CN112379876A - Method and server for customizing voice skills - Google Patents
Method and server for customizing voice skills Download PDFInfo
- Publication number
- CN112379876A CN112379876A CN202011271823.XA CN202011271823A CN112379876A CN 112379876 A CN112379876 A CN 112379876A CN 202011271823 A CN202011271823 A CN 202011271823A CN 112379876 A CN112379876 A CN 112379876A
- Authority
- CN
- China
- Prior art keywords
- script
- module
- vehicle
- server
- voice
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/38—Creation or generation of source code for implementing user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/71—Version control; Configuration management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Human Computer Interaction (AREA)
- Stored Programmes (AREA)
Abstract
The invention discloses a method for self-defining voice skills, which comprises the following steps of 1, starting a server side and a vehicle side, and initializing. And 2, managing the application APP related information prefabricated at the vehicle machine end by the APP management module. And 3, setting verticality and intention for the script by the custom skill script module. And 4, carrying out script development. And 5, combining the scripts of the single operation step into a functional unit capable of being completely executed. And 6, performing script auditing verification. And 7, the script mapping module establishes a mapping relation between the user-defined voice skill script and the APP version on one hand and the mapping relation between the user-defined voice skill script and the vehicle-mounted voice assistant version on the other hand. And 8, the script matching module adapts the custom voice skill script according to the vehicle-mounted voice assistant and the APP version. And 9, combining the customized voice skill script and other related information into a complete protocol by the script integration module. The present solution addresses strong dependencies on speech and content providers.
Description
Technical Field
The invention relates to the technical field of automotive electronics, in particular to a method and a server for customizing a voice skill.
Background
In the existing vehicle-mounted technology, the user-defined voice skill development work is basically carried out by a vehicle-mounted voice assistant at the vehicle end, if new skills need to be supported, the vehicle-mounted voice assistant is required to start a round of development process, develop and adapt the new skills, release a new vehicle-mounted voice assistant version, upgrade the vehicle-mounted voice assistant version through OTA, and a user can experience the new skills; different vehicle-mounted voice assistant versions experience different custom voice skills, and the versions with low versions can only experience less or weaker custom voice skills; moreover, the traditional customized voice skills are strongly dependent on skills supported by a voice provider, the skills which are not supported by the provider are developed at once, and the content provider is required to provide a support interface to complete final execution of the skills when the content provider is adapted.
The existing vehicle-mounted voice assistant has the following problems:
a) the method completely depends on skills supported by a voice supplier, the skill homogenization is serious, and the product has no obvious differentiation and competitiveness;
b) for different vehicle types, if the application versions prefabricated by the vehicle-mounted voice assistant are not consistent, adaptation is possibly needed to normally use the voice skills, and the workload is complicated;
c) the skill of a voice provider is upgraded, the vehicle-mounted voice assistant needs to be upgraded synchronously, and otherwise, the upgrading function cannot be used;
d) the existing voice scheme needs an application to provide interface support, and once an application provider cannot provide support or cannot normally support due to other reasons, the application skill is limited from being used normally;
e) the existing vehicle-mounted voice skill can be realized on a vehicle, a vehicle-mounted voice assistant at the vehicle end is required to perform corresponding development work on the new skill again, the vehicle end is required to be upgraded, a user can experience the new skill of the custom voice, the period is long, and the work is complex.
Aiming at the problems, a method and a server for customizing the voice skills are invented.
Disclosure of Invention
The invention aims to solve the problems that the existing vehicle-mounted voice assistant depends on skills supported by a voice provider, has serious skill homogenization and no obvious differentiation and competitiveness, if versions of the vehicle-mounted voice assistant are inconsistent, adaptation is needed if different vehicle types are different, the skill of the voice provider is upgraded, the vehicle-mounted voice assistant needs to be upgraded synchronously to be normally used, the existing voice scheme needs to be supported by an application interface, once the support is lost, the application skill cannot be used, a new user-defined voice skill is realized on a vehicle machine, the vehicle-mounted voice assistant needs to perform corresponding development work again, the vehicle end is required to be upgraded, a user can experience, the period is long, and the work is complicated. The concrete solution is as follows:
a method for customizing voice skills comprises the following steps:
step 1, starting a server side and a vehicle side, and initializing;
step 2, an APP management module of the server manages application APP related information prefabricated at the vehicle machine end;
step 3, a custom skill script module of the server sets verticality and intention for the script for semantic recognition;
step 4, a user-defined skill script module carries out script development, a script format is defined, and then the operation steps of the application APP are converted into XML or JSON scripts;
step 5, combining the scripts of the single operation step into a functional unit capable of being completely executed for the vehicle-mounted voice assistant to execute so as to complete the control of the application AP P;
step 6, after the script development is completed, the verification of the script is carried out through an auditing/checking module of the server and manual work, whether the script logic and the attribute are correct or not is checked, the next step is executed after the verification is passed, and the step 3 is switched to if the verification is not passed;
step 7, a script mapping module of the server establishes a mapping relation between the customized voice skill script and the APP version on one hand and the mapping relation between the customized voice skill script and the vehicle-mounted voice assistant version on the other hand;
step 8, a script matching module of the server adapts the custom voice skill script according to the vehicle-mounted voice assistant and the APP version;
and 9, combining the customized voice skill script and other related information into a complete protocol by a script integration module of the server, and then wirelessly transmitting the complete protocol to a vehicle terminal through the first wireless transceiver module to execute the customized voice skill script.
Further, the APP related information in step 2 includes an application package name, an application version number, and an application code.
Further, the other related information in step 9 includes APP attributes, vehicle-mounted voice assistant version information, script vertical class, and script intention.
Further, the method for executing the customized voice skill script by the vehicle terminal in step 9 is performed according to the following steps:
step 10, the vehicle end initiates a script request logic to the server end through the second wireless transceiver module;
step 11, an auditing/checking module of the server side checks, and if the request is passed, the next step is carried out, and if the request is not passed, the step 10 is carried out;
step 12, the vehicle terminal transmits the vehicle-mounted voice assistant related information and the APP related information to the server terminal;
step 13, a parameter extraction module of the server side extracts relevant parameters from relevant information transmitted from the vehicle end;
step 14, the script matching module of the server matches the corresponding script according to the extracted relevant parameters;
step 15, integrating the matched scripts by a script integration module of the server side, and supplementing corresponding information including application package names, versions, verticality and intentions;
step 16, the server wirelessly transmits the integrated complete script to the vehicle end through the first wireless transceiver module;
step 17, a vehicle machine analysis module at the vehicle machine end analyzes the complete script;
and step 18, executing the custom voice skill script by a vehicle machine execution module at the vehicle machine end.
Further, the vertical class is defined as a vertical class for each prefabricated application of the vehicle machine and is represented by domain; the intention is defined as one intention for each complete functional operation and is represented by intent; the script comprises an operation type, an operation object, an operation ending condition and an abnormal retry.
Further, the operation types comprise opening an application according to a package name, clicking a control according to text content, dragging a scroll bar according to a resource ID, clicking the control according to the resource ID, inputting a contact according to the resource ID, clicking the contact according to the resource ID, and inputting a text according to the resource ID.
Further, the operation object is a target to be operated by the operation type, specifically, a package name and a control ID.
Further, the operation ending condition is an operation ending condition of each step, and can be set to be an event attribute or an event value or a timeout.
Further, the abnormal retry is an operation response set when the current operation has an abnormal condition.
A server for self-defining voice skills is used for executing the method for self-defining voice skills, and comprises a first controller, a first memory, a first display screen, a first wireless transceiving module, an APP management module, a self-defining skill script module, an auditing/checking module, a script mapping module, a script matching module, a script integration module and a parameter extraction module, wherein the first memory is electrically connected with the first controller respectively, the first memory is used for storing preset programs and system parameters, and the first controller controls each module in the server to perform related operations according to the preset programs.
In summary, the technical scheme of the invention has the following beneficial effects:
the invention solves the problems that the existing vehicle-mounted voice assistant depends on skills supported by a voice provider, the skill homogeneity is serious, no obvious differentiation and competitiveness exist, if the versions of different vehicle types of the vehicle-mounted voice assistant are inconsistent, adaptation is needed, the skill of the voice provider is upgraded, the vehicle-mounted voice assistant needs to be upgraded synchronously so as to be normally used, the existing voice scheme needs to be supported by an application interface, once the support is lost, the application skill cannot be used, the vehicle-mounted voice assistant realizes new self-defined voice skill on a vehicle, the vehicle-mounted voice assistant needs to perform corresponding development work again, the vehicle-mounted voice assistant requires to be upgraded, a user can experience, the period is long, and the work is complicated. The scheme provides a visual server background operating system, custom voice skills are realized in a script customization mode, new custom voice skills are developed, the scripts are customized through the step of simulating the actual operation of a user at an operation vehicle machine end APP, then the scripts are analyzed through a vehicle machine analysis module, and corresponding operation steps are executed to complete the execution of the custom voice skills. The scheme has the following advantages:
(1) resolving strong dependencies on voice providers and content providers by simulating APP operation steps;
(2) the method for customizing the voice skills through the server side is used for solving the problem that the vehicle side supports new skills or repair skills through frequently upgrading versions;
(3) the problem of compatibility of different versions of the APP is solved by establishing a mapping relation between the script and the APP version, and the new user-defined voice skills can be normally used for different vehicle types and different vehicle-mounted voice versions;
(4) the personalization and deep customization of the voice skills are realized;
(5) the skill which is not supported or can not be supported by a third-party voice provider is compensated, and updating and upgrading of the skill can be controlled independently so as to avoid the problem of skill use caused by updating of an application version;
(6) the compatibility of various vehicle-mounted voice versions is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a block diagram of a server side and a vehicle side for customizing a voice skill according to the present invention;
FIG. 2 is a flow chart of a method of customizing speech skills in accordance with the present invention;
FIG. 3 is a step diagram of a method for executing a custom voice skill script at a vehicle end in accordance with the present invention.
Description of reference numerals:
100-a server side, 101-a first controller, 102-a first memory, 103-a first display screen, 104-a first wireless transceiver module, 105-an APP management module, 106-a custom skill script module, 107-an auditing/checking module, 108-a script mapping module, 109-a script matching module, 110-a script integration module, 111-a parameter extraction module, 200-a vehicle side, 201-a second controller, 202-a second memory, 203-a second display screen, 204-a second wireless transceiver module, 205-a vehicle voice module, 206-a vehicle analysis module, 207-a vehicle execution module and 208-a microphone.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1:
as shown in fig. 1, a server (i.e., a server 100) for customizing a voice technology includes a first controller 101, and a first memory 102, a first display screen 103, a first wireless transceiver module 104, an APP management module 105, a customized skill script module 106, an audit/verification module 107, a script mapping module 108, a script matching module 109, a script integration module 110, and a parameter extraction module 111 that are electrically connected to the first controller 101, where the first memory 102 is used to store a preset program and system parameters, and the first controller 101 controls each module in the server to perform related operations according to the preset program.
The car end 200 configured with the server (i.e. the server end 100) includes a second controller 201, a second memory 202 respectively electrically connected to the second controller 201, a second display screen 203, a second wireless transceiver module 204, a car-mounted speech module 205 (for parsing speech and processing speech), a car-mounted speech parsing module 206 (for parsing scripts), a car-mounted execution module 207 (for executing scripts), and a microphone 208 (for picking up speech), wherein the second memory 202 stores car-mounted system programs, applications APP, and a car-mounted speech assistant, and the second controller 201 is configured to control operations of each module of the whole car end 200.
The first wireless transceiver module 104 and the second wireless transceiver module 204 may be any one of 3G, 4G, 5G, and WIFI.
Example 2:
as shown in fig. 2, a method for customizing a speech skill is performed according to the following steps:
step S1, the server 100 and the vehicle 200 are started and initialized;
step S2, the APP management module 105 of the server manages APP related information of the application that is pre-prepared by the vehicle end 200; (the relevant information of the application APP comprises the name of an application package, the version number of the application and an application code.)
Step S3, the user-defined skill script module 106 of the server sets verticality and intention for the script for semantic recognition; (the vertical class is defined as one vertical class for each prefabricated application of the car machine and is represented by domain, the intention is defined as one intention for each complete functional operation and is represented by intent.)
Step S4, the user-defined skill script module 106 develops the script, defines the script format first, and then converts the operation steps of the application APP into XML or JSON script;
step S5, combining the scripts of the single operation step into a functional unit which can be completely executed for the vehicle-mounted voice assistant to execute so as to complete the control of the application AP P;
step S6, after the script development is completed, the auditing/checking module 107 of the server and the manual work are used for auditing and verifying the script, whether the script logic and the attribute are correct or not is checked, the next step is executed after the checking is passed, and the step S3 is switched to if the checking is not passed; (development completion script by development is simultaneously stored in the database in the first memory 102 for later use)
Step S7, (S7-1) the script mapping module 108 of the server establishes the mapping relation between the custom voice skill script and the APP version on one hand, and (S7-2) establishes the mapping relation between the custom voice skill script and the vehicle-mounted voice assistant version on the other hand;
step S8, the script matching module 109 of the server adapts the custom voice skill script according to the vehicle-mounted voice assistant and the APP version;
in step S9, the script integration module 110 of the server combines the customized voice skill script with other related information into a complete protocol, and then wirelessly transmits the complete protocol to the vehicle end 200 through the first wireless transceiver module 104 to execute the customized voice skill script (and simultaneously back up the customized voice skill script in the database in the first memory 102). (other relevant information includes application APP Attribute, vehicle Voice Assistant version information, script vertical class, script intent, etc.)
The script comprises an operation type, an operation object, an operation ending condition and an abnormal retry, and is specifically described as follows:
the operation type (Action) includes opening an application (openAppByPackageName) according to a package name, clicking a control (clickViewByText) according to a text content, dragging a scroll bar (scrollViewByResId) according to a resource ID, clicking a control (clickviewbresid) according to a resource ID, inputting a contact (inputContactNameByResId) according to a resource ID, clicking a contact (clickContactNameByResId) according to a resource ID, and inputting a text (inputTextByResId) according to a resource ID. The operation Object (Object) is an Object to be operated by the operation type, specifically, a package name and a control ID. The operation end condition (step _ end _ condition) may be set to an event attribute (event _ type) or an event value (event _ value) or a timeout (timeout) for each step of the operation end condition. The exception retry (exception _ retry _ step) is an operation response set when an exception occurs in the current operation.
As shown in fig. 3, the method for executing the customized voice skill script by the vehicle end in step S9 is performed according to the following steps:
step S10, the vehicle end 200 initiates a script request logic to the server end 100 through the second wireless transceiver module 204;
step S11, the auditing/checking module 107 of the server 100 checks, if the request is passed, the next step is carried out, and if the request is not passed, the step S10 is carried out;
step S12, the vehicle end 200 transmits the vehicle voice assistant related information and the APP related information to the server end 100;
step S13, the parameter extraction module 111 of the server side extracts the relevant parameters from the relevant information transmitted from the vehicle side;
step S14, the script matching module 109 at the server matches the corresponding script according to the extracted relevant parameters;
step S15, the script integration module 110 at the server side integrates the matching scripts and complements the corresponding information, including the name, version, verticality and intention of the application package;
step S16, the server 100 wirelessly transmits the integrated complete script to the vehicle end 200 via the first wireless transceiver module 104;
step S17, the in-vehicle analysis module 206 at the in-vehicle end analyzes the complete script;
step S18, the car machine execution module 207 at the car machine end executes the custom voice skill script.
Example 3:
in this embodiment 3, the following is described by taking "WeChat Scan" as an example:
domain is defined as wechat;
intent is defined as open _ scan;
the format of script development can be XML, JSON format, wherein
The JSON format is as follows:
the XML format is as follows:
the complete script of "WeChat Scan" is as follows:
the scripts are integrated as follows:
in summary, the technical scheme of the invention has the following beneficial effects:
the invention solves the problems that the existing vehicle-mounted voice assistant depends on skills supported by a voice provider, the skill homogeneity is serious, no obvious differentiation and competitiveness exist, if the versions of different vehicle types of the vehicle-mounted voice assistant are inconsistent, adaptation is needed, the skill of the voice provider is upgraded, the vehicle-mounted voice assistant needs to be upgraded synchronously so as to be normally used, the existing voice scheme needs to be supported by an application interface, once the support is lost, the application skill cannot be used, the vehicle-mounted voice assistant realizes new self-defined voice skill on a vehicle, the vehicle-mounted voice assistant needs to perform corresponding development work again, the vehicle-mounted voice assistant requires to be upgraded, a user can experience, the period is long, and the work is complicated. The scheme provides a visual server background operating system, custom voice skills are realized in a script customization mode, new custom voice skills are developed, the scripts are customized through the step of simulating the actual operation of a user at an operation vehicle machine end APP, then the scripts are analyzed through a vehicle machine analysis module, and corresponding operation steps are executed to complete the execution of the custom voice skills. The scheme has the following advantages:
(1) resolving strong dependencies on voice providers and content providers by simulating APP operation steps;
(2) the method for customizing the voice skills through the server side is used for solving the problem that the vehicle side supports new skills or repair skills through frequently upgrading versions;
(3) the problem of compatibility of different versions of the APP is solved by establishing a mapping relation between the script and the APP version, and the new user-defined voice skills can be normally used for different vehicle types and different vehicle-mounted voice versions;
(4) the personalization and deep customization of the voice skills are realized;
(5) the skill which is not supported or can not be supported by a third-party voice provider is compensated, and updating and upgrading of the skill can be controlled independently so as to avoid the problem of skill use caused by updating of an application version;
(6) the compatibility of various vehicle-mounted voice versions is realized.
The above-described embodiments do not limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the above-described embodiments should be included in the protection scope of the technical solution.
Claims (10)
1. A method for customizing a voice skill is characterized by comprising the following steps:
step 1, starting a server side and a vehicle side, and initializing;
step 2, an APP management module of the server manages application APP related information prefabricated at the vehicle machine end;
step 3, a custom skill script module of the server sets verticality and intention for the script for semantic recognition;
step 4, a user-defined skill script module carries out script development, a script format is defined, and then the operation steps of the application APP are converted into XML or JSON scripts;
step 5, combining the scripts of the single operation step into a functional unit capable of being completely executed for the vehicle-mounted voice assistant to execute so as to complete the control of the application AP P;
step 6, after the script development is completed, the verification of the script is carried out through an auditing/checking module of the server and manual work, whether the script logic and the attribute are correct or not is checked, the next step is executed after the verification is passed, and the step 3 is switched to if the verification is not passed;
step 7, a script mapping module of the server establishes a mapping relation between the customized voice skill script and the APP version on one hand and the mapping relation between the customized voice skill script and the vehicle-mounted voice assistant version on the other hand;
step 8, a script matching module of the server adapts the custom voice skill script according to the vehicle-mounted voice assistant and the APP version;
and 9, combining the customized voice skill script and other related information into a complete protocol by a script integration module of the server, and then wirelessly transmitting the complete protocol to a vehicle terminal through the first wireless transceiver module to execute the customized voice skill script.
2. The method of claim 1, wherein: and 2, the related information of the application APP comprises an application package name, an application version number and an application code.
3. The method of claim 1, wherein: and step 9, the other related information comprises the attribute of the application APP, the version information of the vehicle-mounted voice assistant, the script vertical class and the script intention.
4. The method of claim 1, wherein: the method for executing the custom voice skill script by the vehicle terminal in the step 9 is carried out according to the following steps:
step 10, the vehicle end initiates a script request logic to the server end through the second wireless transceiver module;
step 11, an auditing/checking module of the server side checks, and if the request is passed, the next step is carried out, and if the request is not passed, the step 10 is carried out;
step 12, the vehicle terminal transmits the vehicle-mounted voice assistant related information and the APP related information to the server terminal;
step 13, a parameter extraction module of the server side extracts relevant parameters from relevant information transmitted from the vehicle end;
step 14, the script matching module of the server matches the corresponding script according to the extracted relevant parameters;
step 15, integrating the matched scripts by a script integration module of the server side, and supplementing corresponding information including application package names, versions, verticality and intentions;
step 16, the server wirelessly transmits the integrated complete script to the vehicle end through the first wireless transceiver module;
step 17, a vehicle machine analysis module at the vehicle machine end analyzes the complete script;
and step 18, executing the custom voice skill script by a vehicle machine execution module at the vehicle machine end.
5. The method of claim 1, wherein: the vertical class is defined as a vertical class for each prefabricated application of the vehicle machine and is represented by domain; the intention is defined as one intention for each complete functional operation and is represented by intent; the script comprises an operation type, an operation object, an operation ending condition and an abnormal retry.
6. The method of claim 5, wherein: the operation types comprise opening an application according to a package name, clicking a control according to text content, dragging a scroll bar according to a resource ID, clicking the control according to the resource ID, inputting a contact according to the resource ID, clicking the contact according to the resource ID, and inputting a text according to the resource ID.
7. The method of claim 5, wherein: the operation objects are targets to be operated for operation types, specifically package names and control IDs.
8. The method of claim 5, wherein: the operation ending condition is an operation ending condition of each step and can be set to be an event attribute or an event value or a timeout.
9. The method of claim 5, wherein: the abnormal retry is an operation response set when the current operation has an abnormal condition.
10. A server for customizing voice skills, configured to perform a method for customizing voice skills according to any one of claims 1 to 9, wherein: the system comprises a first controller, a first memory, a first display screen, a first wireless transceiving module, an APP management module, a user-defined skill script module, an auditing/checking module, a script mapping module, a script matching module, a script integration module and a parameter extraction module, wherein the first memory, the first display screen, the first wireless transceiving module, the APP management module, the user-defined skill script module, the auditing/checking module, the script mapping module, the script matching module, the script integration module and the parameter extraction module are electrically connected with the first controller respectively, the first memory is used for storing preset programs and system parameters, and the.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271823.XA CN112379876B (en) | 2020-11-13 | 2020-11-13 | Method and server for customizing voice skills |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011271823.XA CN112379876B (en) | 2020-11-13 | 2020-11-13 | Method and server for customizing voice skills |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112379876A true CN112379876A (en) | 2021-02-19 |
CN112379876B CN112379876B (en) | 2022-03-15 |
Family
ID=74583957
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011271823.XA Active CN112379876B (en) | 2020-11-13 | 2020-11-13 | Method and server for customizing voice skills |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112379876B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110310641A (en) * | 2019-02-26 | 2019-10-08 | 北京蓦然认知科技有限公司 | A kind of method and device for voice assistant |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5737725A (en) * | 1996-01-09 | 1998-04-07 | U S West Marketing Resources Group, Inc. | Method and system for automatically generating new voice files corresponding to new text from a script |
US8325880B1 (en) * | 2010-07-20 | 2012-12-04 | Convergys Customer Management Delaware Llc | Automated application testing |
CN103366731A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术(上海)有限公司 | Text to speech (TTS) method and system |
US20160062970A1 (en) * | 2014-09-02 | 2016-03-03 | Belleau Technologies | Method and System for Dynamic Speech Recognition and Tracking of Prewritten Script |
CN108108158A (en) * | 2017-12-15 | 2018-06-01 | 复旦大学 | A kind of user individual customized voice towards Android controls application process |
CN111599362A (en) * | 2020-05-20 | 2020-08-28 | 湖南华诺科技有限公司 | System and method for self-defining intelligent sound box skill and storage medium |
-
2020
- 2020-11-13 CN CN202011271823.XA patent/CN112379876B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5737725A (en) * | 1996-01-09 | 1998-04-07 | U S West Marketing Resources Group, Inc. | Method and system for automatically generating new voice files corresponding to new text from a script |
US8325880B1 (en) * | 2010-07-20 | 2012-12-04 | Convergys Customer Management Delaware Llc | Automated application testing |
CN103366731A (en) * | 2012-03-31 | 2013-10-23 | 盛乐信息技术(上海)有限公司 | Text to speech (TTS) method and system |
US20160062970A1 (en) * | 2014-09-02 | 2016-03-03 | Belleau Technologies | Method and System for Dynamic Speech Recognition and Tracking of Prewritten Script |
CN108108158A (en) * | 2017-12-15 | 2018-06-01 | 复旦大学 | A kind of user individual customized voice towards Android controls application process |
CN111599362A (en) * | 2020-05-20 | 2020-08-28 | 湖南华诺科技有限公司 | System and method for self-defining intelligent sound box skill and storage medium |
Non-Patent Citations (1)
Title |
---|
邝展鹏: "语音交互设计与研究——以金融自助终端设备语音交互设计为例", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110310641A (en) * | 2019-02-26 | 2019-10-08 | 北京蓦然认知科技有限公司 | A kind of method and device for voice assistant |
Also Published As
Publication number | Publication date |
---|---|
CN112379876B (en) | 2022-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107977214B (en) | Burning method and device for identification code of intelligent equipment and computer readable storage medium | |
CN108769226A (en) | The OAT upgrade methods and car-mounted terminal of vehicle | |
KR101007739B1 (en) | Method and system for providing fota service | |
CN113703814B (en) | Configuration method, system, storage medium and configuration equipment of Internet of vehicles APP | |
CN112379876B (en) | Method and server for customizing voice skills | |
WO2021203604A1 (en) | Update test method and apparatus for vehicle component, and computer device and storage medium | |
CN106775778B (en) | Program updating identification method and system in embedded program development | |
WO2020143574A1 (en) | Method and apparatus for updating firmware in vci device, and automobile fault diagnosis instrument | |
CN112100078A (en) | Method, device and equipment for generating interface test case | |
CN113625695B (en) | Vehicle control function diagnosis method and system based on android service | |
EP4390673A1 (en) | Ecu upgrade method and device, and readable storage medium | |
CN113703781A (en) | Storage system interface generation method and device, electronic equipment and readable storage medium | |
CN111190629A (en) | Embedded terminal upgrading software package and analysis method thereof | |
CN113986256A (en) | Method and device for issuing application program, electronic equipment and storage medium | |
CN113590151A (en) | Method and system for OTA (over the air) upgrade of Bluetooth equipment | |
CN112770108B (en) | Performance test method, device and system and computer readable storage medium | |
CN107729043B (en) | Method and device for checking increment upgrade package and computer readable storage medium | |
CN113448643A (en) | Configuration data management system and method | |
CN112131022B (en) | Open API management method, device, system and computer readable storage medium | |
CN113592109B (en) | Method, system, device and storage medium for binding vehicle-mounted terminal and vehicle networking platform | |
CN107315602B (en) | Application program upgrading method and terminal | |
CN111880780B (en) | Method, device and platform for developing boot loader of MCU | |
JP5766309B2 (en) | Management of information related to secure module applications | |
CN111580857A (en) | Equipment firmware online configuration method, device and system | |
CN111475216B (en) | APP voice control method, computer storage medium and electronic equipment |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |