CN109360557A - The method, apparatus and computer equipment of voice control application program - Google Patents
The method, apparatus and computer equipment of voice control application program Download PDFInfo
- Publication number
- CN109360557A CN109360557A CN201811178885.9A CN201811178885A CN109360557A CN 109360557 A CN109360557 A CN 109360557A CN 201811178885 A CN201811178885 A CN 201811178885A CN 109360557 A CN109360557 A CN 109360557A
- Authority
- CN
- China
- Prior art keywords
- word
- voice messaging
- user
- operational order
- ingredient
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Abstract
The application provides the method, apparatus and computer equipment of a kind of voice control application program, wherein method includes: the voice messaging for acquiring user；Speech recognition is carried out to voice messaging, obtains the corresponding content of text of voice messaging；Content of text is segmented, preset intention library and ingredient library are inquired according to the word that participle obtains, determine result set corresponding with voice messaging；It include: intention word and ingredient word in result set；According to result set, inquiry instruction table generates operational order corresponding with voice messaging；Operational order is executed, the corresponding response message of voice messaging is obtained.This method can simplify the operating procedure of user, enrich the control mode of application program, improve the usage experience of user.
Description
Technical field
This application involves voice control technology field more particularly to a kind of method, apparatus of voice control application program and
Computer equipment.
Background technique
With the continuous development of mobile terminal technology, more and more application programs (Application, abbreviation APP) from
PC (Personal Computer, abbreviation PC) end moves to mobile terminal.Since mobile terminal is compared to the end PC, there is screen
The features such as curtain is small, typewriting is slow, finger dexterity is lower than mouse, therefore for the application program of mobile terminal, the height of operating experience
Low is a very important index.
Currently, typing speed greatly influences the operation of user slowly and makes for the operation of mobile terminal application program
It is converted to for this purpose, mobile terminal application program generally has intelligent sound input function by the voice for inputting user with experience
Content of text, to simplify the operating procedure of user.
In the related technology, mobile terminal application program only has intelligent sound input function, and does not have voice control function.
When user wants to complete preset function, also need to be manually operated, operating procedure is relatively complicated.
Summary of the invention
The application provides the method, apparatus and computer equipment of a kind of voice control application program, to realize according to user
Control application program can be realized in the voice messaging of input, can simplify the operating procedure of user, enriches the control of application program
Mode improves the usage experience of user, only has intelligent sound input work for solving mobile terminal application program in the prior art
Can, and not there is no voice control function.When user wants to complete preset function, also need to be manually operated, operating procedure is more numerous
Trivial technical problem.
The application one side embodiment provides a kind of method of voice control application program, comprising:
Acquire the voice messaging of user；
Speech recognition is carried out to the voice messaging, obtains the corresponding content of text of the voice messaging；
The content of text is segmented, preset intention library and ingredient library are inquired according to the word that participle obtains, really
Fixed result set corresponding with the voice messaging；It include: intention word and ingredient word in the result set；
According to the result set, inquiry instruction table generates operational order corresponding with voice messaging；
The operational order is executed, the corresponding response message of the voice messaging is obtained.
It include: that at least one is intended to word wherein in a kind of specific embodiment, in the intention library；The ingredient
It include: at least one component type and the corresponding ingredient word of the component type in library；
Preset intention library and ingredient library are inquired according to the word that participle obtains, determines knot corresponding with the voice messaging
Fruit collection, comprising:
According to the word that participle obtains, the intention library is inquired, the intention word in the content of text is obtained；
According to the word that participle obtains, the ingredient library is inquired, the ingredient word in the content of text is obtained；
According to the intention word and the ingredient word, result set corresponding with the voice messaging is generated.
Wherein in another specific embodiment, preset intention library and ingredient are inquired according to the word that participle obtains
Library determines result set corresponding with the voice messaging, further includes:
If the intention word in the content of text has not been obtained according to the obtained word of participle, then the is sent to user
One prompt information prompts the user to input and is intended to word, or selection is intended to word in being intended to word list；
If the ingredient word in the content of text has not been obtained according to the obtained word of participle, then the is sent to user
Two prompt informations prompt user's specific input word.
It is described according to the result set, inquiry instruction table, generation and voice wherein in another specific embodiment
The corresponding operational order of information, comprising:
According to the intention word in the result set, inquiry instruction table obtains operation corresponding with the intention word and refers to
It enables；
At least one ingredient word in the result set is carried in the operational order.
It is described according to the result set, inquiry instruction table, generation and voice wherein in another specific embodiment
Before the corresponding operational order of information, further includes:
Obtain the quantity of the result set；
It is described according to the result set, inquiry instruction table generates operational order corresponding with voice messaging, comprising:
When the quantity of the result set is greater than 1, according to each intention word, inquiry instruction table is obtained and each intention
The corresponding operational order of word；
From the corresponding operational order of each intention word, corresponding highest first operational order of weight is selected；
Obtain the corresponding first intention word of first operational order；
At least one ingredient word in result set including the first intention word is carried in first operation
In instruction.
It is described to execute the operational order wherein in another specific embodiment, comprising:
Obtain the permission of the user；
According to the permission of the user, judge whether the user has the permission for executing the operational order；
If the user has the permission for executing the operational order, the operational order is executed.
It is described that the content of text is segmented wherein in another specific embodiment, it is obtained according to participle
Word inquire preset intentions library and ingredient library, before determination result set corresponding with the voice messaging, further includes:
Judge whether there is the text box in input state；
It is in the text box of input state if it exists, then the content of text is inputted into the text box.
The method of the voice control application program of the embodiment of the present application, by acquiring the voice messaging of user, then, to language
Message breath carries out speech recognition, obtains the corresponding content of text of voice messaging and then segments to content of text, according to point
The word that word obtains inquires preset intention library and ingredient library, result set corresponding with voice messaging is determined, finally according to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging, and execute operational order, and it is corresponding to obtain voice messaging
Response message.The voice messaging inputted as a result, according to user, can be realized control application program, can simplify the operation of user
Step enriches the control mode of application program, improves the usage experience of user.
The another aspect embodiment of the application provides a kind of device of voice control application program, comprising:
Acquisition module, for acquiring the voice messaging of user；
Identification module obtains in the corresponding text of the voice messaging for carrying out speech recognition to the voice messaging
Hold；
Determining module inquires preset intention according to the word that participle obtains for segmenting to the content of text
Library and ingredient library determine result set corresponding with the voice messaging；It include: intention word and ingredient in the result set
Word；
Generation module, for according to the result set, inquiry instruction table to generate operational order corresponding with voice messaging；
Execution module obtains the corresponding response message of the voice messaging for executing the operational order.
It include: that at least one is intended to word wherein in a kind of specific embodiment, in the intention library；The ingredient
It include: at least one component type and the corresponding ingredient word of the component type in library；
The determining module is specifically used for,
According to the word that participle obtains, the intention library is inquired, the intention word in the content of text is obtained；
According to the word that participle obtains, the ingredient library is inquired, the ingredient word in the content of text is obtained；
According to the intention word and the ingredient word, result set corresponding with the voice messaging is generated.
Wherein in another specific embodiment, the determining module is specifically also used to,
If the intention word in the content of text has not been obtained according to the obtained word of participle, then the is sent to user
One prompt information prompts the user to input and is intended to word, or selection is intended to word in being intended to word list；
If the ingredient word in the content of text has not been obtained according to the obtained word of participle, then the is sent to user
Two prompt informations prompt user's specific input word.
Wherein in another specific embodiment, the generation module is specifically used for,
According to the intention word in the result set, inquiry instruction table obtains operation corresponding with the intention word and refers to
It enables；
At least one ingredient word in the result set is carried in the operational order.
Wherein in another specific embodiment, described device further include:
Module is obtained, for obtaining the quantity of the result set；
The generation module is specifically used for,
When the quantity of the result set is greater than 1, according to each intention word, inquiry instruction table is obtained and each intention
The corresponding operational order of word；
From the corresponding operational order of each intention word, corresponding highest first operational order of weight is selected；
Obtain the corresponding first intention word of first operational order；
At least one ingredient word in result set including the first intention word is carried in first operation
In instruction.
Wherein in another specific embodiment, the execution module is specifically used for,
Obtain the permission of the user；
According to the permission of the user, judge whether the user has the permission for executing the operational order；
If the user has the permission for executing the operational order, the operational order is executed.
Wherein in another specific embodiment, described device further include:
Judgment module inquires preset meaning according to the word that participle obtains for segmenting to the content of text
Picture library and ingredient library judge whether there is the text in input state before determining result set corresponding with the voice messaging
This frame；
Input module, for when there is the text box for being in input state, the content of text to be inputted the text
Frame.
The device of the voice control application program of the embodiment of the present application, by acquiring the voice messaging of user, then, to language
Message breath carries out speech recognition, obtains the corresponding content of text of voice messaging and then segments to content of text, according to point
The word that word obtains inquires preset intention library and ingredient library, result set corresponding with voice messaging is determined, finally according to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging, and execute operational order, and it is corresponding to obtain voice messaging
Response message.The voice messaging inputted as a result, according to user, can be realized control application program, can simplify the operation of user
Step enriches the control mode of application program, improves the usage experience of user.
The another aspect embodiment of the application provides a kind of computer equipment, including memory, processor and is stored in storage
On device and the computer program that can run on a processor realizes language as described above when the processor executes described program
The method of sound control application program.
The another aspect embodiment of the application provides a kind of non-transitorycomputer readable storage medium, is stored thereon with calculating
Machine program, which realizes voice control application program as described above method when being executed by processor.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the application
Example, and together with specification it is used to explain the principle of the application.
Fig. 1 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application one；
Fig. 2 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application two；
Fig. 3 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application three；
Fig. 4 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application four；
Fig. 5 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application five；
Fig. 6 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application six；
Fig. 7 is the structural schematic diagram figure of the device of voice control application program provided by the embodiment of the present application seven；
Fig. 8 is the structural schematic diagram figure of the device of voice control application program provided by the embodiment of the present application eight；
Fig. 9 is the structural schematic diagram of the application computer equipment one embodiment.
Through the above attached drawings, it has been shown that the specific embodiment of the application will be hereinafter described in more detail.These attached drawings
It is not intended to limit the range of the application design in any manner with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the application.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
With the continuous development of mobile terminal technology, more and more application programs move to mobile terminal from the end PC.For example,
With digital office trend, for sales force, when it is not in company or when leaving computer, by using mobile visitor
Family relationship management system (Customer Relation Management, abbreviation CRM) can be realized and conveniently and efficiently carry out pin
Sell work, check customer information, performance information etc..Alternatively, can be answered whenever and wherever possible using various for ordinary user
Use program.
Since mobile terminal is compared to the end PC, have the characteristics that screen is small, typewriting is slow, finger dexterity is lower than mouse, therefore
For the application program of mobile terminal, the height of operating experience is a very main index.For example, existing apply journey
Sequence is had mostly and identifies the advantages such as understandable, key is larger, the operating procedure of control is convenient, the operating body of user is promoted with this
It tests.
But for the operation of mobile terminal application program, typing speed greatly influences the usage experience of user slowly,
For this purpose, mobile terminal application program generally has intelligent sound input function, be converted in text by the voice for inputting user
Hold, to simplify the operating procedure of user.
In the related technology, mobile terminal application program only has intelligent sound input function, and does not have voice control function.
When user wants to complete preset function, also need to be manually operated, operating procedure is relatively complicated.For example, when user wants in mobile CRM
In when quickly searching the contact details of client A, user needs to choose " customer menu " first, is switched in customer list, then
By the screening function of customer list, required client is filtered out, finally chooses client A again, into client's details page of client A
Face obtains the contact details of client A.Alternatively, being used when user creates in class application program of handling official business or opens default list
Family needs to click corresponding input frame manually, then inputs corresponding content, and operating procedure is extremely cumbersome.Alternatively, when user thinks
When opening the preset function in application program, need to click respective selection, malfunction manually.
The application only has intelligent sound input function mainly for mobile terminal application program in the prior art, and does not have
Voice control function.When user wants to complete preset function, also need to be manually operated, the relatively complicated technology of operating procedure is asked
Topic, a kind of method for proposing voice control application program.
The method of the voice control application program of the embodiment of the present application, by acquiring the voice messaging of user, then, to language
Message breath carries out speech recognition, obtains the corresponding content of text of voice messaging and then segments to content of text, according to point
The word that word obtains inquires preset intention library and ingredient library, result set corresponding with voice messaging is determined, finally according to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging, and execute operational order, and it is corresponding to obtain voice messaging
Response message.The voice messaging inputted as a result, according to user, can be realized control application program, can simplify the operation of user
Step enriches the control mode of application program, improves the usage experience of user.
Fig. 1 is the flow diagram figure of the method for voice control application program provided by the embodiment of the present application one.
The method of voice control application program in the embodiment of the present application can be real by the device of voice control application program
Existing, the device of the voice control application program can be configured in any computer equipment or mobile device, so that the meter
It calculates machine equipment or mobile device executes the function of voice control application program.Mobile device can be mobile phone, tablet computer, a
Personal digital assistant, wearable device etc. have the hardware device of various operating systems, touch screen and/or display screen.
Wherein, application program, which refers to, may operate in computer equipment or mobile device, provide any clothes for user
The software program of business, for example, office class application program, navigation type application program, payment class application program, searching class application journey
Sequence, amusement class application program, class of taking pictures application program etc..
As shown in Figure 1, the method for the voice control application program may comprise steps of:
Step 101, the voice messaging of user is acquired.
In the embodiment of the present application, the display interface of application program can have voice input key, and user can pass through touching
Voice input key is sent out, input voice information activates phonetic function for example, user can input key by long-pressing voice,
Then input voice information.It, can be by the side listened to correspondingly, the device of the voice control application program of the embodiment of the present application
Formula, determines whether user triggers voice input key, when determining that user triggers voice input key, can acquire user
Voice messaging.
As a kind of possible implementation, for the ease of one key input voice messaging of user, in the application, can answer
Key is inputted with the voice that the display interface of program is provided with a suspension, thus when user is in the process using application program
In, it no matter is currently at which page, with that can input key by triggering the voice of the suspension per family, input voice is believed
Breath, promotes the convenience of user's operation.Further, current page is checked in order to avoid voice input key influences user, it should
The voice input key of suspension can be arranged with transparence.
Step 102, speech recognition is carried out to voice messaging, obtains the corresponding content of text of voice messaging.
It is alternatively possible to carry out speech recognition using speech recognition technology in the related technology to voice messaging, obtain language
Message ceases corresponding content of text.For example, can method, the method for template matching, base based on channel model and phonic knowledge
In the method etc. of artificial neural network, speech recognition is carried out to voice messaging, with no restriction to this.
As an example, artificial intelligence (Artificial Intelligence, abbreviation AI) open platform can be provided
Speech recognition application programming interface interface (Application Program Interface, abbreviation API) service, for believing voice
Breath carries out speech recognition.After obtaining voice messaging, speech recognition api interface service can be called, language is carried out to voice messaging
Sound identification obtains the corresponding content of text of voice messaging.Wherein, the format of voice messaging can be PCM, WAV, ARM, SILK
Deng, the sample rate of voice messaging can be 16k or 8k, and sampling resolution can be 16bit, for example, voice messaging to be identified
The information such as format, parameter can be as shown in table 1.
| Rule | Description |
| Transmission mode | HTTPS |
| Requesting method | POST |
| Speech parameter | Meet 16k or 8k sample rate, 16bit sampling resolution, monophonic |
| Phonetic matrix | PCM、WAV、ARM、SILK |
| Character code | It is used uniformly UTF-8 format |
| Response format | It is used uniformly JSON format |
1 recognition rule of table
Step 103, content of text is segmented, preset intention library and ingredient is inquired according to the word that participle obtains
Library determines result set corresponding with voice messaging；It include: intention word and ingredient word in result set.
In the embodiment of the present application, preset intention library and ingredient library are pre-established.Wherein, it is intended that library includes at least one
A intention word, ingredient library include at least one ingredient word.It is understood that for different application programs, it is intended that library
It can be different.For example, for class application program of handling official business, such as moving the application program of CRM, it is intended that library may include visitor
Family, business opportunity, achievement etc. are intended to word, for other applications, it is intended that library may include turn on, clicks, close
Deng intention word.Similarly, for different application programs, ingredient library be can also be different, for example, the application for mobile CRM
For program, ingredient library may include client's abbreviation, brand name, trade connection personnel etc. ingredient word, other are answered
For program, ingredient library may include menu, programmable button etc. ingredient word.
As a kind of possible implementation, for each application program, it is intended that library can be intended to according to corresponding
Word is pre-established with coding is intended to, for example, for the application program of mobile CRM, it is intended that library can be as shown in table 2.
| It is intended to coding | It is intended to word |
| 0 | It is unknown |
| 1 | Client |
| 2 | Business opportunity |
| 3 | Achievement |
| 4 | Bulletin |
| 5 | It is pending |
| 6 | Resource |
Table 2 is intended to library
For each application program, ingredient library can be pre- according to correspondingly ingredient word and intention coding
It first establishes, for example, for the application program of mobile CRM, it is intended that library can be as shown in table 3.
3 ingredient library of table
In the embodiment of the present application, segmentation methods can be based on, content of text are segmented, each word after being segmented
Language.For example, can the segmenting method based on string matching, the segmenting method based on understanding, the segmenting method based on statistics etc.
Deng being segmented to content of text, with no restriction to this.For example, when content of text is " my Yao Kan client Uniliver
When information ", content of text is segmented, each word after obtained participle are as follows: the information of my Yao Kan client Uniliver.
After each word after being segmented, the word that can be obtained according to participle inquires preset intention library and ingredient
Library determines result set corresponding with voice messaging, wherein include: intention word and ingredient word in result set.
Still with above-mentioned example, it is intended that word can be " client ", and ingredient word can be " Uniliver ", then result
Collection can indicate are as follows: (being intended to: client, ingredient: Uniliver).Alternatively, when content of text is that " I will see client, food and drink
When Uniliver and golden arched door under class industry ", it is intended that word can be " client ", and ingredient word can be " food and drink
Class ", " Uniliver " and " golden arched door ", then result set can indicate are as follows: (be intended to: client, ingredient: food beverages, joint benefit
China, golden arched door), (being intended to: client, ingredient: food beverages), (being intended to: client, ingredient: Uniliver), (be intended to: client,
Ingredient: golden arched door), (be intended to: client, ingredient: food beverages, Uniliver), (be intended to: client, ingredient: food beverages,
Golden arched door), and/or (being intended to: client, ingredient: Uniliver, golden arched door).
As an example, it is assumed that when the currently used application program of user is social category application program, work as content of text
When for " collection for opening me ", it is intended that word can be " openings ", and ingredient word can be " my collection ", then result set can be with
It indicates are as follows: (be intended to: opening, ingredient: my collection).
As an example, can provide AI open platform semanteme parsing api interface service, for text to be analyzed into
Row parsing.It is determining text to be analyzed, i.e., after the content of text in step 102, semantic parsing api interface service can be called,
Content of text is parsed, result set corresponding with voice messaging is obtained.Wherein, required parameter can be as shown in table 4, accordingly
Parameter can be as shown in table 5.
4 required parameter of table
| Parameter name | Data type | Description |
| ret | int | Return code；0 indicates successfully, non-zero expression error |
| msg | string | Return information；Ret is non-zero to represent error reason of staggering the time |
| data | object | Returned data；Ret is significant when being 0 |
| +text | string | Text to be analyzed in API request |
| +intent | int | It is intended to coding |
| +com_tokens | array | Ingredient lists |
| ++com_type | string | Component codes |
| ++com_word | int | Ingredient word |
5 response parameter of table
As an example, work as input are as follows:
Then export result are as follows:
It should be noted that due to being intended to there is no incidence relation between word and ingredient word, for example, such as moving CRM
Application program for, when as participle language being client's abbreviation, for example be Uniliver, golden arched door, at this time, it is intended that word can be with
Participle is only acquired into if inquiring preset intention library according to the word that participle obtains for client, business opportunity, achievement etc.
Language, and have not been obtained to obtain and be intended to word, at this point, can send first due to that can not identify that user is really intended to user and mention
Show information, is intended to word to prompt user to input, or selection is intended to word in being intended to word list.
For example, user can be in the text of display interface when after the display interface of application program shows the first prompt information
Intention word is manually entered in this frame, alternatively, user can input key by triggering voice, voice input is intended to word, or
Person, the combobox that display interface can also have selection to be intended to word, user can be by clicking the combobox, and selection is intended to word
Language, alternatively, display interface can also have intention word list, user can select to be intended to word by the intention word list
Language, with no restriction to this.
Similarly, if inquiring preset intention library according to the word that participle obtains, intention word is only acquired, and not
Ingredient word is acquired, for example content of text is " I will see client ", at this point, only can determine that being intended to word is client, and nothing
Method determines that user specifically wants to check that the information of which client or content of text are " I will see business opportunity ", at this point, only can determine that meaning
Figure word is business opportunity, and can not determine user specifically wants to check the business opportunity of which client, the business opportunity in which place, which branch stock
Therefore business opportunity etc. can send the second prompt information to user, to prompt user's specific input word.
It is understood that since ingredient word is more, at this point, if being shown in the form of tabular form or combobox
Ingredient word, user will spend the ingredient word of more selection of time demand, and efficiency is lower, and therefore, user can direct language
Sound specific input word is manually entered ingredient word.
Step 104, according to result set, inquiry instruction table generates operational order corresponding with voice messaging.
It is understood that each application program all have with itself associated instruction, for example, for handle official business class application journey
Sequence, such as moving the application program of CRM, instruction associated with it can be with are as follows: client check instruction, business opportunity check instruction,
Achievement checks instruction etc., and for searching class application program, such as browser, instruction associated with it can be with are as follows: link
Open instructions, links and accesses instruction etc., also, for different types of application program, can also have general instruction, example
Such as are as follows: pre-set button open instructions, preset options open instructions, default closing application program instruction, default application program exit
Instruction etc..Therefore, the corresponding instruction catalogue of the application program can be pre-established according to different application.
It, can be according to result set, the corresponding instruction of inquiry application after definitive result collection in the embodiment of the present application
Table whether there is operational order corresponding with result set in determine instruction table, when there is behaviour corresponding with result set in instruction catalogue
It, can be by the corresponding operational order of the result set, as operational order corresponding with voice messaging when instructing.And work as instruction catalogue
In do not exist operational order corresponding with result set when, it is determined that operational order failure, can in the display interface of application program,
Carry out miscue.
Step 105, operational order is executed, the corresponding response message of voice messaging is obtained.
In the embodiment of the present application, after determining operational order, the operational order can be executed, to obtain voice messaging pair
The response message answered.
In the embodiment of the present application, according to the voice messaging that user inputs, control application program can be realized, can simplify use
The operating procedure at family, for example, the working efficiency of user can be promoted for class application program of handling official business.And it is possible to abundant application
The control mode of program improves the usage experience of user.
The method of the voice control application program of the embodiment of the present application, by acquiring the voice messaging of user, then, to language
Message breath carries out speech recognition, obtains the corresponding content of text of voice messaging and then segments to content of text, according to point
The word that word obtains inquires preset intention library and ingredient library, result set corresponding with voice messaging is determined, finally according to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging, and execute operational order, and it is corresponding to obtain voice messaging
Response message.The voice messaging inputted as a result, according to user, can be realized control application program, can simplify the operation of user
Step enriches the control mode of application program, improves the usage experience of user.
For an embodiment in clear explanation, the method for present embodiments providing another voice control application program, Fig. 2
For the flow diagram of the method for voice control application program provided by the embodiment of the present application four.
As shown in Fig. 2, on the basis of embodiment shown in Fig. 1, after step 104, the side of the voice control application program
Method can with the following steps are included:
Step 201, judge whether the pressing operation for detecting user to programmable button.
In the embodiment of the present application, programmable button specifically can input key with finger speech sound specifically can be by the side of listening to
Formula judges whether the pressing operation for detecting user to pre-set button.
Step 202, if detecting, user to the pressing operation of programmable button, acquires the voice messaging of user.
Specifically, when detecting pressing operation of the user to pre-set button, at this point, user has activated phonetic function, because
This, can acquire the voice messaging of user.And when pressing operation of the user to pre-set button is not detected, at this point, user is simultaneously
Un-activation phonetic function therefore can be without any processing.
Step 203, speech recognition is carried out to voice messaging, obtains the corresponding content of text of voice messaging.
The implementation procedure of step 203 may refer to the implementation procedure of step 102 in above-described embodiment, and this will not be repeated here.
Step 204, the word obtained according to participle, query intention library, it is determined whether get the intention in content of text
Word, if so, step 206 is executed, if it is not, executing step 205.
Step 205, the first prompt information is sent to user, prompts user to input and is intended to word, or be intended to word column
Selection is intended to word in table.
For example, it when the word that participle obtains is " I will see the information of Uniliver ", is not wrapped in content of text
The achievement of Uniliver is still seen also at this point, the business opportunity of user Xiang Kan Uniliver can not be determined containing word is intended to, or is seen
Contact method of Uniliver etc. can not identify that user is really intended to, therefore, the first prompt letter can be sent to user
Breath prompts user to input and is intended to word, or selection is intended to word in being intended to word list.
Step 206, the word obtained according to participle inquires ingredient library, it is determined whether get the ingredient in content of text
Word, if so, step 208 is executed, if it is not, executing step 207.
Step 207, the second prompt information is sent to user, prompts user's specific input word.
It for example, does not include ingredient word in content of text when the word that participle obtains is " I will see business opportunity ",
At this point, only can determine that being intended to word is business opportunity, and it can not determine user and specifically want to check the business opportunity of which client, which place
Therefore business opportunity, business opportunity of which branch stock etc. can send the second prompt information to user, to prompt user to be entered as segmenting
Language.
It should be noted that the embodiment of the present application is only intended to word first to judge whether to have in content of text, it is rear to judge
Whether have ingredient word sample, when practical application, can also first judge whether with ingredient word, after judge whether that there is meaning
Figure word, alternatively, can also judge whether simultaneously with ingredient word and be intended to word, when not with ingredient word and intention
When word, the first prompt information and the second prompt information can be sent to user simultaneously, with no restriction to this.
Step 208, according to word and ingredient word is intended to, result set corresponding with voice messaging is generated.
It is understood that the number of the intention word in content of text can be at least one, and similarly, ingredient word
Number may be at least one.When being intended to word is one, it will directly can be intended to word and ingredient word, combine
To a result set.And when being intended to word and being greater than one, can according to the positional relationship being intended between word and ingredient word,
Definitive result collection.In general, apart from the closer intention word of ingredient word, for the corresponding ingredient word of the intention word, because
This, can will be combined with ingredient word apart from the closer intention word of ingredient word, and obtain result set.
Step 209, according to the intention word in result set, inquiry instruction table obtains operation corresponding with word is intended to and refers to
It enables.
In the embodiment of the present application, it can obtain according to the intention word in result set, inquiry instruction table and be intended to word pair
The operational order answered, for example, when content of text is " information of my Yao Kan client Uniliver ", it is intended that: client, ingredient: connection
Benefit China is closed, then operational order can check instruction for client, alternatively, when content of text is " I will see the business opportunity of place A ", meaning
Figure: business opportunity, ingredient: place A, then operational order can check instruction for business opportunity.
Step 210, at least one ingredient word in result set is carried in operational order.
In the embodiment of the present application, operational order is inquired according to intention word, and operational order is to intention word
Certain operations are executed, for example, being intended to the corresponding operational order of word is exactly for inquiring client if being intended to word is client
List obtains certain customer informations, it is known that, operational order itself has contained the intention for being intended to word, so operation refers to
It only needs to carry ingredient word in order, to determine that is specifically inquired is the information of which client.It specifically, can will be in result set
At least one ingredient word carry in operational order, thus when executing operational order, instruction Processing Interface can be passed through
Corresponding service interface is obtained, is passed to using ingredient word as parameter, carries out the calling of service interface.
It should be noted that the number of operational order can be that at least one can when the number of operational order is multiple
To select the highest operational order of weight, it thereby may be ensured that and only execute an operational order every time.
Step 211, operational order is executed, the corresponding response message of voice messaging is obtained.
As an example, instruction catalogue can be as shown in table 6, can have order ID, command name, every in the instruction catalogue
It is a to order the information such as corresponding weight, corresponding user right, instruction Processing Interface.
6 instruction catalogue of table
As a kind of possible implementation, in order to avoid the illegal user not with permission uses application program, and
It avoids the privacy leakage of user, in the application, before executing operational order, can also determine whether active user has accordingly
Execution operational order permission, only when user have execute operational order permission when, just execution operational order.Below with reference to
The above process is described in detail in Fig. 3.
The flow diagram of the method for voice control application program provided by Fig. 3 the embodiment of the present application three.
As shown in figure 3, step 105 or step 209 can specifically include on the basis of Fig. 1 or embodiment illustrated in fig. 2
Following sub-step:
Step 301, the permission of user is obtained.
Optionally, corresponding permission can be set when using application program in user, alternatively, user is using using journey
When the preset function of sequence, corresponding permission can be set, after the setup, can remember in computer equipment or mobile device
Record has the authority information of user, in the application, can obtain user from the information that computer equipment or mobile device store
Permission.
Step 302, according to the permission of user, judge whether user has the permission for executing operational order.
Specifically, according to the permission of user, when determining that the user has the permission using application program, alternatively, determining should
When user is had using preset function in application program, can determine that the user has the permission for executing operational order, when with
When family has the permission for executing operational order, step 303 can be executed, and when user does not have the permission for executing operational order
When, at this point, the personal secrets of user are ensured in order to avoid the illegal user not with permission uses application program, alternatively, for
Operational order can not be executed, in display circle of application program to ensure the property safety of user by paying class application program
Face carries out related prompt, for example, " your insufficient permission ".
Step 303, if user has the permission for executing operational order, operational order is executed.
It is alternatively possible to be passed to by instructing Processing Interface to obtain corresponding service interface using ingredient word as parameter,
Carry out the calling of service interface.
As an example, for the application program of mobile CRM, by API service interface assembly unified resource
Finger URL (Uniform Resource Locator, abbreviation URL), for example, client checks that instruction is the routing of customer list, quotient
Machine checks that instruction is the routing of business opportunity list, then using ingredient word as querying condition, by way of get parameter, and splicing
In the tail portion of URL.When executing operational order, respective service interface can be called, obtains being corresponding URL, then switches road
By obtaining being corresponding control ID, then asynchronous operation JavaScript (JS) chooses the control.
As another example, when operational order is that control order is chosen in processing, wherein control can for text box,
The controls such as menu, it is assumed that control is text box, can be by text box as input shape after user chooses text box
State to receive voice messaging in next time, and parses when obtaining content of text, content of text directly can be input to text
Frame, specific implementation procedure may refer to Fig. 4.
For example, can be found by ingredient word by control inquiry table as shown in table 7 when control is text box
Corresponding page control ID, what then used JS call back function triggered the control chooses event, and choosing for text box can be realized
Content of text then can be input to text box by effect.User, can be defeated without clicking corresponding text box manually as a result,
Enter corresponding content, can simplify the operating procedure of user, improves the usage experience of user.
| Field | Description | Remarks |
| WidgetID | Page control ID | |
| WidgetName | Page control title | |
| Page | Current page routing | Default value is sky, it is possible to specify value |
7 control inquiry table of table
As a kind of possible implementation, when user inputs voice, the intention of user may not be control application
Program executes preset function, for example, the intention of user may input for text, rather than refer to when user chooses some text box
Input is enabled, therefore, referring to fig. 4, on the basis of embodiment shown in Fig. 1, before step 103, the voice control application program
Method can with the following steps are included:
Step 401, the text box in input state is judged whether there is.
In the embodiment of the present application, it can be determined that with the presence or absence of the text box for belonging to input state, for example, focus can be based on
Follow technology, it is determined whether there is the text box in input state, specifically, technology followed according to focus, can automatically with
With pointer focus, when pointer focus is located in text box, it can determine that text box belongs to input state, at this point it is possible to execute step
Rapid 402, and work as pointer focus and be not located in text box, it determines that text box does not belong to input state, then shows that user is not this moment
Want inputting word information, and be instruction input, therefore, step 103 can be executed.
Step 402, it is in the text box of input state if it exists, then content of text is inputted into text box.
In the embodiment of the present application, when there is the text box for being in input state, show that the intention of user may be text
Input, therefore, can be input to text box for content of text, thus, it is possible to which correctly identification user is intended to.
As a kind of possible implementation, the quantity of the result set in above-described embodiment can be multiple, at this point, according to
The number of each intention word, inquiry instruction table, the operational order corresponding with each intention word of acquisition equally can be more
It is a.In order to guarantee once to only carry out an operational order, can select to correspond to from the corresponding operational order of each intention word
Highest first operational order of weight.Below with reference to Fig. 5, the above process is described in detail.
Fig. 5 is the flow diagram of the method for voice control application program provided by the embodiment of the present application five.
As shown in figure 5, referring to Fig. 1, step 104 can specifically include following sub-step when the quantity of result set is multiple
It is rapid:
Step 501, when the quantity of result set is greater than 1, according to each intention word, inquiry instruction table, obtain with it is each
It is intended to the corresponding operational order of word.
In the embodiment of the present application, when the quantity of result set is greater than 1, at this point, there are multiple intention words, it can be according to each
A intention word, the corresponding instruction catalogue of inquiry application obtain operational order corresponding with each intention word.
Step 502, from the corresponding operational order of each intention word, corresponding highest first operation of weight is selected to refer to
It enables.
In the embodiment of the present application, each instruction can preset corresponding weight, for example, can be according to application program visitor
The relevant information of family end subscriber determines the operation information of application program in user customer, so as to according to operation information,
Each corresponding weight of instruction is determined, for example, determining that most users are universal according to the relevant information of application client user
Instruction is checked using client, secondly checks instruction for business opportunity, then client checks that the weight of instruction can be greater than business opportunity and check instruction.
Specifically, after determining the corresponding operational order of each intention word, the highest operational order of weight can be made
For the first operational order, primary only one operational order of execution thereby may be ensured that, also, the highest operation of weight is selected to refer to
It enables, can satisfy the actual demand of most users.
Step 503, the corresponding first intention word of the first operational order is obtained.
In the embodiment of the present application, after determining the first operational order, the corresponding intention of the first operational order can be determined
Word.
Step 504, at least one ingredient word in the result set including first intention word is carried in the first operation
In instruction.
In the embodiment of the present application, after determining first intention word, it can be obtained and the first intention word with query results
At least one corresponding ingredient word of language can then carry at least one ingredient word in the first operational order.To
It, can be by instructing Processing Interface to obtain corresponding service interface, using ingredient word as ginseng when executing the first operational order
Number is incoming, carries out the calling of service interface.
It is voice control application program provided by the embodiment of the present application six referring to Fig. 6, Fig. 6 as a kind of application scenarios
Method flow diagram.Fig. 6 uses the application program example in mobile phone with user.
, can be by mobile phone microphone input voice information when user's long-pressing voice key, it then can be to voice messaging
It is identified, obtains corresponding content of text, can then determine the selected state of current text frame, if current text frame is selected
In, then content of text is input in text box, if current text frame is not selected, to content of text carry out semantic parsing with
And instruction parsing.
Judge whether active user has permission, and determine whether with valid instruction, if user do not have permission and/
Or not there is no valid instruction, then miscue is shown in Application Program Interface, if user is with permission and has valid instruction,
It executes instruction, and in page presentation.
Following is the application Installation practice, can be used for executing the application embodiment of the method.It is real for the application device
Undisclosed details in example is applied, the application embodiment of the method is please referred to.
Fig. 7 is the structural schematic diagram of the device of voice control application program provided by the embodiment of the present application seven.
As shown in fig. 7, the device 100 of the voice control application program, for realizing any implementation of the application Fig. 1 to Fig. 6
The method for the voice control application program that example provides, the device 100 of above-mentioned voice control application program may include: acquisition module
110, identification module 120, determining module 130, generation module 140 and execution module 150.
Wherein,
Acquisition module 110, for acquiring the voice messaging of user.
Identification module 120 obtains the corresponding content of text of voice messaging for carrying out speech recognition to voice messaging.
Determining module 130 inquires preset intention library according to the word that participle obtains for segmenting to content of text
With ingredient library, result set corresponding with voice messaging is determined；It include: intention word and ingredient word in result set.
Generation module 140, for according to result set, inquiry instruction table to generate operational order corresponding with voice messaging.
Execution module 150, for executing operational order.
As a kind of possible implementation, it is intended that include: that at least one is intended to word in library；Include: in ingredient library to
A few component type and the corresponding ingredient word of component type.
Determining module 130 is specifically used for,
According to the word that participle obtains, query intention library obtains the intention word in content of text；
According to the word that participle obtains, ingredient library is inquired, the ingredient word in content of text is obtained；
According to word and ingredient word is intended to, result set corresponding with voice messaging is generated.
As alternatively possible implementation, determining module 130 is specifically also used to,
If the intention word in content of text has not been obtained according to the word that participle obtains, then first is sent to user and mentioned
Show information, prompts user to input and be intended to word, or selection is intended to word in being intended to word list；
If the ingredient word in content of text has not been obtained according to the word that participle obtains, then second is sent to user and mentioned
Show information, prompts user's specific input word.
As a kind of possible implementation, generation module 140 is specifically used for,
According to the intention word in result set, inquiry instruction table obtains operational order corresponding with word is intended to；
At least one ingredient word in result set is carried in operational order.
Further, in a kind of possible implementation of the embodiment of the present application, referring to Fig. 8, embodiment shown in Fig. 7
On the basis of, the device 100 of the voice control application program can also include:
Module 160 is obtained, for obtaining the quantity of result set；
Corresponding, generation module 140 is specifically used for,
When the quantity of result set is greater than 1, according to each intention word, inquiry instruction table is obtained and each intention word
Corresponding operational order；
From the corresponding operational order of each intention word, corresponding highest first operational order of weight is selected；
Obtain the corresponding first intention word of the first operational order；
At least one ingredient word in result set including first intention word is carried in the first operational order.
As a kind of possible implementation, execution module 150 is specifically used for,
Obtain the permission of user；
According to the permission of user, judge whether user has the permission for executing operational order；
If user has the permission for executing operational order, operational order is executed.
Judgment module 170 inquires preset intention according to the word that participle obtains for segmenting to content of text
Library and ingredient library judge whether there is the text box in input state before determining result set corresponding with voice messaging.
Input module 180, for when there is the text box for being in input state, content of text to be inputted text box.
It should be noted that the aforementioned voice for being also applied for the embodiment to the explanation for logging in method of calibration embodiment
The device 100 of application program is controlled, details are not described herein again.
The device of the voice control application program of the embodiment of the present application, by acquiring the voice messaging of user, then, to language
Message breath carries out speech recognition, obtains the corresponding content of text of voice messaging and then segments to content of text, according to point
The word that word obtains inquires preset intention library and ingredient library, result set corresponding with voice messaging is determined, finally according to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging, and execute operational order, and it is corresponding to obtain voice messaging
Response message.The voice messaging inputted as a result, according to user, can be realized control application program, can simplify the operation of user
Step enriches the control mode of application program, improves the usage experience of user.
Fig. 9 is the structural schematic diagram of the application computer equipment one embodiment, and the computer equipment in the present embodiment can
To realize that the function of voice control application program, above-mentioned computer equipment may include: one or more processors；Memory,
For storing one or more programs；When said one or multiple programs are executed by said one or multiple processors, so that
The voice messaging of said one or multiple processors acquisition user；Speech recognition is carried out to voice messaging, obtains voice messaging pair
The content of text answered；Content of text is segmented, preset intention library and ingredient library are inquired according to the word that participle obtains, really
Fixed result set corresponding with voice messaging；It include: intention word and at least one ingredient word in result set；According to result
Collection, inquiry instruction table generate operational order corresponding with voice messaging；Execute operational order.
Fig. 9 shows the block diagram for being suitable for the exemplary computer device for being used to realize the application embodiment.What Fig. 9 was shown
Computer equipment 12 is only an example, should not function to the embodiment of the present application and use scope bring any restrictions.
As shown in figure 9, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
The present embodiment also provides a kind of non-transitorycomputer readable storage medium, the computer in above-mentioned storage medium
The voice control that executable instruction is provided when being executed by computer processor, for executing the application Fig. 1 to Fig. 6 any embodiment
The method of application program processed.
The present embodiment also provides a kind of computer program product, when the instruction in computer program product is executed by processor
When, the method for the voice control application program that realization the application Fig. 1 to Fig. 6 any embodiment is provided.
It should be noted that term " first ", " second " etc. are used for description purposes only in the description of the present application, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present application, unless otherwise indicated, the meaning of " multiple "
It is two or more.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array
(Programmable Gate Array；Hereinafter referred to as: PGA), field programmable gate array (Field Programmable
Gate Array；Hereinafter referred to as: FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
Suddenly be that relevant hardware can be instructed to complete by program, program can store in a kind of computer readable storage medium
In, which when being executed, includes the steps that one or a combination set of embodiment of the method.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of method of voice control application program characterized by comprising
Acquire the voice messaging of user；
Speech recognition is carried out to the voice messaging, obtains the corresponding content of text of the voice messaging；
The content of text is segmented, preset intentions library and ingredient library are inquired according to the obtained word of participle, determine and
The corresponding result set of the voice messaging；It include: intention word and ingredient word in the result set；
According to the result set, inquiry instruction table generates operational order corresponding with voice messaging；
The operational order is executed, the corresponding response message of the voice messaging is obtained.
2. the method according to claim 1, wherein including: that at least one is intended to word in the intention library；Institute
State in ingredient library includes: at least one component type and the corresponding ingredient word of the component type；
Preset intention library and ingredient library are inquired according to the word that participle obtains, determines result corresponding with the voice messaging
Collection, comprising:
According to the word that participle obtains, the intention library is inquired, the intention word in the content of text is obtained；
According to the word that participle obtains, the ingredient library is inquired, the ingredient word in the content of text is obtained；
According to the intention word and the ingredient word, result set corresponding with the voice messaging is generated.
3. according to the method described in claim 2, it is characterized in that, according to the obtained word of participle inquire preset intentions library with
Ingredient library determines result set corresponding with the voice messaging, further includes:
If the intention word in the content of text has not been obtained according to the word that participle obtains, then first is sent to user and mentioned
Show information, prompts the user to input and be intended to word, or selection is intended to word in being intended to word list；
If the ingredient word in the content of text has not been obtained according to the word that participle obtains, then second is sent to user and mentioned
Show information, prompts user's specific input word.
4. the method according to claim 1, wherein described according to the result set, inquiry instruction table, generate with
The corresponding operational order of voice messaging, comprising:
According to the intention word in the result set, inquiry instruction table obtains operational order corresponding with the intention word；
At least one ingredient word in the result set is carried in the operational order.
5. the method according to claim 1, wherein described according to the result set, inquiry instruction table, generate with
Before the corresponding operational order of voice messaging, further includes:
Obtain the quantity of the result set；
It is described according to the result set, inquiry instruction table generates operational order corresponding with voice messaging, comprising:
When the quantity of the result set is greater than 1, according to each intention word, inquiry instruction table is obtained and each intention word
Corresponding operational order；
From the corresponding operational order of each intention word, corresponding highest first operational order of weight is selected；
Obtain the corresponding first intention word of first operational order；
At least one ingredient word in result set including the first intention word is carried in first operational order
In.
6. the method according to claim 1, wherein described execute the operational order, comprising:
Obtain the permission of the user；
According to the permission of the user, judge whether the user has the permission for executing the operational order；
If the user has the permission for executing the operational order, the operational order is executed.
7. the method according to claim 1, wherein described segment the content of text, according to participle
Obtained word inquires preset intentions library and ingredient library, before determination result set corresponding with the voice messaging, further includes:
Judge whether there is the text box in input state；
It is in the text box of input state if it exists, then the content of text is inputted into the text box.
8. a kind of device of voice control application program characterized by comprising
Acquisition module, for acquiring the voice messaging of user；
Identification module obtains the corresponding content of text of the voice messaging for carrying out speech recognition to the voice messaging；
Determining module, for being segmented to the content of text, according to the obtained word of participle inquire preset intentions library with
Ingredient library determines result set corresponding with the voice messaging；It include: intention word and ingredient word in the result set；
Generation module, for according to the result set, inquiry instruction table to generate operational order corresponding with voice messaging；
Execution module obtains the corresponding response message of the voice messaging for executing the operational order.
9. a kind of computer equipment, which is characterized in that on a memory and can be in processor including memory, processor and storage
The computer program of upper operation, which is characterized in that when the processor executes described program, realize as appointed in claim 1-7
The method of voice control application program described in one.
10. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the program
The method of the voice control application program as described in any in claim 1-7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811178885.9A CN109360557A (en) | 2018-10-10 | 2018-10-10 | The method, apparatus and computer equipment of voice control application program |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811178885.9A CN109360557A (en) | 2018-10-10 | 2018-10-10 | The method, apparatus and computer equipment of voice control application program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109360557A true CN109360557A (en) | 2019-02-19 |
Family
ID=65348996
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811178885.9A Pending CN109360557A (en) | 2018-10-10 | 2018-10-10 | The method, apparatus and computer equipment of voice control application program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109360557A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147216A (en) * | 2019-04-16 | 2019-08-20 | 深圳壹账通智能科技有限公司 | Page switching method, device, computer equipment and the storage medium of application program |
| CN110164450A (en) * | 2019-05-09 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Login method, device, playback equipment and storage medium |
| CN110765375A (en) * | 2019-10-22 | 2020-02-07 | 普信恒业科技发展（北京）有限公司 | Page jump method, device and system |
| CN111161730A (en) * | 2019-12-27 | 2020-05-15 | 中国联合网络通信集团有限公司 | Voice instruction matching method, device, equipment and storage medium |
| CN111273990A (en) * | 2020-01-21 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Information interaction method and device, computer equipment and storage medium |
| CN111276144A (en) * | 2020-02-21 | 2020-06-12 | 北京声智科技有限公司 | Platform matching method, device, equipment and medium |
| CN111833846A (en) * | 2019-04-12 | 2020-10-27 | 广东小天才科技有限公司 | Method and device for starting dictation state according to intention, and storage medium |
| CN112004157A (en) * | 2020-08-11 | 2020-11-27 | 海信电子科技(武汉)有限公司 | Multi-round voice interaction method and display equipment |
| CN112988115A (en) * | 2019-12-13 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Application building method and device and computer readable storage medium |
| WO2023231936A1 (en) * | 2022-06-01 | 2023-12-07 | 华为技术有限公司 | Speech interaction method and terminal |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080013541A (en) * | 2006-08-09 | 2008-02-13 | 삼성전자주식회사 | Apparatus and method for voice control in portable communication system |
| CN104461597A (en) * | 2013-09-24 | 2015-03-25 | 腾讯科技（深圳）有限公司 | Starting control method and device for application program |
| CN105183422A (en) * | 2015-08-31 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Voice control method and apparatus for application program |
| CN105825851A (en) * | 2016-05-17 | 2016-08-03 | Tcl集团股份有限公司 | Method and system for speech control based on Android system |
| CN106504748A (en) * | 2016-10-08 | 2017-03-15 | 珠海格力电器股份有限公司 | A kind of sound control method and device |
| US20170263252A1 (en) * | 2013-02-27 | 2017-09-14 | Blackberry Limited | Method and apparatus for voice control of a mobile device |
-
2018
- 2018-10-10 CN CN201811178885.9A patent/CN109360557A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20080013541A (en) * | 2006-08-09 | 2008-02-13 | 삼성전자주식회사 | Apparatus and method for voice control in portable communication system |
| US20170263252A1 (en) * | 2013-02-27 | 2017-09-14 | Blackberry Limited | Method and apparatus for voice control of a mobile device |
| CN104461597A (en) * | 2013-09-24 | 2015-03-25 | 腾讯科技（深圳）有限公司 | Starting control method and device for application program |
| CN105183422A (en) * | 2015-08-31 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Voice control method and apparatus for application program |
| CN105825851A (en) * | 2016-05-17 | 2016-08-03 | Tcl集团股份有限公司 | Method and system for speech control based on Android system |
| CN106504748A (en) * | 2016-10-08 | 2017-03-15 | 珠海格力电器股份有限公司 | A kind of sound control method and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833846A (en) * | 2019-04-12 | 2020-10-27 | 广东小天才科技有限公司 | Method and device for starting dictation state according to intention, and storage medium |
| CN110147216A (en) * | 2019-04-16 | 2019-08-20 | 深圳壹账通智能科技有限公司 | Page switching method, device, computer equipment and the storage medium of application program |
| CN110164450A (en) * | 2019-05-09 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Login method, device, playback equipment and storage medium |
| CN110164450B (en) * | 2019-05-09 | 2023-11-28 | 腾讯科技（深圳）有限公司 | Login method, login device, playing equipment and storage medium |
| CN110765375B (en) * | 2019-10-22 | 2022-08-02 | 普信恒业科技发展（北京）有限公司 | Page jump method, device and system |
| CN110765375A (en) * | 2019-10-22 | 2020-02-07 | 普信恒业科技发展（北京）有限公司 | Page jump method, device and system |
| CN112988115A (en) * | 2019-12-13 | 2021-06-18 | 阿里巴巴集团控股有限公司 | Application building method and device and computer readable storage medium |
| CN111161730A (en) * | 2019-12-27 | 2020-05-15 | 中国联合网络通信集团有限公司 | Voice instruction matching method, device, equipment and storage medium |
| CN111161730B (en) * | 2019-12-27 | 2022-10-04 | 中国联合网络通信集团有限公司 | Voice instruction matching method, device, equipment and storage medium |
| CN111273990A (en) * | 2020-01-21 | 2020-06-12 | 腾讯科技（深圳）有限公司 | Information interaction method and device, computer equipment and storage medium |
| CN111276144A (en) * | 2020-02-21 | 2020-06-12 | 北京声智科技有限公司 | Platform matching method, device, equipment and medium |
| CN112004157A (en) * | 2020-08-11 | 2020-11-27 | 海信电子科技(武汉)有限公司 | Multi-round voice interaction method and display equipment |
| WO2023231936A1 (en) * | 2022-06-01 | 2023-12-07 | 华为技术有限公司 | Speech interaction method and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360557A (en) | The method, apparatus and computer equipment of voice control application program | |
| US11386893B2 (en) | Human-computer interaction processing system, method, storage medium, and electronic device | |
| EP3695615B1 (en) | Integrating external data processing technologies with a cloud-based collaboration platform | |
| CN111860753B (en) | Directed acyclic graph-based framework for training models | |
| US9996531B1 (en) | Conversational understanding | |
| CN115485690A (en) | Batch technique for handling unbalanced training data of chat robots | |
| US10171656B2 (en) | Systems and methods for providing real-time assistance to call center agents | |
| CN110612545B (en) | Self-learning self-adaptive routing system | |
| CN109313666A (en) | Computer proxy message robot | |
| US20210157989A1 (en) | Systems and methods for dialog management | |
| CN106462418A (en) | Remote invocation of mobile device actions | |
| US10720161B2 (en) | Methods and systems for personalized rendering of presentation content | |
| CN114787814B (en) | Reference resolution | |
| US20230090924A1 (en) | Database systems with automated structural metadata assignment | |
| US11526681B2 (en) | Dynamic multilingual speech recognition | |
| CN114270338A (en) | System and method for facilitating robotic communication | |
| CN115917553A (en) | Entity-level data augmentation to enable robust named entity recognition in chat robots | |
| JP2022105273A (en) | Computer-implemented method, computer-implemented system and computer program product for generating summaries and next actions in real time for multiple users from interaction records in natural language | |
| US20180232355A1 (en) | Cognitive entity reference recognition | |
| US11645138B2 (en) | Diagnosing and resolving technical issues | |
| US11868678B2 (en) | User interface sound emanation activity classification | |
| US11036925B2 (en) | Managing the distinctiveness of multimedia | |
| US20230034085A1 (en) | Score prediction using hierarchical attention | |
| da Silva Gomes | A retail conversational interface to naturally capture unstructured information triggering high value analytical and operational business actions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190219 |
|
| RJ01 | Rejection of invention patent application after publication |