Configuration methods, electronic devices, storage media, and products for intelligent agents

Abstract

This disclosure relates to a configuration method, electronic device, storage medium, and product for an intelligent agent, and pertains to the field of computer technology. The configuration method for the intelligent agent includes: displaying a configuration interface for the intelligent agent, the configuration interface including editable configuration information for the intelligent agent; displaying a preview interface associated with the configuration interface, the preview interface being a dialogue interface between the user and the intelligent agent, wherein messages sent by the intelligent agent are generated based on messages sent by the user and the configuration information; displaying a first message sent by the user on the preview interface; responding to the first message including an adjustment instruction for the configuration information of the intelligent agent, determining the adjustment content of the configuration information based on the first message; and updating the configuration information based on the adjustment content. This disclosure can improve the efficiency of users configuring intelligent agents.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method for configuring an intelligent agent, an electronic device, a storage medium, and a product. Background Technology

[0002] Intelligent agents, also known as intelligent robots or intelligent virtual objects, are virtual objects generated using computer technology that can interact with users. They respond to user input. For example, in a dialogue scenario, an intelligent agent can generate a response message based on the user's message, thus enabling functions such as chatting with the user and helping them solve problems. Summary of the Invention

[0003] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] According to some embodiments of this disclosure, a method for configuring an intelligent agent is provided, comprising: displaying a configuration interface for the intelligent agent, the configuration interface including editable configuration information for the intelligent agent; displaying a preview interface associated with the configuration interface, the preview interface being a dialogue interface between a user and the intelligent agent, wherein messages sent by the intelligent agent are generated based on messages sent by the user and the configuration information; displaying a first message sent by the user on the preview interface; responding to the first message including an adjustment instruction for the configuration information of the intelligent agent, determining the adjustment content of the configuration information based on the first message; and updating the configuration information based on the adjustment content.

[0005] According to some embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to execute a configuration method for an intelligent agent according to any embodiment of the present disclosure based on instructions stored in the memory.

[0006] According to some embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs a configuration method for an intelligent agent according to any embodiment of the present disclosure.

[0007] According to some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the configuration method of the intelligent agent in any embodiment of the present disclosure.

[0008] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0009] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the scope of the disclosure.

[0010] Figure 1 A flowchart illustrating a method for configuring an intelligent agent according to some embodiments of the present disclosure is shown.

[0011] Figure 2 A schematic diagram of a configuration interface for an intelligent agent according to some embodiments of the present disclosure is shown.

[0012] Figure 3 A schematic diagram showing a preview interface of an intelligent agent according to some embodiments of the present disclosure is illustrated.

[0013] Figure 4 A flowchart illustrating a method for adjusting configuration information according to some embodiments of the present disclosure is shown.

[0014] Figure 5 A flowchart illustrating a method for adjusting configuration information according to other embodiments of this disclosure is shown.

[0015] Figure 6 A flowchart illustrating a method for adjusting configuration items according to some embodiments of the present disclosure is shown.

[0016] Figure 7 A schematic diagram of the configuration apparatus for an intelligent agent according to some embodiments of the present disclosure is shown.

[0017] Figure 8 A schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure is shown.

[0018] Figure 9 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0019] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0021] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0022] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0023] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0024] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0025] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0026] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0027] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0028] In some applications, users can create their own agents in addition to those provided by the application. For example, a user can open the agent's configuration interface and enter configuration information for the agent, such as description and settings, in various configuration items. Then, when the agent interacts with the user, it can provide responses that match the user's configuration based on this information.

[0029] However, some problems may still exist in the configuration and application of intelligent agents.

[0030] Currently, the configuration of intelligent agents is highly dependent on the configuration information provided by the user. This configuration information can be user-inputted descriptive information about the intelligent agent being created, such as its personality, background story, and interests. For some intelligent agents based on machine learning models, such as those based on Large Language Models (LLMs) or Foundation Models, the user-provided configuration information may be directly used as input to the model. Therefore, if users provide more accurate and effective configuration information, the generated intelligent agent can more closely resemble the user's needs.

[0031] Some users, lacking experience in creating agents or with limited language skills, fail to accurately convey their intentions through the configuration information they input. Alternatively, the user-input configuration information may be insufficient, lacking effective details, resulting in an agent that lacks distinctive characteristics.

[0032] This can lead to low utilization of agents after creation. If an agent is not used, its creation process, as well as the process of storing the agent and its related data, will waste computing and network resources. Therefore, the configuration efficiency of agents is relatively low.

[0033] Of course, once an agent is created, users can modify it further if they are not satisfied with its use. However, there are multiple other interfaces between the agent's user interface and configuration interface, meaning that users need to navigate through several screens to get from one interface to another. For example, if the agent's user interface is a dialogue interface, users need to exit the dialogue interface and return to the home page, then go to the settings interface, find the agent, and then open its configuration interface.

[0034] Therefore, even though it can be modified after creation, the configuration efficiency of an agent is still relatively low.

[0035] To at least partially solve the above problems, this disclosure provides a method for configuring intelligent agents and related devices to improve the configuration efficiency of intelligent agents, thereby saving computing and storage resources.

[0036] Figure 1 A flowchart illustrating a method for configuring an intelligent agent according to some embodiments of the present disclosure is shown. Figure 1 As shown, the configuration method of this embodiment includes steps S102 to S110.

[0037] In step S102, the configuration interface of the agent is displayed, which includes editable configuration information for the agent.

[0038] The configuration interface for an agent is used to configure an agent that is to be created or modified. This configuration interface may include one or more interactive controls, such as input controls, selection controls, etc., to receive configuration information input or selected by the user.

[0039] The configuration interface can include one or more configuration items, each corresponding to a type of configuration information. Configuration items may include, for example, an avatar, name, settings, opening remarks, language style, etc. Each configuration item can be associated with one or more controls for users to input or select configuration information.

[0040] In step S104, a preview interface associated with the configuration interface is displayed. The preview interface is a dialogue interface between the user and the intelligent agent.

[0041] The messages sent by the agent are generated based on the messages sent by the user and configuration information. For example, when the agent uses a generative model to generate messages, the generative model can process the configuration information and the messages sent by the user to obtain the generated messages. Thus, the messages sent by the agent can respond to the messages sent by the user and match the agent's configuration information.

[0042] The preview and configuration interfaces are linked, meaning they have a direct hierarchical relationship. For example, a user can navigate from one interface to the other with at most one jump. Furthermore, the preview and configuration interfaces can even be displayed on the same page. This allows for efficient switching between the two interfaces.

[0043] In some embodiments, a preview interface associated with the configuration interface is displayed in response to a specified user action. The specified action can be a trigger action on the preview interface that occurs when the configuration interface is displayed. For example, it can be implemented using a trigger control on the configuration interface.

[0044] The preview interface can be used to preview the agent to be created, essentially a "test" before the agent is actually created, allowing users to confirm whether further modifications to the agent's configuration information are needed. In the preview interface, users can send messages to the agent. Messages sent by the user can be at least one of the following types: text, voice, image, video, file, etc.

[0045] Even when the preview interface is displayed and the user has not yet sent any messages, the agent can proactively send messages to the user based on configuration information or default settings, such as greeting the user, guiding the user to engage in dialogue with the agent, etc.

[0046] In step S106, the first message sent by the user is displayed in the preview interface. This first message is sent by the user to the intelligent agent.

[0047] In step S108, in response to the first message including an instruction to adjust the configuration information of the agent, the content of the adjustment to the configuration information is determined based on the first message.

[0048] In actual use of the AI ​​agent, the messages sent by the user are the content the user truly wants to chat about. However, in the preview interface, on the one hand, the AI ​​agent can mimic the actual usage flow and respond to the content sent by the user; on the other hand, it can also determine the content to be adjusted in the configuration information when the user sends a message through the preview interface to indicate that the configuration information of the AI ​​agent needs to be adjusted.

[0049] For example, a user might want to create an agent that is an English speaking teacher, but only entered "English teacher" in the configuration information. In the preview interface, when the user interacts with the agent, they might find that the agent lacks speaking skills. They can then directly send a message to the agent in this interface, such as, "I hope you can help me improve my speaking skills." The configuration information could then be adjusted by adding descriptions related to speaking skills. The user doesn't need to manually determine how to describe English speaking skills; instead, as described in the example above, they can directly express this intention to the agent in a chat-like manner in the preview interface. The agent can then perform semantic understanding on the user's message and determine, based on the results, whether the user intends to make adjustments and, if so, what those adjustments should be. This semantic understanding process can be implemented using semantic analysis models or generative models.

[0050] Adjustments to configuration information can include adding, deleting, or modifying content. These adjustments can directly affect the configuration information or serve as the basis for generating new configuration information. For example, when the configuration information is multimedia content, the adjustment could be a prompt message used to generate new multimedia content, which can then be processed using a generative model to generate the new configuration information.

[0051] In step S110, the configuration information is updated based on the adjusted content.

[0052] The adjustments can be displayed to the user directly or not. The adjustments can be automatically updated, for example, automatically modifying configuration information based on the adjustments. Alternatively, the adjustments can be manually updated by the user; for example, if the adjustments are displayed, the user can remember them and enter them in the configuration interface. Or, the user can copy the displayed content and paste it into the configuration interface.

[0053] Since the configuration interface and the preview interface are linked, users can quickly access the configuration interface even when they manually update the configuration information, thus improving their operational efficiency.

[0054] The aforementioned implementation provides a configuration interface for the intelligent agent and a preview interface associated with the configuration interface. This allows users to quickly preview the configuration effect of the intelligent agent during the configuration process. Furthermore, users can express their intention to adjust the configuration information by sending messages while interacting with the intelligent agent in the preview interface. This assists users in configuring the intelligent agent during test conversations, thus improving the efficiency of intelligent agent configuration. Even users lacking experience in configuring intelligent agents can quickly complete the configuration process, and accurate configuration also improves the usability of the created intelligent agent.

[0055] Figure 2 A schematic diagram of a configuration interface for an intelligent agent according to some embodiments of the present disclosure is shown. For example... Figure 2 As shown. The configuration interface (or editing interface) 2 of this example includes one or more editing controls corresponding to configuration items, such as image editing control 21, name editing control 22, setting editing control 23, opening remarks editing control 24, etc.

[0056] In some embodiments, the configuration interface includes a first control for navigating to a dialog interface.

[0057] In some embodiments, the configuration interface and the preview interface can be side-by-side tabs. For example, in Figure 2 In the configuration interface 2, an edit label control 26 and a preview label control 27 are displayed. The edit label control 26 is active to indicate that the configuration interface is currently displayed. The preview interface can be displayed in response to the triggering of the preview label control 27. The preview label control 27 can be considered the primary control.

[0058] Figure 3 A schematic diagram showing a preview interface of an intelligent agent according to some embodiments of the present disclosure is illustrated. Figure 3 In the preview interface 3 shown, users can send messages to the agent using the message sending control to test the agent. The dialogue between the user and the agent can be displayed in preview interface 3. Figure 3 In the example, messages sent by the agent are displayed in a left-aligned manner, such as messages 31 and 33, while messages sent by the user are displayed in a right-aligned manner, such as messages 32, 34, and 35. Message 34, "I hope you can be my English speaking teacher and practice speaking with me more," includes instructions for adjusting the agent's configuration information, that is, the user expects to create an agent as an English speaking teacher.

[0059] In some embodiments, the dialog interface includes a second control for navigating to a configuration interface. For example, in Figure 3In response to the closing control 36 being triggered, you can jump from the preview interface 3 to the configuration interface 2.

[0060] Furthermore, the configuration interface and the preview interface can be displayed on the same page simultaneously. For example, they can be displayed in a split-screen format, or one interface can be displayed as a floating layer on top of the other, and so on.

[0061] The adjusted configuration information can be updated and displayed in the configuration interface. In some embodiments, the configuration interface displays the updated configuration information based on the adjustments.

[0062] For example, configuration information can be automatically updated based on adjustments and displayed in the configuration interface. This reduces the amount of manual configuration work for users and improves the configuration efficiency of the intelligent agent.

[0063] For example in Figure 2 The AI ​​agent's setup information is "You are my English teacher." (Through...) Figure 3 The dialogue shown indicates that the configuration information has been changed from "English Teacher" to "English Speaking Teacher". Therefore, when the user returns to the configuration interface, the agent's settings will be automatically updated to "You are my English Speaking Teacher; No vocabulary memorization".

[0064] To more clearly inform the user about configuration adjustments, the changes can be displayed in the interface. The adjustments can be displayed in any format. In some embodiments, they can be displayed as a message sent to the user by an agent. For example, a second message sent by the agent to the user can be displayed in the preview interface, including the adjustments to the configuration information.

[0065] That is, the agent can be configured to generate a message to be sent to the user based on the adjusted content after detecting the user's intention to adjust the configuration information and determining the content of the adjustment. For example, a generative model can be used to process the adjusted content, and a confirmation instruction for generating the adjusted content can also be input into the model. This ensures that the generated message expresses the intention to confirm the adjusted content with the user.

[0066] Still with Figure 2 and 3 For example, in preview interface 3, the agent can send a message to the user, "Would you like to update my settings to 'English Speaking Teacher'?" or "My settings have been updated to English Speaking Teacher", to notify the user to adjust the content.

[0067] The following are references respectively. Figure 4 and Figure 5 Two implementation methods are described exemplarily.

[0068] Figure 4A flowchart illustrating a method for adjusting configuration information according to some embodiments of this disclosure is shown. Figure 4 As shown, the adjustment method of this embodiment includes steps S402 to S406.

[0069] In step S402, a second message sent by the agent to the user is displayed on the preview interface. The second message includes adjustments to the configuration information.

[0070] In step S404, the configuration interface receives user editing operations on the configuration information, where the editing operation is determined based on the content to be adjusted. For example, after the second message is displayed, the user can return from the preview interface to the configuration interface and edit the configuration information.

[0071] User editing operations can include text editing, copying and pasting, etc. For example, after seeing the adjustment content, users can manually edit the configuration information according to the adjustment content, or users can directly copy the displayed adjustment content and paste it into the configuration information interface.

[0072] In step S406, the edited configuration information is displayed.

[0073] In this approach, after users see the adjusted content, they can make further fine-tuning adjustments, allowing for more flexible modifications. This improves the accuracy of the configuration.

[0074] Figure 5 A flowchart illustrating a method for adjusting configuration information according to other embodiments of this disclosure is shown. For example... Figure 5 As shown, the adjustment method of this embodiment includes steps S502 to S506.

[0075] In step S502, a second message sent by the agent to the user is displayed on the preview interface. The second message includes adjustments to the configuration information.

[0076] In step S504, the third message sent by the user is displayed in the preview interface.

[0077] The third message can be sent after the second message. The agent can use the second message to send the user adjustments to the configuration information. Based on this, the user can reply using the third message.

[0078] For example, if the agent sends a second message to the user, "Do you need to change my settings to...?", the user can send a third message, such as "OK," to indicate confirmation.

[0079] In step S506, in response to the third message confirming the adjustment, the configuration information is updated.

[0080] In this approach, users can interact with the agent through a preview interface to instruct it to adjust configuration information and to confirm the adjustments. This allows the configuration information to be updated automatically without user intervention, improving operational efficiency.

[0081] Configuration information can be of various types. For example, configuration information may include configuration information for at least one of the following: image, sound, and dialogue of the intelligent agent. In some embodiments of this disclosure, the first message sent by the user can be identified to determine the configuration items that need to be adjusted.

[0082] Figure 6 A flowchart illustrating a method for adjusting configuration items according to some embodiments of this disclosure is shown. Figure 6 As shown, the adjustment method of this embodiment includes steps S602 to S604.

[0083] In step S602, the type of configuration item corresponding to the first message is identified.

[0084] For example, natural language processing models, such as semantic recognition models and semantic understanding models, can be used to process the first message or its key content to determine the type of configuration item corresponding to the first message. The key content in the first message can be keywords or core words extracted from the first message, or the central semantics of the first message obtained through preprocessing.

[0085] For example, classification models can be used to classify the first message or key content within the first message.

[0086] Another approach is to first detect whether the first message directly contains an indication of the type of the configuration item. In some embodiments, it is identified whether the first message includes an indication of the type of the configuration item; in response to the first message not including an indication of the type of the configuration item, the type of the configuration item corresponding to the first message is determined to be a dialogue type; in response to the first message including an indication of the type of the configuration item, the type of the configuration item corresponding to the first message is determined based on that indication. Since the main function of the agent is to engage in dialogue with the user, if the user instructs to adjust the agent but does not explicitly specify which configuration item to adjust, it is determined that the user is adjusting a configuration item of the dialogue type of the agent.

[0087] The dialogue type configuration options influence the dialogue content of the agent. That is, when generating dialogue, the agent generates it based on the configuration information in the dialogue type configuration options. The dialogue type configuration options configure at least one of the agent's language, attributes, and knowledge base.

[0088] For example, if the first message is "You could be a little gentler," which includes an instruction to adjust the agent but doesn't specify which type of configuration item is being adjusted, it can be interpreted as an instruction to make the agent's language style gentler. If the first message is "Your image could be a little gentler," then it can be determined that the user has instructed to adjust the agent's image.

[0089] In step S604, the adjustment content of the configuration information of the configuration item is determined based on the type, the first message, and the configuration information of the configuration item.

[0090] If the configuration item to be adjusted is text-based (e.g., a dialogue), the adjustment can be made to the text itself. If the configuration item is not text-based, the adjustment can be made to the prompt message for that item. Based on the adjusted prompt message, the configuration information for that item can be regenerated, for example, by regenerating images, sounds, etc.

[0091] The above embodiments can automatically identify the configuration items that the user wants to adjust and automatically generate adjustment content matching those configuration items. Therefore, the user can express their adjustment needs simply through a first message, while the specific configuration item to be adjusted is automatically determined, thus improving the user's configuration efficiency.

[0092] In some embodiments, an agent is created based on configuration information in response to a user completing the configuration of the agent. For example, in Figure 2 In the middle, responding to user-triggered control 25, the configuration process can be completed; for example, in Figure 3 In response to user-triggered control 37, the configuration process can be completed. After configuration, the intelligent agent can be officially put into use, such as interacting with users in a dialogue interface, or being published for use by other users.

[0093] The embodiments of the configuration method disclosed herein have been described above. The apparatus for implementing the above embodiments is further described below.

[0094] Figure 7 A schematic diagram of a configuration apparatus for an intelligent agent according to some embodiments of the present disclosure is shown. For example... Figure 7As shown, the configuration device 70 of this embodiment includes: a display module 701, configured to display a configuration interface for an intelligent agent, the configuration interface including editable configuration information for the intelligent agent; a preview interface associated with the configuration interface, the preview interface being a dialogue interface between the user and the intelligent agent, the messages sent by the intelligent agent being generated based on the messages sent by the user and the configuration information; displaying a first message sent by the user on the preview interface; a determination module 702, configured to determine the adjustment content of the configuration information based on the first message in response to the first message including an adjustment instruction for the configuration information of the intelligent agent; and an update module 703, configured to update the configuration information based on the adjustment content.

[0095] In some embodiments, the update module 703 is further configured to display, in the configuration interface, the updated configuration information based on the adjusted content.

[0096] In some embodiments, the display module 701 is further configured to display a second message sent by the agent to the user on the preview interface, the second message including adjustments to the configuration information.

[0097] In some embodiments, the update module 703 is further configured to receive user editing operations on configuration information in the configuration interface, wherein the editing operation is determined according to the content to be adjusted; the display module 701 is further configured to display the edited configuration information.

[0098] In some embodiments, the update module 703 is further configured to: display a third message sent by the user in the preview interface; and update the configuration information in response to the third message confirming the adjustment.

[0099] In some embodiments, the configuration information includes configuration information for at least one of the following configuration items of the agent: image, sound, and dialogue. The determining module 702 is further configured to: identify the type of the configuration item corresponding to the first message; and determine the adjustment content of the configuration information of the configuration item based on the type of the first message and the configuration information of the configuration item.

[0100] In some embodiments, the determining module 702 is further configured to: identify whether the first message includes an indication of the type of a configuration item; in response to the first message not including an indication of the type of a configuration item, determine the type of the configuration item corresponding to the first message as a dialog type; and in response to the first message including an indication of the type of a configuration item, determine the type of the configuration item corresponding to the first message based on the indication.

[0101] In some embodiments, the dialogue type configuration option is used to configure at least one of the agent's language, attributes, and knowledge base.

[0102] In some embodiments, the configuration interface includes a first control for navigating to a dialog interface; the dialog interface includes a second control for navigating to the configuration interface.

[0103] In some embodiments, the configuration interface and the preview interface are displayed on the same page.

[0104] In some embodiments, the configuration device 70 further includes a creation module 704, configured to create an intelligent agent based on configuration information in response to a user completing the configuration of the intelligent agent.

[0105] It should be noted that the above-described units are merely logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above-described units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the units shown in the accompanying drawings with dashed lines indicate that these units may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0106] In addition, although not shown, the device may also include a memory that can store various information generated by the device and its constituent units during operation, programs and data used for operation, data to be transmitted by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in a manner known in the art, such as including communication components like antenna arrays and / or radio frequency links, various types of interfaces, communication units, etc. These will not be described in detail here. Furthermore, the device may also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, etc. These will not be described in detail here.

[0107] Some embodiments of this disclosure also provide an electronic device. Figure 8A schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure is shown. For example, in some embodiments, the electronic device 8 can be various types of devices, including but not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. For example, the electronic device 8 may include a display panel for displaying data and / or execution results utilized in the scheme according to the present disclosure. For example, the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a planar panel, but also a curved panel, or even a spherical panel.

[0108] like Figure 8 As shown, the electronic device 8 of this embodiment includes a memory 81 and a processor 82 coupled to the memory 81. It should be noted that... Figure 8 The components of the electronic device 8 shown are merely exemplary and not limiting; the electronic device 8 may have other components as needed for actual applications. The processor 82 can control other components in the electronic device 8 to perform desired functions.

[0109] In some embodiments, memory 81 is used to store one or more computer-readable instructions. When processor 82 executes the computer-readable instructions, the computer-readable instructions are executed by processor 82 to implement the method according to any of the above embodiments. For specific implementations and related explanations of the various steps of the method, please refer to the above embodiments; repeated details will not be elaborated here.

[0110] For example, processor 82 and memory 81 can communicate with each other directly or indirectly. For example, processor 82 and memory 81 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. Processor 82 and memory 81 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0111] For example, processor 82 can be embodied in various suitable processors, processing devices, such as central processing unit (CPU), graphics processing unit (GPU), network processor (NP), etc.; it can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The central processing unit (CPU) can be an x86 or ARM architecture, etc. For example, memory 81 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Memory 81 can include, for example, system memory, which stores, for example, the operating system, application programs, boot loader, database, and other programs. Various application programs and various data can also be stored in the storage medium.

[0112] Furthermore, according to some embodiments of this disclosure, various operations / processes according to this disclosure, when implemented via software and / or firmware, can be transmitted from a storage medium or network to a computer system with a dedicated hardware architecture, such as... Figure 9 The computer system 90 shown is equipped with the programs that constitute the software. When various programs are installed, the computer system is able to perform various functions, including functions such as those described above. Figure 9 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure is shown.

[0113] exist Figure 9 In this configuration, the Central Processing Unit (CPU) 901 performs various processes based on a program stored in the Read-Only Memory (ROM) 902 or a program loaded into the Random Access Memory (RAM) 903 from the Storage Section 908. The RAM 903 also stores data required when the CPU 901 performs various processes, etc. The CPU is merely exemplary; it can also be other types of processors, such as the various processors described above. The ROM 902, RAM 903, and Storage Section 908 can be various forms of computer-readable storage media, as described below. It should be noted that although... Figure 9 The diagram shows ROM 902, RAM 903 and storage section 908, but one or more of them may be combined or located in the same or different memory or storage modules.

[0114] CPU 901, ROM 902 and RAM 903 are interconnected via bus 904. Input / output interface 905 is also connected to bus 904.

[0115] The following components are connected to the input / output interface 905: input section 906, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 907, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 908, including hard disk, magnetic tape, etc.; and communication section 909, including network interface cards such as LAN cards, modems, etc. The communication section 909 allows communication processing via a network such as the Internet. It is easy to understand that, although... Figure 9 The various devices or modules in the computer system 90 shown communicate via bus 904, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of wireless and wired networks.

[0116] As needed, drive 910 is also connected to input / output interface 905. Removable media 911, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 910 as needed, so that computer programs read from them can be installed into storage section 908 as needed.

[0117] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as a removable medium 911.

[0118] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 909, or installed from storage section 908, or installed from ROM 902. When the computer program is executed by CPU 901, it performs the functions defined in the methods of embodiments of this disclosure.

[0119] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of sending, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0120] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0121] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the method of any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0122] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0124] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0125] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0126] The above description is merely an illustration of some embodiments of this disclosure and the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0127] Many specific details are set forth in the description provided herein. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of the description.

[0128] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0129] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. A method for configuring an intelligent agent, comprising: Displays the configuration interface of the intelligent agent, which includes editable configuration information for the intelligent agent; Display a preview interface associated with the configuration interface. The preview interface is a dialogue interface between the user and the intelligent agent. The messages sent by the intelligent agent are generated based on the messages sent by the user and the configuration information. The preview interface displays the first message sent by the user. In response to the first message including an instruction to adjust the configuration information of the agent, based on the first message, determining the adjustment content of the configuration information includes: identifying the type of the configuration item corresponding to the first message; and determining the adjustment content of the configuration information of the configuration item according to the type, the first message, and the configuration information of the configuration item, wherein the adjustment content of the configuration information includes at least one of added content, deleted content, and modified content. The configuration information is updated based on the adjustment content, including: adjusting the configuration information by adding, deleting, or modifying at least one of the adjustment content, and displaying the automatically updated configuration information based on the adjustment content in the configuration interface; In response to receiving the user's edit operation on the configuration information, the edited configuration information is displayed; In response to the user completing the configuration of the agent, an agent is created based on the configuration information.

2. The configuration method according to claim 1 further includes: The preview interface displays a second message sent by the agent to the user, which includes adjustments to the configuration information.

3. The configuration method according to claim 2, wherein, The updating of the configuration information based on the adjustment includes: In the configuration interface, the user's editing operation on the configuration information is received, wherein the editing operation is determined based on the adjustment content; Displays the edited configuration information.

4. The configuration method according to claim 2, wherein, The updating of the configuration information based on the adjustment includes: The preview interface displays the third message sent by the user; In response to the third message confirming the adjustment, the configuration information is updated.

5. The configuration method according to any one of claims 1 to 4, wherein, The configuration information includes configuration information for at least one of the following configuration items of the intelligent agent: image, sound, and dialogue.

6. The configuration method according to claim 5, wherein, The type of configuration item corresponding to the first message is identified as including: Identify whether the first message includes an indication of the type of configuration item; In response to the first message not including an indication of the type of the configuration item, the type of the configuration item corresponding to the first message is determined to be a dialog type; In response to the first message including an indication of the type of the configuration item, the type of the configuration item corresponding to the first message is determined based on the indication.

7. The configuration method according to claim 6, wherein, The configuration options for the dialogue type are used to configure at least one of the agent's language, attributes, and knowledge base.

8. The configuration method according to any one of claims 1 to 4, wherein: The configuration interface includes a first control for navigating to the dialog interface; The dialog interface includes a second control for navigating to the configuration interface.

9. The configuration method according to any one of claims 1 to 4, wherein, The configuration interface and the preview interface are displayed on the same page.

10. An electronic device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the agent configuration method as described in any one of claims 1 to 9 based on instructions stored in the memory.

11. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the configuration method of the intelligent agent according to any one of claims 1 to 9.

12. A computer program product, when run on a computer, causes the computer to implement the configuration method of the intelligent agent according to any one of claims 1 to 9.

Images