Robot voice configuration method and device and electronic equipment

Abstract

The embodiment of the invention provides a robot voice configuration method and device and electronic equipment, and relates to the technical field of robots, the method comprises the following steps: in response to a configuration operation for a configuration item in a configuration area of a voice interaction function, displaying a configuration parameter set by the configuration operation for the configuration item in the configuration area, the configuration area being located in a configuration page, the configuration page further comprises an interaction preview area; receiving an interaction request for simulating voice interaction with the robot, displaying the interaction request in the interaction preview area, responding to the interaction request based on the configuration parameters of the configuration items in the configuration area, and displaying a response result in the interaction preview area; and in response to the configuration application operation, issuing configuration parameters of each configuration item in the configuration area to the target robot. By applying the scheme provided by the embodiment of the invention, a user can flexibly configure the voice interaction function of the robot according to actual requirements.

Description

Technical Field

[0001] This invention relates to the field of robotics, and in particular to a robot voice configuration method, apparatus, and electronic device. Background Technology

[0002] With the development of technology, robots have been widely used in various scenarios such as home services, logistics and distribution, and retail supermarkets, becoming an important tool for improving production efficiency and optimizing service quality.

[0003] To enhance the convenience of human-computer interaction and provide users with a more intelligent experience, many robots have integrated voice interaction functions. This allows users to wake up the robot and invoke functions via voice, eliminating the need for physical buttons or touchscreens and significantly improving ease of operation.

[0004] In related technologies, the configuration of the voice interaction function integrated into the robot is fixed, while the voice interaction needs of different scenarios and different users are often different. This makes it difficult for the voice interaction function integrated into the robot to adapt to different voice interaction needs. Summary of the Invention

[0005] The purpose of this invention is to provide a robot voice configuration method, device, and electronic device, so that users can flexibly configure the robot's voice interaction functions according to actual needs. The specific technical solution is as follows:

[0006] In a first aspect, embodiments of the present invention provide a robot voice configuration method, the method comprising:

[0007] In response to a configuration operation on a configuration item in the configuration area for a voice interaction function, the configuration parameters set by the configuration operation for the configuration item are displayed in the configuration area, the configuration area being located on a configuration page, the configuration page also including an interactive preview area;

[0008] Receive an interaction request for simulated voice interaction with a robot, display the interaction request in the interaction preview area, respond to the interaction request based on the configuration parameters of each configuration item in the configuration area, and display the response result in the interaction preview area;

[0009] In response to the configuration application operation, the configuration parameters of each configuration item in the configuration area are sent to the target robot.

[0010] Secondly, embodiments of the present invention provide a robot voice configuration device, the device comprising:

[0011] The parameter configuration module is used to respond to configuration operations on configuration items in the configuration area for the voice interaction function, and to display the configuration parameters set for the configuration items by the configuration operation in the configuration area. The configuration area is located on the configuration page, and the configuration page also includes an interactive preview area.

[0012] The interactive preview module is used to receive interactive requests that simulate voice interaction with the robot, display the interactive requests in the interactive preview area, respond to the interactive requests based on the configuration parameters of each configuration item in the configuration area, and display the response results in the interactive preview area.

[0013] The parameter distribution module is used to distribute the configuration parameters of each configuration item in the configuration area to the target robot in response to the configuration application operation.

[0014] Thirdly, embodiments of the present invention provide an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0015] Memory, used to store computer programs;

[0016] When a processor executes a program stored in memory, it implements the steps of the method described in the first aspect.

[0017] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0018] Fifthly, embodiments of the present invention provide a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps of the method described in the first aspect.

[0019] In the solution provided by this embodiment of the invention, the configuration page includes a configuration area for voice interaction functions and an interaction preview area. Users can configure the configuration parameters of the robot's voice interaction functions in the configuration area and simulate voice interaction with the robot in the interaction preview area, previewing the interaction results. After configuration, users can select to apply the current configuration, allowing the platform to send the configuration parameters to the target robot, which can then set up the voice interaction functions according to the configuration parameters.

[0020] As can be seen, the solution provided by this embodiment of the invention offers an intuitive and efficient configuration page. Users can perform simple visual operations on the configuration page according to their actual needs, flexibly and efficiently configuring various configuration items of the robot's voice interaction function. This allows the robot's voice interaction function to adapt to personalized voice interaction needs. Furthermore, users can simulate voice interaction with the robot in the interaction preview area and preview the interaction results, thereby verifying whether the current configuration results meet their needs. If not, targeted configuration adjustments can be made. This greatly facilitates voice configuration for users and improves the user experience.

[0021] Of course, implementing any product or method of the present invention does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0023] Figure 1a This is a schematic diagram of a first interface provided in an embodiment of the present invention;

[0024] Figure 1b This is a schematic diagram of a second interface provided in an embodiment of the present invention;

[0025] Figure 1c This is a schematic diagram of a third interface provided in an embodiment of the present invention;

[0026] Figure 2a This is a schematic diagram of a fourth interface provided in an embodiment of the present invention;

[0027] Figure 2b This is a schematic diagram of the fifth interface provided in an embodiment of the present invention;

[0028] Figure 2c This is a schematic diagram of a sixth interface provided in an embodiment of the present invention;

[0029] Figure 3 This is a schematic diagram of the seventh interface provided in an embodiment of the present invention;

[0030] Figure 4a This is a schematic diagram of the eighth interface provided in an embodiment of the present invention;

[0031] Figure 4b This is a schematic diagram of the ninth interface provided in an embodiment of the present invention;

[0032] Figure 5This is a schematic diagram of the tenth interface provided in an embodiment of the present invention;

[0033] Figure 6a This is an eleventh interface diagram provided in an embodiment of the present invention;

[0034] Figure 6b This is a schematic diagram of the twelfth interface provided in an embodiment of the present invention;

[0035] Figure 6c This is a thirteenth interface diagram provided in an embodiment of the present invention;

[0036] Figure 6d This is a schematic diagram of the fourteenth interface provided in an embodiment of the present invention;

[0037] Figure 6e This is a schematic diagram of the fifteenth interface provided in an embodiment of the present invention;

[0038] Figure 7a This is a schematic diagram of the sixteenth interface provided in an embodiment of the present invention;

[0039] Figure 7b This is a schematic diagram of the seventeenth interface provided in an embodiment of the present invention;

[0040] Figure 7c This is a schematic diagram of the eighteenth interface provided in an embodiment of the present invention;

[0041] Figure 7d This is a schematic diagram of the nineteenth interface provided in an embodiment of the present invention;

[0042] Figure 7e This is a schematic diagram of the twentieth interface provided in an embodiment of the present invention;

[0043] Figure 7f This is a schematic diagram of the twenty-first interface provided in an embodiment of the present invention;

[0044] Figure 7g This is a schematic diagram of the twenty-second interface provided in this embodiment of the invention;

[0045] Figure 8 A flowchart illustrating a robot voice configuration method provided in an embodiment of the present invention;

[0046] Figure 9 This is a schematic diagram of a robot voice configuration provided in an embodiment of the present invention;

[0047] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of the present invention.

[0049] To enhance the convenience of human-computer interaction and provide users with a more intelligent experience, many robots have integrated voice interaction functions. This allows users to wake up the robot and invoke functions via voice, eliminating the need for physical buttons or touchscreens and significantly improving ease of operation.

[0050] In related technologies, the configuration of voice interaction functions integrated into robots is fixed, while the voice interaction needs of different scenarios and users often vary. For example, the complexity of tasks differs in different scenarios, thus placing different demands on the performance and response speed of large language models (used for semantic analysis and natural language generation); furthermore, different users have different preferences for the speaking speed, timbre, and pitch of robot interaction voices. This makes it difficult for the voice interaction functions integrated into robots to adapt to different voice interaction needs.

[0051] To facilitate users in flexibly configuring the robot's voice interaction functions according to their actual needs, this embodiment of the invention provides a robot voice configuration scheme.

[0052] The solution provided in this invention includes a robot voice interaction function configuration platform (hereinafter referred to as the platform), which can be a web page or an application. The platform's configuration page includes a configuration area and an interaction preview area for the voice interaction function. Users can configure the parameters of the robot's voice interaction function in the configuration area and simulate voice interaction with the robot in the interaction preview area, previewing the interaction results. After configuration, users can choose to apply the current configuration, allowing the platform to send the configuration parameters to the target robot, which can then set up the voice interaction function according to the configuration parameters.

[0053] As can be seen, the solution provided by this embodiment of the invention offers an intuitive and efficient configuration page. Users can perform simple visual operations on the configuration page according to their actual needs, flexibly and efficiently configuring various configuration items of the robot's voice interaction function. This allows the robot's voice interaction function to adapt to personalized voice interaction needs. Furthermore, users can simulate voice interaction with the robot in the interaction preview area and preview the interaction results, thereby verifying whether the current configuration results meet their needs. If not, targeted configuration adjustments can be made. This greatly facilitates voice configuration for users and improves the user experience.

[0054] In one possible implementation, to facilitate the differentiation and management of different users' configuration schemes, the platform provides a user login function. In this case, after accessing the platform, users need to enter their registered account's username and password, and then click the login button. The platform will then redirect to a configuration page that includes the aforementioned configuration area and interactive preview area.

[0055] To facilitate understanding of the solutions provided in the embodiments of the present invention, the following description, in conjunction with the page illustrations, will exemplarily introduce the various functions that the above platform may provide from the perspective of user operation.

[0056] I. Voice Interaction Configuration Function

[0057] The voice interaction configuration function is a core feature provided by the aforementioned platform, used by users to configure the robot's voice interaction parameters. In the solution provided by this embodiment of the invention, users can set the configuration parameters for each configuration item in the configuration area.

[0058] Of course, when the configuration page is displayed (e.g., when the user is logged in), the user can directly configure the settings in the configuration area of ​​the configuration page; when the configuration page is not displayed, the user can access the aforementioned platform and log in, at which point the configuration page will be displayed, and the user can then configure the settings in the configuration area of ​​the configuration page.

[0059] The configuration items in the above configuration area can be any configuration item associated with the voice interaction function, and this embodiment of the invention does not limit this.

[0060] To improve configuration flexibility and enable the robot's voice interaction function to meet various voice interaction needs, in one possible implementation, the configuration items in the configuration area may include: a first type of configuration item associated with the voice processing method and a second type of configuration item associated with the voice attributes.

[0061] The first type of configuration item is used to configure speech processing methods such as large language model, model prompt words, speech recognition method, and speech synthesis method; the second type of configuration item is used to configure speech attributes such as timbre and emotion of the output speech.

[0062] Preferably, the first type of configuration items may include, but are not limited to, at least one of the following: large language model selection, model prompt word configuration, speech recognition method configuration, and speech synthesis method configuration; the second type of configuration items may include, but are not limited to, at least one of the following: timbre configuration, tone configuration, speech rate configuration, and intonation configuration. The specific functions of each of the above configuration items are explained later. In this way, users can customize the robot's voice interaction functions by configuring the above diverse configuration items.

[0063] The aforementioned model prompt configuration item can display prompts such as "Please enter the system role prompt for the large language model..." to encourage the user to enter model prompts. Users can enter system role prompts to set the simulated identity, task boundaries, and behavioral guidelines for the large language model, thereby ensuring that the large language model outputs content as expected.

[0064] The above-mentioned timbre selection configuration options offer a variety of different timbre settings, preferably including a variety of female and male voice timbres.

[0065] The above emotion adjustment configuration options provide multiple different voice output emotions such as happiness, sadness, anger, fear, surprise, and neutral, which can be understood as the tone of voice when the robot broadcasts speech.

[0066] Preferred, see Figures 1a to 1c The configuration page offers more granular configuration options. Specifically, for large language models, it provides configuration options for large language model providers and specific optional model configuration options released by the providers; for speech recognition methods, it provides configuration options for speech recognition providers and configuration options for the range of speech to be recognized supported by the providers (used to select the language of the speech to be recognized); for speech synthesis methods, it provides configuration options for speech synthesis providers; and for speech attribute configuration options, in addition to the aforementioned timbre selection and emotion adjustment configuration options, it can also include tone adjustment configuration options and speech rate adjustment configuration options.

[0067] Due to the limited size of the configuration area, it may be difficult to display all configuration items. In this case, users can drag the scroll bar of the configuration area to select the configuration items to be displayed, such as... Figure 1b and Figure 1c As shown.

[0068] For example, to facilitate user operation, some configuration items may include drop-down buttons. When a user clicks a drop-down button, the configuration area can display various configuration parameters for that item, allowing the user to select specific parameters. Figure 2a and Figure 2b As shown, the original configuration parameter of the Large Language Model Provider Configuration Item is P1. After the user clicks the drop-down button in the Large Language Model Provider Configuration Item, the various configuration parameters P1 to P3 of the configuration item are displayed. The user selects P2 from them, and sets the configuration parameter of the Large Language Model Provider Configuration Item to P2.

[0069] For example, to facilitate user operation, some configuration items may include sliders, with a corresponding relationship between the slider position and the parameters of the configuration item. For instance... Figure 2c As shown, users can drag the slider in the tone adjustment configuration item to set the pitch of the output voice.

[0070] II. Interactive Preview Function

[0071] The interactive preview function allows users to verify whether the current configuration parameters meet their actual needs. In the solution provided by this embodiment of the invention, users can simulate dialogue with the robot at any time in the interactive preview area (i.e., the dialogue preview area).

[0072] It's important to note that in real-world scenarios, users interact with the robot via voice; however, during the interaction preview phase, users can directly simulate interaction with the robot by inputting voice or text. The dialogue input box in the dialogue preview area may display a prompt message such as "Please enter your question to simulate a conversation with the robot..."

[0073] The following examples illustrate this.

[0074] Example 1:

[0075] The user enters the dialogue text "Hello" in the dialogue input box in the interactive preview area and clicks the send button. Then, the electronic device deployed with the above platform analyzes the dialogue text according to the configuration parameters of each configuration item and generates the reply text "Hello, how can I help you?". Simultaneously, the electronic device can verbally read the reply text, such as... Figure 3 As shown.

[0076] Preferably, the reply text may include a voice broadcast button (a speaker icon in the reply text). After the user clicks the voice broadcast button, the electronic device can re-broadcast the reply text, so that the user can preview the voice broadcast effect at any time.

[0077] Example 2:

[0078] The user long-presses the voice input button in the interactive preview area ( Figure 3 The microphone icon in the center of the screen displays a message in the interactive preview area that says "The robot is listening...". Figure 4a After the user releases the voice input button, such as Figure 4b As shown, the electronic device converts the user's voice input into the dialogue text "How's the weather today?", displays the dialogue text in the interactive preview area, analyzes the dialogue text, generates the reply text "The weather is sunny today, perfect for going out.", and the electronic device can also read the reply text aloud.

[0079] III. Configuring Application Functions

[0080] See Figure 5After the user completes the configuration and confirms that the current configuration meets their needs through the preview, they can click the save button on the configuration interface to save the configuration parameters, and then click the apply to robot button. The electronic device can then send the configuration parameters displayed in the configuration area to the target robot. In this way, the target robot can configure its own voice interaction functions according to the above configuration parameters to meet the user's actual needs.

[0081] The target robot mentioned above can be a robot that has pre-established a communication connection with an electronic device, a default robot among multiple robots that have pre-established a communication connection with an electronic device, or a robot that the user selects from the multiple robots mentioned above.

[0082] To facilitate user management of voice interaction configurations across different scenarios, one possible implementation of the platform includes project management and solution management functions. These functions save user configuration parameters as voice interaction configuration solutions for robot task projects. Different robot task projects are used to distinguish different voice interaction scenarios, while different solutions within the same robot task project are used to differentiate specific requirements within those scenarios. A detailed explanation follows with reference to the accompanying diagrams.

[0083] IV. Project and Solution Management Functions

[0084] The following is combined with Figures 6a to 6e The process of users creating a project and saving the solution is illustrated with examples.

[0085] 1. Create a project

[0086] In one possible implementation, even if no robot job project has been created in the project list, the configuration area can still display the configuration items in the voice interaction configuration template. However, the configuration items are in a disabled setting state at this time, and the configuration area can display prompts such as "Please select or create a project".

[0087] Of course, in another possible implementation, it is also reasonable that no configuration items are displayed in the display area if no robot job project has been created in the project list.

[0088] After the user clicks the "Create New Project" button, see Figure 6a The configuration page displays a new project control. After entering the project name / identifier "Project 1" in the input box, the user clicks the "Generate Project" button to complete project creation. At this point, as shown... Figure 6bAs shown, the project list displays information cards for newly created robot operation projects. Furthermore, configuration items in the configuration area can now be unblocked, and a "New Scheme (Unsaved)" message will be displayed. The configuration parameters for these items can be empty or displayed as pre-set default parameters.

[0089] 2. Create a solution

[0090] In the solution provided by the embodiments of the present invention, when a user creates a voice interaction configuration scheme for a project, there are multiple optional operation procedures, which are introduced below through examples.

[0091] Example 1:

[0092] The information card for robot operation projects displays buttons such as "Create Plan," "Edit Project Name," and "Delete Project," allowing users to create plans, edit project names, and delete projects. Users can click the "Create Plan" button (a plus sign-shaped button) in the information card for Project 1. At this point, see... Figure 6c The configuration page displays a new plan control. The user enters the plan name "Plan 1" in the new plan control and clicks the confirm / save button. Then... Figure 6d As shown, the information card of the project displays the scheme identifier of the new voice interaction configuration scheme, which is displayed in the form of a card.

[0093] Next, as Figure 6e As shown, users can set the configuration parameters for each configuration item and then click the save button. The platform will save the configuration parameters of each configuration item in the configuration area as an independent voice interaction configuration scheme for that project. This makes it easy for users to manage configuration parameters for different scenarios and allows them to easily browse and reuse various voice interaction configuration schemes at any time.

[0094] Example 2:

[0095] Unlike Example 1, in Figure 6b (After a user creates a new project) Instead of clicking the "Create Solution" button, the user can directly set the configuration parameters for each item and then click the "Save" button; the platform will then redirect to... Figure 6c As shown in the interface, after the user enters the scheme name in the scheme creation control and clicks the confirm / save button, the platform saves the configuration parameters of each configuration item in the configuration area as an independent voice interaction configuration scheme for this project. Then, as... Figure 6d As shown, the information card of the project displays the scheme identifier of the new voice interaction configuration scheme.

[0096] As can be seen from the two examples above, the timing of displaying the solution identifier in the project's information card varies depending on the solution name entered by the user. For the user, they can first enter the solution name, at which point the solution identifier is already displayed in the project's information card, and then the user can configure parameters and save the configuration. Alternatively, the user can first configure and save the parameters, and then enter the solution name; in this case, the solution identifier will only be displayed in the information card after the solution is saved. This demonstrates a high degree of freedom and convenience for users when creating solutions.

[0097] After the voice interaction configuration scheme is created, users can click on the scheme card at any time to view or edit the configuration parameters of each configuration item included in the current voice interaction configuration scheme.

[0098] Of course, the platform can provide functions such as editing the solution name and deleting the solution, which will not be illustrated with attached figures here.

[0099] V. Other Functions

[0100] In one possible implementation, to facilitate users in assigning configuration schemes for different robot operation projects to the desired robots, the platform also provides a binding function between projects and robots.

[0101] Specifically, the configuration page also includes a robot binding control. This allows users to select the robot to bind to a project. When users subsequently apply the project's configuration scheme, the electronic device can distribute the configuration scheme to the robot bound to the project.

[0102] The embodiments of the present invention do not limit the location and specific usage of the robot binding control described above. The following is an example.

[0103] The robot binding control can be displayed in the configuration area. After the user clicks the "Bind Robot" button, see [link / description]. Figure 7a In the pop-up robot binding window, you can enter the robot identifier to be bound, and then click the "Confirm Binding" button. Afterward, the bound robot identifier will be displayed in the display area, and the "Bind Robot" button will change to the "Update Binding" button. Figure 7b As shown.

[0104] Of course, after clicking the "Change Binding" button, users can switch the bound robot in the pop-up "Bind Robot" control. Examples will not be provided here.

[0105] In one possible implementation, to facilitate user management of the validity period of robot operation project configuration schemes, the platform also provides a project validity period setting function.

[0106] Specifically, the configuration page also includes an expiration date setting control. This allows users to set the expiration date of a project. If a selected project exceeds its expiration date, the voice interaction configuration for that project will be disabled.

[0107] The embodiments of the present invention do not limit the location and specific usage of the robot validity period setting control, which will be described below by example.

[0108] The robot binding control can be displayed in the project display area. After the user clicks the "Apply for Project Validity Period" button, they can select the project's expiration date in the pop-up date selection window; then, the project's information card will display the corresponding expiration date, such as... Figure 7c As shown.

[0109] Preferably, information cards for expired items can also be displayed according to a set highlighting effect. This makes it easier for users to intuitively see expired items and reduces the difficulty of managing item expiration dates. The aforementioned highlighting effect can change the background color, font color, etc., of the information card, and add special effects, etc., and the comparison of the embodiments of the present invention is not limited thereto.

[0110] In one possible implementation, to improve the relevance of the robot's voice responses to specific application scenarios and enhance the reasonableness and accuracy of the answers, the platform also provides a knowledge base mounting function.

[0111] Specifically, the configuration page also includes a knowledge base mounting control. This allows users to configure the knowledge base to be mounted on their solutions. The knowledge base can include files and slices; files can include product manuals, formulas, regulations, etc., while slices can be any text that the large language model needs to understand. The knowledge base helps the large language model understand the meaning of the user's input dialogue text and generate targeted responses suitable for specific scenarios.

[0112] The embodiments of the present invention do not limit the location and specific usage of the above-mentioned knowledge base mounting control. The following is an example to illustrate this.

[0113] See Figure 7d and Figure 7e The knowledge base mounting control can be displayed in the project display area. After the user clicks the button in the knowledge base mounting control, the default selected knowledge base 1 will be displayed in the knowledge base mounting control.

[0114] Of course, users can click the drop-down button in the knowledge base mounting control to customize and select the knowledge base to be mounted from multiple knowledge bases. Examples will not be provided here.

[0115] In one possible implementation, the platform also provides knowledge base management functionality to facilitate efficient knowledge base management for users.

[0116] Specifically, the configuration page also includes a knowledge base management button. When a user clicks the knowledge base management button, the configuration page displays knowledge base management controls, allowing the user to perform management operations on the selected knowledge base.

[0117] For example, the above management operations include, but are not limited to, any of the following:

[0118] Create a new knowledge base, delete a knowledge base, rename a knowledge base, add a file to a knowledge base, and add knowledge description text to a knowledge base.

[0119] The following examples illustrate this.

[0120] See Figure 7f The knowledge base management button can be displayed in the knowledge base mounting control. After the user clicks the knowledge base management button, the configuration page will display as follows: Figure 7g The knowledge base management control shown is illustrated. It displays the various created knowledge bases, such as Knowledge Base 1 and Knowledge Base 2 in the figure, and shows the knowledge base files and slices included in each knowledge base. Users can create new knowledge bases, edit knowledge base names, delete knowledge bases, add files to knowledge bases, add slices to knowledge bases, delete files from knowledge bases, and delete slices from knowledge bases, etc., using the knowledge base management control. Specific examples are not provided here with reference to the attached figures. This allows users to easily perform various management operations on knowledge bases, ensuring that the knowledge base meets their specific needs.

[0121] In one possible implementation, to reduce the difficulty of configuration for users and simplify their configuration operations, the platform also provides an automatic configuration function.

[0122] Specifically, the configuration page also includes an auto-configuration control. After the user selects the auto-configuration function in the auto-configuration control, the electronic device can determine the user's voice interaction preference information based on the user's historical usage data of the robot bound to the current project. The aforementioned voice interaction preference information includes: the user's preferred voice processing method and / or voice attributes. Then, based on the voice interaction preference information, the configuration parameters of the configuration items in the configuration area are determined, and the determined configuration parameters are displayed in the configuration area.

[0123] For example, electronic devices can analyze user profiles, robot application scenarios, and other information based on the aforementioned historical usage data; then, based on the user profile, they can determine the user's preferred voice attributes, and determine the configuration parameters of the configuration items associated with the voice attributes according to the determined voice attributes; based on the robot application scenario, they can determine the voice processing method suitable for the current scenario, and determine the configuration parameters of the configuration items associated with the voice processing method according to the determined voice processing method.

[0124] Based on the foregoing embodiments, the following flowchart will be used to describe the motion control command flow generation scheme provided by the embodiments of the present invention.

[0125] See Figure 8 This is a flowchart illustrating a map creation method provided in an embodiment of the present invention. The method includes the following steps S801 to S803.

[0126] Step S801: In response to a configuration operation on a configuration item in the configuration area for the voice interaction function, display the configuration parameters set for the configuration item by the configuration operation in the configuration area.

[0127] As explained above, the configuration area is located on the configuration page, which also includes an interactive preview area.

[0128] Step S802: Receive an interaction request for voice interaction between the simulation and the robot, display the interaction request in the interaction preview area, respond to the interaction request based on the configuration parameters of each configuration item in the configuration area, and display the response result in the interaction preview area.

[0129] As explained above, the voice processing method and voice attributes can be determined based on the configuration parameters of each configuration item in the configuration area. Then, the user's input voice or text can be processed according to the determined configuration information, and a response text can be generated.

[0130] Step S803: In response to the configuration application operation, send the configuration parameters of each configuration item in the configuration area to the target robot.

[0131] In one possible implementation, the configuration page further includes: a display area for robot job projects, which displays information cards of created robot job projects; configuration items in the configuration area include: configuration items for the created voice interaction configuration scheme of the target project, wherein the target project includes: the robot job project corresponding to the selected information card; or, configuration items in the configuration area include: configuration items in the voice interaction configuration template.

[0132] In one possible implementation, prior to performing the response configuration operation, in response to an instruction to create a new configuration scheme for the target project, configuration items in the voice interaction configuration template can be displayed in the configuration area; and in response to a new configuration scheme save operation, a new voice interaction configuration scheme that responds to voice interaction according to the configuration parameters of each configuration item in the configuration area can be saved.

[0133] In one possible implementation, in response to an instruction to create a new configuration scheme for the target project, the scheme identifier of the new voice interaction configuration scheme can also be displayed in the information card of the target project.

[0134] In one possible implementation, after creating a new voice interaction configuration scheme, the scheme identifier of the new voice interaction configuration scheme can be displayed in the information card of the target project.

[0135] In one possible implementation, the configuration page also includes a robot binding control, which can also establish a binding relationship between the target project and the robot indicated by the binding operation in response to a binding operation on the robot binding control; in this case, the target robot is the robot bound to the target project.

[0136] In one possible implementation, the configuration page also includes: an expiration date setting control, which can also respond to setting operations on the expiration date setting control to set the project expiration date of the target project; if the target project exceeds its expiration date, the voice interaction configuration scheme of the target project is set to a disabled application state.

[0137] In one possible implementation, an information card for the target item can be displayed with a set highlighting effect when the target item exceeds its validity period.

[0138] In one possible implementation, the configuration page also includes a knowledge base mounting control, which can also display the selected target knowledge base on the configuration page in response to the selection of the knowledge base mounting control mounting function. In this case, the step of responding to the interaction request based on the configuration parameters of each configuration item in the configuration area can be implemented as follows: respond to the interaction request based on the configuration parameters of each configuration item in the configuration area and the target knowledge base; the step of sending the configuration parameters of each configuration item in the configuration area to the target robot can be implemented as follows: send the configuration parameters of each configuration item in the configuration area and the target knowledge base to the target robot.

[0139] In one possible implementation, the configuration page also includes: a knowledge base management button, which can also display a knowledge base management control in response to selecting the knowledge base management button; and execute the action indicated by the management operation in response to a knowledge base management operation triggered in the knowledge base management control.

[0140] In one possible implementation, the knowledge base management operations include any of the following:

[0141] Create a new knowledge base, delete a knowledge base, rename a knowledge base, add a file to a knowledge base, and add knowledge description text to a knowledge base.

[0142] In one possible implementation, the configuration items in the configuration area include:

[0143] The first type of configuration items is associated with the voice processing method, and the second type of configuration items is associated with the voice attributes.

[0144] In one possible implementation, the first type of configuration item includes at least one of the following:

[0145] Large language model selection options, model prompt word configuration options, speech recognition method configuration options, and speech synthesis method configuration options.

[0146] In one possible implementation, the second type of configuration item includes at least one of the following:

[0147] Voice timbre configuration, pitch configuration, speech rate configuration, tone configuration.

[0148] In one possible implementation, the configuration page further includes: an auto-configuration control, which, in response to selecting the auto-configuration function in the auto-configuration control, determines the user's voice interaction preference information based on the user's historical usage data for the target robot, wherein the voice interaction preference information includes: the user's preferred voice processing method and / or voice attributes; based on the voice interaction preference information, determines the configuration parameters of the configuration items in the configuration area, and displays the determined configuration parameters in the configuration area.

[0149] Corresponding to the above-described robot voice configuration method, this embodiment of the invention also provides a robot voice configuration device.

[0150] See Figure 9 The above is a schematic diagram of a robot voice configuration device provided in an embodiment of the present invention. The device includes the following modules:

[0151] The parameter configuration module 901 is used to respond to the configuration operation of the configuration item in the configuration area for the voice interaction function, and to display the configuration parameters set for the configuration item by the configuration operation in the configuration area. The configuration area is located on the configuration page, and the configuration page also includes an interactive preview area.

[0152] The interactive preview module 902 is used to receive interactive requests for simulated voice interaction with the robot, display the interactive requests in the interactive preview area, respond to the interactive requests based on the configuration parameters of each configuration item in the configuration area, and display the response results in the interactive preview area.

[0153] The parameter distribution module 903 is used to distribute the configuration parameters of each configuration item in the configuration area to the target robot in response to the configuration application operation.

[0154] As can be seen, the solution provided by this embodiment of the invention offers an intuitive and efficient configuration page. Users can perform simple visual operations on the configuration page according to their actual needs, flexibly and efficiently configuring various configuration items of the robot's voice interaction function. This allows the robot's voice interaction function to adapt to personalized voice interaction needs. Furthermore, users can simulate voice interaction with the robot in the interaction preview area and preview the interaction results, thereby verifying whether the current configuration results meet their needs. If not, targeted configuration adjustments can be made. This greatly facilitates voice configuration for users and improves the user experience.

[0155] In one possible implementation, the configuration page also includes: a display area for robot job projects, which displays information cards of the created robot job projects;

[0156] The configuration items in the configuration area include: configuration items for the created voice interaction configuration scheme of the target project, wherein the target project includes: the robot operation project corresponding to the information card that is selected;

[0157] or,

[0158] The configuration items in the configuration area include: the configuration items in the voice interaction configuration template.

[0159] This makes it easier for users to manage voice interaction configurations in different scenarios.

[0160] In one possible implementation, the device further includes: a scheme creation module for displaying configuration items in a voice interaction configuration template in a configuration area in response to an instruction to create a new configuration scheme for the target project;

[0161] The device also includes a scheme saving module, which is used to save a new voice interaction configuration scheme that responds to voice interaction according to the configuration parameters of each configuration item in the configuration area in response to the new configuration scheme saving operation.

[0162] This makes it easier for users to manage configuration parameters in different scenarios, and also allows users to browse and reuse various voice interaction configuration schemes at any time.

[0163] In one possible implementation, the device further includes: a first display module, configured to display a scheme identifier of the new voice interaction configuration scheme in the information card of the target project in response to an instruction to create a new configuration scheme for the target project; or, a second display module, configured to display the scheme identifier of the new voice interaction configuration scheme in the information card of the target project after creating the new voice interaction configuration scheme.

[0164] This gives users a high degree of freedom and convenience when creating plans.

[0165] In one possible implementation, the configuration page further includes: a robot binding control, and the device further includes:

[0166] The binding module is used to establish a binding relationship between the target project and the robot indicated by the binding operation in response to the binding operation on the robot binding control; the target robot is the robot bound to the target project.

[0167] This makes it easier for users to assign configuration schemes for different robot operation projects to the desired robots.

[0168] In one possible implementation, the configuration page further includes: an expiration date setting control, and the device further includes:

[0169] The validity period setting module is used to respond to setting operations on the validity period setting control and set the validity period of the target project.

[0170] The expired processing module is used to set the voice interaction configuration scheme of the target project to a prohibited application state when the target project exceeds its validity period.

[0171] This makes it easier for users to manage the validity period of the configuration scheme for robot operation projects.

[0172] In one possible implementation, the device further includes:

[0173] The highlighting module is used to display the information card of the target item with a set highlighting effect when the target item has exceeded its validity period.

[0174] This makes it easier for users to see overdue projects and reduces the difficulty of managing project deadlines.

[0175] In one possible implementation, the configuration page further includes: a knowledge base mounting control, and the device further includes:

[0176] The knowledge base mounting module is used to respond to the mounting function of the selected knowledge base mounting control and display the selected target knowledge base on the configuration page.

[0177] The interactive preview module is specifically used to respond to interactive requests based on the configuration parameters of each configuration item in the configuration area and the target knowledge base;

[0178] The parameter distribution module is specifically used to distribute the configuration parameters of each configuration item in the configuration area and the target knowledge base to the target robot.

[0179] To improve the relevance of the robot's voice responses to specific application scenarios and to enhance the reasonableness and accuracy of its answers.

[0180] In one possible implementation, the configuration page further includes a knowledge base management button, and the device also includes:

[0181] The management control display module is used to display the knowledge base management control in response to selecting the knowledge base management button.

[0182] The management action execution module is used to respond to knowledge base management operations triggered in the knowledge base management control and execute the actions indicated by the management operation.

[0183] This makes it easier for users to manage the knowledge base efficiently.

[0184] In one possible implementation, the knowledge base management operations include any of the following:

[0185] Create a new knowledge base, delete a knowledge base, rename a knowledge base, add a file to a knowledge base, and add knowledge description text to a knowledge base.

[0186] In this way, users can easily perform various management operations on the knowledge base, thereby enabling the knowledge base to meet their own needs.

[0187] In one possible implementation, the configuration items in the configuration area include:

[0188] The first type of configuration items is associated with the voice processing method, and the second type of configuration items is associated with the voice attributes.

[0189] This improves configuration flexibility, enabling the robot's voice interaction function to meet various voice interaction needs.

[0190] In one possible implementation, the first type of configuration items includes at least one of the following: large language model selection item, model prompt word configuration item, speech recognition method configuration item, and speech synthesis method configuration item;

[0191] And / or,

[0192] The second category of configuration items includes at least one of the following: timbre configuration item, pitch configuration item, speech rate configuration item, and tone configuration item.

[0193] Users can customize the robot's voice interaction functions by configuring the wide variety of settings mentioned above.

[0194] In one possible implementation, the configuration page further includes: an auto-configuration control, and the device further includes:

[0195] The automatic configuration module is used to respond to the automatic configuration function in the automatic configuration control and determine the user's voice interaction preference information based on the user's historical usage data of the target robot. The voice interaction preference information includes: the user's preferred voice processing method and / or voice attributes.

[0196] The parameter display module is used to determine the configuration parameters of the configuration items in the configuration area based on voice interaction preference information, and to display the determined configuration parameters in the configuration area.

[0197] This reduces the difficulty of configuration for users and simplifies the configuration process.

[0198] Corresponding to the above-described robot voice configuration method, this embodiment of the invention also provides an electronic device, a storage medium, and a program product.

[0199] This invention also provides an electronic device, such as... Figure 10 As shown, it includes a processor 1001, a communication interface 1002, a memory 1003, and a communication bus 1004, wherein the processor 1001, the communication interface 1002, and the memory 1003 communicate with each other through the communication bus 1004.

[0200] Memory 1003 is used to store computer programs;

[0201] The processor 1001 is used to implement the aforementioned robot voice configuration method when executing the program stored in the memory 1003.

[0202] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not indicate that there is only one bus or one type of bus.

[0203] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0204] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0205] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0206] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the robot voice configuration methods described above.

[0207] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the robot voice configuration methods described in the above embodiments.

[0208] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0209] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0210] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, electronic devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0211] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A robot voice configuration method, characterized in that, The method includes: In response to a configuration operation on a configuration item in the configuration area for a voice interaction function, the configuration parameters set by the configuration operation for the configuration item are displayed in the configuration area, the configuration area being located on a configuration page, the configuration page also including an interactive preview area; Receive an interaction request for simulated voice interaction with a robot, display the interaction request in the interaction preview area, respond to the interaction request based on the configuration parameters of each configuration item in the configuration area, and display the response result in the interaction preview area; In response to the configuration application operation, the configuration parameters of each configuration item in the configuration area are sent to the target robot.

2. The method according to claim 1, characterized in that, The configuration page also includes a display area for robot operation projects, which displays information cards of the created robot operation projects. The configuration items in the configuration area include: configuration items for the created voice interaction configuration scheme of the target project, wherein the target project includes: the robot operation project corresponding to the information card in the selected state; or, The configuration items in the configuration area include: the configuration items in the voice interaction configuration template.

3. The method according to claim 2, characterized in that, Before responding to the configuration operation, it also includes: In response to an instruction to create a new configuration scheme for the target project, configuration items in the voice interaction configuration template are displayed in the configuration area; The method further includes: In response to the new configuration scheme saving operation, a new voice interaction configuration scheme that responds to voice interaction according to the configuration parameters of each configuration item in the configuration area is saved.

4. The method according to claim 3, characterized in that, The method further includes: In response to an instruction to create a new configuration scheme for the target project, the scheme identifier of the new voice interaction configuration scheme is displayed in the information card of the target project; or, After the new voice interaction configuration scheme is created, the scheme identifier of the new voice interaction configuration scheme is displayed in the information card of the target project.

5. The method according to any one of claims 2 to 4, characterized in that, The configuration page also includes a robot binding control, and the method further includes: In response to a binding operation on the robot binding control, a binding relationship is established between the target project and the robot indicated by the binding operation; the target robot is the robot bound to the target project. And / or, The configuration page also includes: an expiration date setting control, and the method also includes: In response to the setting operation of the validity period setting control, the validity period of the target project is set; if the target project exceeds its validity period, the voice interaction configuration scheme of the target project is set to a disabled application state, and the information card of the target project is displayed with a set highlighting effect.

6. The method according to any one of claims 1 to 5, characterized in that, The configuration page also includes a knowledge base mounting control, and the method further includes: In response to selecting the mounting function of the knowledge base mounting control, the target knowledge base in the selected state is displayed on the configuration page; The response to the interaction request based on the configuration parameters of each configuration item in the configuration area includes: Based on the configuration parameters of each configuration item in the configuration area and the target knowledge base, respond to the interaction request; The step of sending configuration parameters for each configuration item in the configuration area to the target robot includes: The configuration parameters of each configuration item in the configuration area and the target knowledge base are sent to the target robot.

7. The method according to claim 6, characterized in that, The configuration page also includes a knowledge base management button, and the method further includes: In response to selecting the knowledge base management button, the knowledge base management controls are displayed; In response to a knowledge base management operation triggered in the knowledge base management control, execute the action indicated by the management operation; The knowledge base management operation includes any one of the following: Create a new knowledge base, delete a knowledge base, rename a knowledge base, add a file to a knowledge base, and add knowledge description text to a knowledge base.

8. The method according to any one of claims 1 to 7, characterized in that, The configuration items in the configuration area include: The first type of configuration items is associated with the speech processing method, and the second type of configuration items is associated with speech attributes; The first type of configuration items includes at least one of the following: large language model selection item, model prompt word configuration item, speech recognition method configuration item, speech synthesis method configuration item; and / or, the second type of configuration items includes at least one of the following: timbre configuration item, tone configuration item, speech rate configuration item, and intonation configuration item; And / or, The configuration page also includes an automatic configuration control, and the method further includes: In response to selecting the auto-configuration function in the auto-configuration control, the user's voice interaction preference information is determined based on the user's historical usage data for the target robot, wherein the voice interaction preference information includes: the user's preferred voice processing method and / or voice attributes; Based on the voice interaction preference information, the configuration parameters of the configuration items in the configuration area are determined, and the determined configuration parameters are displayed in the configuration area.

9. A robot voice configuration device, characterized in that, The device includes: The parameter configuration module is used to respond to configuration operations on configuration items in the configuration area for the voice interaction function, and to display the configuration parameters set for the configuration items by the configuration operation in the configuration area. The configuration area is located on the configuration page, and the configuration page also includes an interactive preview area. The interactive preview module is used to receive interactive requests that simulate voice interaction with the robot, display the interactive requests in the interactive preview area, respond to the interactive requests based on the configuration parameters of each configuration item in the configuration area, and display the response results in the interactive preview area. The parameter distribution module is used to distribute the configuration parameters of each configuration item in the configuration area to the target robot in response to the configuration application operation.

10. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1 to 8.

Images