Method and apparatus for creating digital assistant, and device, storage medium and program product

Abstract

Provided in the embodiments of the present disclosure are a method and apparatus for creating a digital assistant, and a device, a storage medium and a program product. The method comprises: in a user interface used for creating a digital assistant, presenting a configuration region used for receiving setting information of the digital assistant; in response to detecting an automatic optimization indication for the setting information of the digital assistant, presenting an optimization panel; on the basis of an adjustment indication received by means of the optimization panel and at least one portion of the setting information that is received in the configuration region, presenting, in the optimization panel, at least one portion of the setting information that is adjusted; and on the basis of an acceptance indication or a rejection indication for the at least one portion of the setting information that is adjusted, determining the setting information presented in the configuration region.

Description

Method, device, equipment, storage medium and program product for digital assistant creation

[0001] The present application claims priority to the Chinese patent application No. 202410742949.2, filed on June 07, 2024, entitled “Method, device, equipment, storage medium and program product for digital assistant creation”, the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The example embodiments of the present disclosure generally relate to the field of computer, and in particular, to a method, device, equipment, computer readable storage medium and computer program product for digital assistant creation. BACKGROUND

[0003] Digital assistants are provided to assist users in various task processing needs in different applications and scenarios. Digital assistants usually have intelligent conversation and task processing capabilities. In the interaction with the digital assistant, the user inputs an interaction message, and the digital assistant provides a reply message in response to the user input. Generally, the digital assistant can support the user to input a question in a natural language manner, and perform a task and provide a reply based on the understanding of the natural language input and the logical reasoning capability. Such an interaction mode has become a tool that people love and rely on due to its flexible and convenient characteristics. SUMMARY

[0004] In a first aspect of the present disclosure, a method for digital assistant creation is provided. The method comprises: in a user interface for creating a digital assistant, presenting a configuration area for receiving setting information of the digital assistant, the setting information being used to generate a prompt word input of a first machine learning model, wherein the digital assistant generates a reply to a user based on an output of the first machine learning model; in response to detecting an automatic optimization indication of the setting information of the digital assistant, presenting an optimization panel, the optimization panel comprising at least one of: an input control for receiving an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information; presenting at least part of the adjusted setting information in the optimization panel based on the adjustment indication received via the optimization panel and at least part of the setting information received in the configuration area; determining the setting information presented in the configuration area based on an acceptance indication or a rejection indication of the at least part of the adjusted setting information.

[0005] In a second aspect of the disclosure, an apparatus for digital assistant creation is provided. The apparatus includes: a configuration area presentation module configured to present, in a user interface for creating a digital assistant, a configuration area for receiving setting information of the digital assistant, the setting information being used to generate a prompt word input of a first machine learning model, wherein the digital assistant generates a reply to a user based on an output of the first machine learning model; an optimization panel presentation module configured to present an optimization panel in response to detecting an automatic optimization indication of the setting information of the digital assistant, the optimization panel including at least one of: an input control for receiving an input of an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information; a setting information presentation module configured to present, in the optimization panel, an adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and at least a part of the setting information received in the configuration area; a setting information determination module configured to determine the setting information presented in the configuration area based on an acceptance indication or a rejection indication of the adjusted at least part of the setting information.

[0006] In a third aspect of the disclosure, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by the at least one processor, cause the electronic device to perform the method of the first aspect.

[0007] In a fourth aspect of the disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon computer-executable instructions that are executable by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of the disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a processor, implement the method of the first aspect.

[0009] It should be understood that all statements herein made regarding the exemplary embodiments of the present disclosure are intended to encompass both structural and functional equivalents thereof. Additionally, it is intended that such equivalents include both currently known equivalents as well as equivalents developed in the future (e.g., any elements developed that perform the same function, regardless of structure). The scope of the present disclosure, therefore, is not intended to be limited to the exemplary embodiments described herein. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other features, aspects, and advantages of various embodiments of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which like reference numerals denote like elements, and wherein:

[0011] FIG. 1 illustrates a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG. 2 illustrates an example of a user interface for creating a digital assistant, according to some embodiments of the present disclosure;

[0013] FIGS. 3A-3N illustrate schematic diagrams of example configuration areas, according to some embodiments of the present disclosure;

[0014] FIG. 4 illustrates a flowchart of a process for digital assistant creation, according to some embodiments of the present disclosure;

[0015] FIG. 5 illustrates a schematic structural block diagram of an apparatus for digital assistant creation, according to some embodiments of the present disclosure; and

[0016] FIG. 6 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure can be implemented. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. While certain embodiments of the present disclosure are illustrated in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be interpreted in a limited sense as set forth in the embodiments set forth herein. Rather, the embodiments are provided to more completely and thoroughly understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are merely for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of embodiments of the present disclosure, the term "comprising" and similar terms thereof are understood to be inclusive, i.e., "including but not limited to". The term "based on" is understood to mean "based, at least in part, on". The term "one embodiment" or "the embodiment" is understood to mean "at least one embodiment". The term "some embodiments" is understood to mean "at least some embodiments". Other explicit or implicit definitions can also be included below.

[0019] In this document, unless explicitly stated otherwise, performing a step "in response to" A does not mean that the step is performed immediately after A, but can include one or more intermediate steps.

[0020] It can be understood that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, obtaining, using, storing or deleting of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0021] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means, wherein the relevant user can include any type of right subject, such as an individual, an enterprise, or a group.

[0022] For example, in response to receiving an active request of a user, prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require obtaining and using information of the relevant user, so that the relevant user can autonomously select whether to provide information to the software or hardware, such as an electronic device, an application program, a server or a storage medium, etc. that performs the operation of the technical solution of the present disclosure according to the prompt information.

[0023] As an optional but non-limiting implementation manner, in response to receiving an active request of a relevant user, the manner of sending prompt information to the relevant user may, for example, be a pop-up window manner, in which the prompt information can be presented in the form of text. In addition, the pop-up window can also carry selection controls for the user to select “agree” or “disagree” to provide information to the electronic device.

[0024] It can be understood that the above notification and user authorization obtaining process is only illustrative and does not limit the implementation manner of the present disclosure, and other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0025] As used herein, the term “model” can learn an association between respective inputs and outputs from training data, such that after training, a corresponding output can be generated for a given input. The generation of a model can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is one example of a model based on deep learning. In this document, a “model” can also be referred to as a “machine learning model”, a “learning model”, a “machine learning network” or a “learning network”, which terms are used interchangeably herein.

[0026] A digital assistant can serve as an effective tool for people to work, study and live. Generally, the development of a digital assistant is similar to the development of a general application, which requires a developer with programming ability to define various capabilities of the digital assistant by writing complex code, and deploy the digital assistant on a suitable running platform, so that users can download, install and use the digital assistant.

[0027] As application scenarios diversify and machine learning technology becomes more available, it is desirable to develop digital assistants with different capabilities to support task processing in various subfields or meet the individualized needs of different users. A user can create different prompt inputs and provide the prompt inputs to a machine learning model to determine different digital assistants using the machine learning model. The user can also adjust the digital assistant by adjusting the prompt inputs. Traditionally, the user often needs to manually determine what to modify in the prompt inputs and manually modify the prompt inputs. However, limited by programming ability and limited understanding of the underlying implementation logic of the digital assistant, the user cannot accurately adjust the prompt inputs, and the efficiency of manually adjusting the prompt inputs is poor. Therefore, embodiments of the present disclosure describe technical solutions that can conveniently and quickly determine more accurate prompt inputs, so that more users can obtain the desired digital assistant.

[0028] According to an embodiment of the present disclosure, an improved solution for digital assistant creation is provided. According to the solution, in a user interface for creating a digital assistant, a configuration area for receiving setting information of the digital assistant is presented. The setting information is used to generate a prompt input of a first machine learning model, wherein the digital assistant generates a reply to a user based on an output of the first machine learning model. In response to detecting an automatic optimization indication of the setting information of the digital assistant, an optimization panel is presented. The optimization panel includes at least one of: an input control for receiving an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information. Based on the adjustment indication received via the optimization panel and at least part of the setting information received in the configuration area, at least part of the adjusted setting information is presented in the optimization panel. Based on an acceptance indication or a rejection indication of the at least part of the adjusted setting information, the setting information presented in the configuration area is determined.

[0029] Thus, in the creation process of the digital assistant, the user can conveniently and quickly adjust the prompt input to correspondingly adjust the reply result of the digital assistant.

[0030] FIG. 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. The environment 100 involves an assistant creation platform 110 and an assistant application platform 130.

[0031] As shown in FIG. 1, an assistant creation platform 110 can provide a user 105 with an environment for creation and publishing of digital assistants. In some embodiments, the assistant creation platform 110 can be a low-code platform that provides a collection of tools for digital assistant creation. The assistant creation platform 110 can support visual development of digital assistants, allowing developers to skip the process of hand-coding and speed up the development cycle and cost of applications. The assistant creation platform 110 can support any suitable platform for users to develop digital assistants and other types of applications, which can include, for example, an application platform-as-a-service (aPaaS)-based platform. Such a platform can enable efficient development of applications by users, enabling operations such as application creation, application functionality adjustment, etc.

[0032] The assistant creation platform 110 can be deployed locally on a terminal device of the user 105 and / or can be supported by a remote server. For example, the terminal device of the user 105 can run a client of the assistant creation platform 110, which can support user interaction with the assistant creation platform 110. In a case where the assistant creation platform 110 is run locally on a terminal device of the user, the user 105 can directly interact with the assistant creation platform 110 using the client. In a case where the assistant creation platform 110 is run on a server device, the server device can provide services to the client running on the terminal device based on a communication connection between the server device and the terminal device. The assistant creation platform 110 can present a corresponding interface 122 to the user 105 based on operations of the user 105 to output and / or receive information from the user 105.

[0033] In some embodiments, the assistant creation platform 110 can be associated with a corresponding database that stores data or information required for digital assistant creation processes supported by the assistant creation platform 110. For example, the database can store code and description information corresponding to various functional modules used to compose a digital assistant. The assistant creation platform 110 can also perform operations such as calling, adding, deleting, updating, etc. of functional modules in the database. The database can also store operations executable on different functional blocks. For example, in a scenario where a digital assistant is to be created, the assistant creation platform 110 can call corresponding functional blocks from the database to build the digital assistant.

[0034] In embodiments of the present disclosure, a user 105 can create a digital assistant 120 on the assistant creation platform 110 as needed and publish the digital assistant 120. The digital assistant 120 can be published to any suitable assistant application platform 130 as long as the assistant application platform 130 is capable of supporting the running of the digital assistant 120. After publication, the digital assistant 120 can be used for conversational interaction with a user 135. A client of the assistant application platform 130 can present an interaction window 132, e.g., a conversation window, of the digital assistant 120 in a client interface. The digital assistant 120, as a kind of intelligent assistant, has the capability of intelligent conversation and information processing. The user 135 can input a conversation message in the conversation window, and the digital assistant 120 can determine a reply message based on the created configuration information and present to the user in the interaction window 132. In some embodiments, depending on the configuration of the digital assistant 120, the interaction message with the digital assistant 120 can include messages in multiple modalities, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc.

[0035] The assistant creation platform 110 and / or the assistant application platform 130 can run on suitable electronic devices. An electronic device herein can be any type of device with computing capability, including an end device or a server device. An end device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices or any combination thereof. A server device may, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. In some embodiments, the assistant creation platform 110 and / or the assistant application platform 130 can be implemented based on cloud services.

[0036] It should be understood that the structure and functionality of the environment 100 are described for illustrative purposes only and without implying any limitation on the scope of the present disclosure. For example, while FIG. 1 shows a single user interacting with the assistant creation platform 110 and a single user interacting with the assistant application platform 130, in practice multiple users can access the assistant creation platform 110 to each create a digital assistant, and each digital assistant can be used for interaction with multiple users.

[0037] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings. It should be understood that the pages / interfaces shown in the accompanying drawings are merely examples, and various page / interface designs / interfaces can actually exist. Various graphical elements in the pages / interfaces can have different arrangements and different visual representations, one or more of which can be omitted or replaced, and one or more other elements can also exist. The embodiments of the present disclosure are not limited in this respect.

[0038] The digital assistant creation process described by the embodiments of the present disclosure can be implemented in an assistant creation platform, a terminal device installed with the assistant creation platform, and / or a server corresponding to the assistant creation platform. In the examples below, for the sake of discussion, the perspective of the assistant creation platform is described, such as the assistant creation platform 110 shown in FIG. 1. The interface presented by the assistant creation platform 110 can be presented via the terminal device of the user 105, and user input can be received via the terminal device of the user 105. In this document, the user 105 who creates a digital assistant is also sometimes referred to as an assistant creator, an assistant developer, etc.

[0039] The user 105 can initiate a creation request to the assistant creation platform 110 as needed. In response to receiving the creation request, the assistant creation platform 110 presents an interface for creating a digital assistant. On this interface, the user 105 can configure the digital assistant to be created (assuming it is the digital assistant 120 shown in FIG. 1). Unlike creating a digital assistant by writing code, in the embodiments of the present disclosure, the interface for creating a digital assistant is designed to include at least one configuration area that receives configuration information of the digital assistant, and each configuration area is defined to receive a type of configuration information needed to build the digital assistant. FIG. 2 shows an example of a user interface 200 for creating the digital assistant 120 according to some embodiments of the present disclosure.

[0040] Specifically, the user interface includes at least a first configuration area for receiving setting information input in natural language. For example, the user interface 200 of FIG. 2 gives a configuration area 210, which includes an input box for receiving setting information input by the user in natural language.

[0041] The received setting information, as part of the configuration information of the digital assistant 120, will be used to generate the prompt word input of the first machine learning model based on which the digital assistant 120 determines the reply to the user. That is, the digital assistant 120 to be created will determine the user demand corresponding to the user input by means of the first machine learning model, and provide the reply to the user based on the output of the first machine learning model. The first machine learning model used by the digital assistant 120 can run locally on the assistant creation platform 110 or on a remote server. In some embodiments, the first machine learning model can be based on any appropriate model structure, including but not limited to a Transformer model, a convolutional neural network (CNN), a recurrent neural network (RNN), a deep neural network (DNN), etc. In some embodiments, the first machine learning model can be based on a language model (LM). A language model can have the ability to answer questions by learning from a large amount of corpus. The first machine learning model can also be based on other appropriate models. The specific configuration area is provided for the user to provide setting information during the creation process, and the configuration of the setting information can be completed in a natural language manner. In this way, the user can conveniently constrain the output of the model and configure a diversified digital assistant.

[0042] In some embodiments, the user interface can further include a second configuration area for receiving a configuration of at least one processing component, the configuration of the processing component indicating at least one processing component that the digital assistant 120 can use when processing a user request. In some embodiments, after the configuration of the processing component, the configuration of the processing component can be provided to the model when the created digital assistant 120 interacts with the user, so as to determine which processing component needs to be used to complete when processing the user input, and then determine the reply to the user.

[0043] Each processing component can be understood as a tool that the digital assistant 120 can call when processing a user request, and each processing component can perform a corresponding function or service. The types of processing components can be very diverse, and the user 105 can select, configure or modify from existing processing components, or can allow the user 105 to customize one or more processing components. As shown in FIG. 2, the user interface 200 for receiving a configuration of at least one processing component includes configuration areas 220, 222, 224, etc. The configuration of the processing component will be described in more detail below.

[0044] By understanding user requirements with the help of the model and setting information, and executing user requirements with the help of processing components, the digital assistant 120 will be able to have the function of interacting with users, responding to user requests. The user interface for creating a digital assistant can be templated to provide various configuration areas within the user interface for receiving configuration information of the digital assistant 120, and the user 105 can complete the customization of the digital assistant 120 without performing complex configuration, coding.

[0045] In some embodiments, the assistant creation platform 110 can provide a creation entry of a digital assistant in any appropriate user interface. The user can access the user interface for creating a digital assistant by triggering the creation entry. Based on the input of the user 105 on the user interface for creating a digital assistant, the configuration information received in the user interface can be obtained. The configuration information at least includes setting information received in the first configuration area. After completing the configuration, the user 105 is also allowed to publish the created digital assistant. In response to receiving the publishing request, the assistant creation platform 110 publishes the digital assistant 120 based on the configuration information received in the user interface for interaction with the user. As shown in FIG. 2, the user interface 200 presents a publishing control 250. In response to detecting the triggering of the publishing control 250, the assistant creation platform 110 receives the publishing request of the user, and publishes the digital assistant 120 based on the configuration information received in the user interface 200.

[0046] In some embodiments, the created digital assistant 120 can be published to a default platform to run. In some embodiments, candidate platforms can be provided for the user to select. In response to receiving the publishing request, the assistant creation platform 110 can provide at least one candidate platform, each of the at least one candidate platform supports the running of the digital assistant 120. In response to receiving the confirmation of a target platform in the at least one candidate platform, the digital assistant 120 is published to the target platform, such as the assistant application platform 130 in FIG. 1.

[0047] In some embodiments, the setting information can indicate the definition of the reply style of the digital assistant 120 to be created. By setting the reply style, the reply of the created digital assistant can be differentiated, and can exhibit a specific personality to the user. Alternatively or additionally, in some embodiments, the setting information can indicate the description of the function supported by the digital assistant 120 to be created. For example, in the configuration area 210 of the user interface 200, the user 105 can be allowed to input such setting information as “You are a movie commentator, please explain the movie plot to the user with sharp humorous language, and introduce the newly released movies.” Such setting information can guide the reply style (e.g., “sharp humor”) of the digital assistant 120, and describe the function (e.g., “movie commentary”, “explain the movie plot”, “introduce the newly released movies”) of the digital assistant 120.

[0048] In some embodiments, alternatively or additionally, the setting information can indicate at least one workflow to be created for the digital assistant 120 to perform. Each workflow can correspond to individual operations of the digital assistant 120 in performing a particular function. That is, the user 105 can be allowed to describe, in a natural language manner, how the digital assistant 120 is to perform a certain function.

[0049] In some embodiments, alternatively or additionally, the setting information can indicate at least one reply format for the digital assistant 120 to be created. The reply format can include, for example, Markdown (a lightweight markup language), etc.

[0050] It should be appreciated that the above only gives some examples of the setting information, and embodiments of the present disclosure are not limited in this regard. In fact, because the setting information is to be used to build the model for the prompt input, the user can be allowed to freely try different setting information to build a digital assistant whose reply meets the user’s expectation. For example, in the setting information, the user 105 can be allowed to input requirements for the reply language of the digital assistant 120, constraints for the reply content of the digital assistant 120 (e.g., word count for different types of replies, types of reply content, etc.).

[0051] In some embodiments, to better guide the user to complete the configuration of the digital assistant 120, setting information examples can also be provided in the user interface to guide the user to provide the setting information of the digital assistant 120. The setting information examples can be provided at a location associated with the first configuration area for receiving the setting information. As shown in FIG. 2, setting information examples 212 can be provided near the configuration area 210, which can indicate to the user the general composition of the setting information of the digital assistant 120, and can provide specific setting information of a certain digital assistant as an example for reference.

[0052] In some embodiments, one or more types of selection or configuration options of processing components can be provided for the user 105 to select, enable, or specifically configure as needed.

[0053] In some embodiments, the second configuration region can include a region for plug-in configuration, such as configuration region 220 shown in FIG. 2. In this region, at least one plug-in used by digital assistant 120 can be selected or customized by the user. Each plug-in is configured to perform a corresponding function. For example, a search plug-in can perform a data search function; a browser plug-in can provide a web browsing function; a music plug-in can provide a music search and playing function, and so on. Further, each plug-in can be considered as an atomic capability of digital assistant 110. Digital assistant 120 can invoke one or more plug-ins to handle a user request. In some embodiments, assistant creation platform 110 can provide a plug-in library for user 105 to select from which developed plug-ins. In some embodiments, alternatively or additionally, assistant creation platform 110 can provide a plug-in definition interface for user 105 to define a plug-in with a specific function as needed.

[0054] In some embodiments, the second configuration region can include a region for workflow configuration, such as configuration region 222 shown in FIG. 2. In this region, at least one workflow to be performed by digital assistant 120 can be selected or customized by the user. A workflow can not only be inputted in a natural language manner in the setting information, but also a workflow portal can be provided for user 105 to select an existing workflow or define a workflow through a dedicated interface.

[0055] In some embodiments, the second configuration region can include a region for workflow configuration, such as configuration region 224 shown in FIG. 2. In this region, at least one data set can be selected by the user, which is utilized by digital assistant 120 to determine a reply to the user. Here, the "data set" can also be referred to as "knowledge base". In determining a reply to the user, digital assistant 120 can retrieve corresponding knowledge from the configured data set for reply determination. In some embodiments, assistant creation platform 110 can allow user 105 to select from existing data sets, upload a local data set, or specify an online data set, and the like, to configure the data set of digital assistant 120.

[0056] It can be understood that the second configuration region can further include other regions, such as a region for configuring persistent storage information, a region for configuring tasks, and the like. The present disclosure does not limit this. Example 200 can further include control 226. Assistant creation platform 110 may, for example, present more second configuration regions in response to receiving a triggering operation on control 226.

[0057] As mentioned above, the digital assistant 120 can understand the user request and determine the reply to the user with the help of a model. In some embodiments, the model used by the digital assistant 120 can be a default model without configuration by the creator. In some embodiments, the creator can be allowed to select the model to be used in the process of creating the digital assistant 120. A third configuration area can be provided in the user interface for creating the digital assistant for receiving the selection of the model. The selected model is invoked to determine the reply of the digital assistant 120 to the user. As shown in FIG. 2, the user interface 200 further includes a third configuration area 230 for configuring the model, in which the user 105 can be allowed to select the model to be used.

[0058] The processing components configurable in the process of creating the digital assistant are discussed above. In specific applications, more, less or different processing components can be provided by the assistant creation platform for the creator of the digital assistant to select or configure as needed.

[0059] In some embodiments, in order to enable the user 105 creating the digital assistant to conveniently test the running effect of the created digital assistant 120 in the process of creation, a debugging area for the digital assistant can also be provided in the user interface, such as the debugging area 240 shown in FIG. 2. The debugging area 240 includes an input area 242 for receiving a debugging request for the digital assistant 120, and further includes a presentation area 244 for providing the debugging result (as well as the received debugging request) for the debugging request. The debugging area 240 can be configured in the form of an interactive window, simulating the interactive interface viewed by the interactive user of the digital assistant 120.

[0060] In the debugging process, the debugging result presented in the debugging area 240 can be determined based on the received debugging request and the current configuration information for the digital assistant 120 in the user interface 200. The user 105 can determine whether to continue modifying the configuration information or can publish the digital assistant according to whether the actual running result of the digital assistant 120 conforms to the expectation according to the debugging result. In some embodiments, in addition to providing the debugging result, the underlying running process of the digital assistant 120 determining the debugging result can also be provided for each debugging, such as the invocation of the model, the thinking process of the model, one or more plugins used, etc. This can allow the user 105 to more quickly determine whether the currently configured digital assistant conforms to the expectation.

[0061] The process of creating the digital assistant of some embodiments of the present disclosure is described above. In embodiments of the present disclosure, the assistant creation platform provides sufficient support for the constitution of the digital assistant, thereby enabling the user to conveniently, quickly, flexibly and freely create the desired digital assistant.

[0062] In embodiments of the present disclosure, the assistant creation platform 110 presents, in a user interface (e.g., the user interface 200) for creating a digital assistant, a configuration region (e.g., the configuration region 210) for receiving setting information of the digital assistant. As mentioned previously, the setting information is used to generate the prompt word input of the first machine learning model, and the reply of the digital assistant to the user is determined based on the output of the first machine learning model. The assistant creation platform 110 presents an optimization panel in response to detecting an indication of automatic optimization of the setting information of the digital assistant.

[0063] The optimization panel can include an input control for receiving an adjustment indication of the setting information. The input control can include, for example, an input box, a voice input control, an attachment upload control, or any other suitable input control. The assistant creation platform 110 can receive text type information via the input box. The assistant creation platform 110 can receive voice type information via the voice input control. The assistant creation platform 110 can receive image, video, document, or other type information via the attachment upload control. The assistant creation platform 110 can adjust the setting information based on the information received via the input control. In some embodiments, the assistant creation platform 110 can also receive a user-provided access link via the input box. The assistant creation platform 110 can automatically extract the content of the access link. For example, if the assistant creation platform 110 receives a user-provided web page link via the input box, the assistant creation platform 110 can automatically extract the web page content corresponding to the web page link.

[0064] The optimization panel can also include at least one instruction control. Each instruction control corresponds to an adjustment indication of the setting information. Each instruction control can correspond to a shortcut instruction that can facilitate the user to quickly trigger the instruction control to input the corresponding adjustment indication. The at least one instruction control and the shortcut instruction corresponding to each instruction control can be, for example, pre-defined by the user. The at least one instruction control and the shortcut instruction corresponding to each instruction control can also be, for example, determined by the assistant creation platform 110 based on historical user operations. The present disclosure does not limit the specific determination manner of the at least one instruction control and the shortcut instruction corresponding to each instruction control. The at least one instruction control can include, for example, a first instruction control indicating a global adjustment of the setting information. The at least one instruction control can also include, for example, a second instruction control indicating an adjustment of the setting information based on the debugging result of the digital assistant. The at least one instruction control can also include any other suitable instruction control, which is not limited by the present disclosure.

[0065] The assistant creation platform 110 presents the adjusted at least part of the setting information in the optimization panel based on the adjustment indication received via the optimization panel and the at least part of the setting information received in the configuration area. In some embodiments, the assistant creation platform 110 can determine the adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and the at least part of the setting information received in the configuration area. Specifically, the assistant creation platform 110 can at least provide the adjustment indication received via the optimization panel and the at least part of the setting information received in the configuration area to a second machine learning model, and determine the adjusted at least part of the setting information based on the model output returned by the second machine learning model.

[0066] The second machine learning model can be the same model as the first machine learning model, or can be a different model from the first machine learning model. The second machine learning model can also have any suitable model structure. Details of how the assistant creation platform 110 utilizes the second machine learning model to determine the adjusted at least part of the setting information in different scenarios will be described in detail below in connection with specific embodiments. After the assistant creation platform 110 determines the adjusted at least part of the setting information, the assistant creation platform 110 can present the adjusted at least part of the setting information in the optimization panel.

[0067] The assistant creation platform 110 further determines the setting information presented in the configuration area based on the acceptance indication or the rejection indication for the adjusted at least part of the setting information. For example, if the acceptance indication for the adjusted at least part of the setting information is received, the assistant creation platform 110 determines to present the adjusted at least part of the setting information in the configuration area. If the rejection indication for the adjusted at least part of the setting information is received, the assistant creation platform 110 determines to continue presenting the previous setting information (i.e., without adjusting the setting information) in the configuration area.

[0068] Details of how the setting information is adjusted will be described below in connection with FIGS. 3A-3N. FIGS. 3A-3N illustrate schematic diagrams of an example configuration area (e.g., the configuration area 210) according to some embodiments of the present disclosure.

[0069] In some embodiments, the assistant creation platform 110 can detect an automatic optimization indication for the setting information of the digital assistant in response to receiving a trigger for a predetermined interface element in a user interface (e.g., the user interface 200 shown in FIG. 2). The predetermined interface element can include at least one interface element. For example, the predetermined interface element can include a first interface element presented at a predetermined position near the configuration area, a second interface element presented in association with at least a part of the setting information, a third interface element presented at a current input position in the configuration area, and / or the like.

[0070] For the first interface element, the predetermined location near the configuration area can be any suitable location, which can be located around the configuration area or within the configuration area. Illustratively, as shown in FIG. 3A, the configuration area 210 can include an area 310 configured to present the setting information. The assistant creation platform 110 can present the first interface element 301 at a predetermined location near the configuration area 210, such as the upper right corner of the configuration area 210. The assistant creation platform 110 can detect the automatic optimization indication in response to a trigger of the first interface element 301.

[0071] In some embodiments, the assistant creation platform 110 can present an optimization panel including an input control and / or at least one instruction control in response to detecting the automatic optimization indication of the setting information of the digital assistant. Illustratively, the assistant creation platform 110 can present the configuration area 210 as shown in FIG. 3B in response to detecting the automatic optimization indication of the setting information of the digital assistant. In FIG. 3B, the configuration area 210 includes an optimization panel 320. The optimization panel 320 includes an input control, an instruction control 321 (which can be a first instruction control corresponding to a first shortcut instruction, for example) and an instruction control 322 (which can be a second instruction control corresponding to a second shortcut instruction, for example). The input control can include an input box 323, a voice input control 324 and an attachment upload control 325, for example.

[0072] In some embodiments, the assistant creation platform 110 can automatically adjust the setting information to generate adjusted setting information in response to receiving a trigger of the instruction control 321 in the optimization panel. For example, the assistant creation platform 110 can provide the first shortcut instruction corresponding to the instruction control 321 and at least a portion of the setting information received by the configuration area to a second machine learning model and instruct the second machine learning model to expand the setting information to expand the relatively brief content in the setting information to relatively rich and professional content, for example. For another example, the assistant creation platform 110 can also provide the first shortcut instruction and at least a portion of the setting information received by the configuration area to the second machine learning model and instruct the second machine learning model to adjust the structure of the setting information. In some embodiments, the assistant creation platform 110 can also determine a modification suggestion for the setting information by means of the second machine learning model only, and the assistant creation platform 110 can provide the modification suggestion to the user to adjust the setting information based on the modification suggestion by the user.

[0073] For example, if the assistant creation platform 110 detects the automatic optimization indication in response to the triggering of the first interface element, and receives the triggering of the instruction control 321, since the first interface element is directed to the whole of the setting information in the configuration region, the assistant creation platform 110 can determine the adjusted setting information based on the first shortcut instruction corresponding to the instruction control 321 and the whole of the received setting information in the configuration region.

[0074] In some embodiments, since the second instruction control (e.g., the instruction control 322) indicates that the setting information is to be adjusted based on the debugging result of the digital assistant, in order to determine which part of the debugging result the user is not satisfied with and determine what kind of debugging result the user expects to obtain, the assistant creation platform 110 can further present a first input control and a second input control in the optimization panel in response to receiving the triggering of the second instruction control in the optimization panel. The assistant creation platform 110 can receive, via the first input control, the content to be adjusted in the debugging result of the digital assistant, and can receive, via the second input control, the adjustment target for the content to be adjusted.

[0075] For example, as shown in FIGS. 3B and 3C, the assistant creation platform 110 may, for example, present the configuration region 210 as shown in FIG. 3C in response to receiving the triggering of the instruction control 322 in the optimization panel 320 of FIG. 3B. In FIG. 3C, the assistant creation platform 110 can present an input control 326 (i.e., the first input control) and an input control 327 (i.e., the second input control) in the optimization panel 320. Taking an example that the user is not satisfied with the content A of the debugging result and expects the debugging result to include the content B, the assistant creation platform 110 can receive the text “content A” via the input control 326 and receive the text “the debugging result does not include content A and includes content B” via the input control 327. The optimization panel 320 may, for example, further include a control 328. The assistant creation platform 110 may, for example, determine the adjusted at least part of the setting information based on the content received via the input control 326 and the content received via the input control 327 in response to receiving the triggering of the control 328.

[0076] Thus, if the user finds the debugging result of the digital assistant unsatisfactory during the debugging process, the user has clear adjustment expectations but does not know which aspects of the setting information of the digital assistant to adjust specifically, the user can trigger the second instruction control and enter the place where the user is not satisfied with the debugging result and the adjustment expectation via the first input control and the second input control. The assistant creation platform 110 can then automatically adjust the setting information based on the debugging result based on the content entered by the user, which can achieve convenient and efficient adjustment of the setting information.

[0077] In some embodiments, if the trigger to the second instruction control is received, the assistant creation platform 110 can provide, to a second machine learning model, at least a portion of the setting information received in the configuration area, the content to be adjusted in the debugging result of the digital assistant received via the first input control, the adjustment target for the content to be adjusted received via the second input control, and the second shortcut instruction corresponding to the second instruction control, and determine the adjusted at least a portion of the setting information based on a model output provided by the second machine learning model. Illustratively, if the assistant creation platform 110 detects the automatic optimization indication in response to the trigger to the first interface element, and the trigger to the second instruction control is received, the assistant creation platform 110 can determine the adjusted setting information based on the second shortcut instruction, the content to be adjusted in the debugging result of the digital assistant, the adjustment target for the content to be adjusted, and the entirety of the setting information received in the configuration area.

[0078] In some embodiments, the assistant creation platform 110 can determine the adjusted at least a portion of the setting information based on the received content to be adjusted and adjustment target, at least one historical debugging instruction to the digital assistant, and at least a portion of the setting information received in the configuration area, in response to receiving the trigger to the second instruction control in the optimization panel. The at least one historical debugging instruction here can include, for example, at least one historical adjustment conversation between the user and the digital assistant. The assistant creation platform 110 can provide, for example, the adjustment indication received via the optimization panel, the received content to be adjusted and adjustment target, at least one historical debugging instruction to the digital assistant, and at least a portion of the setting information received in the configuration area to a second machine learning model, and determine the adjusted at least a portion of the setting information based on a model output returned by the second machine learning model.

[0079] Further, if the assistant creation platform 110 detects the automatic optimization indication in response to the trigger to the first interface element, the assistant creation platform 110 can present the adjusted setting information in the optimization panel. The assistant creation platform 110 can present, for example, the adjusted setting information and another input control in the optimization panel, the another input control being used to receive an input of a further adjustment indication to the setting information. Illustratively, as shown in FIG. 3D, the assistant creation platform 110 can present the configuration area 210 as shown in FIG. 3D in response to determining the adjusted setting information. In FIG. 3D, the assistant creation platform 110 can present the adjusted setting information and another input control in the optimization panel 320. The another input control can also include, for example, the input box 336, the voice input control, the attachment upload control, etc. The assistant creation platform 110 can further adjust the adjusted setting information based on an adjustment indication received via the another input control, for example.

[0080] In some embodiments, the assistant creation platform 110 can also present an accept control and a reject control in the optimization panel in association with the adjusted setting information. The assistant creation platform 110 can determine, in response to receiving a trigger for the accept control, that an accept indication is received for at least a portion of the adjusted setting information. The accept control can include, for example, a replace control, an insert control, and the like. In FIG. 3D, the assistant creation platform 110 can also present a replace control 329 and a reject control 331 in the optimization panel in association with the adjusted setting information. The assistant creation platform 110 can determine, in response to receiving a trigger for the replace control 329, that an accept indication is received for the adjusted setting information. The assistant creation platform 110 can determine, in response to receiving the accept indication, that the adjusted setting information is accepted and present the adjusted setting information in the configuration area. The assistant creation platform 110 can replace, for example, the previous setting information with the adjusted setting information to present the adjusted setting information in the configuration area.

[0081] As shown in FIGS. 3D and 3E, the assistant creation platform 110 can present the configuration area 210 as shown in FIG. 3E in response to receiving a trigger for the replace control 329 in FIG. 3D. The assistant creation platform 110 can replace, in the configuration area 210, the previous setting information with the adjusted setting information to present the adjusted setting information in the configuration area.

[0082] The assistant creation platform 110 can determine, in response to receiving a trigger for the reject control, that a reject indication is received for at least a portion of the adjusted setting information. In FIG. 3D, the assistant creation platform 110 can determine, in response to receiving a trigger for the reject control 331, that a reject indication is received for the adjusted setting information. The assistant creation platform 110 can determine, for example, in response to receiving the reject indication, that the setting information is not adjusted and continue to maintain the previous setting information.

[0083] In some embodiments, the assistant creation platform 110 can also present, in the optimization panel, a regenerate control for triggering a regeneration of at least a portion of the adjusted setting information in association with the at least a portion of the adjusted setting information. The assistant creation platform 110 can regenerate, in response to receiving a trigger for the regenerate control, the at least a portion of the adjusted setting information and present the regenerated at least a portion of the adjusted setting information in the optimization panel. In FIG. 3D, the assistant creation platform 110 can also present, in the optimization panel 320, a regenerate control 332 for triggering a regeneration of the adjusted setting information in association with the adjusted setting information. The assistant creation platform 110 can regenerate, in response to receiving a trigger for the regenerate control 332, the adjusted setting information and present the regenerated adjusted setting information in the optimization panel 320.

[0084] The assistant creation platform 110 can also present, in the optimization panel, a copy control for copying the adjusted at least part of the setting information in association with the adjusted at least part of the setting information. The assistant creation platform 110 can copy the adjusted at least part of the setting information in the optimization panel in response to receiving a trigger of the copy control. In FIG. 3D, the assistant creation platform 110 can also present, in the optimization panel 320, a copy control 333 for copying the adjusted setting information in association with the adjusted setting information. The assistant creation platform 110 can copy the adjusted setting information in the optimization panel 320 in response to receiving a trigger of the copy control 333.

[0085] The assistant creation platform 110 can also present, in the optimization panel 320, at least one feedback control for triggering uploading of at least one type of feedback information on the adjusted at least part of the setting information in association with the adjusted at least part of the setting information. In FIG. 3D, the assistant creation platform 110 can also present, in the optimization panel 320, at least one feedback control for triggering uploading of at least one type of feedback information on the adjusted setting information in association with the adjusted setting information. The at least one feedback control can include, for example, a like control 334 and a dislike control 335. The assistant creation platform 110 can determine that the user is satisfied with the adjusted setting information in response to receiving a trigger of the like control 334. The assistant creation platform 110 can determine that the user is not satisfied with the adjusted setting information in response to receiving a trigger of the dislike control 335. The assistant creation platform 110 can adjust the setting information in a subsequent adjustment of the setting information based on the adjusted at least part of the setting information that the user is satisfied with. For example, an adjusted style that the user prefers can be determined based on the adjusted at least part of the setting information that the user is satisfied with, and the setting information can be adjusted in a subsequent adjustment based on this adjusted style. The assistant creation platform 110 can avoid generating similar setting information in a subsequent adjustment based on the adjusted at least part of the setting information that the user is not satisfied with.

[0086] In some embodiments, if the assistant creation platform 110 does not successfully determine the adjusted at least part of the setting information (e.g., the adjusted setting information is not successfully determined due to network reasons), the assistant creation platform 110 can present the configuration area 210 shown in FIG. 3F. In FIG. 3F, the assistant creation platform 110 can present, in the optimization panel 320, a prompt text (e.g., the text “Sorry, something went wrong. Please try again later”) that prompts that the adjusted at least part of the setting information is not successfully determined.

[0087] In some embodiments, in addition to providing the first interface element for triggering the optimization of the overall setting information at a fixed position of the configuration area, the assistant creation platform 110 can also allow the user to perform targeted automatic optimization on the selected portion of the setting information. The assistant creation platform 110 can further present the second interface element in association with the at least a portion of the setting information for triggering the automatic optimization indication in response to receiving the selection operation on the at least a portion of the setting information. The assistant creation platform 110 may, for example, directly present the second interface element in response to receiving the selection operation on the at least a portion of the setting information. Alternatively or additionally, the assistant creation platform 110 may, for example, also present the second interface element in response to a specific user operation after receiving the selection operation on the at least a portion of the setting information. The specific user operation may, for example, include a hover operation, a click operation, etc. on the at least a portion of the setting information. Embodiments of the present disclosure do not limit thereto. As shown in FIG. 3G, the assistant creation platform 110 can present the second interface element 302 in association with the setting information 303 in response to receiving the selection operation on the setting information 303. Similar to the first interface element, the assistant creation platform 110 can detect the automatic optimization indication in response to the triggering of the second interface element 302.

[0088] The assistant creation platform 110 can present an optimization panel including input controls and / or at least one instruction control in response to detecting the automatic optimization indication on the setting information of the digital assistant. As shown in FIG. 3H, the assistant creation platform 110 can present the optimization panel 340 in response to detecting the automatic optimization indication on the setting information of the digital assistant. The optimization panel 340 can include input controls such as an input box, a voice input control, and an attachment upload control, etc. It can be understood that although not shown in the figure, the optimization panel 340 can also include the predetermined at least one instruction control.

[0089] In some embodiments, if the assistant creation platform 110 detects the automatic optimization indication in response to the triggering of the second interface element, the assistant creation platform 110 can determine the adjusted at least a portion of the setting information based on the adjustment indication received via the optimization panel and the selected at least a portion of the setting information. For example, if the user selects content A in the setting information, the assistant creation platform 110 can determine the adjusted content A based on the adjustment indication received via the optimization panel and the content A in the setting information. The assistant creation platform 110 may, for example, provide the selected setting information and the adjustment indication to a second machine learning model to determine the adjusted at least a portion of the setting information by utilizing the second machine learning model.

[0090] In some embodiments, to improve the accuracy of determining the adjusted at least part of the setting information, the assistant creation platform 110 can provide the entirety of the setting information, the selected setting information, and the adjustment indication to a second machine learning model. The assistant creation platform 110 may, for example, determine an identification (e.g., a paragraph number, a line number, etc.) for indicating the selected setting information, and provide the identification, the entirety of the setting information, and the adjustment indication to the second machine learning model. The second machine learning model may, for example, determine the selected setting information based on the identification and the entirety of the setting information. In this way, by providing the entirety of the setting information to the second machine learning model, the second machine learning model can learn the context of the selected setting information, and determine the adjusted at least part of the setting information based on the context, which can improve the accuracy of determining the adjusted at least part of the setting information.

[0091] The assistant creation platform 110 may, for example, present the configuration region 210 as shown in FIG. 31 after determining the adjusted at least part of the setting information. The assistant creation platform 110 may, for example, present the adjusted at least part of the setting information in the optimization panel 340 of the configuration region 210, an accept control (e.g., a replace control 341), a reject control 342, a copy control, a regenerate control, at least one feedback control, and an input control 343 for receiving a further adjustment indication of the setting information. The assistant creation platform 110 may, for example, determine that the accept indication of the adjusted at least part of the setting information is received in response to receiving a trigger of the replace control 341. The assistant creation platform 110 may, in response to receiving the accept indication of the adjusted at least part of the setting information, replace the selected at least part in the configuration region with the adjusted at least part of the setting information. For example, the content A in the setting information in the configuration region can be replaced with the adjusted content A. As shown in FIG. 3J, the assistant creation platform 110 can replace the selected setting information 303 with the adjusted at least part of the setting information. The assistant creation platform 110 can present the setting information 304 in the configuration region 210, which is the adjusted at least part of the setting information.

[0092] In some embodiments, the assistant creation platform 110 can also automatically optimize the setting information in the vicinity of the current input location in the configuration region based on the operation of the user on the current input location in the configuration region. The assistant creation platform 110 can further present a third interface element at the current input location in the configuration region for triggering the automatic optimization indication. The assistant creation platform 110 may, for example, present an input cursor in the configuration region indicating the current input location. The interface element for triggering the automatic optimization indication (i.e., the third interface element) can be presented along with the input cursor to facilitate the user’s ability to trigger the presentation of the optimization panel at any time as needed. The assistant creation platform 110 may, for example, present the third interface element directly in the vicinity of the input cursor. Alternatively or additionally, the assistant creation platform 110 may, for example, also present the third interface element in response to receiving a particular user operation on the input cursor. As shown in FIG. 3K, the assistant creation platform 110 can present the third interface element 306 at the input cursor 305 in the configuration region 210 indicating the current input location.

[0093] Similar to the first interface element, the second interface element, the assistant creation platform 110 can detect the automatic optimization indication in response to the triggering of the third interface element 306. The assistant creation platform 110 can present the optimization panel including the input control and / or the at least one instruction control in response to detecting the automatic optimization indication of the setting information of the digital assistant. As shown in FIG. 3L, the assistant creation platform 110 can present the optimization panel 350 in response to detecting the automatic optimization indication of the setting information of the digital assistant. The optimization panel 350 can include the input control such as the input box, the voice input control, and the attachment upload control. It can be appreciated that although not shown in the figure, the optimization panel 350 can also include the predetermined at least one instruction control. In some embodiments, if the assistant creation platform 110 detects the automatic optimization indication in response to the triggering of the third interface element, the assistant creation platform 110 can determine the additional portion of the setting information based on the adjustment indication received via the optimization panel and the at least a portion of the setting information in the vicinity of the current input location in the configuration region. The assistant creation platform 110 may, for example, provide the adjustment indication received via the optimization panel and the at least a portion of the setting information in the vicinity of the current input location in the configuration region to the second machine learning model to determine the additional portion of the setting information using the second machine learning model.

[0094] In some embodiments, to improve the accuracy of determining the additional portion of the setting information, the assistant creation platform 110 can provide the entirety of the setting information, the adjustment indication received via the optimization panel, and at least a portion of the setting information in the vicinity of the current input position in the configuration area to a second machine learning model. The assistant creation platform 110 may, for example, also determine an identification (e.g., a paragraph number, a line number, etc.) for indicating the at least a portion of the setting information in the vicinity of the current input position, and provide the identification, the entirety of the setting information, and the adjustment indication to the second machine learning model. The second machine learning model may, for example, determine the at least a portion of the setting information in the vicinity of the current input position based on the identification and the entirety of the setting information. In this way, by providing the entirety of the setting information to the second machine learning model, the second machine learning model can be enabled to learn the context of the selected setting information, and determine the additional portion of the setting information based on the context, which can improve the accuracy of determining the additional portion of the setting information.

[0095] The assistant creation platform 110 may, for example, present the configuration area 210 as shown in FIG. 3M after determining the additional portion of the setting information. The assistant creation platform 110 may, for example, present the additional portion of the setting information in the optimization panel 350 of the configuration area 210, an accept control (e.g., an insert control 351), a reject control 352, a copy control, a regenerate control, at least one feedback control, and an input control 353 for receiving a further adjustment indication of the setting information. The assistant creation platform 110 may, for example, determine that an accept indication of the additional portion of the setting information is received in response to receiving a trigger of the insert control 351. The assistant creation platform 110 may, in response to receiving the accept indication of the additional portion of the setting information, insert the additional portion of the setting information at the input cursor 305 indicating the current input position in the configuration area 210. As shown in FIG. 3N, the assistant creation platform 110 may, for example, insert the setting information 307, which is the additional portion of the setting information, at the input cursor 305 in the configuration area 210.

[0096] To sum up, according to the embodiments of the present disclosure, in the creation process of the digital assistant, the user is facilitated to conveniently and quickly adjust the prompt word input, so as to correspondingly adjust the reply result of the digital assistant.

[0097] FIG. 4 shows a flowchart of a process 400 for digital assistant creation, according to some embodiments of the present disclosure. The process 400 can be implemented at the assistant creation platform 110. The process 400 is described below with reference to FIG. 1.

[0098] At block 410, the assistant creation platform 110 presents, in the user interface for creating the digital assistant, a configuration region for receiving setting information of the digital assistant, the setting information being used to generate the prompt word input of the first machine learning model, and the digital assistant generating a reply to the user based on the output of the first machine learning model.

[0099] At block 420, the assistant creation platform 110 presents, in response to detecting the automatic optimization indication of the setting information of the digital assistant, an optimization panel, the optimization panel including at least one of: an input control for receiving an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information.

[0100] At block 430, the assistant creation platform 110 presents, in the optimization panel, an adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and at least a part of the setting information received in the configuration region.

[0101] At block 440, the assistant creation platform 110 determines the setting information presented in the configuration region based on an acceptance indication or a rejection indication of the adjusted at least part of the setting information.

[0102] In some embodiments, the process 400 further includes: in response to receiving a trigger of a predetermined interface element in the user interface, detecting the automatic optimization indication of the setting information of the digital assistant.

[0103] In some embodiments, the predetermined interface element includes one of: a first interface element, the first interface element being presented at a predetermined position adjacent to the configuration region, a second interface element, the second interface element being presented in association with at least a part of the setting information in response to receiving a selection operation of the at least a part of the setting information, or a third interface element, the third interface element being presented at a current input position in the configuration region.

[0104] In some embodiments, the automatic optimization indication is detected in response to the trigger of the first interface element, and wherein presenting the adjusted at least part of the setting information includes: determining the adjusted setting information based on the adjustment indication received via the optimization panel and the entirety of the setting information received in the configuration region; and presenting the adjusted setting information in the optimization panel; and wherein determining the setting information presented in the configuration region includes: in response to receiving an acceptance indication of the adjusted setting information, replacing the setting information in the configuration region with the adjusted setting information.

[0105] In some embodiments, the automatic optimization indication is detected in response to a trigger of the second interface element, and wherein presenting the adjusted at least portion of the setting information comprises: determining the adjusted at least portion of the setting information based on the adjustment indication received via the optimization panel and the at least portion of the setting information selected, and wherein determining the setting information presented in the configuration region comprises: in response to receiving an acceptance indication of the adjusted at least portion of the setting information, replacing the selected at least portion in the configuration region with the adjusted at least portion of the setting information.

[0106] In some embodiments, the automatic optimization indication is detected in response to a trigger of the third interface element, and wherein presenting the adjusted at least portion of the setting information comprises: determining an additional portion of the setting information based on the adjustment indication received via the optimization panel and the at least portion of the setting information near the current input location in the configuration region, and presenting the additional portion of the setting information in the optimization panel, and wherein determining the setting information presented in the configuration region comprises: in response to receiving an acceptance indication of the additional portion of the setting information, inserting the additional portion of the setting information at the current input location in the configuration region.

[0107] In some embodiments, presenting the adjusted at least portion of the setting information comprises: providing at least the adjustment indication received via the optimization panel and the at least portion of the setting information received in the configuration region to a second machine learning model; determining the adjusted at least portion of the setting information based on an output of the second machine learning model; and presenting the adjusted at least portion of the setting information.

[0108] In some embodiments, presenting the adjusted at least portion of the setting information in the optimization panel comprises presenting the adjusted at least portion of the setting information and another input control in the optimization panel, the other input control to receive an input comprising a further adjustment indication to the setting information.

[0109] In some embodiments, the acceptance control and the rejection control are presented in the optimization panel in association with the adjusted at least portion of the setting information, the process 400 further comprising: in response to receiving a trigger of the acceptance control, determining that an acceptance indication of the adjusted at least portion of the setting information is received; in response to receiving a trigger of the rejection control, determining that a rejection indication of the adjusted at least portion of the setting information is received.

[0110] In some embodiments, the presenting the at least one portion of the adjusted setting information in the optimization panel includes presenting at least one of a copy control for copying the at least one portion of the adjusted setting information, a regeneration control for triggering a regeneration of the at least one portion of the adjusted setting information, or at least one feedback control for triggering an upload of at least one type of feedback information on the at least one portion of the adjusted setting information.

[0111] In some embodiments, the at least one instruction control includes at least one of a first instruction control indicating a global adjustment on the setting information, or a second instruction control indicating an adjustment on the setting information based on a debugging result of the digital assistant.

[0112] In some embodiments, the process 400 further includes: in response to receiving a trigger on the second instruction control in the optimization panel, presenting a first input control and a second input control in the optimization panel; receiving, via the first input control, content to be adjusted in the debugging result of the digital assistant; and receiving, via the second input control, an adjustment target for the content to be adjusted.

[0113] In some embodiments, the presenting the at least one portion of the adjusted setting information includes determining the at least one portion of the adjusted setting information based on the received content to be adjusted and adjustment target, at least one historical debugging instruction of the digital assistant, and at least a portion of the setting information received in the configuration area.

[0114] In some embodiments, the input control includes at least one of an input box, a voice input control, and an attachment upload control.

[0115] Embodiments of the present disclosure also provide corresponding apparatuses for implementing the above-described methods or processes. FIG. 5 shows a schematic structural block diagram of an apparatus 500 for digital assistant creation, according to some embodiments of the present disclosure. The apparatus 500 may, for example, be implemented in or included in the assistant creation platform 110. Various modules / components in the apparatus 500 can be implemented by hardware, software, firmware, or any combination thereof.

[0116] As shown, the apparatus 500 includes a configuration area presentation module 510 configured to present, in a user interface for creating a digital assistant, a configuration area for receiving setting information of the digital assistant, the setting information being used to generate a prompt word input of a first machine learning model, and the digital assistant generating a reply to a user based on an output of the first machine learning model.

[0117] The apparatus 500 further includes an optimization panel presentation module 520 configured to, in response to detecting the automatic optimization indication of the setting information of the digital assistant, present an optimization panel, the optimization panel including at least one of: an input control for receiving an input of an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information.

[0118] The apparatus 500 further includes a setting information presentation module 530 configured to, based on the adjustment indication received via the optimization panel and at least a portion of the setting information received in the configuration region, present the adjusted at least a portion of the setting information in the optimization panel. The apparatus 500 further includes a setting information determination module 540 configured to, based on an acceptance indication or a rejection indication of the adjusted at least a portion of the setting information, determine the setting information presented in the configuration region.

[0119] In some embodiments, the apparatus 500 further includes an indication detection module configured to, in response to receiving a trigger of a predetermined interface element in the user interface, detect the automatic optimization indication of the setting information of the digital assistant.

[0120] In some embodiments, the predetermined interface element includes one of: a first interface element presented at a predetermined position in proximity to the configuration region, a second interface element presented in association with at least a portion of the setting information in response to receiving a selection operation of the at least a portion of the setting information, or a third interface element presented at a current input position in the configuration region.

[0121] In some embodiments, the automatic optimization indication is detected in response to the trigger of the first interface element, and the setting information presentation module 530 includes: a first determination module configured to, based on the adjustment indication received via the optimization panel and the entirety of the setting information received in the configuration region, determine the adjusted setting information; and a first presentation module configured to present the adjusted setting information in the optimization panel; and the setting information determination module 540 includes: a first replacement module configured to, in response to receiving an acceptance indication of the adjusted setting information, replace the setting information in the configuration region with the adjusted setting information.

[0122] In some embodiments, the automatic optimization indication is detected in response to a trigger of the second interface element, and the setting information presentation module 530 includes: a second determination module configured to determine an adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and the selected at least part of the setting information; and the setting information determination module 540 includes: a second replacement module configured to replace the selected at least part in the configuration region with the adjusted at least part of the setting information in response to receiving an acceptance indication of the adjusted at least part of the setting information.

[0123] In some embodiments, the automatic optimization indication is detected in response to a trigger of the third interface element, and the setting information presentation module 530 includes: a third determination module configured to determine an additional part of the setting information based on the adjustment indication received via the optimization panel and at least a part of the setting information in a vicinity of the current input position in the configuration region; and a second presentation module configured to present the additional part of the setting information in the optimization panel; and the setting information determination module 540 includes: an insertion module configured to insert the additional part of the setting information at the current input position in the configuration region in response to receiving an acceptance indication of the additional part of the setting information.

[0124] In some embodiments, the setting information presentation module 530 includes: a providing module configured to provide at least the adjustment indication received via the optimization panel and the at least part of the setting information received in the configuration region to a second machine learning model; a fourth determination module configured to determine an adjusted at least part of the setting information based on a model output returned by the second machine learning model; and a third presentation module configured to present the adjusted at least part of the setting information.

[0125] In some embodiments, the setting information presentation module 530 includes: a fourth presentation module configured to present the adjusted at least part of the setting information and another input control in the optimization panel, the other input control being used to receive an input of a further adjustment indication of the setting information.

[0126] In some embodiments, the acceptance control and the rejection control are presented in the optimization panel in association with the adjusted at least part of the setting information, and the apparatus 500 further includes: an acceptance indication determination module configured to determine that an acceptance indication of the adjusted at least part of the setting information is received in response to receiving a trigger of the acceptance control; and a rejection indication determination module configured to determine that a rejection indication of the adjusted at least part of the setting information is received in response to receiving a trigger of the rejection control.

[0127] In some embodiments, at least one of the following is presented in the optimization panel in association with the adjusted at least part of the setting information: a copy control for copying the adjusted at least part of the setting information, a regeneration control for triggering regeneration of the adjusted at least part of the setting information, or at least one feedback control for triggering uploading of at least one type of feedback information on the adjusted at least part of the setting information.

[0128] In some embodiments, the at least one instruction control comprises at least one of: a first instruction control indicating a global adjustment on the setting information, or a second instruction control indicating an adjustment on the setting information based on a debugging result of the digital assistant.

[0129] In some embodiments, the apparatus 500 further comprises: an input control presentation module configured to, in response to receiving a trigger on the second instruction control in the optimization panel, present a first input control and a second input control in the optimization panel; a content to be adjusted receiving module configured to receive, via the first input control, content to be adjusted in the debugging result of the digital assistant; and an adjustment target receiving module configured to receive, via the second input control, an adjustment target for the content to be adjusted.

[0130] In some embodiments, the setting information presentation module 530 comprises: a fifth determination module configured to determine the adjusted at least part of the setting information based on the received content to be adjusted and adjustment target, at least one historical debugging instruction of the digital assistant, and at least part of the setting information received in the configuration area.

[0131] In some embodiments, the input control comprises at least one of an input box, a voice input control, and an attachment uploading control.

[0132] The units and / or modules included in the apparatus 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, e.g., machine executable instructions stored on a storage medium. In addition to or alternatively, some or all of the units and / or modules in the apparatus 500 can be implemented at least partially by one or more hardware logic components. As an example and not by way of limitation, example types of 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), etc.

[0133] FIG. 6 illustrates a block diagram of an electronic device 600 in which one or more embodiments of the disclosure can be implemented. It should be understood that the electronic device 600 illustrated in FIG. 6 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 600 illustrated in FIG. 6 can include or be implemented as the assistant creation platform 110 of FIG. 1, or the apparatus 500 of FIG. 5.

[0134] As illustrated in FIG. 6, the electronic device 600 is in the form of a general electronic device. Components of the electronic device 600 can include, but are not limited to, one or more processors 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processor 610 can be a real or virtual processor and is capable of performing various processing according to programs stored in the memory 620. In a multi-processor system, multiple processors perform computer-executable instructions in parallel to improve parallel processing capabilities of the electronic device 600.

[0135] The electronic device 600 typically includes a number of computer storage media. Such media can be any available media that is accessible by the electronic device 600 and includes both volatile and non-volatile media, removable and non-removable media. The memory 620 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 can be a removable or non-removable media and can include machine-readable media, such as a flash drive, a magnetic disk, or any other media that can be used to store information and / or data and that can be accessed by the electronic device 600.

[0136] The electronic device 600 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 6, a disk drive and a disk drive interface can be provided for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive and disk drive interface can be provided for reading from or writing to a removable, non-volatile optical disk (e.g., a "CD-ROM" or "DVD"). In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 620 can include a computer program product 625 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0137] The communication unit 640 enables communication through communication media with other electronic devices. Additionally, the functionality of the components of the electronic device 600 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating over a communication connection. As such, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0138] The input device 650 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 660 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 can also communicate with one or more external devices (not shown), such as a storage device, a display device, etc., through the communication unit 640, as necessary, with one or more devices that enable a user to interact with the electronic device 600, or with any device (e.g., a network card, a modem, etc.) that enables the electronic device 600 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0139] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0140] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0141] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0142] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0143] The flow diagrams and block diagrams in the attached figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flow diagrams and block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logic functions (s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or acts or combinations of

[0144] implementations have been described above, the description is intended to be illustrative, and not restrictive, and is not intended to exclude other implementations from the scope of the implementations disclosed herein. Many modifications and variations to the implementations described herein are possible and are within the scope of the implementations described herein. The order or sequence of any process or method can be different from that described. Furthermore, any features or combinations of features in the present disclosure are meant to be exemplary and are not meant to suggest that the features are exhaustive or that the combinations are the only ones that can be made. A variety of alternatives and equivalents will be apparent to those of ordinary skill in the art. The terminology used by the inventor in this disclosure has been chosen for reasons of readability and inclusivity, to make a disclosure suitable for use by others skilled in the art.

Claims

1. A method of digital assistant creation, comprising: presenting, in a user interface for creating a digital assistant, a configuration area for receiving setting information of the digital assistant, the setting information being used to generate a prompt word input of a first machine learning model, wherein the digital assistant generates a reply to a user based on an output of the first machine learning model; in response to detecting an automatic optimization indication of the setting information of the digital assistant, presenting an optimization panel, the optimization panel including at least one of: an input control for receiving an input of an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information; presenting, in the optimization panel, an adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and at least a part of the setting information received in the configuration area; determining the setting information presented in the configuration area based on an acceptance indication or a rejection indication of the adjusted at least part of the setting information.

2. The method of claim 1, further comprising: detecting the automatic optimization indication of the setting information of the digital assistant in response to receiving a trigger of a predetermined interface element in the user interface.

3. The method of claim 2, wherein the predetermined interface element includes one of: a first interface element presented at a predetermined position adjacent to the configuration area, a second interface element presented in association with at least a part of the setting information in response to receiving a selection operation of the at least a part of the setting information, or a third interface element presented at a current input position in the configuration area.

4. The method of claim 3, wherein the automatic optimization indication is detected in response to a trigger of the first interface element, and wherein presenting the adjusted at least part of the setting information includes: determining adjusted setting information based on the adjustment indication received via the optimization panel and an entirety of the setting information received in the configuration area; and presenting the adjusted setting information in the optimization panel; and wherein determining the setting information presented in the configuration area includes: in response to receiving an acceptance indication of the adjusted setting information, replacing the setting information in the configuration area with the adjusted setting information.

5. The method of claim 3, wherein the automatic optimization indication is detected in response to a trigger of the second interface element, and wherein presenting the adjusted at least part of the setting information includes: determining the adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and the at least a part of the setting information being selected; and wherein determining the setting information presented in the configuration area includes: ​ ​ ​ In response to receiving an acceptance indication of the adjusted at least one portion of the setting information, replacing the selected at least one portion in the configuration region with the adjusted at least one portion of the setting information.

6. The method of claim 4, wherein the automatic optimization indication is detected in response to a trigger of the third interface element, and wherein presenting the adjusted at least one portion of the setting information comprises: determining an additional portion of the setting information based on an adjustment indication received via the optimization panel and at least one portion of the setting information proximate to a current input location in the configuration region; and presenting the additional portion of the setting information in the optimization panel; and wherein determining the setting information to present in the configuration region comprises: in response to receiving an acceptance indication of the additional portion of the setting information, inserting the additional portion of the setting information at the current input location in the configuration region.

7. The method of claim 1, wherein presenting the adjusted at least one portion of the setting information comprises: providing at least an adjustment indication received via the optimization panel and at least one portion of the setting information received in the configuration region to a second machine learning model; determining the adjusted at least one portion of the setting information based on an output of the second machine learning model; and presenting the adjusted at least one portion of the setting information.

8. The method of claim 1, wherein presenting the adjusted at least one portion of the setting information in the optimization panel comprises: presenting the adjusted at least one portion of the setting information and another input control in the optimization panel, the other input control to receive an input comprising a further adjustment indication to the setting information.

9. The method of claim 1, wherein presenting an acceptance control and a rejection control in the optimization panel in association with the adjusted at least one portion of the setting information, the method further comprising: in response to receiving a trigger to the acceptance control, determining that the acceptance indication of the adjusted at least one portion of the setting information is received, or in response to receiving a trigger to the rejection control, determining that a rejection indication to the adjusted at least one portion of the setting information is received.

10. The method of claim 1, wherein presenting at least one of the following in the optimization panel in association with the adjusted at least one portion of the setting information: a copy control to copy the adjusted at least one portion of the setting information, a regenerate control to trigger a regeneration of the adjusted at least one portion of the setting information, or at least one feedback control to trigger an upload of at least one type of feedback information to the adjusted at least one portion of the setting information.

11. The method of claim 1, wherein the at least one instruction control comprises at least one of: a first instruction control indicating a global adjustment to the setting information, or a second instruction control indicating a local adjustment to the setting information. a second instruction control indicating to adjust the setting information based on a debugging result of the digital assistant. 12.The method of claim 11, further comprising: in response to receiving a trigger of the second instruction control in the optimization panel, presenting a first input control and a second input control in the optimization panel; receiving, via the first input control, an adjusted content in the debugging result of the digital assistant; and receiving, via the second input control, an adjustment target for the adjusted content. 13.The method of claim 12, wherein presenting the adjusted at least part of the setting information comprises: determining the adjusted at least part of the setting information based on the received adjusted content and the adjustment target, at least one historical debugging instruction of the digital assistant, and at least part of the setting information received in the configuration area. 14.The method of claim 1, wherein the input control comprises at least one of an input box, a voice input control, and an attachment upload control. 15.An apparatus for digital assistant creation, comprising: a configuration area presenting module configured to present, in a user interface for creating a digital assistant, a configuration area for receiving setting information of the digital assistant, the setting information being used to generate a prompt word input of a first machine learning model, wherein the digital assistant generates a reply to a user based on an output of the first machine learning model; an optimization panel presenting module configured to present, in response to detecting an automatic optimization indication of the setting information of the digital assistant, an optimization panel, the optimization panel comprising at least one of: an input control for receiving an adjustment indication of the setting information, at least one instruction control, each instruction control corresponding to an adjustment indication of the setting information; a setting information presenting module configured to present, in the optimization panel, an adjusted at least part of the setting information based on the adjustment indication received via the optimization panel and at least part of the setting information received in the configuration area; a setting information determining module configured to determine the setting information presented in the configuration area based on an acceptance indication or a rejection indication of the adjusted at least part of the setting information. 16.An electronic device, comprising: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, causing the electronic device to perform the method according to any one of claims 1-14. 17.A computer-readable storage medium having computer-executable instructions stored thereon that are executable by a processor to implement the method according to any one of claims 1-14.

18. A computer program product, the computer program product being tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method of any one of claims 1-14.

Images