Method, device and equipment for interactive dialogue and storage medium

Abstract

According to the embodiment of the invention, a method, a device and equipment for interactive dialogue and a storage medium are provided. The method comprises the following steps: based on user input to a digital assistant, determining whether a user demand indicated by the user input meets corresponding predetermined conditions in multiple dimensions; presenting a group of queries associated with a first dimension in an interactive form in response to the user demand not satisfying a predetermined condition for the first dimension on the first dimension in the plurality of dimensions; determining a user demand at least based on an interactive operation received from the interactive form; and generating a response of the digital assistant to the user input based on the determined user demand, the response including content for addressing the determined user demand.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for interactive dialogue. Background Art

[0002] With the development of information technology, various terminal devices can provide people with various services in work and life. Applications that provide these services can be deployed on these terminal devices. Applications can be designed to provide users with digital assistants and interactive conversation services. Digital assistants can provide content that addresses user needs through interactive conversations with users. Summary of the Invention

[0003] In a first aspect of the present disclosure, a method for interactive dialogue is provided. The method includes: based on user input to a digital assistant, determining whether a user demand indicated by the user input satisfies corresponding predetermined conditions in multiple dimensions; in response to the user demand not satisfying the predetermined condition for the first dimension in a first dimension of the multiple dimensions, presenting a set of queries associated with the first dimension in an interactive form; determining the user demand based at least on an interaction operation received from the interactive form; and generating a response from the digital assistant to the user input based on the determined user demand, the response including content for resolving the determined user demand.

[0004] In a second aspect of the present disclosure, a device for interactive dialogue is provided. The device includes: a first determination module configured to determine, based on user input to a digital assistant, whether a user demand indicated by the user input satisfies corresponding predetermined conditions in multiple dimensions; a presentation module configured to present, in response to the user demand not satisfying the predetermined condition for the first dimension in a first dimension among the multiple dimensions, a set of queries associated with the first dimension in an interactive form; a second determination module configured to determine the user demand based on at least an interactive operation received from the interactive form; and a response module configured to generate a response of the digital assistant to the user input based on the determined user demand, the response including content for resolving the determined user demand.

[0005] In a third aspect of the present 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. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions, which, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram illustrating an example environment in which embodiments according to the present disclosure may be implemented;

[0011] Figures 2 to 3 A flowchart illustrating an example architecture for an interactive dialog according to some embodiments of the present disclosure;

[0012] Figures 4A to 4B A schematic diagram illustrating an example interface for interactive dialogue according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A flowchart illustrating an example process for an interactive dialog according to some embodiments of the present disclosure is shown;

[0014] Figure 6 A schematic structural block diagram showing an example apparatus for interactive dialogue according to some embodiments of the present disclosure; and

[0015] Figure 7 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0016] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0017] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0019] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects shall comply with the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms them. Accordingly, when implementing the various embodiments of the present disclosure, the types, scope of use, and usage scenarios of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method may vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0020] If this specification and the solutions in the examples involve the processing of personal information, such processing will be done only with a legitimate basis (such as with the consent of the subject of personal information or as necessary for the performance of a contract) and only within the prescribed or agreed scope. A user's refusal to process personal information other than that required for basic functions will not affect the user's use of basic functions.

[0021] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after training is completed, corresponding outputs can be generated for given inputs. The generation of the model can be based on machine learning technology. 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 an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0022] Figure 1FIG2 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100 , a component execution platform 110 can support the execution of a business component 125 . A user 140 can interact with the business component 125 via a client of the component execution platform 110 .

[0023] In some embodiments, the business component 125 can be downloaded and installed on the terminal device of the user 140. In some embodiments, the business component 125 can also be accessed through other means, such as through a web page. Figure 1 In the environment 100 , in response to the business component 125 being started, the client of the component execution platform 110 may present the interface 150 of the business component 125 .

[0024] The business component 125 includes but is not limited to one or more of the following: chat business component (also known as instant messaging business IM component), document business component, audio and video conference business component, email business component, task business component, calendar business component, objectives and key results (OKR) business component, etc. It can be understood that although Figure 1 Although a single business component is shown in the figure, multiple business components can actually be installed on the component runtime platform 110. Multiple business components can be integrated on the component runtime platform 110, and such a component runtime platform 110 can be considered a multifunctional collaboration platform. When multiple business components are installed on a terminal device, these multiple business components can be integrated on one or more component runtime platforms 110. On the component runtime platform 110, people can launch different business components as needed to complete corresponding information processing, sharing, communication, etc. Business component 125 can provide content entity 126. Content entity 126 can be a content instance created by user 140 or other users on business component 125. For example, depending on the type of business component 125, content entity 126 can be a document (e.g., a Word document, a PDF document, a presentation, a spreadsheet document, etc.), an email, a message (e.g., a conversation message on an instant messaging business component), a calendar, a schedule, a task, audio, video, an image, etc.

[0025] In some embodiments, the component execution platform 110 may provide a digital assistant 120. The digital assistant 120 may be provided by a separate business component, or may be integrated into a business component 125 that can provide a content entity. The business component for providing a client interface for the digital assistant may correspond to a single-function business component or a multi-function collaboration platform, such as an office suite or other collaboration platform that can integrate multiple components. It is understood that similar to the business component, although Figure 1 A single digital assistant is shown in the figure, but there can actually be multiple digital assistants.

[0026] In some embodiments, the digital assistant 120 supports the use of plug-ins. Each plug-in can provide one or more functions of a business component. Such plug-ins include, but are not limited to, one or more of the following: a search plug-in, a contact plug-in, a message plug-in, a document plug-in, a spreadsheet plug-in, an email plug-in, a calendar plug-in, a schedule plug-in, a task plug-in, and the like.

[0027] The digital assistant 120 can be an intelligent assistant for the user, having intelligent dialogue and information processing capabilities. In an embodiment of the present disclosure, the digital assistant 120 is used to interact with the user 140 to assist the user 140 in using a terminal device or a service component. An interaction window with the digital assistant 120 can be presented in the client interface. In the interaction window, the user 140 can communicate with the digital assistant 120 by inputting natural language, pictures, audio files, video files, web page files, etc., to instruct the digital assistant to assist in completing various tasks, including operations on the content entity 126.

[0028] In some embodiments, user 140 has a corresponding relationship with digital assistant 120. For example, the first digital assistant corresponds to the first user, the second digital assistant corresponds to the second user, and so on. In some embodiments, the first digital assistant can uniquely correspond to the first user, the second digital assistant can uniquely correspond to the second user, and so on. That is, the first digital assistant of the first user can be specific to or exclusive to the first user. For example, in the process of the first digital assistant providing assistance or services to the first user, the first digital assistant can utilize its historical interaction information with the first user, the data authorized by the first user that it can access, the current interaction context with the first user, etc. If the first user is an individual or person, the first digital assistant can be regarded as a personal digital assistant. It will be understood that in the disclosed embodiments, the first digital assistant accesses the data to which it is granted permission based on the authorization of the first user. It should be understood that "uniquely corresponding" or similar expressions in this disclosure are not intended to limit the first digital assistant to being updated accordingly based on the interaction process between the first user and the first digital assistant. Of course, depending on actual needs, the digital assistant 120 does not have to be specific to the current user 140, but can be a general digital assistant.

[0029] In some embodiments, multiple interaction modes can be provided between user 140 and digital assistant 120, and flexible switching between the multiple interaction modes can be achieved. When a certain interaction mode is triggered, a corresponding interaction area is presented to facilitate interaction between user 140 and digital assistant 120. In different interaction modes, the interaction methods between user 140 and digital assistant 120 are different, which can flexibly adapt to the interaction needs in different scenarios.

[0030] The digital assistant 120 can be called or awakened by an appropriate means (e.g., a shortcut key, a button, or voice) to present an interaction window with the user 140. By selecting the digital assistant 120, the interaction window with the digital assistant 120 can be opened. The interaction window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and so on. In other embodiments, the digital assistant 120 can be awakened through an entry control or menu provided in a page, or by inputting a preset instruction.

[0031] The interaction window between the digital assistant 120 and the user 140 may include a conversation window, such as a conversation window in an instant messaging service component or an instant messaging module of a target service component. In the conversation window, the interaction between the digital assistant 120 and the user 140 may be presented in the form of conversation messages. Alternatively or additionally, the interaction window between the digital assistant 120 and the user 140 may also include other types of windows, such as a window in a floating window mode, in which the user 140 can trigger the digital assistant 120 to perform corresponding operations by inputting instructions, selecting shortcut instructions, etc.

[0032] In some embodiments, digital assistant 120 may support a conversation window interaction mode, also referred to as conversation mode. In this interaction mode, a conversation window is presented between user 140 and digital assistant 120, in which user 140 and digital assistant 120 interact through conversation messages. In conversation mode, digital assistant 120 can perform tasks based on the conversation messages in the conversation window. In the interaction window, user 140 enters interaction messages, and digital assistant 120 provides reply messages in response to the user input.

[0033] In some embodiments, the conversation mode between user 140 and digital assistant 120 can be invoked or awakened by an appropriate means (e.g., a shortcut key, button, or voice) to present a conversation window. By selecting digital assistant 120, a conversation window with digital assistant 120 can be opened. The conversation window may include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like.

[0034] In some embodiments, the digital assistant 120 may support an interactive mode of a floating window (or floating window), also referred to as a floating window mode. When the floating window mode is triggered, the operation panel (also referred to as a floating window) corresponding to the digital assistant 120 is presented, and the user 140 can issue instructions to the digital assistant 120 based on the operation panel. In some embodiments, the operation panel may include at least one candidate shortcut instruction. Alternatively or additionally, the operation panel may include an input control for receiving instructions. In floating window mode, the digital assistant 120 can perform tasks according to instructions issued by the user 140 through the operation panel.

[0035] In some embodiments, the floating window mode of the user 140 and the digital assistant 120 can also be called or awakened by an appropriate means (for example, a shortcut key, a button, or voice) to present the corresponding operation panel. In some embodiments, the awakening of the digital assistant 120 can be supported in a specific business component, such as a document business component, to provide interaction in the floating window mode. In some embodiments, in order to trigger the floating window mode to present the operation panel corresponding to the digital assistant 120, an entry control for the digital assistant 120 can be presented in the business component interface. In response to detecting a triggering operation for the entry control, it can be determined that the floating window mode is triggered, and the operation panel corresponding to the digital assistant 120 is presented in the target interface area.

[0036] In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly taken as an example, which is a conversation window.

[0037] The component operation platform 110 can be deployed locally on the terminal device of each user 140, and / or can be supported by a server-side device. For example, the terminal device of user 140 can run a client of the component operation platform 110, which can support the interaction between the user 140 and the component operation platform 110 provided by the server. In the case where the component operation platform 110 runs locally on the user's terminal device, the user 145 can directly use the terminal device to interact with the local component operation platform 110. In the case where the component operation platform 110 runs on the server-side device, the server-side device can realize the service provision of the client running in the terminal device based on the communication connection between the terminal device. The component operation platform 110 can present a corresponding interface 150 to the user 140 based on the operation of the user 140, so as to output and / or receive information related to the use of the component to the user 140 and / or from the user 140.

[0038] In some embodiments, at least some functionality of business component 125 and / or at least some functionality of digital assistant 120 can be implemented based on models. During the operation of business component 125, one or more models 155 can be invoked. Models 155 can be used to understand user input and provide services based on the output of model 155, such as providing responses to the user.

[0039] Although shown as being independent of the component execution platform 110, one or more models 155 can run on the component execution platform 110 or other remote servers. In some embodiments, the model 155 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). A language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 can also be based on other appropriate models.

[0040] The component operation platform 110 can run on an appropriate electronic device. The electronic device here can be any type of device with computing capabilities, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, 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 gaming device or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the component operation platform 110 can be implemented based on a cloud service.

[0041] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the present disclosure.

[0042] As mentioned above, the application in the terminal device can provide interactive dialogue services for the user. The digital assistant in the application can respond to the user input and provide the user with content for solving the user needs indicated by the user input. The traditional method for interactive dialogue requires the user to input accurate content once or as few times as possible. Only in this way can the content for solving the user needs be provided to the user. However, it is usually difficult for users to accurately express their needs, or the user is not clear about what information needs to be provided. In these cases, the traditional method for interactive dialogue cannot respond or cannot accurately respond to the user input. This defect results in poor interactivity and poor user experience of the traditional method for interactive dialogue.

[0043] Furthermore, conventional interactive dialogue methods can only passively respond to user input, but cannot proactively inquire about issues with the user input. This shortcoming results in a lack of flexibility in conventional interactive dialogue methods. If the user needs indicated by the user input change during an interactive dialogue, conventional interactive dialogue methods are unable to dynamically adjust the content used to address the user needs based on the changes. This shortcoming further results in a poor flexibility and user experience for conventional interactive dialogue methods.

[0044] In view of this, an embodiment of the present disclosure proposes a solution for interactive dialogue. The solution of the present disclosure determines whether the user needs indicated by the user input meet corresponding predetermined conditions in multiple dimensions based on the user input to the digital assistant. In response to the user needs not meeting the predetermined conditions for the first dimension in a first dimension among the multiple dimensions, a set of inquiries associated with the first dimension are presented in an interactive form. The user needs are determined based at least on the interactive operations received from the interactive form. Based on the determined user needs, a response of the digital assistant to the user input is generated, and the response includes content for solving the determined user needs.

[0045] In an embodiment of the present disclosure, user needs are considered from multiple dimensions. When the user needs do not meet the predetermined conditions for the first dimension in a first dimension among multiple dimensions, a set of inquiries associated with the first dimension are actively presented to the user in an interactive form. The user can perform interactive operations on the presented interactive form. This improves the interactivity between the user and the digital assistant. The presentation style of the interactive form used is clearer, more intuitive, and convenient for user operation, which improves the interaction friendliness. According to an embodiment of the present disclosure, based on the received interactive operations for the presented inquiries, more information on the first dimension can be determined, thereby re-determining the user needs. In other words, the embodiment of the present disclosure can update the user needs based on the received interactive operations for the presented inquiries. In this way, the embodiment of the present disclosure can adapt to the dynamic changes of user needs, improve the flexibility of interactive dialogues and user experience.

[0046] Various example implementations of this solution are described in detail below in conjunction with the accompanying drawings.

[0047] Figure 2 1 shows a flow chart of an example architecture 200 for interactive dialogue according to some embodiments of the present disclosure. The example architecture 200 can be implemented in Figure 1 The components of the operating platform 110 will refer to Figure 1 The method 200 is described with reference to the environment 100 of FIG. Hereinafter, the example embodiments will be primarily described with respect to the component execution platform 110. It should be understood that the actions described with respect to the component execution platform 110 may be performed by the component execution platform 110 in collaboration with its server. For example, in a scenario where the actions are performed by the component execution platform 110 in collaboration with its server, the component execution platform 110 may request the server to provide information to be presented, or the server may proactively or in response to an operation of the component execution platform 110 provide the information to be presented to the component execution platform 110.

[0048] In block 210, user 140 may input some content via component runtime platform 110. This content may include, but is not limited to, text, media, documents, and charts. This content may indicate user requirements. For example, if user 140 wishes to compare and analyze several documents, they may input links to the documents to be analyzed and textually, "Please compare the different examples referred to in document XX to document XX," via component runtime platform 110. It should be understood that this is merely an example of user input via component runtime platform 110. In actual applications, users may input more, less, or other types of content via component runtime platform 110.

[0049] In box 215, the component execution platform 110 can determine whether the user needs indicated by the user input meet corresponding predetermined conditions in multiple dimensions based on the user input to the digital assistant 120. Different dimensions can be used to evaluate, detect or judge the quality of user needs in specific aspects. As an example and not limitation, the multiple dimensions may include complexity dimension, fuzziness dimension, need completeness dimension and context relevance dimension. The complexity dimension can be used to evaluate the quality of user needs in multiple aspects such as lexical complexity, syntactic complexity, semantic complexity, semantic diversity, etc. The fuzziness dimension can be used to detect vague expressions in user needs. Fuzzy expressions may include but are not limited to: semantically general words, unclear objects in sentences, and implicit meanings of content expressed using rhetoric. The need completeness dimension can be used to evaluate whether there is missing information in the user needs, such as whether the user needs are missing key information about a certain object (such as age, height, etc.). The context relevance dimension can be used to determine whether the context information of the user needs is related, such as whether the background information contained in the user needs is related to the problem that the user expects to solve contained in the user needs.

[0050] In some embodiments, the predetermined condition for a dimension may indicate that the quality of the user demand in a specific aspect is qualified. Exemplarily, the predetermined condition may be determined based on a threshold value corresponding to the dimension. The threshold value may be determined by any suitable method. As an example, the threshold value may be a configured fixed value. As another example, the threshold value may be a value dynamically determined by analyzing the user demand indicated by the user input using a model. The predetermined condition may be that the user demand meets the threshold value corresponding to the dimension in a specific aspect associated with the dimension. In other words, the quality of the user demand that meets the threshold value corresponding to the dimension in the specific aspect associated with the dimension is qualified.

[0051] Alternatively or additionally, the predetermined condition may be determined based on various factors associated with the dimension. Exemplarily, the factors associated with the completeness of the user's needs may include, but are not limited to, goals, paths, user preferences, information density, and creative direction. The predetermined condition for the completeness of the user's needs may be whether these factors are always present in the user's needs. It should be understood that only an example determination of the predetermined condition is given here. In actual applications, the predetermined condition can be determined in any suitable manner, and the embodiments of the present disclosure are not limited to this.

[0052] In some embodiments, the correspondence between dimensions and predetermined conditions can be various. Dimensions can correspond to predetermined conditions one-to-one. One dimension can correspond to multiple predetermined conditions. One predetermined condition can correspond to multiple dimensions. In the embodiments of the present disclosure, various embodiments are described by taking the one-to-one correspondence between dimensions and predetermined conditions as an example. Under such conditions, each dimension can correspond to a specific threshold and / or to a specific element. For example, the complexity dimension can correspond to a complexity threshold. The fuzziness dimension can correspond to a fuzziness threshold. The requirement completeness dimension can correspond to some elements (such as the goals, paths, user preferences, etc. mentioned above). The context relevance dimension can correspond to a relevance threshold. The process of determining whether the user requirements in a specific dimension meet the corresponding predetermined conditions for the specific dimension is described in detail below.

[0053] In box 211, the component operation platform 110 can determine whether the user demand indicated by the user input meets the predetermined conditions of the complexity dimension. The predetermined condition for the complexity dimension can be that the complexity of the user demand is lower than or equal to the complexity threshold. Exemplarily, if it is determined that at least one aspect of the vocabulary, sentence structure, semantics, etc. involved in the user demand is relatively complex, resulting in the inability to determine the key information about the user demand, it can be determined that the complexity of the user demand is higher than the complexity threshold. In other words, it can be determined that the user demand does not meet the predetermined conditions of the complexity dimension. It can be understood that the key information about the user demand can be used to clarify the user demand so as to provide the user with accurate content for solving the user demand.

[0054] In some embodiments, at block 212, the component execution platform 110 may determine whether the user requirement indicated by the user input satisfies a predetermined condition in the ambiguity dimension. The predetermined condition in the ambiguity dimension may be that the ambiguity of the user requirement is less than or equal to a ambiguity threshold. If it is determined that the target of the user requirement and / or other content in the user requirement cannot be clarified, it may be determined that the ambiguity of the user requirement is greater than the ambiguity threshold. In other words, it may be determined that the user requirement does not satisfy the predetermined condition in the ambiguity dimension.

[0055] In some embodiments, at block 213, the component execution platform 110 may determine whether the user requirement indicated by the user input satisfies predetermined conditions for the dimension of requirement completeness. The predetermined conditions for the dimension of requirement completeness may be whether the user requirement includes certain elements (such as the aforementioned elements of goal, path, user preferences, etc.). If it is determined that the user requirement lacks one or more of these elements, it may be determined that the user requirement does not meet the predetermined conditions for the dimension of requirement completeness.

[0056] In some embodiments, at block 214, the component execution platform 110 may determine whether the user need indicated by the user input satisfies a predetermined condition in the context relevance dimension. The context relevance of the user need relative to the predetermined condition in the context relevance dimension may be equal to or greater than a relevance threshold. If it is determined that the context information of the user need is not relevant, it may be determined that the context relevance of the user need is less than the relevance threshold. In other words, it may be determined that the user need does not satisfy the predetermined condition in the context relevance dimension.

[0057] It should be understood that the above only provides an example process for determining whether a user need satisfies an example predetermined condition for an example dimension. In practice, it is also possible to determine whether a user need satisfies predetermined conditions for more, fewer, or other dimensions. As long as these dimensions and the predetermined conditions for the dimensions help clarify the user need or help determine the accurate user need, the embodiments of the present disclosure are not limited thereto.

[0058] In some embodiments, the component operation platform 110 may use any suitable method to determine whether the user demand meets the corresponding predetermined conditions in multiple dimensions. As an example, the component operation platform 110 may determine whether the user demand meets the corresponding predetermined conditions in multiple dimensions in a parallel manner. In other words, the component operation platform 110 may determine whether the user demand meets the corresponding predetermined conditions in each dimension in response to receiving user input from the user 140. This can improve the efficiency of responding to user input. Alternatively or additionally, the component operation platform 110 may determine whether the user demand meets the corresponding predetermined conditions in multiple dimensions in a serial manner. In other words, the component operation platform 110 may determine whether the user demand meets the corresponding predetermined conditions in each dimension one by one or progressively in response to receiving user input from the user 140. In this way, resource consumption can be reduced.

[0059] If the user demand does not meet the predetermined conditions for a certain dimension, the component execution platform 110 may present a set of inquiries associated with the dimension. In an embodiment of the present disclosure, a set of inquiries may include one or more inquiries, such as one or more questions. These inquiries may be closed (for example, with multiple predetermined answers for the user to choose from), or may be open (for example, the user can freely enter information). Inquiries can be presented in multiple suitable styles. Examples of styles include, but are not limited to, interactive forms, text, voice, pictures, and the like.

[0060] In some embodiments, the component execution platform 110 may present a set of inquiries associated with the first dimension in an interactive form in response to the user demand not satisfying the predetermined condition for the first dimension in the first dimension of the multiple dimensions. The interactive form supports the user to provide responses to the inquiries through various suitable interactive operations (for example, clicking on an option, entering text, entering voice, specifying an image, specifying a document). Inquiries presented in an interactive form may include closed questions that have multiple predetermined answers. For closed questions, the user can provide responses through interactive operations such as clicking on an option. Alternatively or additionally, inquiries presented in an interactive form may include open questions that do not have fixed or standard answers. For open questions, the user can provide responses through interactive operations such as entering text, entering voice, specifying an image, specifying a document, etc. Reference will be made below. Figure 4A and Figure 4B Describes an example of an interactive form.

[0061] In some embodiments, the component execution platform 110 may present at least one set of queries associated with at least one of the multiple dimensions in response to a user request not satisfying a corresponding predetermined condition for at least one of the multiple dimensions. It will be appreciated that the first dimension and the second dimension may be any dimension or a combination of two or more dimensions as described above, or any other suitable dimension or dimensions other than the multiple dimensions described above. The second dimension is different from the first dimension. The queries associated with the first or second dimension may instruct the user 140 to provide or clarify certain information associated with the first or second dimension. For example, the first or second dimension may be a complexity dimension, and the set of queries associated with the complexity dimension may instruct the user 140 to provide key information regarding the user request. For example, suppose the user 140 inputs multiple documents via the component execution platform 110 and enters the text "Please summarize the main points of the documents." In this case, since it is unclear which document's main points need to be summarized, a set of queries specific to the document may be presented.

[0062] Alternatively or additionally, the first dimension or the second dimension may be an ambiguity dimension, and a set of queries associated with the ambiguity dimension may indicate to the user 140 the goal of clarifying the user requirement. For example, assuming that the user 140 has only input a plurality of documents via the component execution platform 110, in this case, since it is unclear how the input documents need to be processed, a set of queries targeting the goals of the input documents may be presented.

[0063] Alternatively or additionally, the first dimension or the second dimension may be a requirement completeness dimension. A set of queries associated with the requirement completeness dimension may instruct user 140 to provide missing information in the user requirement. For example, suppose user 140 enters the text "My child has cold symptoms. Please recommend appropriate treatments and medications" via component execution platform 110. In this case, a set of queries may be presented targeting missing information such as "child's age," "time of symptom onset," and "specific manifestations of the symptoms."

[0064] Alternatively or additionally, the first dimension or the second dimension may be a contextual relevance dimension, and a set of queries associated with the contextual relevance dimension may instruct user 140 to provide contextual information associated with the user's needs. For example, assume that user 140 enters text content via component execution platform 110: "I'm considering buying a new phone, and my budget is around XXX yuan. Do you have any recommended models? And please help me check tomorrow's weather." In this case, since the needs of "buying a phone" and "checking the weather" are unrelated, a set of queries instructing the user to provide contextual information related to "buying a phone" and "checking the weather" may be presented, or a set of queries specific to background information related to "checking the weather" may be presented.

[0065] It should be understood that the above only provides example queries associated with dimensions. In actual applications, queries associated with dimensions may indicate more, less, or other information.

[0066] In some embodiments, the types of inquiries can be diverse. As an example and not a limitation, the types of inquiries can include: simple yes or no inquiries, open-ended inquiries, inquiries that require further explanation of specific concepts and / or terms, inquiries that collect multiple associated parameters and / or options, and the like. It is understandable that a group of inquiries can be a combination of multiple inquiries of the same type or different types. Each inquiry can be an inquiry for specific information on a specific dimension of user needs. In this way, when it is determined that the user needs are unclear or inaccurate in a certain dimension, inquiries for that dimension can be actively presented to the user. In other words, it is possible to actively initiate interaction with the user at the appropriate time to obtain more or other information about the user needs. In this way, the interactivity of the platform can be improved and the user's experience of using the platform can be improved.

[0067] Continue to refer Figure 2 In some embodiments, in block 225, if it is determined that the user need does not meet the corresponding predetermined conditions for a certain dimension, or if it is determined that the user need does not meet the corresponding predetermined conditions for a dimension in multiple dimensions, it may be determined whether the quality of the content generated for the acquired information is below a quality threshold. The acquired information here may include information such as the acquired user input and historical interaction operations and / or historical user responses received for historical queries. The content generation quality may indicate the quality of the content generated based on the acquired information to address the user need. Exemplarily, the content generation quality may be assessed using a confidence level. The higher the confidence level, the better the quality of the content generated based on the acquired information to address the user need. In other words, the higher the confidence level, the more accurate the content generated based on the acquired information to address the user need. It will be understood that the quality threshold may indicate a qualified benchmark for the quality of the content generated based on the acquired information to address the user need. If it is determined that the content generation quality for the acquired information is equal to or higher than the quality threshold, the quality of the content generated based on the acquired information to address the user need may be determined to be qualified. Accordingly, if it is determined that the quality of content generation for the acquired information is lower than the quality threshold, it can be determined that the quality of the content generated based on the acquired information to solve the user's needs is unqualified.

[0068] In some embodiments, in box 230, the component execution platform 110 may, in response to determining that the content generation quality is lower than the quality threshold, determine the priority of multiple candidate queries associated with the dimension for at least one dimension that is determined not to meet the corresponding predetermined conditions. It is understandable that the multiple candidate queries can be queries for specific information associated with the dimension. The priority of multiple candidate queries can be determined based on the importance of the specific information to the user's needs. In some embodiments, the importance of information to the user's needs can be pre-configured. For example, for the five elements of goal, path, user preference, information density, and creative direction associated with the completeness of the requirements, the order of the elements from high to low importance can be configured as goal, path, information density, user preference, and creative direction. It should be understood that only an example method for determining the priority of candidate queries is given here. In actual applications, any suitable method can be used to determine the priority of candidate queries.

[0069] In box 235, a predetermined number of queries can be determined from multiple candidate queries according to the determined priority. The predetermined number can be a fixed number configured for the component runtime platform 110, or it can be a number specified by the user 140. As an example, assume that the multiple candidate queries determined for requirement completeness include queries for goals of user needs, queries for user preferences of user needs, and queries for information density of user needs. According to the determined priority, two queries with higher priorities can be selected as a group of queries associated with requirement completeness. In other words, the query for the goal of user needs with the highest priority and the query for information density of user needs with the second highest priority are selected as a group of queries associated with requirement completeness. In this way, user fatigue caused by presenting a large number of queries to the user at one time can be avoided.

[0070] In box 240, the determined predetermined number of inquiries can be presented. In some embodiments, for the first dimension that is determined not to meet the corresponding predetermined condition, a group of inquiries associated with the first dimension can be presented in an interactive form. The interactive form is a presentation style for inquiries. The presentation style for inquiries can be any appropriate style, including but not limited to: questionnaires, text, icons, progress bars. In some embodiments, the presentation style for inquiries can be indicated by the inquiry mode for presenting inquiries. An inquiry mode can be configured to correspond to one or more presentation styles. In addition, the inquiry mode can also indicate any other appropriate presentation information for the inquiry. These presentation information can include but are not limited to: presentation position, interactive animation, and layout of inquiries.

[0071] In some embodiments, multiple predetermined inquiry modes can be pre-configured. The configured multiple predetermined inquiry modes may include, but are not limited to: an inquiry mode for follow-up questions for clarification, an inquiry mode based on an interactive form or questionnaire, and an inquiry mode based on a confirmation mechanism. Exemplarily, the inquiry mode for follow-up questions for clarification may include an inquiry mode through natural language dialogue, an inquiry mode that presents option buttons, and so on. The inquiry mode based on an interactive form or questionnaire may include a distributed inquiry mode, an inquiry mode that presents preset options. The inquiry mode based on a confirmation mechanism may include an inquiry mode that requests confirmation of any appropriate information (such as a user plan for user needs, an outline of content for solving user needs).

[0072] It is understandable that different inquiry modes can be applicable to different types of inquiries. As an example, an inquiry mode through natural language dialogue can be applicable to open-ended inquiries, inquiries that require further explanation of specific concepts and / or terms, and other types of inquiries. An inquiry mode that presents option buttons can be applicable to simple yes or no inquiries, inquiries that require the user to confirm whether their understanding of the user's needs is correct, and other types of inquiries. An inquiry mode based on an interactive form or questionnaire can be applicable to inquiries that collect multiple associated parameters and / or options, inquiries that have clear classification selections and / or scoring requirements, inquiries for information with structured characteristics, and other types of inquiries. An inquiry mode based on a confirmation mechanism can be applicable to inquiries about user plans and / or content outlines for user needs involving the creation of complex content structures, inquiries that require the user to confirm the overall direction and / or creation framework for content creation based on user needs, and other types of inquiries.

[0073] In some embodiments, for an inquiry mode based on an interactive form or questionnaire, when designing an interactive form or questionnaire tailored to user needs, some configured design principles may be followed. These design principles may include, but are not limited to: each interactive form or questionnaire focuses on a small number of important inquiries, providing concise descriptions of the options in the interactive form or questionnaire and recommended options in a selected state, distributed inquiries (for example, based on the option selected by the user for the previous inquiry, presenting the next inquiry associated with the selected option), and presenting new inquiries after completing a certain stage of inquiry tasks. It is understandable that the interactive form or questionnaire designed according to these design principles is more concise and can give priority to presenting important information of the inquiry. This can improve inquiry efficiency and reduce costs.

[0074] In some embodiments, a query pattern for a set of queries associated with a dimension may be specified by a user. Alternatively or additionally, a target query pattern for a set of queries associated with a dimension may be selected from a plurality of predetermined query patterns based on information associated with the set of queries.

[0075] In some embodiments, a target query mode can be selected from a plurality of predetermined query modes based on the complexity of a set of queries associated with a particular dimension. For example, assuming the first dimension is a complexity dimension, if the complexity of the set of queries associated with the first dimension is determined to be low, a query mode using natural language dialogue can be selected as the target query mode for the set of queries associated with the first dimension. If the complexity of the set of queries associated with the first dimension is determined to be high, a query mode based on an interactive form can be selected as the target query mode for the set of queries associated with the first dimension.

[0076] Alternatively or additionally, a target query pattern can be selected from a plurality of predetermined query patterns based on the query structuredness. As an example, assuming the first dimension is a complexity dimension, if the structuredness of the set of queries associated with the first dimension is determined to be low, a query pattern using natural language dialogue can be selected as the target query pattern for the set of queries associated with the first dimension. If the structuredness of the set of queries associated with the first dimension is determined to be high, a query pattern based on an interactive form can be selected as the target query pattern for the set of queries associated with the first dimension.

[0077] Alternatively or additionally, a target inquiry mode may be selected from a plurality of predetermined inquiry modes based on historical interaction behaviors between the user 140 and the digital assistant 120. The historical interaction behaviors between the user 140 and the digital assistant 120 may include the interaction habits of the user 140 or the feedback of the user 140 on historical inquiries. Exemplarily, for a plurality of historical inquiries presented to the user 140 in a plurality of different target inquiry modes, if the user 140 responds to the historical inquiries presented in the first inquiry mode but does not respond to the historical inquiries presented in the second inquiry mode. In this case, it can be determined that the user 140 prefers to receive inquiries presented in the first inquiry mode. If it is subsequently determined that an inquiry needs to be presented, the first inquiry mode may be selected as the target inquiry mode for the inquiry to be presented.

[0078] Alternatively or additionally, a target query pattern can be selected from a plurality of predetermined query patterns based on the corresponding costs of interacting with the user via the plurality of predetermined query patterns. The cost of interacting with the user via the query pattern can be determined by factors such as the number of user actions required to respond to the query indicated by the query pattern, the duration of the query presented using the query pattern, and so on. For example, a query pattern that requires fewer user actions to respond to the query has a lower cost of interacting with the user. A query pattern that requires a longer duration of query presentation has a higher cost of interacting with the user. It will be appreciated that a query pattern with a lower cost of interacting with the user among the plurality of predetermined query patterns can be selected as the target query pattern for the query to be presented.

[0079] Alternatively or additionally, a target inquiry mode may be selected from a plurality of predetermined inquiry modes based on the progress of the interaction between the user and the digital assistant in response to the user's needs. The progress of the interaction between the user and the digital assistant in response to the user's needs may include multiple stages such as initial, mid-term, and late stages. For example, in the initial stage of the interaction between the user and the digital assistant in response to the user's needs, an inquiry mode based on an interactive form may be used as the target inquiry mode for the inquiry to be presented. In the late stage of the interaction between the user and the digital assistant in response to the user's needs, an inquiry mode based on a confirmation mechanism may be used as the target inquiry mode for the inquiry to be presented.

[0080] In some embodiments, the target query mode for the query to be presented can be comprehensively determined based on a combination of multiple factors such as the complexity of the query, the level of structuring of the query, the historical interaction behavior between the user and the digital assistant, the corresponding cost of interacting with the user through multiple query modes, and the progress of the interaction between the user and the digital assistant based on user needs.

[0081] Through the various embodiments described above, the flexibility of selecting a target query mode from multiple predetermined query modes can be improved, so that the selected target query mode can be more adapted to the user's personalized needs and enhance the interactive experience between the user and the digital assistant.

[0082] It should be understood that the above only provides example reference factors for selecting a target query mode from multiple predetermined query modes. In actual applications, the target query mode can be selected from multiple predetermined query modes based on more, fewer, or other factors. As long as these factors help improve the accuracy of selecting the target query mode and enable the selected target query mode to better meet the user's personalized needs, the embodiments of the present disclosure are not limited to this. In addition, the above only provides an example method for determining the target query mode for the query to be presented. In actual applications, the target query mode for the query to be presented can be determined in any appropriate manner, and the embodiments of the present disclosure are not limited to this.

[0083] In some embodiments, a set of queries associated with different dimensions can be presented separately according to different query modes (or query presentation styles). A set of queries associated with a first dimension can be presented in an interactive form or according to a query mode based on an interactive form. At least one set of queries associated with at least one second dimension can be presented in a style different from the interactive form (e.g., an icon), or at least one set of queries associated with at least one second dimension can be presented in a query mode different from the interactive form (e.g., a query mode based on a confirmation mechanism).

[0084] Continue to refer Figure 2 In some embodiments, at block 250, the component execution platform 110 may receive an interaction performed by the user 140 on the presented query (e.g., a set of queries associated with the first dimension). The interaction may include, but is not limited to, clicking, sliding, and zooming. Alternatively or additionally, at block 250, the component execution platform 110 may obtain a response (also referred to herein as a user response) input by the user 140 to the presented query (e.g., a set of queries associated with the first dimension).

[0085] The following combination Figure 4A and Figure 4B The example interface shown describes the interaction between the user 110 and the component execution platform 110.

[0086] As an example, Figure 4A In the example interface 400A shown, the component execution platform 110 can receive user input 410 via a digital assistant. Then, the user needs indicated by the user input 410 can be analyzed to see whether they meet corresponding predetermined conditions in multiple dimensions. The component execution platform 110 can present information 415 such as the analysis process and analysis results for the user needs indicated by the user input 410, thereby responding to the user input 410 in a timely manner. If it is determined that the user needs do not meet the predetermined conditions for the corresponding dimensions in one or more dimensions, an interactive form 420 can be presented. The interactive form 420 can include one or more determined queries. The user 110 can perform interactive operations on the presented queries or enter responses to the presented queries. For example, the user 110 can enter a response to "child's age" in the input box 422. For another example, the user 110 can select "time of symptom onset" from the multiple options presented in area 424. The selected option can be highlighted as being selected (for example, the state of the selected option "1-2 weeks" shown in interface 400A). If the component execution platform 110 receives a signal via the digital assistant that the “Submit” button 426 is triggered, the user needs may be further determined based on the information of the submitted interactive form 420 .

[0087] As another example, Figure 4B In the example interface 400B shown, the component operation platform 110 can receive user input 430 via a digital assistant. Then, it is possible to analyze whether the user demand indicated by the user input 430 meets the corresponding predetermined conditions in multiple dimensions. The component operation platform 110 can present information 435 such as the analysis process and analysis results of the user demand indicated by the user input 430, thereby responding to the user input 430 in a timely manner. If it is determined that the user demand does not meet the predetermined conditions for the corresponding dimensions in one or more dimensions, an interactive form 440 can be presented. The interactive form 440 can include multiple inquiries such as "your current Chinese level", "the time available for study per week", and "the preferred learning method". The user 110 can perform interactive operations on the presented inquiries, or input a reply to the presented inquiries. For example, the user 110 can select a target option from the multiple options presented for "your current Chinese level". The selected target option can be highlighted as being in a selected state (e.g., the state of the selected option "beginner" shown in the interface 400B). If the component execution platform 110 receives a signal via the digital assistant that the “Submit” button 442 is triggered, the user needs may be further determined based on the information of the submitted interactive form 440 .

[0088] It should be understood that the above merely illustrates an example interactive interface for an interactive dialogue. In actual applications, the interactive interface may present more, less, or other information, and the embodiments of the present disclosure are not limited thereto. For example, the determined query may be presented in another query mode. For another example, a response to the user input may be presented directly without presenting the query.

[0089] In box 245, the component operation platform 110 may redetermine the user needs based on the interactive operations and / or user responses to the inquiries. In some embodiments, if the component operation platform 110 progressively presents inquiries for different dimensions, the component operation platform 110 may update the user needs based on the received interactive operations and / or user responses to the inquiries for the first dimension. Then, in box 215, the component operation platform 110 may re-determine whether the updated user needs meet the predetermined conditions for the corresponding dimensions in multiple dimensions. If it is determined that the updated user needs do not meet the predetermined conditions for the second dimension, a query associated with the second dimension may be presented. In this way, complete and accurate user needs can be determined based on the received interactive operations and / or user responses to the inquiries.

[0090] In block 220, if it is determined that the user need satisfies the predetermined conditions for the corresponding dimensions in multiple dimensions, the digital assistant 120 may generate a response to the user input based on the determined user need. The response may include the content generated to address the determined user need. In some embodiments, for scenarios where the user need may involve complex content creation, the component runtime platform 110 may first present an outline of the response to the user input. The outline may include a direction or framework for the content used to address the user need indicated by the user input. In response to receiving confirmation of the outline from the user 140, the component runtime platform 110 may generate a response based on the determined user need according to the outline. Alternatively or additionally, the component runtime platform 110 may generate a response based on the determined user need according to the modified outline in response to receiving a change to the outline. In this way, the interactivity between the digital assistant 120 and the user 140 can be improved, and the user 140's participation in content creation can be increased. The content included in the generated response can be made more responsive to the user need, thereby improving the user's 140 satisfaction.

[0091] In some embodiments, at block 220, if it is determined that the user demand satisfies the predetermined conditions for the corresponding dimension in a single dimension, a preliminary response of the digital assistant 120 to the user input in the corresponding dimension may be generated based on the determined user demand. If it is determined that the user demand satisfies the predetermined conditions for the corresponding dimensions in multiple dimensions, the preliminary responses in the different dimensions may be integrated to determine a complete response to the user demand. This facilitates the user 140 to understand the progress of the digital assistant 120 in processing the user input and enhances the user 140's confidence in continuing to interact with the digital assistant 120.

[0092] In some embodiments, there may be multiple solutions or multiple types of content for solving the determined user needs. If the user's preference cannot be determined, the component runtime platform 110 can present multiple solutions or multiple types of content for solving the determined user needs. The user 140 can freely select the desired solution or content from them. This can enhance the user's 140 experience with the digital assistant 120.

[0093] The following combination Figure 3 The flowchart 300 shown in FIG. 1 is used to describe an example interactive dialogue scenario between the user 140 and the digital assistant 120. Figure 3 As shown, at block 310, user input indicating a user need may be received. At block 315, the user need may be analyzed for need completeness using a machine learning model 320. At block 325, a determination may be made as to whether the need completeness of the user need satisfies a predetermined condition for need completeness. In other words, a determination may be made as to whether the need completeness of the user need meets a completeness threshold. At block 385, if it is determined that the need completeness of the user need meets the completeness threshold, content may be generated to address the user need indicated by the user input.

[0094] In box 335, if it is determined that the completeness of the user requirement does not reach the completeness threshold, the machine learning model 330 can be used to identify the missing information in the user requirement. It can be understood that the machine learning model 320 can be the same as or partially the same as the machine learning model. In box 340, based on the missing information in the identified user requirement, queries for the missing information can be generated. The queries here can be one or more groups of queries. Each group of queries can include multiple queries for a specific type of missing information. Exemplarily, the type of information can include but is not limited to: information associated with vocabulary, information associated with sentences, and information associated with semantics. A group of queries for vocabulary can include multiple queries for different vocabulary. A group of queries for sentences can include multiple queries for the structures of different sentences. It should be understood that only example queries for requirement completeness are given here. In actual applications, more or other queries for requirement completeness can be determined as needed.

[0095] In block 345, a query generated based on the missing information may be presented. In block 355, the user need may be updated or re-determined based on the received interaction and / or user response 350 to the presented query. In block 360, content may be generated to address the updated user need. In block 365, the generated content to address the updated user need may be presented to the user 140. In block 370, it may be determined whether feedback information from the user 140 regarding the presented content has been received. In block 375, the user need may be further updated in response to the feedback information received from the user 140 regarding the presented content. The steps of blocks 315 to 370 may then be iteratively performed until it is determined that the completeness of the updated user need meets a completeness threshold.

[0096] At block 380, if no feedback information regarding the presented content is received from user 140, a determination may be made as to whether further queries addressing the user's need should be presented. For example, the determination as to whether further queries should be presented may be made by determining the quality of the content generated by the acquired information. If it is determined that further queries should be presented, block 335 and subsequent steps may be iteratively executed until the completeness of the user's need is determined to have reached a completeness threshold, or until the quality of the content generated by the acquired information has reached a quality threshold. If it is determined that further queries should not be presented, complete content addressing the determined user need may be generated at block 385.

[0097] Through the various embodiments of the present disclosure, the present disclosure can achieve the accuracy of determining the user needs indicated by user input based on multiple dimensions. When it is determined that the user needs do not meet the predetermined conditions for a certain dimension in a certain dimension, at least one set of queries associated with the dimension is actively presented to the user. In this way, the burden of expressing user needs is reduced for the user, and the interactivity between the user and the digital assistant is improved. The embodiments of the present disclosure can also present queries associated with different dimensions in different query modes indicating the presentation style. In particular, queries associated with specific dimensions can be presented in an interactive form. This can make the presented queries clearer and more intuitive, and improve the interaction friendliness with the user. In addition, the embodiments of the present disclosure can redetermine the user needs based on the interactive operations and / or user responses to the presented queries. In this way, the embodiments of the present disclosure can adapt to the dynamic changes in user needs, improve the flexibility of interactive dialogues and user experience.

[0098] Figure 5 FIG. 5 is a flow chart showing an example process 500 for interactive dialogue according to some embodiments of the present disclosure. The process 500 may be implemented at the component execution platform 110. Figure 1 5. The process 500 is described below.

[0099] like Figure 5 As shown, in box 510, the component execution platform 110 determines whether the user needs indicated by the user input meet corresponding predetermined conditions in multiple dimensions based on the user input to the digital assistant.

[0100] In block 520 , in response to the user requirement not satisfying a predetermined condition for a first dimension in a first dimension among the multiple dimensions, the component execution platform 110 presents a set of queries associated with the first dimension in an interactive form.

[0101] At block 530 , the component execution platform 110 determines a user need based at least on the interaction operation received from the interactive form.

[0102] In block 540 , the component execution platform 110 generates a response of the digital assistant to the user input based on the determined user need, where the response includes content for resolving the determined user need.

[0103] In some embodiments, the multiple dimensions include a complexity dimension, and the component execution platform 110 generates a set of queries associated with the complexity dimension in response to determining that the complexity of the user requirement is above a complexity threshold to instruct the user to provide key information about the user requirement.

[0104] In some embodiments, the plurality of dimensions includes an ambiguity dimension, and the component execution platform 110 generates a set of queries associated with the ambiguity dimension in response to determining that the ambiguity of the user requirement is above an ambiguity threshold to indicate a goal of the user to clarify the user requirement.

[0105] In some embodiments, the multiple dimensions include a requirement completeness dimension, and the component execution platform 110 generates a set of queries associated with the requirement completeness dimension in response to determining that there is missing information in the user requirement to instruct the user to provide the missing information.

[0106] In some embodiments, the multiple dimensions include a context relevance dimension, and the component execution platform 110 generates a set of queries associated with the context relevance in response to determining that the context relevance of the user requirement is below a relevance threshold to instruct the user to provide context information associated with the user requirement.

[0107] In some embodiments, the component execution platform 110 presents at least one set of queries respectively associated with at least one second dimension in response to determining that the user needs do not meet the corresponding predetermined conditions for at least one second dimension in at least one second dimension among multiple dimensions, and at least one second dimension is different from the first dimension; and obtains user responses to at least one set of queries, and wherein the user needs are determined based on the interactive operation and the user responses.

[0108] In some embodiments, at least one set of queries is presented separately in a format other than the interactive form.

[0109] In some embodiments, the component operating platform 110 determines a content generation quality for the acquired information, where the content generation quality indicates the quality of content generated based on the acquired information to address user needs; in response to determining that the content generation quality is lower than a quality threshold, determines the priorities of multiple candidate queries associated with the dimension; and determines a predetermined number of queries from the multiple candidate queries according to the determined priorities.

[0110] In some embodiments, a set of queries is presented according to an interactive form-based query mode, and the interactive form-based query mode is selected from a plurality of predetermined query modes based on at least one of the following: the complexity of the set of queries, the level of structure of the set of queries, the historical interaction behavior between the user and the digital assistant, the corresponding cost of interacting with the user via the plurality of predetermined query modes, or the progress of the interaction between the user and the digital assistant in response to the user's needs.

[0111] In some embodiments, the component execution platform 110 presents an outline of a response to user input; in response to receiving confirmation of the outline, generates a response according to the outline based on the determined user requirements; and in response to receiving a change to the outline, generates a response according to the changed outline based on the determined user requirements.

[0112] In some embodiments, the component execution platform 110 updates the user requirements based on at least the interaction operation; and in response to determining that the updated user requirements do not meet a predetermined condition for a second dimension of the multiple dimensions, presents a set of queries associated with the second dimension.

[0113] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 6 1 shows a schematic structural block diagram of an example apparatus 600 for interactive dialogue according to some embodiments of the present disclosure. The apparatus 600 may be implemented as or included in the electronic device 110. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0114] like Figure 6As shown, the device 600 includes: a first determination module 610, configured to determine whether the user needs indicated by the user input meet corresponding predetermined conditions in multiple dimensions based on the user input to the digital assistant; a presentation module 620, configured to present a set of queries associated with the first dimension in an interactive form in response to the user needs not meeting the predetermined conditions for the first dimension in a first dimension among the multiple dimensions; a second determination module 630, configured to determine the user needs based at least on the interactive operations received from the interactive form; and a response module 640, configured to generate a response of the digital assistant to the user input based on the determined user needs, the response including content for solving the determined user needs.

[0115] In some embodiments, the multiple dimensions include a complexity dimension, and the device 600 also includes: a first generation module, configured to generate a set of queries associated with the complexity dimension in response to determining that the complexity of the user needs is higher than a complexity threshold, to instruct the user to provide key information about the user needs.

[0116] In some embodiments, the multiple dimensions include an ambiguity dimension, and the device 600 also includes: a second generation module, configured to generate a set of queries associated with the ambiguity dimension in response to determining that the ambiguity of the user requirement is higher than the ambiguity threshold, to indicate the user's goal of clarifying the user requirement.

[0117] In some embodiments, the multiple dimensions include a requirement completeness dimension, and the device 600 also includes: a third generation module, configured to generate a set of queries associated with the requirement completeness dimension in response to determining that there is missing information in the user requirements to instruct the user to provide the missing information.

[0118] In some embodiments, the multiple dimensions include a contextual relevance dimension, and the device 600 also includes: a fourth generation module, configured to generate a set of queries associated with the contextual relevance in response to determining that the contextual relevance of the user need is lower than the relevance threshold, to instruct the user to provide contextual information associated with the user need.

[0119] In some embodiments, the device 600 also includes: a user response acquisition module, configured to present at least one group of inquiries respectively associated with at least one second dimension in response to determining that the user needs do not meet the corresponding predetermined conditions for at least one second dimension in at least one second dimension among multiple dimensions, and at least one second dimension is different from the first dimension; and obtain user responses to at least one group of inquiries, wherein the user needs are determined based on the interactive operation and the user responses.

[0120] In some embodiments, at least one set of queries is presented separately in a format other than the interactive form.

[0121] In some embodiments, a predetermined number of queries are presented for at least one second dimension and a dimension in the first dimension, and the device 600 also includes: a query determination module, configured to determine the content generation quality for the acquired information, the content generation quality indicating the quality of content generated based on the acquired information to solve user needs; in response to determining that the content generation quality is lower than the quality threshold, determining the priority of multiple candidate queries associated with the dimension; and determining a predetermined number of queries from the multiple candidate queries according to the determined priority.

[0122] In some embodiments, a set of queries is presented according to an interactive form-based query mode, and the interactive form-based query mode is selected from a plurality of predetermined query modes based on at least one of the following: the complexity of the set of queries, the level of structure of the set of queries, the historical interaction behavior between the user and the digital assistant, the corresponding cost of interacting with the user via the plurality of predetermined query modes, or the progress of the interaction between the user and the digital assistant in response to the user's needs.

[0123] In some embodiments, the response module 640 may also be configured to: present an outline of a response to the user input; in response to receiving confirmation of the outline, generate a response according to the outline based on the determined user requirements; and in response to receiving a change to the outline, generate a response according to the changed outline based on the determined user requirements.

[0124] In some embodiments, the device 600 also includes: an update module configured to update the user requirements based at least on the interaction operation; and in response to determining that the updated user requirements do not meet the predetermined conditions for the second dimension of the multiple dimensions, presenting a set of queries associated with the second dimension.

[0125] Figure 7 1 shows a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. Figure 7 As shown, electronic device 700 is in the form of a general electronic device. Components of electronic device 700 may include, but are not limited to, at least one processor or processing unit 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processor 710 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multi-processor system, multiple processors execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 700.

[0126] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 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 730 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 700.

[0127] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules configured to perform the various methods or actions of various embodiments of the present disclosure.

[0128] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0129] Input device 770 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 760 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 700 may also communicate with one or more external devices (not shown) via communication unit 740, as needed. External devices such as storage devices, display devices, and the like may also be used to communicate with one or more devices that allow a user to interact with electronic device 700, or with any device that allows electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0130] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0131] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0132] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine such that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0133] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0134] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0135] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for interactive dialogue, comprising: Based on user input to the digital assistant, determining whether the user demand indicated by the user input meets corresponding predetermined conditions in multiple dimensions; In response to the user demand not satisfying a predetermined condition for a first dimension of the plurality of dimensions, presenting a set of queries associated with the first dimension in an interactive form; determining the user need based at least on an interaction operation received from the interactive form; as well as Based on the determined user need, a response of the digital assistant to the user input is generated, the response including content for resolving the determined user need.

2. The method of claim 1 , wherein the plurality of dimensions includes a complexity dimension, and the method further comprises: In response to determining that the complexity of the user requirement is above a complexity threshold, a set of queries associated with the complexity dimension is generated to instruct a user to provide key information about the user requirement.

3. The method of claim 1 , wherein the plurality of dimensions includes a fuzziness dimension, and the method further comprises: In response to determining that the ambiguity of the user requirement is above an ambiguity threshold, a set of queries associated with the ambiguity dimension are generated to instruct a user to clarify a goal of the user requirement.

4. The method of claim 1 , wherein the plurality of dimensions includes a requirement completeness dimension, and the method further comprises: In response to determining that there is missing information in the user requirements, a set of queries associated with the requirement completeness dimension is generated to instruct the user to provide the missing information.

5. The method of claim 1 , wherein the plurality of dimensions includes a contextual relevance dimension, and the method further comprises: In response to determining that the contextual relevance of the user need is below a relevance threshold, a set of queries associated with the contextual relevance are generated to instruct a user to provide contextual information associated with the user need.

6. The method according to claim 1, further comprising: In response to determining that the user demand does not satisfy a corresponding predetermined condition for at least one second dimension in the plurality of dimensions, presenting at least one set of queries respectively associated with the at least one second dimension, the at least one second dimension being different from the first dimension; as well as obtaining user responses to the at least one set of queries, and The user demand is determined based on the interactive operation and the user response.

7. The method of claim 6, wherein the at least one set of queries is presented separately in a format different from the interactive form.

8. The method of claim 6, wherein a predetermined number of queries are presented for the at least one second dimension and a dimension of the first dimension, and the predetermined number of queries is determined by: determining a content generation quality for the acquired information, the content generation quality indicating a quality of content generated based on the acquired information for solving the user need; In response to determining that the content generation quality is below a quality threshold, prioritizing a plurality of candidate queries associated with the dimension; as well as A predetermined number of queries are determined from the plurality of candidate queries according to the determined priorities.

9. The method of claim 1 , wherein the set of queries is presented according to an interactive form-based query mode, and the interactive form-based query mode is selected from a plurality of predetermined query modes based on at least one of the following: The complexity of a set of queries, A set of questions about the level of structure, Historical interaction behaviors between the user and the digital assistant, the corresponding costs of interacting with the user via the plurality of predetermined inquiry modes, or The progress of the user's interaction with the digital assistant in response to the user's needs.

10. The method of claim 1 , wherein generating a response of the digital assistant to the user input comprises: presenting an outline of the response to the user input; In response to receiving confirmation of the outline, generating the response according to the outline based on the determined user needs; as well as In response to receiving a change to the outline, the response is generated according to the changed outline based on the determined user needs.

11. The method according to claim 1 , further comprising: updating the user requirement based on at least the interactive operation; as well as In response to determining that the updated user needs do not satisfy a predetermined condition for a second dimension of the plurality of dimensions, a set of queries associated with the second dimension is presented.

12. An apparatus for interactive dialogue, comprising: A first determination module is configured to determine, based on a user input to the digital assistant, whether a user demand indicated by the user input satisfies corresponding predetermined conditions in multiple dimensions; a presenting module configured to present, in response to the user demand not satisfying a predetermined condition for a first dimension in the plurality of dimensions, a set of queries associated with the first dimension in an interactive form; a second determining module configured to determine the user demand based at least on the interactive operation received from the interactive form; as well as A response module is configured to generate a response of the digital assistant to the user input based on the determined user needs.

13. An electronic device comprising: at least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 11 when executed by the at least one processor.

14. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions can be executed by a processor to implement the method according to any one of claims 1 to 11.

15. A computer program product tangibly stored in a computer storage medium and comprising computer executable instructions which, when executed by a device, cause the device to perform the method according to any one of claims 1 to 11.

Images