CN109697979B - Voice assistant skill adding method, device, storage medium and server - Google Patents
Voice assistant skill adding method, device, storage medium and server Download PDFInfo
- Publication number
- CN109697979B CN109697979B CN201811594341.0A CN201811594341A CN109697979B CN 109697979 B CN109697979 B CN 109697979B CN 201811594341 A CN201811594341 A CN 201811594341A CN 109697979 B CN109697979 B CN 109697979B
- Authority
- CN
- China
- Prior art keywords
- skill
- voice assistant
- information
- user
- skills
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000013461 design Methods 0.000 claims abstract description 57
- 230000006870 function Effects 0.000 claims description 42
- 238000005516 engineering process Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003058 natural language processing Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 239000002609 medium Substances 0.000 description 12
- 230000008901 benefit Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012550 audit Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 235000004789 Rosa xanthina Nutrition 0.000 description 1
- 241000109329 Rosa xanthina Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000012120 mounting media Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/01—Assessment or evaluation of speech recognition systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the application discloses a method and a device for adding voice assistant skills, a storage medium and a server. The method comprises the following steps: acquiring skill design information of a skill to be added, which is input by a user; determining corresponding skill factors according to the skill design information; and generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function. By adopting the technical scheme, the embodiment of the application can allow a third-party developer or a user of the voice assistant terminal to complete autonomous skill design and addition, and support the terminal configured with the voice assistant function to call the newly added skills, thereby enriching the skill types of the voice assistant in the terminal and perfecting the voice assistant function.
Description
Technical Field
The embodiment of the application relates to the technical field of voice recognition, in particular to a method, a device, a storage medium and a server for adding voice assistant skills.
Background
Speech recognition technology is a technology that allows a machine to convert speech signals into corresponding text or commands through a process of recognition and understanding. In recent years, with the rapid development of speech recognition technology, the applied field is more and more extensive. At present, the voice recognition technology is successfully applied to various intelligent terminals, so that the functions of the intelligent terminals are richer.
The voice recognition technology generally exists in an intelligent terminal in the form of a voice assistant, a plurality of skills are configured in the voice assistant, a user can send a command to the terminal by using the voice assistant in a natural language mode to trigger the corresponding skills, and the terminal can recognize and understand the natural language of the user, so that the corresponding skills are realized, and great convenience is brought to the user. In the related art, the skill of the voice assistant is solidified monotonously and is not perfect, and improvement is needed.
Disclosure of Invention
The embodiment of the application provides a method, a device, a storage medium and a server for adding skills of a voice assistant, which can realize the skill addition of the voice assistant.
In a first aspect, an embodiment of the present application provides a voice assistant skill adding method, including:
acquiring skill design information of a skill to be added, which is input by a user;
determining corresponding skill factors according to the skill design information;
and generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
In a second aspect, an embodiment of the present application provides a voice assistant skill adding apparatus, including:
the skill design information acquisition module is used for acquiring skill design information of skills to be added, which is input by a user;
the skill element determining module is used for determining corresponding skill elements according to the skill design information;
and the skill generation module is used for generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
In a third aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a voice assistant skill adding method according to embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a server, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the voice assistant skill adding method according to embodiments of the present application when executing the computer program.
According to the voice assistant skill adding scheme provided by the embodiment of the application, skill design information of a skill to be added, which is input by a user, is obtained, a corresponding skill element is determined according to the skill design information, and a corresponding skill is generated according to the skill element so as to be called by a terminal provided with a voice assistant function. By adopting the technical scheme, a third-party developer or a user of the voice assistant terminal can be allowed to complete the autonomous skill design and addition, and the terminal configured with the voice assistant function is supported to call the newly added skills, so that the skill types of the voice assistant in the terminal are enriched, and the voice assistant function is perfected.
Drawings
FIG. 1 is a flowchart illustrating a method for adding skills of a voice assistant according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating another method for adding speech assistant skills according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a method for adding skills of a voice assistant according to an embodiment of the present application;
FIG. 4 is a block diagram illustrating an exemplary embodiment of a voice assistant skill adding apparatus;
fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
The technical scheme of the application is further explained by the specific implementation mode in combination with the attached drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
At present, many terminals are provided with sound collection components such as microphones, and the sound collection components can realize a voice assistant function by combining with a voice recognition technology besides realizing a recording function. After the terminal enters the voice assistant function, the user can interact with the terminal by adopting natural language, the terminal can answer the questions of the user or execute corresponding operation according to the voice instruction of the user, the man-machine interaction function of the terminal is enriched, and great convenience is brought to the use of the user. In the related art, the matters (which may be called skills) that the voice assistant can accomplish are determined by the terminal system settings, and the inventor finds that this way makes the skills of the voice assistant single, and cannot meet the diversified requirements of the terminal user. In the embodiment of the application, a skill adding scheme of the voice assistant is provided, which can allow a third-party developer or a user of the voice assistant terminal to complete the autonomous skill design and addition, and enrich the skill types of the voice assistant in the terminal.
Fig. 1 is a flowchart of a voice assistant skill adding method according to an embodiment of the present application, which may be executed by a voice assistant skill adding apparatus, where the apparatus may be implemented by software and/or hardware, and may be generally integrated in a server. As shown in fig. 1, the method includes:
For example, the embodiment of the application may be implemented by a voice skill platform, the server may be used as an entity device corresponding to the voice skill platform, and a third party developer, a user of a terminal configured with a voice assistant, or another person (referred to as a user in this embodiment of the application) may implement skill addition of the voice assistant by accessing the voice skill platform.
For example, a user may access the voice skill platform by logging in a web page or a client application program on a computer, a mobile phone, a tablet computer, or other terminal (collectively referred to as a client in this embodiment), and input skill design information to be added with a skill in a page provided by the voice skill platform.
By way of example, the skill to be added may be understood as a new skill that the user wants to add in the terminal where the voice assistant is located. The skill design information may include relevant information desired by the user to achieve the skill to be added, such as skill name, skill description, skills to trigger the skill, skill intent, form of skill feedback, and other information needed to achieve or generate the skill. Optionally, when inputting skill design information, the user may input the skill design information in a natural language manner, may input corresponding characters, and may also input corresponding voice information; corresponding columns or options can also be provided by the voice skill platform for the user to fill out or select so as to help the user complete the input of skill design information.
And 102, determining corresponding skill factors according to the skill design information.
For example, the skill element may include relevant information required by the server when generating the skill to be added, such as a skill name, a skill description, a skill triggering technique, a skill intention, a skill feedback form, a skill implementing or generating manner, and the like, and the corresponding skill element may be determined by directly extracting from the skill design information or by intelligently identifying the skill design information.
And 103, generating corresponding skills according to the skill elements so as to be called by the terminal with the voice assistant function.
Illustratively, after acquiring the skill elements, the voice skill platform may generate corresponding skills according to the skill elements and issue the skills. The terminal (hereinafter referred to as an intelligent terminal) equipped with the voice assistant function can directly invoke the newly generated skills in a manner of remotely accessing the voice skill platform. Optionally, after the voice skill platform generates the skill, the skill may also be uploaded to a voice assistant cloud platform, and the intelligent terminal may invoke the skill by accessing the voice assistant cloud platform. The advantage of setting up like this lies in, makes things convenient for voice assistant cloud platform to carry out unified management to voice assistant skill, also can multiplex the call logic of system skill, and intelligent terminal need not carry out other changes, practices thrift the cost.
Optionally, the voice skill adding scheme provided by the embodiment of the application can be understood as an autonomous personalized customization scheme of the voice assistant skill, in order to ensure reasonable validity of the skill, an auditing function can be configured in the voice skill platform, an operator of the voice skill platform audits the newly designed skill of the user, and after the auditing is passed, the skill can be called.
Optionally, after the skill generation is finished, the voice skill platform may further provide a test function, and the user may test the skill effect through the test function to determine whether the skill effect reaches the expectation; the user can also use the intelligent terminal to call skills and test the aspects of voice interaction, skill display and the like.
According to the voice assistant skill adding method provided by the embodiment of the application, skill design information of a skill to be added, which is input by a user, is obtained, a corresponding skill element is determined according to the skill design information, and a corresponding skill is generated according to the skill element so as to be called by a terminal provided with a voice assistant function. By adopting the technical scheme, a third-party developer or a user of the voice assistant terminal can be allowed to complete the autonomous skill design and addition, and the terminal configured with the voice assistant function is supported to call the newly added skills, so that the skill types of the voice assistant in the terminal are enriched, and the voice assistant function is perfected.
In some embodiments, the acquiring the skill design information of the skill to be added, which is input by the user, includes: and acquiring the intention expression information and the skill reply setting information of the skill to be added, which are input by the user. Correspondingly, the determining the corresponding skill element according to the skill design information includes: determining corresponding slot position information according to the intention expression information; and determining a corresponding skill reply form and skill reply content according to the skill reply setting information. The method has the advantages that corresponding slot position information can be automatically determined according to intention expression information, so that the skill generation can be conveniently realized by clearly extracting corresponding keywords from the intelligent terminal user conversation, meanwhile, the corresponding skill reply form and reply content can be determined according to the skill reply setting information input by the user, and the skill generation can be conveniently realized by clearly feeding back skill results to the intelligent terminal user.
In some embodiments, the skill response form includes text, cards, audio, an application program, a quick application, or a web page. The advantage of this arrangement is that multiple forms of skill recovery can be supported, increasing the flexibility of skill design.
In some embodiments, after determining the corresponding slot position information according to the intention expression information, the method further includes: and receiving the update operation of the slot position information by a user, and updating the slot position information according to the update operation, wherein the update operation comprises an adding operation, a deleting operation and a modifying operation. The advantage of setting up like this is that when the slot position information that the pronunciation skill platform was automatic to be confirmed can not accord with the user expectation, can allow the user to adjust the slot position information for the skill that generates more accords with user's design original intention.
In some embodiments, after determining the corresponding slot position information according to the intention expression information, the method further includes: and receiving the call-following technical information corresponding to the slot position information input by the user, and listing the call-following technical information into the skill factor. The intelligent terminal user can be guided by the voice assistant to speak the keyword in a question seeking mode if the keyword corresponding to a certain slot position does not appear in the conversation when the intelligent terminal user actually uses the skill, so that the result can be successfully fed back by the skill, and the user can design the question seeking operation in a personalized mode when designing the skill.
In some embodiments, before or during the process of acquiring the skill design information of the skill to be added, the method further includes: providing the user with skill design guidance information. The advantage of setting up like this is that can let the user in the in-process of adding skill, how to carry out skill design fast, improves the efficiency of skill design and the success rate of skill addition.
Fig. 2 is a schematic flowchart of another voice assistant skill adding method provided in the embodiment of the present application, where the method includes the following steps:
Illustratively, the intention expression information may include functions, operations or matters that the user wants to implement by the voice assistant, and may be input in natural language with reference to the speaking mode of the intelligent terminal user, such as "i want to order an air ticket".
For example, the skill reply setting information may include information such as the form or manner in which the user wishes the skill to be called and feeds back the result to the intelligent terminal user.
And step 202, determining corresponding slot position information according to the intention expression information.
Illustratively, a semantic slot (slot for short) is a specific concept extracted from a sentence by a natural language processing technology, the slot is composed of slot positions, the slot positions can be understood as information required for realizing intentions, and when an intelligent terminal user uses skills, information corresponding to the slot positions is obtained according to keywords in a dialog of the intelligent terminal user and is used as a value to fill the slot positions. Taking the above "i want to order an air ticket" as an example, it is necessary to know the time, the departure place, and the destination to complete the ordering of the air ticket, and therefore, the corresponding slot position information can be automatically determined as the time, the place 1 (departure place), and the place 2 (destination).
And 203, receiving the updating operation of the slot position information by the user, and updating the slot position information according to the updating operation.
Wherein the update operation comprises an add operation, a delete operation, and a modify operation.
And step 204, determining a corresponding skill reply form and skill reply content according to the skill reply setting information.
Exemplary skill response forms include text, cards, audio, Application (APP), quick applications, or web pages, wherein cards may include plain text cards, picture cards, graphic cards, audio cards, or the like. Optionally, the audio, the application program, the fast application and the webpage may be subjected to skill reply by means of direct playing or jumping, or may be displayed in a card form, which is not limited in the embodiment of the present application. The web page may be, for example, a fifth-version HyperText Markup Language (HyperText Markup Language5, HTML5, H5 for short) page. The fast application is developed by using a front-end technology stack, is rendered as native, and has the double advantages of an H5 page and a native application. The page address opened when opening the page of the fast application, APP or HTML5 may be specified by a Uniform Resource Locator (URL), and accordingly, the skill reply content may include the corresponding URL. In addition, when replying, the method not only can support internal reply of the intelligent terminal, but also can support external service call, and can set an external call Interface to realize external service call, such as Application Programming Interface (API), optionally, the method can call the external service through a POST mode.
And step 205, generating corresponding skills according to the slot position information, the skill reply form and the skill reply content, and uploading the skills to the voice assistant cloud platform, wherein the terminal configured with the voice assistant function calls the skills in a mode of accessing the voice assistant cloud platform.
According to the skill adding method of the voice assistant, the intention expression information and the skill reply setting information of the skill to be added, which are input by a user, are obtained, the corresponding slot position information is determined according to the intention expression information, the corresponding skill reply form and the skill reply content are determined according to the skill reply setting information, the skill is generated according to the determined information, and the skill is sent to the voice assistant cloud platform, so that the intelligent terminal can call the generated skill. Therefore, third-party developers and intelligent terminal users can customize personalized voice assistant skills according to self requirements, skill types in the voice assistant cloud platform are enriched, terminals which can be configured with voice assistant functions can call more skills, the voice assistant functions are improved, and the voice assistant functions are more personalized.
Fig. 3 is a flowchart illustrating a voice assistant skill adding method according to an embodiment of the present application, as shown in fig. 3, the method includes:
and 301, acquiring a skill name of the skill to be added, which is input by the user.
For example, in order to facilitate the voice skill platform to manage skills, the user may be allowed to name the added skill name, and the skill name may also be used as a skill calling name, which facilitates the intelligent terminal user to call the skill. Skill names such as "air ticket booking", "flower express", "constellation query", and "fortune query", etc.
Illustratively, guidance information can be displayed on an interface in the whole skill adding process, so that a user can be helped to quickly know the adding process and the content required to be input, and the skill generating efficiency is improved.
Illustratively, the user may make the input in a natural language, such as "help me book 99 roses".
And 303, determining corresponding slot position information according to the intention expression information, and listing the slot position information into the skill factor.
Illustratively, an intent engine (IntentEngnine), which may be implemented based on machine learning techniques, may be integrated in the voice skills platform to help the user automatically build high quality intent models. In addition, the natural language processing technology can be used for realizing semantic analysis, expression conflict detection, automatic slot position information identification of a multi-analyzer and the like.
For example, it may be automatically recognized that the intent to add a skill is to book a flower, and the corresponding slot information may include the number (number) and flower type (flower).
And 304, receiving the updating operation of the slot position information by the user, and updating the slot position information according to the updating operation.
For example, the slot position information that is automatically identified may be displayed, and the user may update the slot position information if the slot position information that is automatically identified is deemed to be inaccurate enough. For example, a distribution address is needed when flowers are reserved, and therefore, a slot address (addresses) can be added; as another example, a user may want to make a reservation from a fixed website or store, and thus, a slot store (store) or the like may be added.
And 305, receiving the interview skill information corresponding to the slot position information input by the user, and listing the interview skill information into the skill factor.
When the intelligent terminal user actually uses the skills, if the keywords corresponding to a certain slot position do not appear in the conversation, the voice assistant can guide the intelligent terminal user to speak the keywords in a question-following mode, so that the skills can successfully feed back the result, and the user can design the skills in an individualized way.
As an example, the question asking operation may be "how many pieces to order the question"; the question-chasing of flower species may be "what flower you want to order"; the question-chasing of the address may be "where you want to let me send the flower", etc. Therefore, when the intelligent terminal user uses the voice assistant, if the skill of fast flower delivery is called, and the voice assistant says that 'I want to order 99 flowers', the voice assistant can continuously ask 'you want to order what flowers' and 'you want to send the flowers to where', and after the user answers the two questions, the voice assistant can successfully finish slot filling, so that the success rate of skill completion is ensured.
And step 306, acquiring the skill reply setting information of the skill to be added, which is input by the user.
And 307, determining a corresponding skill reply form and skill reply content according to the skill reply setting information, and listing the skill reply form and the skill reply content into the skill factors.
And 308, generating corresponding skills according to all the skill elements.
And step 310, if the test and the audit are passed, uploading the skill to a voice assistant cloud platform, wherein the terminal configured with the voice assistant function calls the skill in a mode of accessing the voice assistant cloud platform.
According to the skill adding method of the voice assistant, the skill name, the intention expression information, the question answering information and the skill reply setting information input by the user are gradually acquired through the voice skill platform, the intention model, the slot position information and the skill reply form and the skill reply content are automatically established, the skill required by the user is generated according to the information, after the skill is tested and audited, the skill is published to the voice assistant cloud platform for the intelligent terminal to call, third party developers and intelligent terminal users can be allowed to conveniently and quickly add the voice assistant skill, the skill types in the voice assistant cloud platform are enriched, the terminal with the voice assistant function can call more skills, the content and the service provided by the voice assistant are more efficient, and the voice assistant is more personalized.
Fig. 4 is a block diagram of a voice assistant skill adding apparatus according to an embodiment of the present invention, which may be implemented by software and/or hardware, and is generally integrated in a server, and may implement voice assistant skill adding by executing a voice assistant skill adding method. As shown in fig. 4, the apparatus includes:
a skill design information obtaining module 401, configured to obtain skill design information of a skill to be added, where the skill design information is input by a user;
a skill element determination module 402, configured to determine a corresponding skill element according to the skill design information;
and a skill generating module 403, configured to generate a corresponding skill according to the skill element, so as to be invoked by a terminal equipped with a voice assistant function.
The voice assistant skill adding device provided in the embodiment of the application acquires skill design information of a skill to be added, which is input by a user, determines a corresponding skill element according to the skill design information, and generates a corresponding skill according to the skill element so as to be called by a terminal provided with a voice assistant function. By adopting the technical scheme, a third-party developer or a user of the voice assistant terminal can be allowed to complete the autonomous skill design and addition, and the terminal configured with the voice assistant function is supported to call the newly added skills, so that the skill types of the voice assistant in the terminal are enriched, and the voice assistant function is perfected.
Optionally, the acquiring skill design information of the skill to be added, which is input by the user, includes:
and acquiring the intention expression information and the skill reply setting information of the skill to be added, which are input by the user.
Correspondingly, the determining the corresponding skill element according to the skill design information includes:
determining corresponding slot position information according to the intention expression information;
and determining a corresponding skill reply form and skill reply content according to the skill reply setting information.
Optionally, the skill reply form includes text, card, audio, application program, fast application or web page.
Optionally, the apparatus further comprises:
and the slot position updating module is used for receiving the updating operation of the slot position information by a user after the corresponding slot position information is determined according to the intention expression information, and updating the slot position information according to the updating operation, wherein the updating operation comprises an adding operation, a deleting operation and a modifying operation.
Optionally, the apparatus further comprises:
and the question-following setting module is used for receiving the question-following information corresponding to the slot position information input by the user after determining the corresponding slot position information according to the intention expression information, and listing the question-following information into the skill element.
Optionally, the apparatus further comprises:
and the guidance information providing module is used for providing skill design guidance information for the user before or in the process of acquiring the skill design information of the skill to be added, which is input by the user.
Optionally, generating a corresponding skill according to the skill element for a terminal equipped with a voice assistant function to call, where the generating includes:
and generating corresponding skills according to the skill elements, and uploading the skills to a voice assistant cloud platform, wherein the terminal configured with a voice assistant function calls the skills in a mode of accessing the voice assistant cloud platform.
Embodiments of the present application also provide a storage medium containing computer-executable instructions that, when executed by a computer processor, perform a voice assistant skill addition method, the method comprising:
acquiring skill design information of a skill to be added, which is input by a user;
determining corresponding skill factors according to the skill design information;
and generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDRRAM, SRAM, EDORAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.
Of course, the storage medium provided in the embodiments of the present application contains computer-executable instructions, and the computer-executable instructions are not limited to the voice assistant skill adding operation described above, and may also perform related operations in the voice assistant skill adding method provided in any embodiment of the present application.
The embodiment of the application provides a server, and the voice assistant skill adding device provided by the embodiment of the application can be integrated in the server. Fig. 5 is a schematic structural diagram of a terminal according to an embodiment of the present application. The terminal 500 may include: a memory 501, a processor 502 and a computer program stored on the memory 501 and executable on the processor, wherein the processor 502 implements the voice assistant skill adding method according to the embodiment of the present application when executing the computer program:
acquiring skill design information of a skill to be added, which is input by a user;
determining corresponding skill factors according to the skill design information;
and generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
Optionally, the acquiring skill design information of the skill to be added, which is input by the user, includes:
and acquiring the intention expression information and the skill reply setting information of the skill to be added, which are input by the user.
Correspondingly, the determining the corresponding skill element according to the skill design information includes:
determining corresponding slot position information according to the intention expression information;
and determining a corresponding skill reply form and skill reply content according to the skill reply setting information.
Optionally, the skill reply form includes text, card, audio, application program, fast application or web page.
Optionally, after determining the corresponding slot information according to the intention expression information, the method further includes:
and receiving the update operation of the slot position information by a user, and updating the slot position information according to the update operation, wherein the update operation comprises an adding operation, a deleting operation and a modifying operation.
Optionally, after determining the corresponding slot information according to the intention expression information, the method further includes:
and receiving the call-following technical information corresponding to the slot position information input by the user, and listing the call-following technical information into the skill factor.
Optionally, before or during the process of acquiring the skill design information of the skill to be added, the method further includes:
providing the user with skill design guidance information.
Optionally, generating a corresponding skill according to the skill element for a terminal equipped with a voice assistant function to call, where the generating includes:
and generating corresponding skills according to the skill elements, and uploading the skills to a voice assistant cloud platform, wherein the terminal configured with a voice assistant function calls the skills in a mode of accessing the voice assistant cloud platform.
The server provided by the embodiment of the application can allow a third-party developer or a user of the voice assistant terminal to complete autonomous skill design and addition, and supports the terminal configured with the voice assistant function to call newly added skills, so that the skill types of the voice assistant in the terminal are enriched, and the voice assistant function is perfected.
The voice assistant skill adding device, the storage medium and the server provided in the above embodiments may execute the voice assistant skill adding method provided in any embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in the above embodiments, reference may be made to the voice assistant skill adding method provided in any of the embodiments of the present application.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.
Claims (9)
1. A voice assistant skill adding method, comprising:
acquiring intention expression information and skill reply setting information of skills to be added, which are input by a user through natural language, wherein the user comprises a user of a terminal configured with a voice assistant;
according to the intention expression information, semantic analysis, expression conflict detection and automatic identification of corresponding slot position information by a multi-analyzer are realized by utilizing a natural language processing technology, and the slot position information is listed into a skill factor;
determining a corresponding skill reply form and skill reply content according to the skill reply setting information, and listing the skill reply form and the skill reply content into skill elements;
and generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
2. The method of claim 1, wherein the skill response form comprises text, cards, audio, application programs, quick applications, or web pages.
3. The method of claim 1, further comprising, after determining corresponding slot information from the intent expression information:
and receiving the update operation of the slot position information by a user, and updating the slot position information according to the update operation, wherein the update operation comprises an adding operation, a deleting operation and a modifying operation.
4. The method of claim 1, further comprising, after determining corresponding slot information from the intent expression information:
and receiving the call-following technical information corresponding to the slot position information input by the user, and listing the call-following technical information into the skill factor.
5. The method according to claim 1, before or during the process of acquiring skill design information to be added with skill input by a user, further comprising:
providing the user with skill design guidance information.
6. The method according to any one of claims 1-5, wherein generating corresponding skills from the skill elements for invocation by a terminal equipped with a voice assistant function comprises:
and generating corresponding skills according to the skill elements, and uploading the skills to a voice assistant cloud platform, wherein the terminal configured with a voice assistant function calls the skills in a mode of accessing the voice assistant cloud platform.
7. A voice assistant skill adding apparatus, comprising:
the skill design information acquisition module is used for acquiring intention expression information and skill reply setting information of skills to be added, which are input by a user through natural language, wherein the user comprises a user of a terminal configured with a voice assistant;
the skill element determining module is used for realizing semantic analysis, expression conflict detection and automatic identification of corresponding slot position information by a multi-analyzer by utilizing a natural language processing technology according to the intention expression information, listing the slot position information into a skill element, determining a corresponding skill reply form and skill reply content according to the skill reply setting information, and listing the skill reply form and the skill reply content into the skill element;
and the skill generation module is used for generating corresponding skills according to the skill elements so as to be called by the terminal provided with the voice assistant function.
8. A computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the voice assistant skill adding method of any one of claims 1-6.
9. A server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the voice assistant skill addition method of any of claims 1-6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811594341.0A CN109697979B (en) | 2018-12-25 | 2018-12-25 | Voice assistant skill adding method, device, storage medium and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811594341.0A CN109697979B (en) | 2018-12-25 | 2018-12-25 | Voice assistant skill adding method, device, storage medium and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109697979A CN109697979A (en) | 2019-04-30 |
| CN109697979B true CN109697979B (en) | 2021-02-19 |
Family
ID=66232839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811594341.0A Active CN109697979B (en) | 2018-12-25 | 2018-12-25 | Voice assistant skill adding method, device, storage medium and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109697979B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110310641B (en) * | 2019-02-26 | 2022-08-26 | 杭州蓦然认知科技有限公司 | Method and device for voice assistant |
| CN110327622A (en) * | 2019-05-09 | 2019-10-15 | 百度在线网络技术（北京）有限公司 | A kind of game control method, device and terminal |
| CN110083695A (en) * | 2019-05-10 | 2019-08-02 | 百度在线网络技术（北京）有限公司 | Craft services call method, device and storage medium |
| CN110334352B (en) * | 2019-07-08 | 2023-07-07 | 腾讯科技（深圳）有限公司 | Guide information display method, device, terminal and storage medium |
| CN110570866A (en) * | 2019-09-11 | 2019-12-13 | 百度在线网络技术（北京）有限公司 | Voice skill creating method, device, electronic equipment and medium |
| CN110718219B (en) | 2019-09-12 | 2022-07-22 | 百度在线网络技术（北京）有限公司 | Voice processing method, device, equipment and computer storage medium |
| CN110706701B (en) * | 2019-10-08 | 2023-04-18 | 百度在线网络技术（北京）有限公司 | Voice skill recommendation method, device, equipment and storage medium |
| CN110928995B (en) * | 2019-11-28 | 2022-12-09 | 中国建设银行股份有限公司 | Interactive information processing method, device, equipment and storage medium |
| CN111314451A (en) * | 2020-02-07 | 2020-06-19 | 普强时代(珠海横琴)信息技术有限公司 | Language processing system based on cloud computing application |
| CN111324708A (en) * | 2020-02-07 | 2020-06-23 | 普强时代(珠海横琴)信息技术有限公司 | Natural language processing system based on human-computer interaction |
| CN112562658A (en) * | 2020-12-04 | 2021-03-26 | 广州橙行智动汽车科技有限公司 | Groove filling method and device |
| CN113553843B (en) * | 2021-06-24 | 2023-12-19 | 青岛海尔科技有限公司 | Skill creation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237050A (en) * | 2013-03-22 | 2013-08-07 | 广东电网公司佛山供电局 | Method and system for intelligent voice interaction |
| JP2015203835A (en) * | 2014-04-16 | 2015-11-16 | 株式会社日立システムズ | Text edition device, text edition method, and program |
| CN108564946A (en) * | 2018-03-16 | 2018-09-21 | 苏州思必驰信息科技有限公司 | Technical ability, the method and system of voice dialogue product are created in voice dialogue platform |
| CN108959436A (en) * | 2018-06-12 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Dictionary edit methods and system for voice dialogue platform |
| CN108984157A (en) * | 2018-07-27 | 2018-12-11 | 苏州思必驰信息科技有限公司 | Technical ability configuration and call method and system for voice dialogue platform |
-
2018
- 2018-12-25 CN CN201811594341.0A patent/CN109697979B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237050A (en) * | 2013-03-22 | 2013-08-07 | 广东电网公司佛山供电局 | Method and system for intelligent voice interaction |
| JP2015203835A (en) * | 2014-04-16 | 2015-11-16 | 株式会社日立システムズ | Text edition device, text edition method, and program |
| CN108564946A (en) * | 2018-03-16 | 2018-09-21 | 苏州思必驰信息科技有限公司 | Technical ability, the method and system of voice dialogue product are created in voice dialogue platform |
| CN108959436A (en) * | 2018-06-12 | 2018-12-07 | 苏州思必驰信息科技有限公司 | Dictionary edit methods and system for voice dialogue platform |
| CN108984157A (en) * | 2018-07-27 | 2018-12-11 | 苏州思必驰信息科技有限公司 | Technical ability configuration and call method and system for voice dialogue platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109697979A (en) | 2019-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697979B (en) | Voice assistant skill adding method, device, storage medium and server | |
| US10489112B1 (en) | Method for user training of information dialogue system | |
| US10547747B1 (en) | Configurable natural language contact flow | |
| CN111400518B (en) | Method, device, terminal, server and system for generating and editing works | |
| US7890333B2 (en) | Using a WIKI editor to create speech-enabled applications | |
| US8032379B2 (en) | Creating and editing web 2.0 entries including voice enabled ones using a voice only interface | |
| CN105940446B (en) | Method for machine-to-human interaction, computer storage medium, and humanoid robot | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| US10154144B2 (en) | Adjustable interactive voice response system and methods of using same | |
| CN110244941B (en) | Task development method and device, electronic equipment and computer readable storage medium | |
| KR20190139966A (en) | Initiate a conversation with an automated agent via selectable graphical elements | |
| CN110998526B (en) | User-configured and custom interactive dialog applications | |
| CN108877800A (en) | Voice interactive method, device, electronic equipment and readable storage medium storing program for executing | |
| KR20200011198A (en) | Method, apparatus and computer program for providing interaction message | |
| US11886891B2 (en) | Context-based multiexperience element dynamically generated using natural language processing | |
| US7395206B1 (en) | Systems and methods for managing and building directed dialogue portal applications | |
| US20190347067A1 (en) | User interface interaction channel | |
| US9894210B2 (en) | Adjustable dual-tone multi-frequency phone system | |
| CN111026378A (en) | Method for realizing voice interaction by using native android technology in illusion engine | |
| CN114462376A (en) | RPA and AI-based court trial record generation method, device, equipment and medium | |
| US20060031853A1 (en) | System and method for optimizing processing speed to run multiple dialogs between multiple users and a virtual agent | |
| US20060140357A1 (en) | Graphical tool for creating a call routing application | |
| McGraw | Collecting speech from crowds | |
| Basu et al. | Designing an IVR Based Framework for Telephony Speech Data Collection and Transcription in Under-Resourced Languages. | |
| CN112204656A (en) | Efficient dialog configuration |
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 |