CN111176622A - Implementation method, management system and management method for unified management of voice skills of solution - Google Patents
Implementation method, management system and management method for unified management of voice skills of solution Download PDFInfo
- Publication number
- CN111176622A CN111176622A CN201911397502.1A CN201911397502A CN111176622A CN 111176622 A CN111176622 A CN 111176622A CN 201911397502 A CN201911397502 A CN 201911397502A CN 111176622 A CN111176622 A CN 111176622A
- Authority
- CN
- China
- Prior art keywords
- voice
- solution
- skill
- skills
- voice skill
- 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
- G06F8/20—Software design
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
- G06F9/4451—User profiles; Roaming
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Telephonic Communication Services (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method for realizing unified management of voice skills of a solution, which comprises the following steps: in the development stage of the voice skills, setting a conversation mode according to requirements, and developing and publishing the voice skills according to the conversation mode; after the development of the voice skills is completed, configuring an applicable conversation mode label for the developed voice skills, and storing the voice skills provided with the applicable conversation mode label as a voice skill tool set; an operating platform capable of communicating with a voice skill toolset is configured to enable a user to conduct voice skill configuration of a solution using the voice skill toolset via the operating platform. The invention also discloses a solution voice skill management system and a solution voice skill management method. According to the method and the system disclosed by the invention, the development and maintenance of the solution scheme based on the conversation mode can be realized, the resource reuse and the fast switching of the scheme can be realized, and the development efficiency of the voice interaction product can be improved.
Description
Technical Field
The invention relates to the technical field of intelligent voice, in particular to a method for realizing unified management of voice skills of a solution, a system and a method for realizing the voice skills of the solution and a method for managing the voice skills of the solution.
Background
In recent years, with the development of intelligent voice technology, various requirements based on voice interaction are increasing. In order to meet different voice interaction requirements of users, developers often provide a set of solutions (namely, product solutions with voice interaction functions) containing one or more voice skills for the users. The voice skill is an abstraction of voice functions in the field of intelligent voice, and particularly refers to a function or a service provided through voice, for example, "view weather" is a voice skill, and "listen to music" is also a skill, which is an important guarantee for realizing a solution.
At present, in a solution production process, a solution producer or a product developer generally obtains a standardized skill template based on a certain application scenario (such as vehicle-mounted, home, and children robots) through a voice open platform provided by the skill developer such as Baidu, Fei, and the like. In the aspect of solution voice skill management, solution producers respectively adopt different modes to maintain solutions, and the granularity of skill maintenance is coarse. If the product developers have different needs for voice skills in the solution, the solution production team often performs offline customization of the characteristics according to the needs of each product developer. The solutions obtained in this way can only provide standardized speech resources according to application scenarios, and are generally divided into two cases:
1. the hardware equipment provided by the platform is strongly related, for example, a home solution provided by the message flight is bound with the hardware of the message flight, and voice interaction is required to be performed by using a remote controller produced by the message flight, so that equipment control is realized. This results in a complete adaptation of the voice skill requirements of the solution to the flight skills, loss of flexibility and reduced options for the voice product developer, especially those with hardware or production hardware capabilities.
2. The method is weak in association with equipment and strongly related to application scenes, for example, intelligent customer service solutions can be applied to various application scenes such as mobile phone voice assistants, webpage-side online customer service, voice navigation, telephone consultation and the like, which means that a set of solutions needs to be maintained for each application scene, and the solutions are almost the same in other voice technical resources except for voice technical resources, so that resource waste is caused, and the maintenance cost is very high.
In addition, different solutions are generally produced by different teams respectively in different modes, and a relatively large number of repeated voice skill resources are generated, however, different teams separately perform production, maintenance and management of resources, and different management and use modes may be adopted, so that the problem of repeated resource development is caused, and meanwhile, the cost and difficulty in scheme switching are high. Meanwhile, the lack of global management of all solution technical resources also causes difficulty in effectively controlling the input and output links of the resources.
Disclosure of Invention
In order to solve the problems, the inventor conceives that the attribute concept of the conversation mode is provided on the design of the voice skill, so that the voice skill is developed and managed based on the conversation mode, the voice skill is uniformly opened to a scheme manufacturer based on the conversation mode, the scheme manufacturer is configured according to the scheme requirement, and secondary configuration is performed on the product developer level based on the conversation mode, so that the voice skill of the solution is uniformly managed and maintained based on the conversation mode, the voice skill resources are efficiently utilized, and the problems of resource waste, difficulty in switching and the like are solved.
According to a first aspect of the present invention, there is provided a method for implementing unified management of voice skills of a solution, including:
in the development stage of the voice skills, setting a conversation mode according to requirements, and developing and publishing the voice skills according to the conversation mode;
after the development of the voice skills is completed, configuring an applicable conversation mode label for the developed voice skills, and storing the voice skills provided with the applicable conversation mode label as a voice skill tool set;
configuring an operating platform capable of communicating with the voice skill toolset to enable a user to conduct voice skill configuration of a solution with the voice skill toolset through the operating platform.
According to a second aspect of the present invention there is provided a solution voice skill management system comprising
The voice skill collection module is used for acquiring voice skill configuration information storage according to a received request for adding voice skills, wherein the configuration information comprises voice skill names and corresponding conversation mode labels;
the skill tool set module is used for responding to the received solution production request and outputting and displaying a first user interface according to the stored voice skill configuration information, wherein the first user interface comprises all voice skill configuration information opened to the current requester;
the skill adding module is used for receiving a selection request of the displayed voice skill on the first user interface, acquiring selected voice skill configuration information, storing the selected voice skill configuration information into the current solution, displaying and outputting a second user interface, wherein the second user interface comprises the selected voice skill configuration information for the current solution; and
and the mode configuration module is used for receiving a conversation mode setting request for the displayed voice skills on the second user interface, acquiring conversation mode information set for the voice skills of the solution and storing the conversation mode information into the current solution.
According to a third aspect of the present invention, there is provided a method for implementing a solution voice skill management system, comprising
Acquiring voice skill configuration information storage according to a received request for adding voice skills, wherein the configuration information comprises voice skill names and corresponding conversation mode labels;
responding to a solution production request, and acquiring a stored voice skill name and a corresponding conversation mode label output display;
responding to a selection request of voice skills, acquiring selected voice skill configuration information and storing the selected voice skill configuration information in a current solution;
in response to a dialogue mode setting request for a voice skill of a current solution, dialogue mode information for voice skill setting of the solution is acquired and stored into the current solution.
According to a fourth aspect of the present invention, there is provided a method of managing solution voice skills, comprising
Setting a conversation mode according to requirements at a first user end, developing and issuing voice skills according to the conversation mode, and uploading the issued voice skill configuration information to a second user end for storage;
acquiring voice skill configuration information uploaded by a first user side to configure a solution at a second user side, wherein the voice skill configuration information comprises voice skills required for the solution selection, a conversation mode for the voice skills of the selected solution, and the configured solution is transmitted to a third user side;
and at the third user side, acquiring the voice skill configuration information of the configured solution, and modifying the dialogue mode of the voice skill of the solution according to the requirement.
According to the management scheme of the voice skills in the solution provided by the embodiment of the invention, the configuration and the management of the voice skills in the solution can be realized based on the conversation mode, so that the same voice skill can be configured in different solutions according to different conversation modes, and different conversation modes can be selected for voice interaction response according to requirements in the same solution, thereby respectively maintaining different solutions for different scenes, and realizing the resource multiplexing and the rapid switching of the solution. In addition, the scheme of the embodiment of the invention can be connected in series to realize voice interaction and use a plurality of roles (a skill developer, a solution producer and a voice interaction product developer) on joint debugging, the resources produced by the skill developer are utilized to the maximum extent, the solution producer is convenient to carry out the optimal collocation of the voice skill resource content, the most flexible resource customization mode is provided for the product developer, the skill resource content combination is carried out by matching with a conversation mode, the operation is simple and easy, and the maintenance and the updating are simple.
Drawings
FIG. 1 is a flowchart of a method for implementing a unified management of voice skills of a solution according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a solution voice skill management system in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the effect of the first user interface and the second user interface of the system shown in FIG. 2 according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for implementing a solution voice skill management system in accordance with an embodiment of the present invention;
FIG. 5 is a flowchart of a method for managing solution voice skills, in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present 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.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
As used in this disclosure, "module," "device," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes based on a signal having one or more data packets, e.g., from a data packet interacting with another element in a local system, distributed system, and/or across a network in the internet with other systems by way of the signal.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The voice skill management method of the embodiment of the invention can be applied to the development process of any voice interaction product, for example, the development process of the voice interaction scheme of a computer with a voice function, a smart phone, a tablet computer, a smart home and other terminal devices, and the invention is not limited thereto. The scheme provided by the invention can realize the configuration and management of the voice skills in the solution based on the conversation mode, so that the same voice skill can be configured into different solutions according to different conversation modes, and different conversation modes can be selected according to requirements in the same solution to carry out voice interaction response, thereby avoiding the need of respectively maintaining different solutions aiming at different scenes, realizing the resource multiplexing and the rapid switching of the solutions, realizing the voice skill of the personalized customized solution according to the requirements, and improving the development and maintenance efficiency of voice interaction products.
The present invention will be described in further detail with reference to the accompanying drawings.
Fig. 1 schematically shows a method flow of an implementation method for unified management of voice skills of a solution according to an embodiment of the present invention, and as shown in fig. 1, the method of this embodiment includes the following steps:
step S101: and in the development stage of the voice skills, setting a conversation mode according to the requirement, and developing and publishing the voice skills according to the conversation mode. The skill developer can design a dialogue mode according to requirements, wherein the dialogue mode refers to different application scenes of voice skills, such as a child mode without a screen, an adult mode with a screen, and the like. The development of the voice skills is carried out according to the designed conversation modes by designing different conversation modes, which is a precondition for realizing the management of the voice skills based on the conversation modes. And the conversation mode is designed according to different application scenes and application requirements, so that developed voice skills can be well classified, version management is facilitated, the developed voice skills can be reused based on the application scenes, and resource waste is avoided. Preferably, the speech skill conversation mode set by the embodiment of the invention is set according to the three-dimensional conversation mode of screen condition, user classification and custom customization, and the skill developer produces and publishes speech skills according to the set conversation mode classification.
Step S102: after the development of the voice skills is completed, configuring applicable conversation mode labels for the developed voice skills, and storing the voice skills provided with the applicable conversation mode labels as a voice skill tool set. Since the voice skill development is performed based on the dialog mode, after the development and the release are completed, the corresponding dialog mode tag, that is, the scene mode tag that can be applied, for example, the voice skill setting of the "navigation" of the development, can be set for the voice skill: the screen condition is a conversation mode with a screen and a user classified as an adult, and the set voice skills of listening to music are researched and developed in multiple versions according to different application scenes, and are respectively and correspondingly set: the screen case is a general conversation mode in which the user is classified as an adult, and the screen case is a general conversation mode in which the user is classified as a child. In other preferred embodiments, custom-made dialog mode tags can also be designed according to requirements. After the corresponding conversation mode labels which can be applied to the voice skills are configured, the voice skills are added into the voice skill set to be used as a voice skill tool set for unified storage, so that the voice skills can be uniformly managed and used by a solution production team.
Step S103: an operating platform capable of communicating with the voice skill toolset is configured to enable a user to conduct voice skill configuration of a solution using the voice skill toolset through the operating platform. According to the embodiment of the invention, an operation platform is configured to design a solution based on the voice skill based on the conversation mode uploaded by the voice skill developer in the voice skill tool set. A solution refers to a product solution designed by a solution developer to solve the user's voice interaction requirements, and generally includes one or more voice skills. The traditional solution design method is that a solution developer performs preliminary solution design based on a standard voice skill template on a voice open platform provided by the skill developer, and performs personalized customization and maintenance of offline solutions based on different user requirements. The embodiment of the invention configures an operation platform which is communicated with the voice skill tool set, so that a scheme developer can design a solution based on the operation platform and directly perform online personalized customization and maintenance on the voice skill in the solution based on a conversation mode when the scheme developer faces the requirement. Since the voice skill has a plurality of applicable conversation mode labels, the same voice skill can be applied to different scenes according to requirements, for example, the voice skill of 'listening to music' can be applied to the conversation mode of adults and the conversation mode of children, only the resources such as versions of the corresponding voice skill are different, thus when a solution A is designed and the voice skill is added, the solution A can be reused for other application scenes different from users, only the conversation mode of the voice skill needs to be changed into the children mode, other modifications of the solution A are not needed (other resources such as voice recognition resources, language models and the like can be reused), thus, the resources are reused, a set of solution is not needed to be maintained for each scene, only configuration is needed based on the conversation mode, and development, management and maintenance of the solution are facilitated.
Based on this, in a specific implementation, to achieve the above object, a voice skill configuration of a solution allowed to be performed by a solution developer on an operation platform may be implemented to include: adding the voice skills required for the solution and the dialog mode setting the voice skills for the solution.
Preferably, in order to facilitate customized configuration and personalized implementation of the solution, the voice skill configuration of the solution allowed to be performed by the solution developer on the operation platform may further include: the speech skills added to the solution are classified into selectable skills and preset skills. The selectable skills mean that after a voice product developer uses a solution, the voice product developer still needs to add operation to use the voice skill in the product, and the product developer can be allowed to perform personalized configuration of the scheme according to the requirement through the attributes; the preset skills mean that the product developers can directly use the voice skills in the products without manual addition after using the solution, and the preset skills are default semantic skill options of the product scheme.
Fig. 2 schematically shows a solution voice skill management system according to an embodiment of the present invention, which is a most preferred implementation of the above-described operation platform. As shown in FIG. 2, the system is implemented to include
The voice skill collection module 20 is configured to obtain voice skill configuration information according to the received request for adding the voice skill, where the configuration information includes a voice skill name and a dialog mode tag corresponding to the voice skill name;
the skill tool set module 21 is configured to respond to the received solution production request, and output and display a first user interface according to the stored voice skill configuration information, where the first user interface includes all voice skill configuration information open to the current requester;
the skill adding module 22 is configured to receive a selection request for a displayed voice skill on the first user interface, acquire selected voice skill configuration information, store the selected voice skill configuration information in a current solution, and display and output a second user interface, where the second user interface includes voice skill configuration information selected for the current solution; and
and the mode configuration module 23 is configured to receive a dialog mode setting request for the displayed voice skill on the second user interface, acquire dialog mode information for the voice skill setting of the solution, and store the dialog mode information in the current solution.
As shown in FIG. 2, as a preferred embodiment, the skill adding module 22 is implemented to include
The first adding unit 22A is configured to receive a first selection request for a displayed voice skill on the first user interface, acquire selected voice skill configuration information, store the selected voice skill configuration information in the current solution, and mark the selected voice skill configuration information as a selectable skill;
the second adding unit 22B is configured to receive a second selection request for the displayed voice skill on the first user interface, acquire selected voice skill configuration information, store the selected voice skill configuration information in the current solution, and mark the selected voice skill configuration information as a preset skill; and
and the display unit 22C is used for displaying the voice skill configuration information selected by the current solution in a classified manner in the second user interface according to the processing of the first adding unit or the second adding unit.
The voice skill collection module 20 in the embodiment of the present invention may correspond to step S101 in the above method implementation example, and implement a function of collecting a voice skill that is developed by a developer based on a dialog mode to form a voice skill tool set, and of course, the skill developer may also perform unified storage of the voice skill based on a development background of the skill developer instead of performing uploading and storage of the voice skill based on the dialog mode through the management system, and link the management system of the embodiment of the present invention to a stored server, which is not to be considered as a limitation to this embodiment of the present invention. Fig. 3 shows the presentation effect of the first user interface 30 and the second user interface 31 of one implementation, and as shown in fig. 3, the addition operation of the voice skill required by the solution can be realized based on the voice skill presented by the first user interface 30, and after the voice skill required to be added to the solution is selected, a first addition request can be issued by clicking the first addition button 32 to add the voice skill to the selectable skill, and a second addition request can be issued by clicking the second addition button 33 to add the voice skill to the preset skill. The speech skills added to the solution are displayed in a second user interface by category, and their dialog mode can be configured by clicking on the corresponding skills. Among them, preferably, when embodied, the dialog mode information set for the voice skill of the solution may be embodied to include the first type dialog mode information and/or the second type dialog mode information. The first type of dialog mode information refers to default dialog mode configuration information which is common to the voice skills of the whole solution, for example, the solution a applies a screen setting, and the first type of dialog mode with a screen can be set for the whole solution, so that most voice skills in the solution are applicable to the dialog mode. The second type of dialogue mode information refers to personalized dialogue mode configuration information applicable to a single voice skill, for example, the "listening to music" voice skill and the "weather" voice skill in the solution a are each provided with a second type of dialogue mode applicable only to itself.
By setting the management system, a scheme developer can add voice skills to the solution through the first user interface and set a conversation mode for the voice skills in the scheme through the second user interface, so that the solution is developed conveniently. In addition, the formed scheme can be multiplexed to different application scenes based on the setting of the conversation mode, the management and maintenance cost of the scheme is reduced, and the repeated development of resources is reduced.
Fig. 4 schematically shows an implementation method of the above-mentioned solution voice skill management system, and as shown in fig. 4, the method includes the following steps:
step S401: and acquiring voice skill configuration information storage according to the received request for adding the voice skill, wherein the configuration information comprises a voice skill name and a corresponding conversation mode label. After the skill developer completes the pattern-based voice skill development and release, the voice skills are added to the system, forming a voice skill toolset store. And the management system receives the adding request, and acquires and stores the voice skill configuration information input when adding.
Step S402: and responding to the solution production request, and acquiring the stored voice skill names and the corresponding conversation mode tags thereof to output and display. The method comprises the steps that a scheme developer develops a solution in a management system according to scheme requirements and inputs a scheme production request through a corresponding user interface, when the management system receives a request event, all voice skill configuration information stored in a tool set is acquired and output and displayed on a first user interface, and the scheme developer adds voice skills according to the requirements.
Step S403: in response to a request for selection of a voice skill, selected voice skill configuration information is retrieved and stored in the current solution. When the solution developer selects the voice skill to be added to the solution, the management system acquires the selection request and stores the added voice skill in association with the solution.
The voice skill storage is marked as a selectable skill when the first selection request is received, and the voice skill storage is marked as a preset skill when the second selection request is received.
Step S404: in response to a dialogue mode setting request for a voice skill of a current solution, dialogue mode information for voice skill setting of the solution is acquired and stored into the current solution. After adding voice skills to the solution, the added voice skills can be configured into a conversation mode, and the management system stores the conversation mode information set for the voice skills or for the solution, such as conversation mode label names, in association with the current solution or voice skills according to the received conversation mode setting request. Among them, the solution developer can select the dialog mode best suitable for the current solution from a plurality of dialog modes provided by the skill developer to set the dialog mode of the voice skill (i.e. set the dialog mode of the second kind) or set the default dialog mode for the whole solution according to the requirement (i.e. set the dialog mode of the first kind).
In other embodiments, the first user interface and the second user interface are not limited to the implementation shown in fig. 3 that are displayed on the same interface, and may be separate interfaces. The configuration information for adding the voice skill input may not be limited to the skill name and the dialog mode tag, and may further include version information, etc., and for example, may correspond to different dialog modes through version management, where the version of the selected voice skill is also set at the same time when the setting of step S404 is performed.
FIG. 5 illustrates a method for managing voice skills of a solution according to an embodiment of the present invention, which includes
Step S501: and setting a conversation mode according to requirements at the first user end, developing and issuing voice skills according to the conversation mode, and uploading the issued voice skill configuration information to the second user end for storage. Wherein the first user terminal is a voice skill development platform of a skill developer, such as a thoughtful DUI voice open platform. And the skill developer produces the voice skill resources in the background of the voice open platform according to the conversation mode and issues the voice skill resources to a cloud server of the voice open platform for the product developer to call. The second user terminal is the solution voice skill management system, and the skill developer adds the voice skill and the applicable conversation mode to the management system so as to develop and manage the applicable scheme through the management system by the scheme developer.
Step S502: and at the second user side, acquiring the voice skill configuration information uploaded by the first user side to configure the solution, wherein the configuration comprises the steps of selecting the required voice skill for the solution, setting a conversation mode for the voice skill of the selected solution and transmitting the configured solution to the third user side. Wherein the speech skill addition and the dialog mode setting on the management system can be made with reference to the foregoing. The third user side refers to a voice open platform used by a product developer to interface voice skills, for example, a thoughtful DUI voice open platform, and the product developer uses the voice skills on the DUI open platform through an access solution.
Step S503: and at the third user side, acquiring the voice skill configuration information of the configured solution, and modifying the dialogue mode of the voice skill of the solution according to the requirement. When a product developer accesses a solution, the product developer can configure the dialogue mode of the voice skill for the second time, and select the dialogue mode suitable for the voice interaction product from a plurality of dialogue modes selected by a solution producer, or directly use the default dialogue mode provided by the solution, thereby realizing the personalized customization of the product according to the requirement.
In a preferred implementation, the second user end classifies the selectable skills and the preset skills of the selected voice skills, so that the third user end selects the selectable skills of the solution according to the requirements and adds the selectable skills to the preset skills, and the extension of the voice skills of the product is realized according to the requirements.
By the scheme of the embodiment of the invention, a plurality of roles (a skill developer, a solution producer and a voice interaction product developer) on joint tone can be used in series for voice interaction, the resources produced by the skill developer are utilized to the maximum extent, the solution producer is convenient to optimally match the contents of the voice skill resources, the most flexible resource customization mode is provided for the product developer, the skill resources are combined in a matching way, the operation is simple and easy, and the maintenance and the updating are simple.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions substantially or contributing to the related art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. The implementation method for uniformly managing the voice skills of the solution is characterized by comprising the following steps:
in the development stage of the voice skills, setting a conversation mode according to requirements, and developing and publishing the voice skills according to the conversation mode;
after the development of the voice skills is completed, configuring an applicable conversation mode label for the developed voice skills, and storing the voice skills provided with the applicable conversation mode label as a voice skill tool set;
configuring an operating platform capable of communicating with the voice skill toolset to enable a user to conduct voice skill configuration of a solution with the voice skill toolset through the operating platform.
2. The implementation method of claim 1, wherein the voice skill configuration of the user-enabled solution configured on the operation platform comprises a dialogue mode for adding a voice skill required for a solution and setting a voice skill for a solution.
3. The implementation method of claim 2, wherein the voice skill configuration of the user-enabled solution configured on the operation platform further comprises classifying the voice skills added to the solution into selectable skills and preset skills.
4. A solution voice skill management system, comprising
The voice skill collection module is used for acquiring voice skill configuration information storage according to a received request for adding voice skills, wherein the configuration information comprises voice skill names and corresponding conversation mode labels;
the skill tool set module is used for responding to the received solution production request and outputting and displaying a first user interface according to the stored voice skill configuration information, wherein the first user interface comprises all voice skill configuration information opened to the current requester;
the skill adding module is used for receiving a selection request of the displayed voice skill on the first user interface, acquiring selected voice skill configuration information, storing the selected voice skill configuration information into the current solution, displaying and outputting a second user interface, wherein the second user interface comprises the selected voice skill configuration information for the current solution; and
and the mode configuration module is used for receiving a conversation mode setting request for the displayed voice skills on the second user interface, acquiring conversation mode information set for the voice skills of the solution and storing the conversation mode information into the current solution.
5. The system of claim 4, wherein the skill addition module comprises
The first adding unit is used for receiving a first selection request for the displayed voice skill on the first user interface, acquiring selected voice skill configuration information, storing the selected voice skill configuration information into the current solution and marking the selected voice skill configuration information as a selectable skill;
the second adding unit is used for receiving a second selection request for the displayed voice skill on the first user interface, acquiring selected voice skill configuration information, storing the selected voice skill configuration information into the current solution and marking the selected voice skill configuration information as a preset skill; and
and the display unit is used for displaying the voice skill configuration information selected by the current solution in a classified manner in the second user interface according to the processing of the first adding unit or the second adding unit.
6. The system according to claim 4 or 5, characterized in that the dialogue mode information for the voice skill setting of the solution comprises a first type of dialogue mode information and/or a second type of dialogue mode information.
7. The method of implementing a solution voice skill management system of claim 6 comprising
Acquiring voice skill configuration information storage according to a received request for adding voice skills, wherein the configuration information comprises voice skill names and corresponding conversation mode labels;
responding to a solution production request, and acquiring a stored voice skill name and a corresponding conversation mode label output display;
responding to a selection request of voice skills, acquiring selected voice skill configuration information and storing the selected voice skill configuration information in a current solution;
in response to a dialogue mode setting request for a voice skill of a current solution, dialogue mode information for voice skill setting of the solution is acquired and stored into the current solution.
8. The method of claim 7 wherein the selection request comprises a first selection request and a second selection request, and wherein the selected voice skills are further categorized and labeled according to the selection request when the selected voice skill configuration information is stored in the current solution.
9. A method for managing a voice skill of a solution, comprising
Setting a conversation mode according to requirements at a first user end, developing and issuing voice skills according to the conversation mode, and uploading the issued voice skill configuration information to a second user end for storage;
acquiring voice skill configuration information uploaded by a first user side to configure a solution at a second user side, wherein the voice skill configuration information comprises voice skills required for the solution selection, a conversation mode for the voice skills of the selected solution, and the configured solution is transmitted to a third user side;
and at the third user side, acquiring the voice skill configuration information of the configured solution, and modifying the dialogue mode of the voice skill of the solution according to the requirement.
10. The method of claim 9, further comprising
Classifying the selected voice skills by the selectable skills and the preset skills at the second user end;
the third user terminal also selects the optional skills of the solution according to the requirement and adds the optional skills to the preset skills.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911397502.1A CN111176622B (en) | 2019-12-30 | 2019-12-30 | Implementation method, management system and management method for unified management of voice skills of solution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911397502.1A CN111176622B (en) | 2019-12-30 | 2019-12-30 | Implementation method, management system and management method for unified management of voice skills of solution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111176622A true CN111176622A (en) | 2020-05-19 |
| CN111176622B CN111176622B (en) | 2022-07-08 |
Family
ID=70623307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911397502.1A Active CN111176622B (en) | 2019-12-30 | 2019-12-30 | Implementation method, management system and management method for unified management of voice skills of solution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111176622B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030007609A1 (en) * | 2001-07-03 | 2003-01-09 | Yuen Michael S. | Method and apparatus for development, deployment, and maintenance of a voice software application for distribution to one or more consumers |
| CN108491188A (en) * | 2018-03-19 | 2018-09-04 | 苏州思必驰信息科技有限公司 | The exploitative management method and device of voice dialogue product |
| CN109684805A (en) * | 2018-12-25 | 2019-04-26 | 苏州思必驰信息科技有限公司 | Voice technical ability sharing method and system for voice dialogue platform |
-
2019
- 2019-12-30 CN CN201911397502.1A patent/CN111176622B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030007609A1 (en) * | 2001-07-03 | 2003-01-09 | Yuen Michael S. | Method and apparatus for development, deployment, and maintenance of a voice software application for distribution to one or more consumers |
| CN108491188A (en) * | 2018-03-19 | 2018-09-04 | 苏州思必驰信息科技有限公司 | The exploitative management method and device of voice dialogue product |
| CN109684805A (en) * | 2018-12-25 | 2019-04-26 | 苏州思必驰信息科技有限公司 | Voice technical ability sharing method and system for voice dialogue platform |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111176622B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8751558B2 (en) | Mashup infrastructure with learning mechanism | |
| US10855625B1 (en) | Intelligent, adaptable, and trainable bot that orchestrates automation and workflows across multiple applications | |
| US7756905B2 (en) | System and method for building mixed mode execution environment for component applications | |
| JP5248964B2 (en) | Method and system for generating screen elements or data objects for wireless applications | |
| CN109545205B (en) | Context-based virtual assistant implementation | |
| CN115485690A (en) | Batch technique for handling unbalanced training data of chat robots | |
| EP3673421A1 (en) | Automating communications using an intent classifier | |
| US11615425B2 (en) | Method and apparatus for autonomous services composition | |
| US11288598B2 (en) | Third-party analytics service with virtual assistant interface | |
| US11272015B2 (en) | Function-as-a-service for two-way communication systems | |
| CN109313668B (en) | System and method for constructing session understanding system | |
| CN110457011A (en) | Software application method for customizing and exploitation server-side | |
| CN111009245B (en) | Instruction execution method, system and storage medium | |
| JP2021197153A (en) | Method and apparatus for recognizing word slot, electronic apparatus, storage medium and computer program | |
| CN111176622B (en) | Implementation method, management system and management method for unified management of voice skills of solution | |
| CN113934832A (en) | Interactive processing method, device, equipment, medium and program product based on session | |
| CN112837683A (en) | Voice service method and device | |
| CN110442698A (en) | Conversation content generation method and system | |
| CN111031141B (en) | Method and server for realizing customized configuration of voice skills | |
| CN108804088A (en) | Protocol processes method and apparatus | |
| Mitrevski | Developing Conversational Interfaces for IOS: Add Responsive Voice Control to Your Apps | |
| US11157341B1 (en) | Data contracts | |
| US11803358B1 (en) | Adaptive issue type identification platform | |
| US8631037B2 (en) | Information delivery using queries and changeable database containing queries, advisory information, and flow logic | |
| CN110321155B (en) | Method and device for configuring applications in batches |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant after: Sipic Technology Co.,Ltd. Address before: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Applicant before: AI SPEECH Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |