Summary of the invention
Main purpose of the present invention is to provide a kind of generation of voice reminder information, voice prompting method and device, well can not embody the problem of the fluency of man-machine interaction solve at least speech synthesis technique in prior art.
To achieve these goals, according to an aspect of the present invention, provide a kind of generation method of voice reminder information, comprising: when terminal use and terminal carry out interactive voice, described terminal obtains the first specified speech information of carrying in user speech information; According to pre-defined rule, described first specified speech information and the second specified speech information are combined, obtain and the voice reminder information being used to indicate specified services and occurring; Wherein, described second specified speech information is the voice messaging that described terminal local stores.
Preferably, the associated person information associated with described specified services is carried in described first specified speech information.
Preferably, according to pre-defined rule, described first specified speech information and the second specified speech information are combined, obtain be used to indicate voice reminder information that specified services occurs after, comprising: the incidence relation setting up contact person indicated by described voice reminder information and described associated person information.
Preferably, described terminal obtains first appointed information of carrying in user speech information and comprises: described terminal obtains the voice messaging associated with described specified services from described user speech information, using the voice messaging that associates with described specified services as described first specified speech information.
Preferably, described second specified speech information obtains in the following manner: described terminal obtains the voice messaging that associates with described specified services from the voice messaging that described this locality stores, using the voice messaging that associates with described specified services as described second specified speech information.
According to another aspect of the present invention, provide a kind of method of voice reminder, comprising: whether terminal detects specified services and occur; When detecting that described specified services occurs, report the voice reminder information for reminding described specified services to occur, wherein, described voice reminder information is that the second voice messaging that the first specified speech information and terminal local store combines the voice messaging obtained, described first specified speech information is when terminal use and described terminal carry out interactive voice, the voice messaging obtained from user speech information.
Preferably, the associated person information associated with described specified services is carried in described first specified speech information.
Preferably, there is incidence relation in contact person indicated by described voice reminder information and described associated person information.
According to a further aspect of the present invention, provide a kind of generating apparatus of voice reminder information, comprising: acquisition module, for when terminal use and terminal carry out interactive voice, described terminal obtains the first specified speech information of carrying in user speech information; Composite module, for combining described first specified speech information and the second specified speech information according to pre-defined rule, obtains and the voice reminder information being used to indicate specified services and occurring; Wherein, described second specified speech information is the voice messaging that described terminal local stores.
Preferably, the associated person information associated with described specified services is carried in described first specified speech information.
Preferably, described device also comprises: set up module, for setting up the incidence relation of contact person indicated by described voice reminder information and described associated person information.
According to another aspect of the present invention, provide a kind of device of voice reminder, comprising: detection module, detect specified services for terminal and whether occur; Report module, for when detecting that described specified services occurs, report the voice reminder information for reminding described specified services to occur, wherein, described voice reminder information is that the second voice messaging that the first specified speech information and terminal local store combines the voice messaging obtained, described first specified speech information is when terminal use and described terminal carry out interactive voice, the voice messaging obtained from user speech information.
Preferably, the associated person information associated with described specified services is carried in described first specified speech information.
Preferably, there is incidence relation in contact person indicated by described voice reminder information and described associated person information.
By the present invention, adopt when terminal use and terminal carry out interactive voice, described terminal obtains the first specified speech information of carrying in user speech information; According to pre-defined rule, described first specified speech information and the second specified speech information are combined, obtain and the voice reminder information being used to indicate specified services and occurring; Wherein, described second specified speech information is the voice messaging that described terminal local stores.Solve speech synthesis technique in prior art and well can not embody the problem of the fluency of man-machine interaction, and then improve the experience effect of user.
Embodiment
Hereinafter also describe the present invention in detail with reference to accompanying drawing in conjunction with the embodiments.It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.
Provide a kind of generation method of voice reminder information of the embodiment of the present invention in the present embodiment, Fig. 1 is the flow chart of the generation method of voice reminder information according to the embodiment of the present invention, and as shown in Figure 1, this flow process comprises the steps:
Step S102: when terminal use and terminal carry out interactive voice, terminal obtains the first specified speech information of carrying in user speech information;
Step S104: combine the first specified speech information and the second specified speech information according to pre-defined rule, obtains and the voice reminder information being used to indicate specified services and occurring; Wherein, the second specified speech information is the voice messaging that terminal local stores.
By the embodiment of the present invention, adopt when terminal use and terminal carry out interactive voice, terminal obtains the first specified speech information of carrying in user speech information; According to pre-defined rule, the first specified speech information and the second specified speech information are combined, obtain and the voice reminder information being used to indicate specified services and occurring; Wherein, the second specified speech information is the voice messaging that terminal local stores.Solve speech synthesis technique in prior art and well can not embody the problem of the fluency of man-machine interaction, and then improve the experience effect of user.
Preferably, the associated person information associated with specified services is carried in above-mentioned first specified speech information, it should be noted that in the present invention and be not limited only to associated person information with the information of business association, it can also be other application information, the such as friend information of mobile edition Tencent QQ, when sending video between QQ good friend, by the generation of the voice messaging reminding user QQ video after combination.
Preferably, after stating step S104 on the invention, also comprise the incidence relation setting up contact person indicated by voice reminder information and associated person information.
Preferably, terminal obtains first appointed information of carrying in user speech information and comprises: terminal obtains the voice messaging associated with specified services from user speech information, using the voice messaging that associates with specified services as the first specified speech information; First identify the voice messaging for specified services association, afterwards this voice messaging is split out.
Preferably, the second specified speech information obtains in the following manner: terminal obtains the voice messaging associated with specified services from the voice messaging that this locality stores, using the voice messaging that associates with specified services as the second specified speech information.
Additionally provide a kind of operating means of mobile terminal in the present embodiment, this device is used for realizing above-described embodiment and preferred implementation, has carried out repeating no more of explanation.As used below, term " module " can realize the software of predetermined function and/or the combination of hardware.Although the device described by following examples preferably realizes with software, hardware, or the realization of the combination of software and hardware also may and conceived.
Fig. 2 is the structured flowchart of the generating apparatus of voice reminder information according to the embodiment of the present invention, as shown in Figure 2, this device comprises: acquisition module 22, and for when terminal use and terminal carry out interactive voice, terminal obtains the first specified speech information of carrying in user speech information; Composite module 24, for combining the first specified speech information and the second specified speech information according to pre-defined rule, obtains and the voice reminder information being used to indicate specified services and occurring; Wherein, the second specified speech information is the voice messaging that terminal local stores.
Preferably, the associated person information associated with specified services is carried in the first specified speech information.
Fig. 3 is the preferred structure block diagram of the generating apparatus of voice reminder information according to the embodiment of the present invention, and as shown in Figure 3, device also comprises: set up module 32, for setting up the incidence relation of contact person indicated by voice reminder information and associated person information.
Provide a kind of generation method of voice reminder information of the embodiment of the present invention in the present embodiment, Fig. 4 is the flow chart of the method for voice reminder according to the embodiment of the present invention, and as shown in Figure 4, this flow process comprises the steps:
Step S402: whether terminal detects specified services and occur;
Step S404: when detecting that specified services occurs, report the voice reminder information for reminding specified services to occur, wherein, voice reminder information is that the second voice messaging that the first specified speech information and terminal local store combines the voice messaging obtained, first specified speech information is when terminal use and terminal carry out interactive voice, the voice messaging obtained from user speech information.
Preferably, the associated person information associated with specified services is carried in the first specified speech information.
Preferably, there is incidence relation in contact person indicated by voice reminder information and associated person information.
Additionally provide a kind of operating means of mobile terminal in the present embodiment, this device is used for realizing above-described embodiment and preferred implementation, has carried out repeating no more of explanation.As used below, term " module " can realize the software of predetermined function and/or the combination of hardware.Although the device described by following examples preferably realizes with software, hardware, or the realization of the combination of software and hardware also may and conceived.
Whether Fig. 5 is the structured flowchart of the speech prompting device according to the embodiment of the present invention, and as shown in Figure 5, this device comprises: detection module 52, detect specified services occur for terminal; Report module 54, for when detecting that specified services occurs, report the voice reminder information for reminding specified services to occur, wherein, voice reminder information is that the second voice messaging that the first specified speech information and terminal local store combines the voice messaging obtained, first specified speech information is when terminal use and terminal carry out interactive voice, the voice messaging obtained from user speech information.
Preferably, state in the first specified speech information and carry the associated person information associated with specified services; Indicated by voice reminder information and associated person information there is incidence relation in contact person.
In order to better the present invention will be described, be described below in conjunction with the preferred embodiments of the present invention.
The object of the preferred embodiment of the present invention is, a kind of method of voice reminder of the speech combination producing based on user oneself is provided, system can intellectual analysis user when carrying out interactive voice with mobile phone, the dialogue speech of user oneself, the content meeting intelligent sound prompting in speech is gathered, again distribution combination, the intelligent sound after combination is provided to remind alternately, thus adding users carries out the affinity of voice reminder and good speech recognition for mobile phone, it is associated with contact person simultaneously, can sharing and synchronously share by contact person, individual character is talked about sound to transmit between different mobile phones and share, different mobile phones can be made to have the intelligent reminding sound of multiple different cordiality.
In order to achieve the above object, the preferred embodiment of the present invention by the following technical solutions, comprise: cell phone system initiatively collects the interactive voice of user and mobile phone, by speech analysis module user speech analyzed and combine, again synthesized by voice synthetic module again, generate the intelligent reminding of corresponding relationship people, when there being the business (as sent a telegram here or carrying out note etc.) needing to remind, according to the voice contact people information generated, with the generation of the corresponding business of the tone intonation reminding user of user.
Below in conjunction with accompanying drawing, the execution mode of the preferred embodiment of the present invention is described.
Fig. 6 is the method flow diagram of intelligences combination voice reminder according to the preferred embodiment of the invention, and as shown in Figure 6, this step comprises:
Step S602: voice messaging filters and collects;
Wherein, voice messaging filters with collection module by existing sound identification module, when carrying out interactive voice according to user and mobile phone, the speech of user, identify the content whether comprising and need in associated person information (name or number etc.) and phonetic rules, thus will associated person information be comprised and phonetic rules needs the voice of content to sort out, for further decomposing and processing.Such as calling, when user tells mobile phone: " calling Li Ming ", speech recognition interactive module is while the action performing user's requirement, corresponding filter analysis Li Ming is a contact person, therefore this speech is stored, and to set its type be contact name and the fractionation node from the sound source position before Li Ming, be further processed for next functional steps.
Step S604: phonetic structure is recombinated;
Wherein, for the source information collected step S602 carries out fractionation combination, according to the phonetic rules set, take out the voice, the setting type that store from S0 step, with fractionation nodal information, from existing source of sound, increase abundanter voice resource, setting splits node and composition rule.As above example: set source of sound from " Li Ming " and split node, increases the speech (incoming call speech can be that system carries, the user speech collected before also can being) of " calling ", sets after it is placed on " Li Ming ".
Step S606: phonetic synthesis;
Wherein, for the phonetic synthesis generated step S604 is regular and corresponding source of sound, again intelligent reminding is synthesized.It receives from transmitting next composition rule and mixing source of sound in step S604, according to Regular Shearing combination, regenerates new intelligent reminding source of sound.As above example: be cut into " Li Ming " by the source of sound of " calling Li Ming ", source of sound of " calling " combines with it, regenerates the source of sound of " Li Ming calls ".
Step S608: synthesized voice stores and management;
Wherein, be the store and management of synthesized voice.The synthesized voice that step S606 generates stores by it, and associates with the associated person information mated in user interactions in step S602.Perform the function that current synthesis source of sound is increased, deletes or revised simultaneously.As above example: the combination source of sound storing " Li Ming calls ", and it is associated with " Li Ming " contact person record in contact person, be stored as the integrated mode that user's sound and automatic sound are sent a telegram here simultaneously, " calling " source of sound being convenient to subsequent acquisition user reconfigures, and upgrades original combination.
Step S610: combined sound is play;
Wherein, combination source of sound is play, when mobile phone needs the business generation (as sent a telegram here or carrying out note) reminded, systems axiol-ogy is contact person in mobile phone to current behavior target, and this contact store has corresponding combination source of sound, then to play the form of combination source of sound, with the natural voice reminder user of cordiality, the generation of this business.
These are only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.