CN113450778A - Training method based on voice interaction control and storage medium - Google Patents
Training method based on voice interaction control and storage medium Download PDFInfo
- Publication number
- CN113450778A CN113450778A CN202110643034.2A CN202110643034A CN113450778A CN 113450778 A CN113450778 A CN 113450778A CN 202110643034 A CN202110643034 A CN 202110643034A CN 113450778 A CN113450778 A CN 113450778A
- Authority
- CN
- China
- Prior art keywords
- voice
- instruction
- training
- interaction control
- information
- 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
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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0631—Creating reference templates; Clustering
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0638—Interactive procedures
Abstract
The invention relates to the technical field of voice interaction, and provides a training method based on voice interaction control and a storage medium, wherein a self-defined training mechanism of voice interaction control is preset through setting steps S1-S4, and when a voice training instruction is recognized, a training teaching mode is entered for executing operation and self-defined setting of the voice instruction; gradually executing a voice operation instruction input by a user according to the current interface information until the training is finished (when the training instruction is recognized to be finished), integrating all executing operations in the training teaching mode into a target instruction operation set, and binding the target instruction operation set with a self-defined threshold voice instruction and importing the target instruction operation set into a voice instruction database; therefore, the preferred voice instruction can be customized according to the use habit of the user, and the limitation of a fixed and rigid voice instruction database is eliminated, so that the voice interaction control equipment is more flexible, intelligent and personalized.
Description
Technical Field
The present invention relates to the field of voice interaction technology, and in particular, to a training method and a storage medium based on voice interaction control.
Background
At present, the on-board voice assistant instruction function is limited, the voice control instruction and the execution operation of the on-board system are fixed, a user needs to complete corresponding voice control according to a specified voice instruction provided by a product provider, and the voice control operation is limited and the flexibility is poor, so that the personalized voice control requirements of all users cannot be met. The existing voice assistant conversation is mature and intelligent, and the technical core is as follows: and receiving a voice command of a user and executing an operation corresponding to the command.
However, the voice control command is still limited to the command set of the official setting, and the following defects exist:
firstly, when the user exceeds the voice control instruction set preset in advance by the official, the corresponding operation cannot be executed, namely the control operation required by the user cannot be executed.
Secondly, because the instruction set is relatively fixed, personalized adjustment cannot be performed according to personal habits of the user, and the user experience is poor.
Disclosure of Invention
The invention provides a training method and a storage medium based on voice interaction control, which solve the technical problems of poor flexibility and poor user experience of the existing voice interaction control which is limited to a preset instruction set (after a non-factory preset voice command occurs, a corresponding execution action cannot be found).
In order to solve the technical problems, the invention provides a training method based on voice interaction control, which comprises the following steps:
s1, acquiring a voice training instruction, and entering a training teaching mode;
s2, acquiring a voice operation instruction and current interface information, and executing the voice operation instruction according to the interface information;
s3, when a training instruction is recognized to be completed, ending the training and teaching mode, and integrating the execution operation corresponding to each voice operation instruction in the training and teaching mode to obtain a target instruction operation set;
and S4, importing the target instruction operation set and the corresponding preset voice instruction into a voice instruction database.
The basic scheme presets a self-defined training mechanism of voice interaction control through setting steps S1-S4, and enters a training teaching mode when a voice training instruction is recognized to perform execution operation and self-defined setting of the voice instruction; gradually executing a voice operation instruction input by a user according to the current interface information until the training is finished (when the training instruction is recognized to be finished), integrating all executing operations in the training teaching mode into a target instruction operation set, and binding the target instruction operation set with a self-defined threshold voice instruction and importing the target instruction operation set into a voice instruction database; therefore, the preferred voice instruction can be customized according to the use habit of the user, and the limitation of a fixed and rigid voice instruction database is eliminated, so that the voice interaction control equipment is more flexible, intelligent and personalized.
In further embodiments, the step S1 includes:
s11, acquiring a voice input instruction of a user, and performing voice recognition to obtain text information;
and S12, comparing the text information with a preset voice training instruction, and entering a training teaching mode if the comparison is consistent.
In further embodiments, the step S2 includes:
s21, acquiring a voice operation instruction input by a user;
s22, acquiring current system software installation information and interface information;
and S23, searching and executing an operation control corresponding to the voice operation instruction according to the system software installation information and the interface information.
According to the scheme, after the voice training instruction is used as a mark to enter a training teaching mode, the collected user artificial voice is matched for training guidance according to actual interface information and corresponding system software installation information, and the voice operation instruction is highly consistent with the system interface, so that the user guidance difficulty can be reduced, and the training precision is improved.
In further embodiments, the step S3 includes:
s31, when the obtained voice input instruction is judged to be matched with the instruction for finishing the training, ending the teaching mode of the training, otherwise, executing the step S2 in a circulating way;
and S32, integrating the execution operation corresponding to each voice operation instruction during the training teaching mode to obtain a target instruction operation set and defining a voice control command corresponding to the target instruction operation set as a preset voice instruction.
According to the scheme, all execution operations realized under the voice operation instruction of the user in the primary training teaching mode are integrated into the target instruction operation set, and at the moment, the target instruction operation set is bound with the preset voice instruction defined by the user, so that the whole target instruction operation set can be directly and automatically completed when the preset voice instruction is identified in the follow-up process, the personalized requirement of the user is fully considered, and the intelligent degree of voice interaction control is further realized.
In a further embodiment, in the step S22, the interface information includes attribute information, text information, color information, and shape information of all controls on the current interface.
In a further embodiment, in the step S21, the voice operation instruction is a basic voice instruction, including a "click" instruction, an "open" instruction, and a "page turn" instruction.
In a further embodiment, the present invention further comprises the steps of:
and S5, when the preset voice command is recognized, matching the preset voice command with the voice command database to obtain and execute the target command operation set.
The present invention also provides a storage medium having a computer program stored thereon, the computer program being used for implementing the above training method based on voice interaction control. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
Drawings
FIG. 1 is a flowchart of a training method based on voice interaction control according to an embodiment of the present invention;
fig. 2 is a flowchart of a training method based on voice interaction control according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, which are given solely for the purpose of illustration and are not to be construed as limitations of the invention, including the drawings which are incorporated herein by reference and for illustration only and are not to be construed as limitations of the invention, since many variations thereof are possible without departing from the spirit and scope of the invention.
Example 1
As shown in fig. 1 and 2, the training method based on voice interaction control according to the embodiment of the present invention includes steps S1 to S5:
s1, obtaining a voice training instruction, and entering a training teaching mode, wherein the method comprises the following steps of S11-S12:
s11, acquiring a voice input instruction of a user, and performing voice recognition to obtain text information;
and S12, comparing the text information with a preset voice training instruction, and entering a training teaching mode if the comparison is consistent.
S2, acquiring the voice operation instruction and the current interface information, and executing the voice operation instruction according to the interface information, wherein the steps S21-S23 are as follows:
s21, acquiring a voice operation instruction input by a user;
in this embodiment, in step S21, the voice operation instruction is a basic voice instruction, including but not limited to a "click" instruction, an "open" instruction, and a "page turn" instruction.
S22, acquiring current system software installation information and interface information;
in the present embodiment, in step S22, the interface information includes, but is not limited to, attribute information, text information, color information, and shape information of all controls on the current interface.
And S23, searching and executing the operation control corresponding to the voice operation instruction according to the system software installation information and the interface information.
According to the scheme, after the voice training instruction is used as a mark to enter a training teaching mode, the collected user artificial voice is matched for training guidance according to actual interface information and corresponding system software installation information, and the voice operation instruction is highly consistent with the system interface, so that the user guidance difficulty can be reduced, and the training precision is improved.
S3, when the training instruction is recognized, ending the teaching mode of the training, and integrating the execution operation corresponding to each voice operation instruction during the teaching mode of the training to obtain a target instruction operation set, including steps S31-S32:
s31, when the obtained voice input instruction is judged to be matched with the training completion instruction, ending the training teaching mode, otherwise, executing the step S2 in a circulating mode;
and S32, integrating the execution operation corresponding to each voice operation instruction during the training teaching mode to obtain a target instruction operation set and defining a voice control command corresponding to the target instruction operation set as a preset voice instruction.
According to the scheme, all execution operations realized under the voice operation instruction of the user in the primary training teaching mode are integrated into the target instruction operation set, and at the moment, the target instruction operation set is bound with the preset voice instruction defined by the user, so that the whole target instruction operation set can be directly and automatically completed when the preset voice instruction is identified in the follow-up process, the personalized requirement of the user is fully considered, and the intelligent degree of voice interaction control is further realized.
And S4, importing the target instruction operation set and the corresponding preset voice instruction into a voice instruction database.
And S5, when the preset voice command is recognized, matching the preset voice command with a voice command database to obtain a target command operation set and executing the target command operation set.
Specifically, taking "you want to do the following operation" as a voice training instruction and "save this operation instruction" as a training instruction, the working process of the training method based on voice interaction control provided by this embodiment is as follows:
the voice assistant collects the voice input instruction input by the user, "when i say to navigate to yesterday, you want to do the following" and enters the training teaching mode.
At the moment, a voice operation instruction of opening a map, which is input by a user, is collected, a voice team member executes the operation of opening the map, and the system interface is converted into an interface (such as a main interface of the hundred-degree map) after the map is opened; the user continues to input a voice operation instruction of clicking characters in the interface, the voice assistant executes the voice operation instruction to click the My icon displayed on the current interface, so that the user continues to input instructions of sliding to the next page, clicking the gray footprint icon, clicking the last record and the like, and meanwhile the voice assistant completes corresponding operation on the current interface according to each voice operation instruction.
Until the voice assistant recognizes that the operation instruction is saved, integrating the execution operation corresponding to each voice operation instruction in the training teaching mode into a target instruction operation set, and taking a corresponding voice control command of navigating to the place yesterday as a preset voice instruction. And finally, binding and updating the target instruction operation set and the preset voice instruction to a voice instruction database. Thus completing the training of the voice interaction control.
The embodiment of the invention presets a self-defined training mechanism of voice interaction control through setting steps S1-S4, and enters a training teaching mode when a voice training instruction is recognized to carry out execution operation and self-defined setting of the voice instruction; gradually executing a voice operation instruction input by a user according to the current interface information until the training is finished (when the training instruction is recognized to be finished), integrating all executing operations in the training teaching mode into a target instruction operation set, and binding the target instruction operation set with a self-defined threshold voice instruction and importing the target instruction operation set into a voice instruction database; therefore, the preferred voice instruction can be customized according to the use habit of the user, and the limitation of a fixed and rigid voice instruction database is eliminated, so that the voice interaction control equipment is more flexible, intelligent and personalized.
Example 2
An embodiment of the present invention further provides a storage medium, where a computer program is stored on the storage medium, and the computer program is used to implement the training method based on voice interaction control in embodiment 1. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (8)
1. A training method based on voice interaction control is characterized by comprising the following steps:
s1, acquiring a voice training instruction, and entering a training teaching mode;
s2, acquiring a voice operation instruction and current interface information, and executing the voice operation instruction according to the interface information;
s3, when a training instruction is recognized to be completed, ending the training and teaching mode, and integrating the execution operation corresponding to each voice operation instruction in the training and teaching mode to obtain a target instruction operation set;
and S4, importing the target instruction operation set and the corresponding preset voice instruction into a voice instruction database.
2. The training method based on voice interaction control as claimed in claim 1, wherein the step S1 includes:
s11, acquiring a voice input instruction of a user, and performing voice recognition to obtain text information;
and S12, comparing the text information with a preset voice training instruction, and entering a training teaching mode if the comparison is consistent.
3. The training method based on voice interaction control as claimed in claim 2, wherein the step S2 includes:
s21, acquiring a voice operation instruction input by a user;
s22, acquiring current system software installation information and interface information;
and S23, searching and executing an operation control corresponding to the voice operation instruction according to the system software installation information and the interface information.
4. The training method based on voice interaction control as claimed in claim 1, wherein the step S3 includes:
s31, when the obtained voice input instruction is judged to be matched with the instruction for finishing the training, ending the teaching mode of the training, otherwise, executing the step S2 in a circulating way;
and S32, integrating the execution operation corresponding to each voice operation instruction during the training teaching mode to obtain a target instruction operation set and defining a voice control command corresponding to the target instruction operation set as a preset voice instruction.
5. A training method based on voice interaction control as claimed in claim 3, wherein in the step S22: the interface information comprises attribute information, character information, color information and shape information of all controls on the current interface.
6. A training method based on voice interaction control as claimed in claim 3, wherein in the step S21: the voice operation instruction is a basic voice instruction and comprises a click instruction, an opening instruction and a page turning instruction.
7. The training method based on voice interaction control as claimed in claim 1, further comprising the steps of:
and S5, when the preset voice command is recognized, matching the preset voice command with the voice command database to obtain and execute the target command operation set.
8. A storage medium having a computer program stored thereon, characterized in that: the computer program is used for implementing a real vehicle-based voice wake-up rate test method according to claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110643034.2A CN113450778A (en) | 2021-06-09 | 2021-06-09 | Training method based on voice interaction control and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110643034.2A CN113450778A (en) | 2021-06-09 | 2021-06-09 | Training method based on voice interaction control and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113450778A true CN113450778A (en) | 2021-09-28 |
Family
ID=77810960
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110643034.2A Pending CN113450778A (en) | 2021-06-09 | 2021-06-09 | Training method based on voice interaction control and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113450778A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104965596A (en) * | 2015-07-24 | 2015-10-07 | 上海宝宏软件有限公司 | Voice control system |
US20180039477A1 (en) * | 2016-08-02 | 2018-02-08 | Google Inc. | Component libraries for voice interaction services |
CN107992587A (en) * | 2017-12-08 | 2018-05-04 | 北京百度网讯科技有限公司 | A kind of voice interactive method of browser, device, terminal and storage medium |
CN108364644A (en) * | 2018-01-17 | 2018-08-03 | 深圳市金立通信设备有限公司 | A kind of voice interactive method, terminal and computer-readable medium |
CN110197662A (en) * | 2019-05-31 | 2019-09-03 | 努比亚技术有限公司 | Sound control method, wearable device and computer readable storage medium |
CN111768780A (en) * | 2020-06-28 | 2020-10-13 | 广州小鹏车联网科技有限公司 | Voice control method, information processing method, vehicle and server |
CN111883118A (en) * | 2020-07-09 | 2020-11-03 | 浙江吉利汽车研究院有限公司 | Vehicle control method and device based on personalized voice and storage medium |
CN112735387A (en) * | 2020-12-25 | 2021-04-30 | 惠州市德赛西威汽车电子股份有限公司 | User-defined vehicle-mounted voice skill system and method |
-
2021
- 2021-06-09 CN CN202110643034.2A patent/CN113450778A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104965596A (en) * | 2015-07-24 | 2015-10-07 | 上海宝宏软件有限公司 | Voice control system |
US20180039477A1 (en) * | 2016-08-02 | 2018-02-08 | Google Inc. | Component libraries for voice interaction services |
CN107992587A (en) * | 2017-12-08 | 2018-05-04 | 北京百度网讯科技有限公司 | A kind of voice interactive method of browser, device, terminal and storage medium |
CN108364644A (en) * | 2018-01-17 | 2018-08-03 | 深圳市金立通信设备有限公司 | A kind of voice interactive method, terminal and computer-readable medium |
CN110197662A (en) * | 2019-05-31 | 2019-09-03 | 努比亚技术有限公司 | Sound control method, wearable device and computer readable storage medium |
CN111768780A (en) * | 2020-06-28 | 2020-10-13 | 广州小鹏车联网科技有限公司 | Voice control method, information processing method, vehicle and server |
CN111883118A (en) * | 2020-07-09 | 2020-11-03 | 浙江吉利汽车研究院有限公司 | Vehicle control method and device based on personalized voice and storage medium |
CN112735387A (en) * | 2020-12-25 | 2021-04-30 | 惠州市德赛西威汽车电子股份有限公司 | User-defined vehicle-mounted voice skill system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108733343B (en) | Method, device and storage medium for generating voice control instruction | |
CN107895572A (en) | A kind of speech recognition training method and system | |
CN105283914A (en) | System and methods for recognizing speech | |
CN107306380A (en) | A kind of method and device of the object language of mobile terminal automatic identification voiced translation | |
JP2008203559A (en) | Interaction device and method | |
CN106378781A (en) | Service robot guide system and method | |
CN107195300A (en) | Sound control method and system | |
CN103365970A (en) | Method and device for automatically acquiring learning material information | |
CN102223448A (en) | Information prompt method and device and terminal | |
CN103489444A (en) | Speech recognition method and device | |
CN112966806A (en) | Processing device, processing method, and recording medium | |
CN113284502A (en) | Intelligent customer service voice interaction method and system | |
CN104900231A (en) | VOICE SEARCH DEVICE and VOICE SEARCH METHOD | |
CN100559464C (en) | Depend on the method and the speech recognition system of Speaker Identification voice | |
CN115064167A (en) | Voice interaction method, server and storage medium | |
CN109344374A (en) | Report generation method and device, electronic equipment based on big data, storage medium | |
CN109637529A (en) | Voice-based functional localization method, apparatus, computer equipment and storage medium | |
CN117216212A (en) | Dialogue processing method, dialogue model training method, device, equipment and medium | |
KR20190044359A (en) | Self-designing modeling system and method using artificial intelligence | |
CN111399629B (en) | Operation guiding method of terminal equipment, terminal equipment and storage medium | |
CN107395487A (en) | Message updating method and system | |
CN107894882B (en) | Voice input method of mobile terminal | |
CN113450778A (en) | Training method based on voice interaction control and storage medium | |
CN106372203A (en) | Information response method and device for smart terminal and smart terminal | |
CN107861706A (en) | The response method and device of a kind of phonetic order |
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: 20210928 |
|
RJ01 | Rejection of invention patent application after publication |