CN103646644A - Method and apparatus for obtaining voice recognition service information recognition - Google Patents
Method and apparatus for obtaining voice recognition service information recognition Download PDFInfo
- Publication number
- CN103646644A CN103646644A CN201310683946.8A CN201310683946A CN103646644A CN 103646644 A CN103646644 A CN 103646644A CN 201310683946 A CN201310683946 A CN 201310683946A CN 103646644 A CN103646644 A CN 103646644A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- speech recognition
- business information
- recognition
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of voice recognition, and provides a method and apparatus for obtaining voice recognition service information recognition, for improving interaction information processing efficiency. The method comprises: acquiring voice information of a user; obtaining an operation instruction corresponding to the voice information, voice recognition service information corresponding to the operation instruction and an information collecting template corresponding to the voice recognition service information, wherein the information collecting template comprises a set of reaction information of the user for the voice recognition service information; presenting the voice recognition service information to the user; collecting the reaction information of the user for the voice recognition service information; and according to the collected reaction information and the information collecting template, obtaining the recognition of the user for the voice recognition service information. The method and apparatus provided by the invention are applied to a mobile terminal technology.
Description
Technical field
The present invention relates to speech recognition technology field, relate in particular to a kind of method and apparatus that obtains speech recognition business information degree of recognition.
Background technology
The utilization of speech recognition technology on mobile terminal can provide the man-machine interaction service that is easy to experience for user.Because speech recognition technology is not yet ripe, in utilization process, speech recognition system need to be collected mobile phone users for the accuracy rate of speech recognition or the evaluation of satisfaction feedback, and is optimized adjustment according to user's evaluation feedback, to improve the accuracy rate of speech recognition.
The speech recognition system of mobile terminal comprises voice assistant, phonitic entry method etc.When voice assistant moves, usually adopt and repeat the mode of confirming, for user provides an optimum recognition result, prompting user confirms or cancels this recognition result; When phonitic entry method is moved, usually a plurality of recognition results are presented to user, prompting user selects the most satisfied result.User, confirm, after the feedback such as cancellation or selection, according to user's feedback, determine that user is for the satisfaction of recognition result.
Due to the reason such as user pronunciation is nonstandard, user speech information is indefinite or recognition capability is limited, that voice assistant or phonitic entry method all usually cannot identify the expressed content of user uniquely, therefore, at this moment needing provides plural recognition result to user, and allows user therefrom according to self wish, initiatively select the result of its expectation.But the efficiency of processing interactive information by the interactive mode that this user of needs selects is lower.
Summary of the invention
Embodiments of the invention provide a kind of method and apparatus that obtains the degree of recognition of speech recognition business information, can improve the efficiency of processing interactive information.
For achieving the above object, embodiments of the invention adopt following technical scheme:
First aspect, provides a kind of method of obtaining the degree of recognition of speech recognition business information, comprising:
Gather user's voice messaging;
Obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
To described user, present described speech recognition business information;
Collect the reaction information of described user to described speech recognition business information;
According to described reaction information and the described information search template collected, obtain the degree of recognition of described user to described speech recognition business information.
In conjunction with first aspect, in the possible implementation of the first of first aspect, described obtain speech recognition business information that the operational order that described voice messaging is corresponding, described operational order are corresponding and information search template corresponding to described speech recognition business information before, described method also comprises:
To server, upload described user's voice messaging, so that described server is determined the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding according to described voice messaging;
Describedly obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding comprise:
Receive corresponding speech recognition business information and information search template corresponding to described speech recognition business information of operational order, described operational order corresponding to described voice messaging that described server sends.
In conjunction with the possible implementation of the first of first aspect or first aspect, in the possible implementation of the second of first aspect, described information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of described business information and business information;
Described according to described reaction information and the described information search template collected, obtain described user the degree of recognition of described speech recognition business information is comprised:
According to the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information in the described reaction information of collecting and described information search template, determine the degree of recognition of described user to described speech recognition business information.
In conjunction with the possible implementation of the first of first aspect, in the third possible implementation of first aspect, described according to described reaction information and the described information search template collected, obtain described user the degree of recognition of described speech recognition business information is comprised:
To described server, upload the described reaction information of collection, so that the user that described server is preserved according to self determines the degree of recognition of described user to described speech recognition business information to the corresponding relation of the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Receive described user that described server the sends degree of recognition to described speech recognition business information.
In conjunction with first aspect, in the 4th kind of possible implementation of first aspect, described obtain described user to the degree of recognition of described speech recognition business information after, described method also comprises:
According to described user, the degree of recognition of described speech recognition business information is optimized speech recognition algorithm;
Or, to described server, upload the degree of recognition of described user to described speech recognition business information, so that described server is optimized speech recognition algorithm the degree of recognition of described speech recognition business information according to described user.
In conjunction with first aspect, in the 5th kind of possible implementation of first aspect, described obtain described user to the degree of recognition of described speech recognition business information after, described method also comprises:
To described user, show described degree of recognition;
Obtain the actual degree of recognition of the speech recognition business information after described user modifies to described degree of recognition;
According to described actual degree of recognition, the accuracy rate of statistics of speech recognition.
Second aspect, provides a kind of device that obtains the degree of recognition of speech recognition business information, comprising:
Acquiring unit, for gathering user's voice messaging;
Described acquiring unit also for: obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
Output unit, the described speech recognition business information of obtaining for present described acquiring unit to described user;
Described acquiring unit also for: collect the reaction information of described user to described speech recognition business information;
Processing unit, for described reaction information and the described information search template of collecting according to described acquiring unit, obtains the degree of recognition of described user to described speech recognition business information.
In conjunction with second aspect, in the possible implementation of the first of second aspect, described device also comprises:
Transmitting element, for upload the described user's of described acquiring unit collection voice messaging to server, so that described server is determined the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding according to described voice messaging;
Described acquiring unit specifically for:
Receive corresponding speech recognition business information and information search template corresponding to described speech recognition business information of operational order, described operational order corresponding to described voice messaging that described server sends.
In conjunction with the possible implementation of the first of second aspect or second aspect, in the possible implementation of the second of second aspect, described information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Described processing unit specifically for:
The corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information in the described information search template that the described reaction information of collecting according to described acquiring unit and described acquiring unit obtain, determines the degree of recognition of described user to described speech recognition business information.
In conjunction with the possible implementation of the first of second aspect, in the third possible implementation of second aspect, described processing unit specifically for:
To described server, upload the described reaction information that described acquiring unit is collected, so that the user that described server is preserved according to self determines the degree of recognition of described user to described speech recognition business information to the corresponding relation of the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Receive described user that described server the sends degree of recognition to described speech recognition business information.
In conjunction with second aspect, in the 4th kind of possible implementation of second aspect, described processing unit also for:
The described user who obtains according to described acquiring unit is optimized speech recognition algorithm the degree of recognition of described speech recognition business information;
Or, to described server, upload described user that described acquiring unit the obtains degree of recognition to described speech recognition business information, so that described server is optimized speech recognition algorithm the degree of recognition of described speech recognition business information according to described user.
In conjunction with second aspect, in the 5th kind of possible implementation of second aspect, described output unit also for: to described user, show the described degree of recognition that described processing unit obtains;
Described acquiring unit is also for the actual degree of recognition of obtaining the described speech recognition business information after described user modifies to described degree of recognition;
Described processing unit is also for the described actual degree of recognition of obtaining according to described acquiring unit, the accuracy rate of statistics of speech recognition.
The method and apparatus of the degree of recognition of obtaining speech recognition business information providing according to embodiments of the invention, after gathering user's voice messaging, obtains described voice messaging is carried out to speech recognition speech recognition business information afterwards.Then, to user, show and present described speech recognition business information, and collect the reaction information of user to described speech recognition business information.Because whether user approves the attitude of described speech recognition business information, lie in described reaction information, therefore, in conjunction with described reaction information and information search template corresponding to described business information obtained in advance, can obtain the degree of recognition of described user to described speech recognition business information.Lower with respect to the efficiency that may cause for the result that user provides plural recognition result and prompting user therefrom to select to meet expectation processing interactive information in prior art, the method and apparatus that obtains speech recognition business information degree of recognition that the embodiment of the present invention provides can obtain the degree of recognition of user to described speech recognition business information without user's active intervention, therefore, can improve the efficiency of processing interactive information.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of an embodiment of the method for the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 2 is the process flow diagram of another embodiment of the method for the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 3 is the process flow diagram of another embodiment of the method for the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 4 is the process flow diagram of a specific embodiment of the method for the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 5 A is the structural drawing of an embodiment of the device of the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 5 B is the structural drawing of another embodiment of the device of the present invention's degree of recognition of obtaining speech recognition business information;
Fig. 6 is the structural drawing of another embodiment of the device of the present invention's degree of recognition of obtaining speech recognition business information.
Embodiment
Below in conjunction with accompanying drawing, the technical scheme of the embodiment of the present invention is clearly described, obviously, described embodiment is only a part of embodiment of the present invention, rather than whole embodiment.Embodiment based in the present invention, the every other embodiment that those of ordinary skills obtain under the prerequisite of not making creative work, belongs to the scope of protection of the invention.
The method that the embodiment of the present invention provides can be implemented by the mobile terminal with speech recognition system, and described mobile terminal can be for example mobile phone, panel computer etc.Described mobile terminal also can interconnection network, under the support of the speech engine of server, works.
Fig. 1 is the process flow diagram of an embodiment of the present invention's method of obtaining speech recognition business information degree of recognition.For easy, speech recognition business information can be called business information.The method of the degree of recognition of obtaining speech recognition business information that as shown in Figure 1, the embodiment of the present invention provides comprises:
11, collection user's voice messaging.
At mobile terminal, start after speech-recognition services, mobile terminal gathers user's voice messaging.Described voice messaging can be for example: order mobile terminal is carried out a certain operation, and order mobile terminal is according to the automatic input characters of user's speech, and order mobile terminal is answered the problem of user's proposition etc.
12, obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information.
In concrete application, mobile terminal can self be determined or obtain described operational order, described business information and described information search template from server.That is,, after collecting voice messaging, mobile terminal can carry out speech recognition to this voice messaging and obtain operational order, business information, and definite information search template; Or, after collecting voice messaging, mobile terminal also can send server by this voice messaging, by server, this voice messaging is carried out to speech recognition and obtain operational order, business information and determine information search template, then mobile terminal obtains business information and information search template by server again.
Wherein, operational order is by carrying out speech recognition to voice messaging and semantic analysis obtains.By executable operations instruction, can call various forms of business information.Described business information can be various media formats, such as word, sound, image, animation etc.; Can be that mobile terminal calls from the storage of this locality, can be also that mobile terminal obtains from network; Can be the various media informations of presenting to user while starting to call certain program, can be also the program user's of presenting in service various media informations.Particularly, by speech recognition, obtain and the corresponding word of this voice messaging.In some applications, for example, in phonitic entry method, can be using word as business information.Generally, can also carry out semantic analysis to word, through obtaining after semantic analysis and the semantic corresponding operational order of word, with the corresponding operational order of voice messaging.Then, by executable operations instruction, obtain the business information that voice messaging is corresponding.
Determine that the information search template procedure corresponding with business information is specially: according to business information, determine the application scenarios (for example, make a phone call, consult a map etc.) that this business information is pointed to.Then, can be according to judged application scenarios, from comprise the database of the corresponding information search template of numerous application scenarioss, select the information search template corresponding with judged application scenarios.Information search template can comprise the set of user to the multiple reaction information of business information.For example, send under the scene of voice messaging " being please my reading short message " user to mobile terminal, it is to report note that server is judged application scenarios.Under this application scenarios, the information search template that server produces can comprise: collected user and double-click homepage key and interrupt note and report, do not collect user and double-click homepage key and interrupt note and report, collected user and say other orders, or do not collect user and say other orders etc.
13, to described user, present described business information.
In this step, the business information that described mobile terminal can direct various media formats is presented to user.
14, collect the reaction information of described user to described business information.
Mobile terminal can be to user's display business information, or from gathering user's voice messaging, collect the reaction information of user to this business information.In this process, whether described mobile terminal does not clearly point out user accurately to evaluate described business information, that is, described reaction information is initiatively got involved without user, and mobile terminal can obtain.Wherein, the button operation that user's reaction information for example can carry out for user on described mobile terminal, touch screen operation, phonetic entry operation etc.
15, according to described reaction information and the described information search template collected, obtain the degree of recognition of described user to described business information.
In this step, in the situation that mobile terminal self is determined information search template, if this information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of business information and business information, mobile terminal can, directly according to reaction information and the information search template collected, be determined the degree of recognition of this user to this business information; If information search template does not comprise described corresponding relation, described mobile terminal can be after collecting described reaction information, then determine described degree of recognition according to the described corresponding relation in the storage of this locality.
In the situation that mobile terminal is collected template from server obtaining information, if information search template comprises the corresponding relation of user to the degree of recognition of the reaction information of business information and business information, mobile terminal can, directly according to reaction information and the described information search template collected, be determined the degree of recognition of user to business information; If described information search template does not comprise described corresponding relation, mobile terminal can send to server by reaction information, the described corresponding relation of being stored according to self by server is determined described degree of recognition, this server, after determining described degree of recognition, sends to mobile terminal by described degree of recognition.
The degree of recognition of user to speech recognition business information, is also the degree of recognition of user to business information, refers to the degree that user thinks that business information is consistent with user's voice messaging.Because user comprises the feedback information of user to business information to the reaction information of business information, for example comprise the attitude whether user approves this business information, therefore, although user does not have directly to provide clearly the degree of recognition to described business information, mobile terminal and server can obtain the degree of recognition of user to business information to the reaction information of business information by analysis user.And, because the criterion that mobile terminal or server judgement user adopts the degree of recognition of business information is unified and objective, can reduce the different errors in judgement that cause because of user, therefore, than user self, directly provide degree of recognition, the degree of recognition judging according to method provided by the invention has more objectivity.
For example, in the situation that user requires mobile terminal to be its inquiry traffic, when mobile terminal is shown electronic chart for user, for example, if this mobile terminal in the given time (30 seconds) does not receive user's instruction, can determine a reaction information (being not receive user's instruction in the schedule time).Although user clearly answers, whether do not approve this inquiry,, the information of this inquiry of customer's approval is in implicit this reaction information, therefore, mobile terminal can be according to this reaction information judgement customer's approval this inquiry.Visible, user's reaction can be non-action.Again for example, in the situation that mobile terminal receives user's the order of calling, mobile terminal after the order that identifies user, not inquiry " you will make a phone call to Zhang San? confirm or cancel ", but directly to Zhang San, make a phone call.If mobile terminal was not collected the reaction that user hangs up the telephone immediately, can judge this speech recognition of customer's approval.
In this step, because the user who collects may be a lot of to the reaction information of business information, therefore, need in conjunction with the information search template of obtaining in advance, determine the user be contained in this information search template reaction information to business information, thereby realize user's obtaining the degree of recognition of business information.
Above-described embodiment is the description to a speech recognition, and wherein, mobile terminal can be take user to user to the collection process of the reaction information of business information and be sent voice messaging as starting point, till display business information completes; Also the beginning display business information of can take is starting point, till display business information completes.In addition, in a front speech recognition and display business information, not yet finish, in the situation that a rear speech recognition has started, mobile terminal can using the user's who collects reaction information as user the reaction information to a rear speech recognition.Certainly, under special circumstances, for example to trigger the action of a rear speech recognition be the reaction to a front business information to user input voice information in essence, user input voice information trigger the action message of a rear speech recognition need be as the reaction information of a front speech recognition.
In the embodiment of the present invention, mobile terminal gathers user's voice messaging, also obtains this voice messaging is carried out to speech recognition business information afterwards.Then, mobile terminal presents this business information to user, and collects the reaction information of user to described business information.Because whether user approves the attitude of described business information, be included in described reaction information, therefore, in conjunction with described reaction information and information search template corresponding to described business information obtained in advance, can obtain the degree of recognition of described user to described business information.Therefore, with respect to may plural recognition result being provided and pointing out user therefrom to select to meet the result of expectation for user in prior art, cause processing the efficiency of interactive information lower and increase user's operation burden and cause user's dislike, the method of obtaining speech recognition business information degree of recognition providing according to the embodiment of the present invention, by automatic collection user to the reaction information of the business information of speech recognition and described information search template, in the situation that initiatively getting involved without user, just can obtain the degree of recognition of user to business information, therefore, can improve the efficiency of processing interactive information.
Fig. 2 is the process flow diagram of another embodiment of the present invention's method of obtaining speech recognition business information degree of recognition.The present embodiment is applied to mobile terminal and from server, obtains the scene of operational order, business information and information search template.As shown in Figure 2, the method for obtaining speech recognition degree of recognition that the embodiment of the present invention provides comprises:
21, mobile terminal gathers user's voice messaging and this voice messaging is sent to server.
After starting speech-recognition services, mobile terminal can gather in the mode of recording user's voice messaging.After recording completes, mobile terminal can send to server by this voice messaging.
22, server carries out speech recognition to voice messaging and obtains the operational order that this voice messaging is corresponding and this operational order is sent to mobile terminal.
Particularly, server (comprising the speech engine on it), after receiving the voice messaging of mobile terminal transmission, can carry out speech recognition to this voice messaging, obtains the possible outcome of speech recognition.Described possible outcome is and the corresponding word of this voice messaging.Limited in one's ability due to speech recognition, possible outcome may be for a plurality of.If the possible outcome of speech recognition is a plurality of, server can be selected optimum result from the possible outcome of a plurality of speech recognitions, the result meeting most with voice messaging.And server can also further carry out semantic analysis to described word and obtain and the semantic corresponding operational order of described word.Then, server sends to mobile terminal by this operational order.
23, mobile terminal receives also executable operations instruction to obtain business information and information search template corresponding to this business information from server.
Mobile terminal is by carrying out the operational order corresponding with voice messaging to obtain the business information corresponding with this operational order from server.Wherein, mobile terminal is different from prior art when executable operations instruction can produce the result that a plurality of users of needs select, but an independent execution result.Like this, can simplify user's operation, the experience of optimizing user.Business information can apply in speech control system or Intelligent dialogue inquiry system.Wherein, speech control system refers to the system of carrying out the operation of opertaing device with voice messaging.Intelligent dialogue inquiry system refers to according to user's voice messaging and operates, for user provides the system of nature, friendly Database Retrieval Service.
After determining business information, server also needs further to determine the information search template corresponding with this business information, and its process can be with reference to the process of determining the information search template corresponding with business information of describing in step 12.
24, server sends to mobile terminal by business information and information search template, and mobile terminal is presented to user by this business information.
In this step, business information and information search template that mobile terminal reception server sends, and business information is presented to user.
For example, if user to mobile terminal is said " near traffic how? " voice messaging, it is " near traffic " that server can identify the corresponding word of this voice messaging, and to analyze semanteme that word is corresponding be inquiry traffic, place is near the current position of user.Then, server controls mobile terminal starts electronic chart, for user shows that a width is with the map of Real-time Traffic Information, and the current position of user is presented to center.
25, mobile terminal is collected the reaction information of user to business information.
In this step, mobile terminal for example can be in the mode to the operation of mobile terminal of supervisory user, monitoring and collection user's reaction information.
For example, when the present invention applies to speech control system or Intelligent dialogue inquiry system, if mobile terminal is presented to user's business information and user's voice messaging conforms to, and user approves the reaction of business information, such as user, do not interrupt that business information continues to present etc., collected user be that user does not interrupt business information and continues to present to the reaction information of business information to mobile terminal.If if mobile terminal business information and user's voice messaging is not inconsistent, and user does not approve the reaction of business information, such as presenting of User break business information etc., collected user be presenting of User break business information to the reaction information of business information to mobile terminal.
26, mobile terminal is determined the user be contained in the information search template reaction information to business information.
According to mentioned above, after determining business information, server can further be determined the information search template corresponding with this business information, and this information search template is sent to mobile terminal.Like this, get user to the information of business information after, mobile terminal can be in conjunction with the information search template of obtaining in advance, determines the user that is contained in the information search template reaction information to business information, thereby realizes user's obtaining business information degree of recognition.
In addition, due to user do reactions vary establish a capital relevant to business information degree of recognition to user, therefore, collection user reaction information complete after, can utilize information search template to screen reaction information, select and can determine the reaction information of user to the degree of recognition of business information.
27, mobile terminal, according to being contained in user in information search template to the set of the reaction information of business information, the corresponding relation of user to the degree of recognition of the reaction information of business information and business information, is determined the degree of recognition of user to business information.
User can be contained in information search template the corresponding relation of the degree of recognition of the reaction information of business information and business information.Described corresponding relation can be used as and judges whether user approves the criterion of speech recognition business information.For example, in the example of above-mentioned report note, described corresponding relation can be: user does not double-click homepage key, and to interrupt the degree of recognition of respective user high; The degree of recognition that user does not say other order respective user is high; User double-clicks homepage key, and to interrupt the degree of recognition of respective user very low; The degree of recognition that user says other order respective user is very low.
After determining that the user be contained in information search template is to the reaction information of business information, in conjunction with described corresponding relation, can judge the degree of recognition of user to business information.
In addition, mobile terminal according to above-mentioned mode, judge user to the degree of recognition of business information after, this degree of recognition can be sent to server.Or, mobile terminal does not carry out the judgement of degree of recognition, but user is sent to server to the reaction information of business information or the user that is contained in information search template to the reaction information of business information, so that the user that server is preserved according to self judges the degree of recognition of user to business information to the corresponding relation of the degree of recognition of the reaction information of business information and business information.After judging described degree of recognition, server can return to this degree of recognition to mobile terminal.
Server obtain described user to the degree of recognition of described business information after, can to speech recognition algorithm, be optimized according to described degree of recognition, algorithm strengthens again.Algorithm strengthen again refer to server according to the user that repeatedly obtains the degree of recognition to business information, this degree of recognition is carried out to the processing such as statistical study, draw for a certain definite voice messaging the degree of recognition sequence of a plurality of speech recognition possible outcomes.Like this, in identification afterwards, for same voice messaging, tending to provides for user the recognition result that degree of recognition is the highest.
28, mobile terminal shows described degree of recognition to user, and obtains the actual degree of recognition of the business information after user modifies to described degree of recognition.
After definite user is to the degree of recognition of business information, mobile terminal can also show described degree of recognition to user.The icon that for example, can show a degree of recognition on mobile terminal.Like this, user can be by checking that this icon knows the degree of recognition of mobile terminal or server automatic discrimination.And user can be revised as described degree of recognition the actual degree of recognition of user to business information.Mobile terminal can also obtain this actual degree of recognition, and then the accuracy rate of adding up repeatedly speech recognition.According to this accuracy rate, can optimize decision rule and speech recognition algorithm.
With respect to providing plural recognition result for user in prior art, and prompting user therefrom selects the result of its expectation, cause processing the efficiency of interactive information lower and increase user's operation burden and cause user's dislike, the method of obtaining speech recognition business information degree of recognition providing according to the embodiment of the present invention, by automatic collection user to the reaction information of the business information of speech recognition and information search template, can be in the situation that initiatively getting involved without user, just can the degree of recognition of automatic acquisition user to business information, therefore, can improve the efficiency of processing interactive information.
Fig. 3 is the process flow diagram of the another embodiment of the present invention's method of obtaining speech recognition business information degree of recognition.The present embodiment is applied to the scene that mobile terminal self is determined operational order, business information and information search template.As shown in Figure 3, the method for obtaining speech recognition business information degree of recognition that the embodiment of the present invention provides comprises:
31, mobile terminal gathers user's voice messaging.
32, mobile terminal identification voice messaging obtains the operational order that this voice messaging is corresponding.
With reference to the explanation of step 12, after getting voice messaging, mobile terminal can carry out speech recognition and semantic analysis to this voice messaging, obtains the word that this voice messaging is corresponding, and the operational order of described word is extracted in generation from lteral data storehouse.
33, the instruction of mobile terminal executable operations obtains the business information that this operational order is corresponding, and determines information search template corresponding to this business information.
In the situation that user's wish is passed through voice entry system input characters, the instruction of mobile terminal executable operations is extracted corresponding word as business information from lteral data storehouse.And mobile terminal also needs to determine information search template corresponding to business information.
34, mobile terminal is to user's display business information.
After obtaining the business information of written form, mobile terminal can directly show the word content of user's wish input on display screen.
35, mobile terminal is collected the reaction information of user to business information.
In this step, if the word that mobile terminal shows to user conforms to user's voice messaging, and user approves the reaction of described word, for example user can retain described word, input follow-up word etc., collected user be that user retains described word to the reaction information of business information to mobile terminal, inputs follow-up word.If described word and voice messaging are not inconsistent, user do not approve the reaction of described word, and for example user can delete described word, re-enters word etc., collected user be that user deletes described word to the reaction information of business information to mobile terminal, re-enters word etc.Mobile terminal can start input voice information from user and start, and in the mode of the operational order of supervisory user, user is monitored and is collected the reaction information of business information.
36, mobile terminal is determined the degree of recognition of user to business information according to reaction information and information search template.
37, mobile terminal shows described degree of recognition to user, and obtains the actual degree of recognition of the business information after user modifies to described degree of recognition.
Mobile terminal, after definite user is to the degree of recognition of business information, can be optimized speech recognition algorithm according to described degree of recognition, and detailed process can be with reference to the description of step 27 and 28.
With respect to providing plural recognition result for user in prior art, and prompting user therefrom selects to meet the result of expectation, cause processing the efficiency of interactive information lower and increase user's operation burden and cause user's dislike, the method of obtaining speech recognition business information degree of recognition that the embodiment of the present invention provides initiatively gets involved without user, just can automatic acquisition user to the degree of recognition of business information and raising, process the efficiency of interactive information.
For understanding better the present invention, several specific embodiments of take again are below further described the present invention as example.Also must note, below cited embodiment be a part of embodiment of the present invention, those skilled in the art, by content of the present invention, can be easy to expect other embodiment, they all within the scope of the invention.
Fig. 4 is the process flow diagram of a specific embodiment of the present invention's method of obtaining speech recognition business information degree of recognition.In this specific embodiment, to be mobile phone describe as example the mobile terminal of take.The speech engine on server with speech identifying function.For easy, the relative side of the mobile phone with as mobile terminal is referred to as to server (comprising speech engine).As shown in Figure 4, the method for obtaining speech recognition business information degree of recognition that the specific embodiment of the invention provides comprises:
41, the voice messaging that mobile phone is inquired about weather to user is recorded, and the voice messaging after recording is sent to server.
For example, after the application program (can be voice assistant) of mobile phone opening voice identification service, user sends voice messaging to mobile phone.For example, user says " these two days Shanghai weather how ".Then, what is said or talked about records to user for mobile phone.After recording completes, mobile phone can send to server by the recording fragment/recording stream obtaining by recording.
42, server carries out speech recognition and semantic analysis to voice messaging, obtains inquiring about the operational order of weather and selects the information search template corresponding with this operational order.
For example, the word that server identifies is " two days Shanghai weather ", and analyze relevant semanteme be inquiry weather, place is Shanghai.Server can, according to described semanteme, produce the operational order of controlling mobile phone unlocking electronic map.
In addition, server, also according to analyzed semanteme, judges the application scenarios (for example, make a phone call, consult a map etc.) that voice messaging points to.Then, can be according to judged application scenarios, from comprise the database of the corresponding information search template of numerous application scenarioss, select the information search template corresponding with this application scenarios.For example, the in the situation that of above-mentioned inquiry weather, information search template can comprise: when mobile phone is reported Weather information, user has listened the fruit that finishes, or user listened the fruit that finishes to be less than 10%, or user has clicked the link in result etc.In the situation that user requires mobile phone, be that it inquires about traffic conditions or cartographic information near its position, information search template can comprise: at mobile phone, be that the user of institute is while showing a secondary map, user's attonity time surpasses 30s, or user's gesture etc. of not sliding.
43, server sends to mobile phone by operational order and information search template, and mobile phone receives and carry out this operational order, obtains Weather information and reports this Weather information to user.
Execution result can be carried out immediately and produce to mobile phone after receiving operational order, do not need user confirm, cancel or select.The above-mentioned inquiry Shanghai weather on the same day of also take is example, server is not when going out semanteme for " inquiry weather ", send to the fill order of mobile phone can not be " weather in inquiry Shanghai; PLSCONFM or cancellation ", but do not inquire user, directly obtain the weather by the Shanghai of server lookup, and Weather information is reported to user.
44, mobile phone is collected the reaction information of user to Weather information automatically.
User, to mobile phone, say under the scene of order of " these two days Shanghai weather how ", if mobile phone is reported the Weather information weather condition in this two days Shanghai just to user, user may listen and finished fruit or clicked the link in result.Now, mobile phone was collected user is that user has listened the fruit that finishes to the reaction information of Weather information, or user has clicked the link in result.If mobile phone reports to user the weather condition that Weather information is not this two days Shanghai, user may listen the fruit that finishes to be less than 10%.Now, mobile phone collected user to the reaction information of Weather information be user listened finish fruit be less than 10%.
45, mobile phone, is determined and is contained in the reaction information of the user of this information search template to this Weather information the reaction information of Weather information and information search template according to user.
For example, under scene at above-mentioned user command mobile phone for its inquiry Shanghai weather, processor in mobile phone was collected user: user has listened the fruit that finishes, and user has clicked link or the user in result and listened the fruit that finishes to be less than 10%.Mobile phone can judge that according to information search template above-mentioned reaction information all belongs to the reaction information of user to this Weather information.Except above-mentioned reaction information, mobile phone also may be collected user and do other actions, for example, answered phone, but this action is not contained in information search template, and therefore, mobile phone excludes user's reaction information possible to this Weather information by this action.Like this, can realize obtaining of described degree of recognition.
46, mobile phone is according to being contained in the user of information search template to the reaction information of Weather information, the corresponding relation of user to the degree of recognition of the reaction information of Weather information and business information, determine the degree of recognition of user to this Weather information, and described degree of recognition is sent to server.
User can use scoring or the mode of classification to the degree of recognition of Weather information, such as feeling quite pleased, be satisfied with, general, be unsatisfied with etc.User can be for judging whether user approves the criterion of described Weather information to the corresponding relation of the degree of recognition of the reaction information of Weather information and business information.For example, in the example of above-mentioned inquiry weather, described corresponding relation can be: if user has listened the fruit that finishes, judge that user identifies degree of recognition high; If user has listened the fruit that finishes to be less than 10%, judge that user identifies degree of recognition very low; If user has clicked the link in result, judge that user identifies degree of recognition high.
With respect to providing plural recognition result for user in prior art, and prompting user therefrom selects the result of its expectation, cause processing the efficiency of interactive information lower and increase user's operation burden and cause user's dislike, the method of obtaining speech recognition business information degree of recognition providing according to the embodiment of the present invention, by automatic collection user to the reaction information of the business information of speech recognition and described information search template, can be in the situation that initiatively getting involved without user, just can the degree of recognition of automatic acquisition user to business information, therefore, can improve the efficiency of processing interactive information.
A kind of method of obtaining speech recognition business information degree of recognition providing with the embodiment of the present invention is corresponding, and the embodiment of the present invention also provides a kind of device that obtains speech recognition business information degree of recognition, and described device is specifically as follows mobile phone, computing machine etc.As shown in Figure 5A, a kind of device 50 that obtains speech recognition business information degree of recognition that the embodiment of the present invention provides comprises:
Acquiring unit 51, for gathering user's voice messaging;
Described acquiring unit 51 also for: obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
Described acquiring unit 51 also for: collect the reaction information of described user to described speech recognition business information;
Processing unit 53, for described reaction information and the described information search template of collecting according to acquiring unit 51, obtains the degree of recognition of described user to described speech recognition business information.
Further, described information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information; Processing unit 53 specifically for: the described reaction information of collecting according to acquiring unit 51 and and the described information search template obtained of acquiring unit 51 in the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information, determine the degree of recognition of described user to described speech recognition business information.
Alternatively, processing unit 53 also for: the described user who obtains according to acquiring unit 51 is optimized speech recognition algorithm the degree of recognition of described speech recognition business information.
Alternatively, output unit 52 is also for the described degree of recognition obtained to described user's display processing unit 53; Acquiring unit 51 is also for the actual degree of recognition of obtaining the described speech recognition business information after described user modifies to described degree of recognition; Processing unit 53 is also for the described actual degree of recognition of obtaining according to acquiring unit 51, the accuracy rate of statistical service information.
The device that obtains speech recognition business information degree of recognition providing according to embodiments of the invention, described device, after gathering user's voice messaging, obtains described voice messaging is carried out to speech recognition business information afterwards.Then, described device shows described business information to user, and collects the reaction information of user to described business information.Because whether user approves the attitude of described business information, be included in described reaction information, therefore, in conjunction with described reaction information and information search template corresponding to described business information obtained in advance, can obtain the degree of recognition of described user to described business information.With respect to providing plural recognition result for user in prior art, and need user therefrom to select the result of its expectation, cause increasing user's operation burden and cause user's dislike, the device that obtains speech recognition business information degree of recognition that the embodiment of the present invention provides is initiatively being got involved and can obtained the degree of recognition of user to described speech recognition business information without user, therefore, can improve the efficiency of processing interactive information.
As shown in Figure 5 B, alternatively, in the present invention, obtain in another embodiment of device 50 of speech recognition business information degree of recognition, described device 50 also comprises: transmitting element 54, for upload the described user's of acquiring unit 51 collections voice messaging to server, so that described server is determined the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding according to described voice messaging; Acquiring unit 51 specifically for: receive corresponding speech recognition business information and information search template corresponding to described speech recognition business information of operational order, described operational order corresponding to described voice messaging that described server sends.
Alternatively, processing unit 53 also for: to described server, upload described user that acquiring unit 51 the obtains degree of recognition to described speech recognition business information, so that described server is optimized speech recognition algorithm the degree of recognition of described speech recognition business information according to described user.
Alternatively, processing unit 53 specifically for: to described server, upload the described reaction information that acquiring unit 51 is collected, so that the user that described server is preserved according to self determines the degree of recognition of described user to described business information to the corresponding relation of the degree of recognition of the speech recognition reaction information of described business information and speech recognition business information; And, receive described user that described server the sends degree of recognition to described speech recognition business information.
Fig. 6 is the structural drawing of the another embodiment of the present invention's device of obtaining speech recognition business information degree of recognition.As shown in Figure 6, the device 60 that obtains speech recognition business information degree of recognition of the present embodiment comprises: at least one processor 61, storer 62, microphone 63, display screen and loudspeaker 64, communication interface 65 and bus.Processor 61, storer 62, microphone 63, display screen and loudspeaker 64, communication interface 65 are connected by bus and complete mutual communication.Described bus can be industry standard architecture (Industry Standard Architecture, referred to as ISA) bus, peripheral component interconnect (Peripheral Component, referred to as PCI) bus or extended industry-standard architecture (Extended Industry Standard Architecture, referred to as EISA) bus etc.Described bus can be divided into address bus, data bus, control bus etc.For ease of representing, in Fig. 6, only with a thick line, represent, but do not represent only to have the bus of a bus or a type.Wherein:
Microphone 63 is for gathering user's voice messaging;
Processor 61 is for obtaining the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding from storer 62, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
The described speech recognition business information that display screen and loudspeaker 64 obtain for present processor 61 to described user;
Processor 61 is also for collecting the reaction information of described user to described speech recognition business information, and according to described reaction information and the described information search template collected, obtains the degree of recognition of described user to described speech recognition business information.
Processor 61 may be a central processing unit (Central Processing Unit, referred to as CPU), or specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or be configured to implement one or more integrated circuit of the embodiment of the present invention.
It should be noted that, above-mentioned processor 61, except having above-mentioned functions, also can be used for carrying out other flow processs in said method embodiment, does not repeat them here.
Storer 62 may comprise high-speed RAM storer, also may also comprise nonvolatile memory (non-volatile memory), for example at least one magnetic disk memory.
Communication interface 65 is mainly used in realizing the device 60 that obtains speech recognition business information degree of recognition the communicating by letter with other equipment or between installing of the present embodiment.
Each embodiment in this instructions is existing to be stressed to be described, between each embodiment identical similar part mutually referring to, each embodiment stresses is the difference with other embodiment.Especially, for device embodiment, because it is substantially similar in appearance to embodiment of the method, so describe fairly simplely, relevant part is referring to the part explanation of embodiment of the method.
It should be noted that, device embodiment described above is only schematic, the wherein said unit as separating component explanation can or can not be also physically to separate, the parts that show as unit can be or can not be also physical locations, can be positioned at a place, or also can be distributed in a plurality of network element.Can select according to the actual needs some or all of module wherein to realize the object of the present embodiment scheme.In addition, in device embodiment accompanying drawing provided by the invention, the annexation between module represents to have communication connection between them, specifically can be implemented as one or more communication bus or signal wire.Those of ordinary skills, in the situation that not paying creative work, are appreciated that and implement.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited to this, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (12)
1. a method of obtaining the degree of recognition of speech recognition business information, is characterized in that, comprising:
Gather user's voice messaging;
Obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
To described user, present described speech recognition business information;
Collect the reaction information of described user to described speech recognition business information;
According to described reaction information and the described information search template collected, obtain the degree of recognition of described user to described speech recognition business information.
2. method according to claim 1, it is characterized in that, described obtain speech recognition business information that the operational order that described voice messaging is corresponding, described operational order are corresponding and information search template corresponding to described speech recognition business information before, described method also comprises:
To server, upload described user's voice messaging, so that described server is determined the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding according to described voice messaging;
Describedly obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding comprise:
Receive corresponding speech recognition business information and information search template corresponding to described speech recognition business information of operational order, described operational order corresponding to described voice messaging that described server sends.
3. method according to claim 1 and 2, is characterized in that, described information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Described according to described reaction information and the described information search template collected, obtain described user the degree of recognition of described speech recognition business information is comprised:
According to the corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information in the described reaction information of collecting and described information search template, determine the degree of recognition of described user to described speech recognition business information.
4. method according to claim 2, is characterized in that, described according to described reaction information and the described information search template collected, obtains described user the degree of recognition of described speech recognition business information is comprised:
To described server, upload the described reaction information of collection, so that the user that described server is preserved according to self determines the degree of recognition of described user to described speech recognition business information to the corresponding relation of the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Receive described user that described server the sends degree of recognition to described speech recognition business information.
5. method according to claim 1, is characterized in that, described obtain described user to the degree of recognition of described speech recognition business information after, described method also comprises:
According to described user, the degree of recognition of described speech recognition business information is optimized speech recognition algorithm;
Or, to described server, upload the degree of recognition of described user to described speech recognition business information, so that described server is optimized speech recognition algorithm the degree of recognition of described speech recognition business information according to described user.
6. method according to claim 1, is characterized in that, described obtain described user to the degree of recognition of described speech recognition business information after, described method also comprises:
To described user, show described degree of recognition;
Obtain the actual degree of recognition of the speech recognition business information after described user modifies to described degree of recognition;
According to described actual degree of recognition, the accuracy rate of statistics of speech recognition.
7. a device that obtains the degree of recognition of speech recognition business information, is characterized in that, comprising:
Acquiring unit, for gathering user's voice messaging;
Described acquiring unit also for: obtain the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding, wherein, described information search template comprises the set of user to the reaction information of described speech recognition business information;
Output unit, the described speech recognition business information of obtaining for present described acquiring unit to described user;
Described acquiring unit also for: collect the reaction information of described user to described speech recognition business information;
Processing unit, for described reaction information and the described information search template of collecting according to described acquiring unit, obtains the degree of recognition of described user to described speech recognition business information.
8. device according to claim 7, is characterized in that, described device also comprises:
Transmitting element, for upload the described user's of described acquiring unit collection voice messaging to server, so that described server is determined the operational order that described voice messaging is corresponding, speech recognition business information and information search template corresponding to described speech recognition business information that described operational order is corresponding according to described voice messaging;
Described acquiring unit specifically for:
Receive corresponding speech recognition business information and information search template corresponding to described speech recognition business information of operational order, described operational order corresponding to described voice messaging that described server sends.
9. according to the device described in claim 7 or 8, it is characterized in that, described information search template also comprises the corresponding relation of user to the degree of recognition of the reaction information of described business information and speech recognition business information;
Described processing unit specifically for:
The corresponding relation of user to the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information in the described information search template that the described reaction information of collecting according to described acquiring unit and described acquiring unit obtain, determines the degree of recognition of described user to described speech recognition business information.
10. device according to claim 8, is characterized in that, described processing unit specifically for:
To described server, upload the described reaction information that described acquiring unit is collected, so that the user that described server is preserved according to self determines the degree of recognition of described user to described speech recognition business information to the corresponding relation of the degree of recognition of the reaction information of described speech recognition business information and speech recognition business information;
Receive described user that described server the sends degree of recognition to described speech recognition business information.
11. devices according to claim 7, is characterized in that, described processing unit also for:
The described user who obtains according to described acquiring unit is optimized speech recognition algorithm the degree of recognition of described speech recognition business information;
Or, to described server, upload described user that described acquiring unit the obtains degree of recognition to described speech recognition business information, so that described server is optimized speech recognition algorithm the degree of recognition of described speech recognition business information according to described user.
12. devices according to claim 7, is characterized in that,
Described output unit also for: to described user, show the described degree of recognition that described processing unit obtains;
Described acquiring unit is also for the actual degree of recognition of obtaining the described speech recognition business information after described user modifies to described degree of recognition;
Described processing unit is also for the described actual degree of recognition of obtaining according to described acquiring unit, the accuracy rate of statistics of speech recognition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310683946.8A CN103646644A (en) | 2013-12-12 | 2013-12-12 | Method and apparatus for obtaining voice recognition service information recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310683946.8A CN103646644A (en) | 2013-12-12 | 2013-12-12 | Method and apparatus for obtaining voice recognition service information recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103646644A true CN103646644A (en) | 2014-03-19 |
Family
ID=50251846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310683946.8A Pending CN103646644A (en) | 2013-12-12 | 2013-12-12 | Method and apparatus for obtaining voice recognition service information recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103646644A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104681023A (en) * | 2015-02-15 | 2015-06-03 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105138250A (en) * | 2015-08-03 | 2015-12-09 | 科大讯飞股份有限公司 | Human-computer interaction operation guide method, human-computer interaction operation guide system, human-computer interaction device and server |
| CN105631641A (en) * | 2015-12-28 | 2016-06-01 | 北京致远协创软件有限公司 | Flow processing method and apparatus |
| CN110619876A (en) * | 2019-09-26 | 2019-12-27 | 山东鲁能软件技术有限公司 | Voice processing method and device based on power transmission mobile application |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074230A (en) * | 2009-11-20 | 2011-05-25 | 索尼公司 | Speech recognition device, speech recognition method, and program |
| CN102760312A (en) * | 2012-06-20 | 2012-10-31 | 太仓博天网络科技有限公司 | Intelligent door control system with speech recognition |
| CN102800314A (en) * | 2012-07-17 | 2012-11-28 | 广东外语外贸大学 | English sentence recognizing and evaluating system with feedback guidance and method of system |
| CN103077234A (en) * | 2013-01-07 | 2013-05-01 | 季雪峰 | Voice website navigation system and method |
-
2013
- 2013-12-12 CN CN201310683946.8A patent/CN103646644A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102074230A (en) * | 2009-11-20 | 2011-05-25 | 索尼公司 | Speech recognition device, speech recognition method, and program |
| CN102760312A (en) * | 2012-06-20 | 2012-10-31 | 太仓博天网络科技有限公司 | Intelligent door control system with speech recognition |
| CN102800314A (en) * | 2012-07-17 | 2012-11-28 | 广东外语外贸大学 | English sentence recognizing and evaluating system with feedback guidance and method of system |
| CN103077234A (en) * | 2013-01-07 | 2013-05-01 | 季雪峰 | Voice website navigation system and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104681023A (en) * | 2015-02-15 | 2015-06-03 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN105138250A (en) * | 2015-08-03 | 2015-12-09 | 科大讯飞股份有限公司 | Human-computer interaction operation guide method, human-computer interaction operation guide system, human-computer interaction device and server |
| CN105631641A (en) * | 2015-12-28 | 2016-06-01 | 北京致远协创软件有限公司 | Flow processing method and apparatus |
| CN110619876A (en) * | 2019-09-26 | 2019-12-27 | 山东鲁能软件技术有限公司 | Voice processing method and device based on power transmission mobile application |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110782335B (en) | Method, device and storage medium for processing credit data based on artificial intelligence | |
| CN111611368B (en) | Method and device for backtracking public scene dialogue in multiple rounds of dialogue | |
| CN110381221B (en) | Call processing method, device, system, equipment and computer storage medium | |
| CN106993089A (en) | The method and apparatus that voice menu is shown | |
| CN106023994A (en) | Speech processing method, device and system | |
| CN109274831A (en) | A kind of audio communication method, device, equipment and readable storage medium storing program for executing | |
| CN105653233A (en) | Method and control terminal for associating voice signal with control instruction | |
| CN108933946B (en) | Voice-control-based live broadcasting attention method, storage medium, electronic equipment and system | |
| CN103646644A (en) | Method and apparatus for obtaining voice recognition service information recognition | |
| CN110399576B (en) | Page switching method and device, readable medium and electronic equipment | |
| CN113705943B (en) | Task management method and system based on voice intercom function and mobile device | |
| CN104967719A (en) | Contact information prompting method and terminal | |
| CN110784591A (en) | Intelligent voice automatic detection method, device and system | |
| CN111462726B (en) | Method, device, equipment and medium for answering out call | |
| CN112637428A (en) | Invalid call judgment method and device, computer equipment and storage medium | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| CN104463393A (en) | Speech-based agricultural product price collection method | |
| CN111710339A (en) | Voice recognition interaction system and method based on data visualization display technology | |
| CN110931010A (en) | Voice control system | |
| CN114997989A (en) | Loan request processing method and device based on block chain | |
| CN110634478A (en) | Method and apparatus for processing speech signal | |
| CN114202363A (en) | Artificial intelligence based call method, device, computer equipment and medium | |
| CN112101810A (en) | Risk event control method, device and system | |
| CN109857472A (en) | Towards the exchange method and device for having screen equipment | |
| CN110543556A (en) | Dialogue configuration method, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20171030 Address after: Metro Songshan Lake high tech Industrial Development Zone, Guangdong Province, Dongguan City Road 523808 No. 2 South Factory (1) project B2 -5 production workshop Applicant after: HUAWEI terminal (Dongguan) Co., Ltd. Address before: 518129 Longgang District, Guangdong, Bantian HUAWEI base B District, building 2, building No. Applicant before: Huawei Device Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140319 |
|
| RJ01 | Rejection of invention patent application after publication |