined according to the semantic analysis result and/or the index of related service is determined according to the semantic analysis result；And
By the feedback voice data and/or the index of related service, it is determined as the feedback data.
The third aspect, the embodiment of the present application also provides a kind of voice interaction devices, are configured at intelligent robot, comprising:
Voice data sending module, the voice data for being set as will acquire are sent to server；
Feedback data receiving module is set as receiving the feedback data that server is sent；And
Interactive information display module is set as showing interactive information according to the feedback data.
Optionally, interactive information display module is arranged are as follows:
According to the feedback data, corresponding voice is played, corresponding robot limb movement is executed and/or shows corresponding content on a display screen.
Optionally, the feedback data includes:
Related service index and/or feedback language data.
Fourth aspect, the embodiment of the present application also provides a kind of voice interaction devices, are configured at server, comprising:
Voice data receiving module is set as receiving the voice data that intelligent robot is sent；
Semantic analysis result generation module is set as carrying out the voice data speech recognition and semantic parsing, and generative semantics analyze result；
Feedback data determining module is set as determining feedback data according to the semantic analysis result；And
Feedback data sending module is set as the feedback data being sent to intelligent robot.
Optionally, semantic analysis result generation module is arranged are as follows:
Speech recognition is carried out to the voice data, generates text；
The text is segmented, and near synonym replacement is carried out to participle, generates participle replacement text；And
Text is replaced according to the participle and default semantic base carries out semantic matches, determines semantic analysis result.
Optionally, feedback data determining module is arranged are as follows:
Feedback voice data is determined according to the semantic analysis result and/or the index of related service is determined according to the semantic analysis result；And
By the feedback voice data and/or the index of related service, it is determined as the feedback data.
5th aspect, the embodiment of the present application also provides a kind of voice interactive systems, including server described in intelligent robot and fourth aspect described in the third aspect.
6th aspect, the embodiment of the present application also provide a kind of intelligent robot, comprising:
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory is stored with the instruction that can be executed by one processor, and described instruction is executed by least one described processor, so that at least one described processor is able to carry out the voice interactive method of intelligent robot side any in the embodiment of the present application.
7th aspect, the embodiment of the present application also provides a kind of non-transient computer readable storage medium, wherein, the non-transient computer readable storage medium stores computer instruction, the voice interactive method that the computer instruction is used to that the computer to be made to execute intelligent robot side any in the embodiment of the present application.
Eighth aspect, the embodiment of the present application also provides a kind of computer program product, wherein, the computer program product includes the calculation procedure being stored in non-transient computer readable storage medium, the computer program includes program instruction, when described program instruction is computer-executed, the computer is made to execute the voice interactive method of intelligent robot side any in the embodiment of the present application.
9th aspect, the embodiment of the present application also provide a kind of server, comprising:
At least one processor；And
The memory being connect at least one described processor communication；Wherein,
The memory is stored with the instruction that can be executed by one processor, and described instruction is executed by least one described processor, so that at least one described processor is able to carry out the voice interactive method of server side any in the embodiment of the present application.
Tenth aspect, the embodiment of the present application also provides a kind of non-transient computer readable storage medium, wherein, the non-transient computer readable storage medium stores computer instruction, the voice interactive method that the computer instruction is used to that the computer to be made to execute server side any in the embodiment of the present application.
Tenth on the one hand, and the embodiment of the present application also provides a kind of computer program product, wherein the computer program product includes the calculation procedure being stored in non-transient computer readable storage medium, the meterCalculation machine program includes program instruction, when described program instruction is computer-executed, the computer is made to execute the voice interactive method of server side any in the embodiment of the present application.
The phonetic order that the embodiment of the present application passes through identification and analysis user, corresponding service is provided using the artificial user of intelligence machine, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Detailed description of the inventionFig. 1 is the flow chart of one of the embodiment of the present application one voice interactive method；
Fig. 2 is the flow chart of one of the embodiment of the present application two voice interactive method；
Fig. 3 is the structural schematic diagram of one of the embodiment of the present application three voice interaction device；
Fig. 4 is the structural schematic diagram of one of the embodiment of the present application four voice interaction device；
Fig. 5 is the data flowchart of one of the embodiment of the present application five voice interactive system；
Fig. 6 is the hardware structural diagram of one of the embodiment of the present application five intelligent robot；And
Fig. 7 is the structural schematic diagram of one of the embodiment of the present application five server.
Specific embodimentThe application is illustrated with reference to the accompanying drawings and examples.It is understood that alternative embodiment described herein is used only for explaining the application, rather than the restriction to the application.For ease of description, part relevant to the application is illustrated only in attached drawing rather than entire infrastructure.In the absence of conflict, the feature in embodiment and embodiment can mutual any combination.
Embodiment one
Fig. 1 is a kind of flow chart for voice interactive method that the embodiment of the present application one provides, the present embodiment is applicable to the case where intelligent robot and user's progress interactive voice, this method can be executed by being applied to the voice interaction device of intelligent robot, the device can be realized that voice interactive method includes: by hardware and/or software
In S110, the voice data that will acquire is sent to server.
Wherein, the phonetic order that user issues is obtained by the microphone being equipped on intelligent robot, voice signal is converted to electrical signal by microphone, the electrical signal is saved as into voice data, and voice data is sent to server, it is exemplary, voice data can be sent to by mobile communications network by server by the mobile communication module being equipped on intelligent robot.
In S120, the feedback data that server is sent is received.
Wherein, server carries out voice converting text according to the voice data that intelligent robot is sent, text semantic is parsed, determine the intention of user, and the service of user's offer is provided according to the user's intention and/or replys the voice content of user speech instruction, it is sent to intelligent robot using the index of related service and/or feedback voice data as feedback data, intelligent robot receives the feedback data.
In S130, according to feedback data, interactive information is shown.
Intelligent robot shows corresponding interactive information by parsing feedback data, for user.Optionally, show that interactive information includes: to play corresponding voice, execute corresponding robot limb movement and/or show corresponding content on a display screen.It is exemplary, feedback data includes the voice data of the service index and current weather conditions of current weather conditions, intelligent robot is after receiving feedback data, it shows the information of weather condition on a display screen according to the service index of the current weather conditions in feedback data, and plays the voice of current weather conditions by loudspeaker.
The technical solution of the present embodiment, the phonetic order of user is received by intelligent robot, and corresponding service is provided using the artificial user of intelligence machine, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Embodiment two
Fig. 2 is a kind of flow chart for voice interactive method that the embodiment of the present application two provides, the present embodiment is applicable to the case where intelligent robot and user's progress interactive voice, this method can be executed by being applied to the voice interaction device of server, the device can be realized that voice interactive method includes: by hardware and/or software
In S210, the voice data that intelligent robot is sent is received.
In S220, speech recognition and semantic parsing are carried out to voice data, generative semantics analyze result.
Wherein, speech recognition is carried out to voice data, converts voice data into text, semantic parsing then is carried out to text, the meaning of the phonetic order of user is obtained, determines the intention of user.Optionally, S220 includes: to carry out speech recognition to voice data, generates text；Text is segmented, and near synonym replacement is carried out to participle, generates participle replacement text；And semantic matches are carried out according to participle replacement text and default semantic base, determine semantic analysis result.Wherein, it after segmenting to text, determines the part of speech of each participle, carries out near synonym replacement in conjunction with the part of speech of participle, generate participle replacement text.According to participle part of speech, the sentence elements such as subject-predicate object are extracted from participle replacement text, the participle replacement text for extracting sentence element and default semantic base are then subjected to semantic matches, semantic data has been stored in advance in default semantic base.Exemplary, user issues the phonetic order of " today, weather was how ", first replaces near synonym: how=such asWhat, then sentence element is extracted, subject=weather, predicate=how, text is converted speech into using speech recognition system, obtain text, then text is segmented, and determines participle part of speech, the text " today (noun)/weather (noun)/how (interrogative) " after being segmented, near synonym replacement is carried out to the text after participle, how=how, then extract the subject-predicate object of participle replacement text, subject=weather, predicate=how, last semantic analysis result is to determine weather condition.
In S230, feedback data is determined according to semantic analysis result.
Wherein, it is determining semantic analysis result, that is, after the intention that user has been determined, is determining the service for needing to provide for user according to the user's intention and/or reply the feedback voice data of user.Optionally, S230 includes: to determine feedback voice data according to semantic analysis result and/or determine the index of related service according to semantic analysis result；And the index that voice data and/or related service will be fed back, it is determined as feedback data.It is exemplary, after the semantic analysis result for the phonetic order for determining user is to determine weather condition, directly access ambient weather database, then time parameter=today is determined according to the time adverbial in sentence, obtain corresponding weather data, such as " today, weather was clear to cloudy, 24~30 degrees Celsius of temperature ", it is voice data by the text conversion of weather data, using the voice data as feedback data.
In S240, feedback data is sent to intelligent robot.
The technical solution of the present embodiment, the voice data sent by server according to the intelligent robot received, determine the intention of user, and corresponding feedback data is fed back to intelligent robot, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Embodiment three
Fig. 3 is a kind of structural schematic diagram for voice interaction device that the embodiment of the present application three provides, which is configured in intelligent robot, and the intelligent robot further includes microphone, loudspeaker, display screen and communication module.Voice interaction device 30 includes:
Voice data sending module 310, the voice data for being set as will acquire are sent to server；
Feedback data receiving module 320 is set as receiving the feedback data that server is sent；And
Interactive information display module 330 is set as showing interactive information according to feedback data.
Optionally, interactive information display module 330 is arranged are as follows:
According to feedback data, corresponding voice is played, corresponding robot limb movement is executed and/or shows corresponding content on a display screen.
Optionally, feedback data includes:
Related service index and/or feedback language data.
The technical solution of the present embodiment, the phonetic order of user is received by intelligent robot, and corresponding service is provided using the artificial user of intelligence machine, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Example IV
Fig. 4 is a kind of structural schematic diagram for voice interaction device that the embodiment of the present application four provides, which is configured at server, and voice interaction device 40 includes:
Voice data receiving module 410 is set as receiving the voice data that intelligent robot is sent；
Semantic analysis result generation module 420 is set as carrying out voice data speech recognition and semantic parsing, and generative semantics analyze result；
Feedback data determining module 430 is set as determining feedback data according to semantic analysis result；And
Feedback data sending module 440 is set as feedback data being sent to intelligent robot.
Optionally, semantic analysis result generation module 420 is arranged are as follows:
Speech recognition is carried out to voice data, generates text；
Text is segmented, and near synonym replacement is carried out to participle, generates participle replacement text；And
Semantic matches are carried out according to participle replacement text and default semantic base, determine semantic analysis result.
Optionally, feedback data determining module 430 is arranged are as follows:
Feedback voice data is determined according to semantic analysis result and/or the index of related service is determined according to semantic analysis result；And
The index of voice data and/or related service will be fed back, is determined as feedback data.
The technical solution of the present embodiment, the voice data sent by server according to the intelligent robot received, determine the intention of user, and corresponding feedback data is fed back to intelligent robot, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Embodiment five
Fig. 5 is a kind of data flowchart for voice interactive system that the embodiment of the present application five provides, and voice interactive system provided in this embodiment includes:
Intelligent robot 510 is intelligent robot described in embodiment three.
Server 520 is server described in example IV.
As shown in figure 5, intelligent robot obtains voice data by microphone, and the voice data that will acquire is sent to server.Server receives the voice data that intelligent robot is sent；Server is to voice numberAccording to speech recognition and semantic parsing is carried out, generative semantics analyze result；Server determines feedback data according to semantic analysis result；Feedback data is sent to intelligent robot by server.Intelligent robot receives the feedback data that server is sent；Intelligent robot shows interactive information according to feedback data.
The phonetic order that the embodiment of the present application passes through identification and analysis user, corresponding service is provided using the artificial user of intelligence machine, solve the problems, such as that the function of company robot in the related technology is only limitted to the voice dialogue being fixed in scope with user, the life that can be convenient user promotes the experience of user.
Method provided by the application any embodiment can be performed in the said goods, has the corresponding functional module of execution method and beneficial effect.
The embodiment of the present application also provides a kind of non-transient computer storage medium, and the computer storage medium is stored with computer executable instructions, which can be performed the voice interactive method of the intelligent robot side in above-mentioned any embodiment.
Fig. 6 is that the embodiment of the present application provides a kind of hardware structural diagram of intelligent robot, as shown in fig. 6, the intelligent robot includes:
One or more processors 610 and memory 620, in Fig. 6 by taking a processor 610 as an example.
Intelligent robot can also include: input unit 630 and output device 640.
Processor 610, memory 620, input unit 630 and output device 640 can be connected by bus or other modes, in Fig. 6 for being connected by bus.
Memory 620 is used as a kind of non-transient computer readable storage medium, it can be used for storing non-transient software program, non-transient computer executable program and module, as the corresponding program instruction/module of the voice interactive method in the embodiment of the present application (such as, attached voice data sending module 310 shown in Fig. 3, feedback data receiving module 320 and interactive information display module 330).Non-transient software program, instruction and the module that processor 610 is stored in memory 620 by operation realize the voice interactive method of above method embodiment intelligent robot side thereby executing the various functions of intelligent robot and data processing.
Memory 620 may include storing program area and storage data area, wherein storing program area can application program required for storage program area, at least one function；Storage data area, which can be stored, uses created data etc. according to the interactive server of application program.In addition, memory 620 may include high-speed random access memory, it can also include non-transient memory, a for example, at least disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, it includes the memory remotely located relative to processor 610 that memory 620 is optional, these remote memories can be by being connected to the network to the server of application program interaction.
The example of above-mentioned network is chosen as internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 630 can receive the number or character information of input, and generate the user setting and the related key signals input of function control of the terminal interacted with application program.Output device 640 may include that display screen etc. shows equipment.
One or more of modules are stored in the memory 620, when being executed by one or more of processors 610, execute the voice interactive method of the intelligent robot side in above-mentioned any means embodiment.
The embodiment of the present application also provides a kind of non-transient computer storage medium, and the computer storage medium is stored with computer executable instructions, which can be performed the voice interactive method of the server side in above-mentioned any embodiment.
Fig. 7 is that the embodiment of the present application provides a kind of structural schematic diagram of server, as shown in fig. 7, the server includes:
One or more processors 710 and memory 720, in Fig. 7 by taking a processor 710 as an example.
Server can also include: input unit 730 and output device 740.
Processor 710, memory 720, input unit 730 and output device 740 can be connected by bus or other modes, in Fig. 7 for being connected by bus.
Memory 720 is used as a kind of non-transient computer readable storage medium, it can be used for storing non-transient software program, non-transient computer executable program and module, as the corresponding program instruction/module of the voice interactive method in the embodiment of the present application (such as, attached voice data receiving module 410 shown in Fig. 4, semantic analysis result generation module 420, feedback data determining module 430 and feedback data sending module 440).Non-transient software program, instruction and the module that processor 710 is stored in memory 720 by operation realize the voice interactive method of above method embodiment server side thereby executing the various functions of server and data processing.
Memory 720 may include storing program area and storage data area, wherein storing program area can application program required for storage program area, at least one function；Storage data area, which can be stored, uses created data etc. according to the interactive intelligent robot of application program.In addition, memory 720 may include high-speed random access memory, it can also include non-transient memory, a for example, at least disk memory, flush memory device or other non-transient solid-state memories.In some embodiments, it includes the memory remotely located relative to processor 710 that memory 720 is optional, these remote memories can be by being connected to the network to the intelligent robot of application program interaction.
The example of above-mentioned network is chosen as internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 730 can receive the number or character information of input, and generate the user setting and the related key signals input of function control of the terminal interacted with application program.Output device 740 may include that display screen etc. shows equipment.
One or more of modules are stored in the memory 720, when being executed by one or more of processors 710, execute the voice interactive method of the server side in above-mentioned any means embodiment.
Note that above are only the alternative embodiment of the application.It will be appreciated by those skilled in the art that the application can be above-described alternative embodiment, the protection scope for being able to carry out a variety of variations for a person skilled in the art, readjusting and substituting without departing from the application.Therefore, although being described in further detail by above embodiments to the application, the application is not limited only to above embodiments.
Industrial applicibilityThe embodiment of the present application is by using above-mentioned technical proposal, by identifying and analyzing the phonetic order of user, provides corresponding service using the artificial user of intelligence machine, facilitates the life of user, promote the experience of user.