Task processing method and device, equipment and storage medium
By using plug-ins to generate prompt words in the interaction between users and digital assistants and calling functional components of target applications, the problem of inflexible task processing functions of digital assistants in the prior art is solved, and the requirements of flexible task processing and multi-category applications are realized satisfy.
Patent Information
- Application Number
- CN202311109780.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-30
- Publication Date
- 2024-11-22
AI Technical Summary
The interactive functions of existing digital assistants in task processing are not flexible enough and it is difficult to meet users' diverse task needs.
In the interaction between the user and the digital assistant, the plug-in generates prompt words for the model, determine the required parameters of the functional components in the target application, and call the corresponding functional components to achieve task processing requirements.
It realizes users' flexible task processing in digital assistant interaction, meets the task needs of multiple applications, and improves user experience.
Smart Images

Figure CN119003023A_ABST
Abstract
Description
Technical Field
[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, devices, apparatuses, and computer-readable storage media for task processing. Background Art
[0002] With the rapid development of Internet technology, the Internet has become an important platform for people to obtain and share content. Users can access the Internet through terminal devices to enjoy various Internet services. The terminal device presents the corresponding content through the user interface of the application and interacts with the user and provides services to the user. Therefore, the colorful interactive interface of the application is an important means to improve the user experience. With the development of information technology, various terminal devices can provide various services to people in work and life. For example, applications that provide services can be deployed in terminal devices. Terminal devices or applications can provide users with digital assistant functions to assist users in using terminal devices or applications. How to improve the flexibility of interaction between users and digital assistants is a technical problem to be explored at present. Summary of the invention
[0003] In a first aspect of the present disclosure, a method for task processing is provided. The method includes: in the interaction between a user and a digital assistant, determining a task processing requirement associated with a target application from interaction information from the user; using a first plug-in, generating a prompt word for a model based at least on the interaction information, the first plug-in corresponding to at least one functional component in the target application; obtaining a model output by providing the prompt word to the model, the model output at least including parameters required when calling a first functional component in at least one functional component to implement the task processing requirement; and using the first plug-in, calling the first functional component in the target application based on the parameters to generate at least a partial processing result of the task processing requirement.
[0004] In the second aspect of the present disclosure, a device for task processing is provided. The device includes: a demand determination module, configured to determine the task processing demand associated with the target application from the interaction information from the user in the interaction between the user and the digital assistant; a prompt word generation module, configured to use a first plug-in to generate a prompt word for the model based on at least the interaction information, the first plug-in at least corresponding to at least one functional component in the target application; a model calling module, configured to obtain a model output by providing a prompt word to the model, the model output at least including the parameters required when calling the first functional component in at least one functional component to implement the task processing demand; and a functional component calling module, configured to use the first plug-in to call the first functional component in the target application based on the parameters to generate at least a partial processing result of the task processing demand.
[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes 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] It should be understood that the content described in this 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
[0008] 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:
[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;
[0010] Figure 2 A schematic diagram showing an example user interface presenting an interaction window between a user and a digital assistant according to some embodiments of the present disclosure is shown;
[0011] Figure 3 A schematic diagram showing a data flow in task processing according to some embodiments of the present disclosure;
[0012] Figure 4 An example user interface for plugin selection during user interaction with a digital assistant according to some embodiments of the present disclosure is shown;
[0013] Figure 5 A schematic diagram showing a signaling flow of task processing in a project management application according to some embodiments of the present disclosure;
[0014] Fig. 6A and Figure 6B An example of an interactive interface with a digital assistant in a project management application according to some embodiments of the present disclosure is shown.
[0015] Figure 7 A flowchart showing a process for task processing according to some embodiments of the present disclosure is shown;
[0016] Figure 8A block diagram showing an apparatus for task processing according to some embodiments of the present disclosure; and
[0017] Fig. 9 A block diagram of an electronic device is shown in which one or more embodiments of the present disclosure can be implemented. DETAILED DESCRIPTION
[0018] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments set forth herein. On the contrary, 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0019] 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 also be included below.
[0020] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
[0021] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.
[0022] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.
[0023] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.
[0024] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.
[0025] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.
[0026] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In the example environment 100, an application 120 is installed in a terminal device 110. A user 140 can interact with the application 120 via the terminal device 110 and / or an attached device of the terminal device 110.
[0027] In some embodiments, the application 120 can be downloaded and installed on the terminal device 110. In some embodiments, the application 120 can also be accessed through other means, such as through a web page. Figure 1 In the environment 100, if the application 120 is started, the terminal device 110 can present the interface 150 of the application 120. The interface 150 may include various user interfaces that the application 120 can provide. The interface 150 is sometimes also referred to as a user interface.
[0028] Application 120 includes, but is not limited to, one or more of the following: chat application (also known as instant messaging application), document application, audio and video conferencing application, email application, task application, objectives and key results (OKR) application, and the like. Application 120 may support the use of plug-ins. Such plug-ins include, but are not limited to, one or more of the following: search plug-in, contact plug-in, message plug-in, document plug-in, table plug-in, email plug-in, calendar plug-in, schedule plug-in, task plug-in, and the like. In some embodiments, application 120 may include a multi-functional collaboration platform, such as an office collaboration platform (also known as an office suite) that can provide integration of various types of applications or components to facilitate people's office work, communication and other activities. In the multi-functional collaboration platform, people can start different applications or components as needed to complete corresponding information processing, sharing, communication, and the like.
[0029] In some embodiments, the terminal device 110 communicates with the server 130 to provide services for the application 120. The terminal device 110 may 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 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. In some embodiments, the terminal device 110 may also support any type of interface for the user (such as a "wearable" circuit, etc.). The application 130 may be a computing system / server of various types that can provide computing power, including but not limited to a mainframe, an edge computing node, a computing device in a cloud environment, and the like.
[0030] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.
[0031] As briefly mentioned above, digital assistants can assist users in using terminal devices or applications. In addition to being able to have free conversations with digital assistants, users can also use natural language instructions to enable digital assistants to complete tasks related to specific applications, such as retrieving project views, creating documents, inviting schedules, creating tasks, etc. However, the interactive functions provided by these applications are not flexible enough, and sometimes it is difficult for digital assistants to help users complete certain tasks within the application.
[0032] According to some embodiments of the present disclosure, an improved scheme for task processing is proposed. In an embodiment of the present disclosure, if it is determined that the user's task processing needs are associated with a target application in the interaction between the user and the digital assistant, a plug-in corresponding to one or more functional components of the target application is used to generate prompt words for the model based on the user's interaction information. The model determines the parameters required when calling a specific functional component of the target application to achieve the user's task processing needs based on the prompt words. In this way, the plug-in can call a specific functional component in the target application based on the parameters to output at least part of the processing results of the task processing needs. In this scheme, by providing a plug-in corresponding to one or more functional components of the target application, and using the plug-in to coordinate the use of the model and the call to the functional components in the application, the user's task processing needs can be met flexibly and conveniently. In this way, the user can conveniently complete the task processing needs involving various applications by issuing task processing needs in the interaction with the digital assistant.
[0033] Some example embodiments of the present disclosure will be described in detail below with reference to examples of the accompanying drawings.
[0034] In an embodiment of the present disclosure, a digital assistant is used to interact with a user. An interaction window between a user and a digital assistant may be presented in a user interface. The interaction window between a user and a digital assistant may include a conversation window, in which the interaction between the user and the digital assistant may be presented in the form of a conversation message. Alternatively or additionally, the interaction window between a user and a digital assistant may also include other types of windows, such as a window in a floating window mode, in which a user may trigger the digital assistant to perform a corresponding operation by inputting instructions, selecting shortcut instructions, and the like. As an intelligent assistant, the digital assistant has intelligent dialogue and information processing capabilities. In the interaction window, the user inputs an interactive message, and the digital assistant provides a reply message in response to the user input. The user interface for providing a digital assistant may correspond to a single-function application or a multi-function collaboration platform, such as an office suite or other collaboration platform capable of integrating multiple components.
[0035] The digital assistant can be called or awakened by an appropriate means (e.g., shortcut keys, buttons, or voice) to present an interaction window with the user. In some embodiments, the digital assistant can be included in the current user's contact list in the application, or included in the information flow of the chat application as a contact of the user. By selecting the digital assistant, the interaction window with the digital assistant can be opened. The interaction window may include interface elements for task processing, such as input boxes, message lists, message bubbles, and so on. In other embodiments, the digital assistant can be awakened through an entry control or menu provided in the page, or by inputting a preset instruction. In some embodiments described below, for ease of discussion, the interaction window between the user and the digital assistant is mainly illustrated as a session window.
[0036] In some embodiments, multiple interaction modes between the user and the digital assistant can be provided, and the multiple interaction modes can be flexibly switched. When a certain interaction mode is triggered, the corresponding interaction area is presented to facilitate the interaction between the user and the digital assistant. The user interacts with the digital assistant in different ways in different interaction modes, so that it can be flexibly adapted to the interaction needs in different application scenarios.
[0037] In some embodiments, users have a corresponding relationship with digital assistants. 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 may correspond uniquely to the first user, the second digital assistant may correspond uniquely to the second user, and so on. That is, the first digital assistant of the first user may be specific to or exclusive to the first user. For example, in the process of the first digital assistant providing assistance or service to the first user, the first digital assistant may utilize its historical interaction information with the first user, the data authorized by the first user that it can access, and the current interaction context with the first user. If the first user is an individual or an individual, the first digital assistant may be regarded as a personal digital assistant. It can be understood that in the disclosed embodiments, the first digital assistant is based on the authorized access to the data to which the permission is granted by the first user. It should be understood that "uniquely corresponding" or similar expressions in the present disclosure are not intended to limit the first digital assistant to be updated accordingly based on the interaction process between the first user and the first digital assistant.
[0038] In some embodiments, it is possible to provide information processing or task processing services specific to the user based on the historical interaction information between the user and the digital assistant and / or the data range specific to the user. In some embodiments, the historical interaction information of the user interacting with the digital assistant in multiple interaction modes can be stored in association with the user. In this way, in one interaction mode (any one or a specified one of the interaction modes) among the multiple interaction modes, the digital assistant can provide services to the user based on the historical interaction information stored in association with the user.
[0039] Figure 2 An example user interface 201 of presenting an interaction window between a user and a digital assistant according to some embodiments of the present disclosure is shown. The user interface 201 may be presented, for example, on Figure 1 The following embodiments will refer to the terminal device 110. Figure 1 It should be noted that the operations performed by the terminal device 110 described later may be performed by related applications installed on the terminal device 110.
[0040] In some embodiments, the terminal device 110 invokes the digital assistant in response to a user's preset operation (e.g., selecting a digital assistant from a contact list). The interaction window between the digital assistant ("XX assistant") and the current user ("user A") is presented in area 210 of the interface 201. In the interaction window of area 210, the user can input a message through the input box 218 or through other appropriate means (e.g., voice), and the digital assistant can provide a reply message based on the input message and in combination with relevant knowledge.
[0041] exist Figure 2In the example of , the digital assistant can be regarded as one of the user's contacts and is presented in the information flow (feed) of the instant messaging application. The information flow is presented in another area 220 of the interface 201. By selecting the digital assistant, the user can enter the interaction window with the digital assistant.
[0042] It should be understood that Figure 2 Only one example of starting the interactive window between the user and the digital assistant is shown. As mentioned above, the interactive window can also be started in other ways. Figure 2 The various specific information, icons, etc. provided are merely examples, and are not intended to limit the scope of the embodiments of the present disclosure.
[0043] Figure 3 FIG. 3 is a schematic diagram showing a data flow 300 in task processing according to some embodiments of the present disclosure. Figure 3 As shown, after triggering the interaction with the digital assistant 320, the user 140 inputs the interaction information to the digital assistant in step 312. For example, the user 140 may Figure 2 In a similar interactive window as shown, the digital assistant 320 (i.e. Figure 2 The user 140 can input interactive information to the digital assistant 320 in a natural language.
[0044] The digital assistant 320 determines the task processing requirements associated with the target application 350 from the interactive information from the user 140. Generally, the task scenarios that users expect to process in an application are diverse. For example, in a project management application, tasks such as creating projects, filtering and finding projects, and analyzing views may be required, and in a calendar application, tasks such as scheduling meetings and checking free and busy status may be required.
[0045] In some embodiments, the digital assistant 320 can use a model (e.g., model 340) to confirm the user's task processing requirements from the user's interactive information, that is, determine whether the task processing requirements are associated with an application, or whether they are associated with a functional component in the application. In some embodiments, model 340 can be any model suitable for processing text modal or multimodal data, such as various types of generative models. In some embodiments, the digital assistant 320 can generate corresponding prompt words based on the interactive information and input the prompt words to the model 340 in step 326. In the field of model processing, the prompt word can include a piece of text or a sentence that is used to start and guide the model to output a specific type, theme or format of output. Model 340 processes the prompt word to analyze the task processing requirements in the user's interactive information, and returns the task processing requirements to the digital assistant 320 in step 328.
[0046] If it is determined that the interaction information of the user 140 involves a task processing requirement with the target application 350, the digital assistant 320 may request a plug-in 330 corresponding to one or more functional components 352 in the target application 350 to assist in processing the task processing requirement in step 322. The plug-in 330 (sometimes referred to herein as a "first plug-in") is a set of functions that are configured according to the target application 350 and can be called by the digital assistant 320. In some embodiments, if multiple plug-ins are configured for the target application 350, each plug-in corresponds to a different functional component of the target application 350, then the plug-in to be requested may be selected depending on the specific functional component required for the user's task processing requirement.
[0047] In an embodiment of the present disclosure, a plug-in is provided for use by a digital assistant 320. A plug-in can be understood as a collection of functions, each of which can include one or more tools, and a tool can be understood as a unit function or atomic function in a plug-in. With the help of multiple tools, a plug-in can be used to implement a class of tasks desired by a user. In an embodiment of the present disclosure, plug-ins available to a digital assistant can be configured according to the functional components of a specific application. For example, for a project management application, a project search and filtering plug-in can be configured, which can implement a search function and a filtering function for content of a project type; for a document application, a document plug-in can be configured, which can implement the creation of document content, content search, content rewriting, etc. In some embodiments, the plug-in 330 may include an application programming interface (API) to at least one functional component 352 in the target application 350 for calling the corresponding functional component.
[0048] In some embodiments, plug-in 330 can be selected by user 140 during the interaction between user 140 and digital assistant 320. Figure 4 An example user interface 401 for selecting a plug-in during the interaction between a user and a digital assistant according to some embodiments of the present disclosure is shown. The user interface 401 may be presented by the terminal device 110, for example. Figure 4As shown, in the interaction window 410 between the user and the digital assistant, after a new topic is created, a plug-in selection control 412 may be provided. The user may select the plug-in to be used in the interaction process between the user and the digital assistant by clicking the plug-in selection control 412. In response to the user clicking the plug-in selection control 412, the terminal device 110 may present a list of selectable plug-ins, and may provide a search box 414 to support the user in searching for plug-ins. For example, if the user selects the "project search and filter plug-in" 416, a functional introduction to the plug-in may be further displayed to help the user understand the functions that the plug-in can achieve. For example, the "project search and filter plug-in" 416 corresponds to the search component and the filter component in the project management application. Other plug-ins may also correspond to functional components under specific applications, for example, a mail plug-in corresponds to the mail sending and receiving function in the mail application, a message plug-in corresponds to the message-related function in the instant messaging application, and so on.
[0049] In some embodiments, during the interaction between the user 140 and the digital assistant 320, the default plug-in to be used can be determined. For example, in the case where the user 140 does not specify the plug-in to be used, one or more default plug-ins can be provided. In some embodiments, during the interaction between the user 140 and the digital assistant 320, the plug-in can be selected by topic. That is, for each newly created topic, the user can be allowed to customize or the system can select one or more plug-ins to be used under the topic by default. Here, "topic" corresponds to a specific context of the interaction. During the interaction of each topic, the interaction information between the user and the digital assistant will be regarded as contextual information to assist the digital assistant in determining subsequent conversation messages. In some embodiments, the number of selectable plug-ins under each topic may have a maximum limit.
[0050] Continue to refer back Figure 3 , if the plug-in 330 is called by the digital assistant 320, the plug-in 330 will be used to determine at least part of the processing results of the task processing requirements of the user 140. The plug-in 330 generates prompt words for the model 340 based at least on the interaction information of the user 140, and inputs the generated prompt words to the model 340 in step 332. Note that the digital assistant 320 uses the model 340 to understand the user's interaction information to determine the user's task processing requirements from the interaction information; and the plug-in 330 corresponds to one or more functional components 352 in the target application 350, so it is expected to use the model 340 to determine how to call the functional components of the target application 350 to meet the user's task processing requirements.
[0051] In some embodiments, the prompt words provided by the plug-in 330 to the model 340 include at least description information related to at least one functional component in the target application, so as to indicate the processing capability of the plug-in 330 to the model 340. In some embodiments, the prompt words provided by the plug-in 330 to the model 340 also include task description information related to the task processing requirement. In some embodiments, the prompt words provided by the plug-in 330 to the model 340 may also include at least one example of how to process the task processing requirement, so as to help and guide the model 340 to determine how to process the current task processing requirement.
[0052] The model 340 processes the prompt word from the plug-in 330, and provides the model output to the plug-in 330 at step 334. The model output includes at least the parameters required when calling one or more functional components in the target application 350 to implement the task processing requirements. The one or more functional components indicated by the model output may be one, some or all functional components 352 of the functional components corresponding to the plug-in 330. In this document, for the purpose of discussion, the functional component indicated by the model output is sometimes referred to as the "first functional component".
[0053] In some embodiments, based on the prompt word, the model output of the model 340 may include an executable code snippet for one or more functional components 352 (i.e., the first functional component) in the target application 350, and the executable code snippet includes the parameters required when calling the one or more functional components 352 to implement the task processing requirements. In some embodiments, the model 34- may be provided with a code target corresponding to the one or more functional components 352, and the executable code snippet is generated based on the code template corresponding to the functional component 352. That is, the plug-in 330 can automatically generate code for calling the functional component in the target application 350 with the help of the model 340. In some embodiments, the model output of the model 340 may include the parameters required when calling the one or more functional components 352 to implement the task processing requirements. After receiving these parameters, the plug-in 330 can generate an executable code snippet for this or these functional components by filling the parameters into the code template corresponding to the indicated one or more functional components 352.
[0054] After obtaining the model output, in step 336, the plug-in 330 calls the corresponding functional component 352 (ie, the first functional component) in the target application 350 based on the parameters indicated by the model output to generate at least a partial processing result of the task processing requirement. Figure 3As shown, in step 338, the plug-in 330 obtains at least part of the processing result of the task processing requirement from the target application 350. In step 324, the plug-in 330 returns the obtained at least part of the processing result for the task processing requirement to the digital assistant 320. The digital assistant 320 determines a reply to the interaction information based on at least part of the processing result obtained from the plug-in 330 to present to the user. For example, the digital assistant 320 provides a reply to the user 140 in step 314 to indicate the processing result of the interaction information of the user 140.
[0055] Although Figure 3 Only a single plug-in 330 is shown in the figure, but in some embodiments, the task processing requirements of the user 140 may involve multiple plug-ins of the same application or different applications, so the digital assistant 320 can request multiple plug-ins to determine their respective partial processing results. The digital assistant 320 can aggregate the partial processing results from multiple plug-ins to obtain the final processing result for the task processing requirements of the user 140.
[0056] The above discussion discusses how, in a general application, a user's digital assistant completes the response to the user's task processing needs with the help of plug-ins corresponding to functional components in the application. For easier understanding, the following description is made in more detail by taking the target application 350 including a project management application as an example. Before the specific discussion, some basic concepts of the project management application are briefly introduced.
[0057] Project management applications are mainly used to manage user-created projects (also called work items). In some implementations, a project space (or, simply called space) can be created to manage all projects of an organization, team, or individual. The data hierarchy in the project management application can be divided from high to low into: space, project type, and project instance. A project instance can also be referred to as a project, which is a project created under a certain project type. The basic components of a project instance are fields. Each project can be used to manage a corresponding project (a certain work content item), such as work requirements, defects, version work types, etc. In each different project type, there are system default fields and custom fields. Each workflow consists of different nodes, such as product, prototype design, R&D, and testing nodes in requirements. Instances refer to different projects created under different types of work items. For example, I can create requirements in a requirements work item, and this requirement is an instance.
[0058] For project-related content, a work item or a project instance under a work item type can be displayed in a table-like view format, which can include various forms, such as tables, dashboards, lists, Gantt charts, etc. In some examples, the views of project management applications can include conditional views, which are sorted and grouped based on filter conditions and displayed; fixed views, which are generated as fixed views by globally searching for a keyword and generating instances containing the keyword as a fixed view; and panoramic views, which can be conditional views or fixed views, but the data source may come from multiple work projects or multiple work item spaces.
[0059] In the following example, it is assumed that the plug-in to be called by the digital assistant 320 corresponds to the search component and / or the filter component in the project management application, for example, the plug-in 330 is Figure 4 The project search and filter plug-in shown. In some embodiments, the parameters required when calling the search component to implement the task processing requirements include at least one of the following: view type, view name, and search keywords. In some embodiments, the parameters required when calling the filter component to implement the task processing requirements include at least one of the following: view type, view name, and at least one filter condition.
[0060] Figure 5 FIG. 5 is a schematic diagram showing a signaling flow 500 of task processing in a project management application according to some embodiments of the present disclosure. The signaling flow 500 can be viewed as Figure 3 An example of a data flow 300 where Figure 5 The project management application 505 can be considered as Figure 3 An example of a target application 350; the search component 304 is Figure 3 An example of a functional component 352; the project search and filter plug-in 502 can be considered as Figure 3 An example of a plug-in 330 that corresponds to a search component and a filter component in a project management application 505.
[0061] User 140 requests (510) digital assistant 320 to search for project instances in the project management application. For example, user 140 may send an interactive request to digital assistant 320 in natural language, such as "help me search for technical requirements related to XX program". In some embodiments, digital assistant 320 may use model 340 to identify the user's task processing requirements from the natural language input of user 140, and determine the target application or functional plug-in of the target application corresponding to the task processing requirements.
[0062] exist Figure 5In the example of , it is assumed that from the user's input, the digital assistant 320 identifies that the task processing requirement is associated with the project management application 305, and the digital assistant 320 is able to use the project search and filter plug-in 502 created for the project management application 305. The project search and filter plug-in 502 can be selected by the user 140 for interaction with the digital assistant 320. The digital assistant 320 can call (512) the project search and filter plug-in 502. After being called, the project search and filter plug-in 502 can generate an executable code snippet that conforms to the user input, and send the executable code snippet to the project management application 305 to generate the project view required by the user. The project search and filter plug-in 502 can send the generated view to the digital assistant 320 for presentation to the user 140.
[0063] In order to complete the generation of the view, the project search and filter plug-in 502 can obtain the executable code snippet for view generation with the help of the model. The project search and filter plug-in 502 can construct prompt words for the model, which can include a basic description of the project management application 305 and the functional components therein (i.e., the search component and the filter component), including the definition of the project space, project type, fields of specific data in the project, views, etc. in the project management application 305. In some examples, the prompt words can also include task descriptions related to the user's task processing requirements to describe to the model what needs to be completed and what is the process for completing the task.
[0064] To generate the prompt word, Figure 5 In the example, the project search and filter plug-in 502 can query (514) and obtain (516) user information 508 of the user 140 or other users involved in the task processing requirements in the project management application 505, fuzzy search (518) the project space and corresponding project 506 where the project involved in the task processing requirements is located, and obtain (520) space and project information. In the project management application, the project space can be considered as a collection of a type of project. In some examples, the project search and filter plug-in 502 can also query (522) the user's team information, query (524) the project field list information, and obtain (526, 528) the project field list information and the user's team information. The project field list information indicates the field list defined in the project, and the user's team information can be applicable in scenarios involving enterprises and organizations.
[0065] Based on the acquired information, the project search and filter plug-in 502 may generate (520) prompt words for the model and call the model 340 to perform (532) the prompt word task. Based on the prompt words, the model 340 generates a model output and sends (534) the model output to the project search and filter plug-in 502. The model output includes at least the parameters required when calling the search component and / or the filter component in the project management application to implement the user's task processing requirements.
[0066] In some embodiments, based on the task processing requirements indicated in the user's interactive information, it can be determined that a fixed view corresponding to the search component or a conditional view corresponding to the screening component is to be generated. For example, from the user input "Help me search for technical requirements related to XX program", it can be determined that a fuzzy search is required for items related to the keyword "XX program", and the search component needs to be called to generate a fixed view. If the user inputs "Help me search for requirements whose requirement names contain tests", it can be determined that a screening task is involved, and the screening condition is "the requirement name contains tests", so the screening component needs to be called to generate a conditional view.
[0067] In some embodiments, the prompt words for the model 340 generated by the project search and filtering plug-in 502 can determine the type of view to be generated based on the natural language input by the user. For example, based on the user's input, the field type {{fieldtype}} that matches the corresponding project in the corresponding space can be determined. For the filtering language input by the user, the field name and field key (Key) information in the field type fieldtype need to be matched when outputting the filtering conditions. When matching fields, default fields and custom fields can be distinguished. For example, the default field usually has a fixed field name, field key, and the corresponding operator type, so it is necessary to match the user's field information in the project in the space and the field value corresponding to the default field. For another example, for a custom field, it is necessary to match the user's field information in the work item in the space, including the field name, field key, field type, field value, and field value ID.
[0068] In some embodiments, when the user inputs a field name and field key that cannot be matched to a work item, an error code and a corresponding error code description are returned. For example, if the user inputs "Help me find defects with a priority of P5", and after matching, it is found that there is no priority field under the defect work item, then the digital assistant 320 can reply to the user "Sorry, the priority field you want to query does not exist." In some embodiments, the digital assistant 320 can also further clarify the details of the task processing requirements to the user to ensure that the user's requirements can be met.
[0069] In some embodiments, when the user inputs a field name and field key that can be matched to a work item, but cannot match the field value and field value ID, the user needs to be told which field values can be used under this field, and the output is performed after the user selects. For example, the user inputs "Help me find the business line that is a basic experience requirement", and after matching, it is found that the option values of the business line field are search, test, and research and development, but there is no basic experience. At this time, the digital assistant 320 can reply to the user "Sorry, based on the information you provided, the option values of the business line field are: search, test, and research and development, and there is no basic experience option. Please provide the correct business line option value, and I will check it for you."
[0070] In some embodiments, the model output may be generated according to a predetermined code template. For example, if the model output is to indicate a call to a search component in the project management application 505, the parameters indicated by the model output may include the view type, view name, and search keywords filled in the code template. In some embodiments, the code template corresponding to the search component may be a template corresponding to a fixed view. In some embodiments, the view name may be generated based on the user's search keyword and / or timestamp naming. The output format for the search component is shown in Table 1 below:
[0071] Table 1
[0072]
[0073] If the model output is to indicate a call to a filter component in the project management application 505, the parameters indicated by the model output may include the view type, view name, and at least one filter condition filled in the code template. In some embodiments, the code template corresponding to the filter component may be a template for a conditional view. In some embodiments, the view name may be generated based on the user's filter condition keywords and / or timestamp naming. The output format for the filter component is as shown in Table 2 below:
[0074] Table 2
[0075]
[0076] For ease of understanding, several specific examples are used for illustration. In one example, if the user inputs "Help me find bugs related to rebranding in the test space". The digital assistant 320 determines to call the project search and filter plug-in 502. The project search and filter plug-in 502 constructs prompt words for the model 340 based on the user input. Based on the prompt words, the model 340 determines that the input query is mainly about fuzzy keyword search, and a fixed view needs to be generated, and then determines the category and name of the view, and determines that the keyword that the user needs to query is rebranding. In this example, the input of the model 340 is as shown in Table 3 below:
[0077] Table 3
[0078]
[0079] In another example, if the user inputs "In the X project space, what are the requirements with higher business priority?". The digital assistant 320 determines to call the project search and filter plug-in 502. The project search and filter plug-in 502 constructs prompt words for the model 340 based on the user input. Based on the prompt words, the model 340 determines that the user's needs involve a filter condition category, and thus a conditional view is to be generated. However, considering that the user input is vague, it is necessary to first confirm with the user which priorities are higher priority. The model 340 can determine that the business side priority field is matched, and the relevant information is as follows: field name: business side priority; field key: business_priority; field type: select; option value and option value ID are: (P0, xxss), (P1, esfgt), (P2, xsgf), (P3, xsghe), (P4, ayhr). The output of the model 340 can instruct the digital assistant 320 to clearly define the high priority to the user, for example, output to the user "What priorities are higher priority? For example: P0 and P1?". If the user confirms the definition of high priority, the digital assistant 320 continues to generate the conditional view with the help of the model 340. At this time, the prompt words provided by the digital assistant 320 to the model 340 can be based on the previous multiple rounds of interaction information between the user and the digital assistant.
[0080] exist Figure 5 In the example, it is assumed that based on the model output, it is determined that the search component 504 in the project management application 505 needs to be called. After obtaining the model output, the project search and filter plug-in 502 parses (540) the model output to extract parameters therefrom. In some embodiments, if the execution of the prompt word task by the model 340 is asynchronous and requires a certain amount of time, the project search and filter plug-in 502 can temporarily store (537) user information, control information, project information, etc. in the cache 509, and receive (538) cache success feedback from the cache 509. After parsing the model output, the project search and filter plug-in 502 can read (542) the cache information from the cache 509 to obtain (544) the cached user information, control information, project information, etc.
[0081] The project search and filter plug-in 502 may query (546) the default field list of the project view from the project management application 505 and obtain (548) the default field list of the project view. The project search and filter plug-in 502 may call the search component 504 in the project management application 505 to create a view based on the model output. By calling the search plug-in 504, the project search and filter plug-in 502 obtains (552) the view identifier from the project management application 505. The project search and filter plug-in 502 may provide (554) a view link of the generated view to the digital assistant 320. The digital assistant 320 may present (556) the view link to the user 140 as a reply to the user 140.
[0082] Fig. 6A and Figure 6B An example of an interactive interface with a digital assistant in a project management application according to some embodiments of the present disclosure is shown. Fig. 6A In the interactive interface 601 shown, the user interacts with the digital assistant (i.e., "XX Assistant") in the interactive window 610. Based on the interactive information 612 input by the user, the digital assistant determines the generated view with the help of the project search and filter plug-in, and provides the user with a reply message 612, which includes a view link 616. By clicking on the view link 616, the user can access the following view: Figure 6B The view 602 shown is a view generated by a search component in a project management application.
[0083] It should be understood that some embodiments of the present disclosure are explained above under the example of project management applications, and the specific implementation of the project management applications and their functional components described in these embodiments is not limited thereto. In actual scenarios, there may be various other types of project management applications and their functional components. In addition, the embodiments of the present disclosure may also be applicable to other applications besides project management applications.
[0084] Figure 7 FIG. 7 is a flowchart of a process 700 for task processing according to some embodiments of the present disclosure. The process 700 may be implemented at the terminal device 110. For ease of discussion, reference will be made to FIG. Figure 1 The process 700 is described with reference to the environment 100 .
[0085] In box 710, the terminal device 110 determines the task processing requirements associated with the target application from the interaction information from the user during the interaction between the user and the digital assistant. In box 720, the terminal device 110 uses a first plug-in to generate a prompt word for the model based on at least the interaction information, and the first plug-in corresponds to at least one functional component in the target application. In some embodiments, the first plug-in is selected by the user during the interaction between the user and the digital assistant. In some embodiments, the first plug-in includes an application programming interface API for at least one functional component in the target application.
[0086] In some embodiments, the prompt word includes at least one of the following: description information related to at least one functional component in the target application, task description information related to task processing requirements, and at least one example.
[0087] In box 730, the terminal device 110 obtains a model output by providing a prompt word to the model, and the model output includes at least the parameters required when calling the first functional component in the at least one functional component to implement the task processing requirement. In some embodiments, the model output includes an executable code snippet for the first functional component, the executable code snippet includes the parameters, and the executable code snippet is generated based on at least the code template corresponding to the first functional component. In some embodiments, the model output includes the parameters, and the process 700 also includes: generating an executable code snippet for the first functional component by filling the parameters into the code template corresponding to the first functional component.
[0088] In block 740 , the terminal device 110 uses the first plug-in to call the first functional component in the target application based on the parameters to generate at least a partial processing result of the task processing requirement.
[0089] In some embodiments, process 700 further includes: obtaining at least part of the processing result from the target application; and determining a reply to the interaction information based on at least part of the processing result to present to the user.
[0090] In some embodiments, the target application includes a project management application. In some embodiments, the first plug-in corresponds to at least one of a search component and a filter component in the project management application.
[0091] In some embodiments, the parameters required when calling the search component to implement the task processing requirements include at least one of the following: view type, view name, and search keyword. In some embodiments, the parameters required when calling the filter component to implement the task processing requirements include at least one of the following: view type, view name, and at least one filter condition.
[0092] Figure 8A schematic structural block diagram of an apparatus 800 for task processing according to some embodiments of the present disclosure is shown. The apparatus 800 may be implemented as or included in a terminal device 110. Each module / component in the apparatus 800 may be implemented by hardware, software, firmware, or any combination thereof.
[0093] The device 800 includes a requirement determination module 810, which is configured to determine the task processing requirement associated with the target application from the interaction information from the user in the interaction between the user and the digital assistant; and a prompt word generation module 820, which is configured to use a first plug-in to generate a prompt word for the model based on at least the interaction information, and the first plug-in corresponds to at least one functional component in the target application. The device 800 also includes a model calling module 830, which is configured to obtain a model output by providing a prompt word to the model, and the model output at least includes the parameters required when calling the first functional component in at least one functional component to implement the task processing requirement; and a functional component calling module 840, which is configured to use the first plug-in to call the first functional component in the target application based on the parameters to generate at least a partial processing result of the task processing requirement.
[0094] In some embodiments, the first plug-in is selected by the user during the user's interaction with the digital assistant.
[0095] In some embodiments, the device 800 also includes: a result acquisition module configured to obtain at least part of the processing results from the target application; and a reply determination module configured to determine a reply to the interactive information based on at least part of the processing results for presentation to the user.
[0096] In some embodiments, the prompt word includes at least one of the following: description information related to at least one functional component in the target application, task description information related to task processing requirements, and at least one example.
[0097] In some embodiments, the model output includes an executable code snippet for the first functional component, the executable code snippet includes parameters, and the executable code snippet is generated based on at least a code template corresponding to the first functional component. In some embodiments, the model output includes parameters, and the device 800 also includes a template filling module configured to generate an executable code snippet for the first functional component by filling the parameters into the code template corresponding to the first functional component.
[0098] In some embodiments, the first plug-in includes an application programming interface API to at least one functional component in the target application.
[0099] In some embodiments, the target application includes a project management application. In some embodiments, the first plug-in corresponds to at least one of a search component and a filter component in the project management application.
[0100] In some embodiments, the parameters required when calling the search component to implement the task processing requirements include at least one of the following: view type, view name, and search keyword. In some embodiments, the parameters required when calling the filter component to implement the task processing requirements include at least one of the following: view type, view name, and at least one filter condition.
[0101] It should be understood that one or more steps in the above method can be performed by a suitable electronic device or a combination of electronic devices. Such an electronic device or a combination of electronic devices may include, for example, Figure 1 The server 130, the terminal device 110 and / or the combination of the server 130 and the terminal device 110.
[0102] Fig. 9 FIG. 9 is a block diagram of an electronic device 900 suitable for implementing an embodiment of the present disclosure. It should be understood that Fig. 9 The electronic device 900 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Fig. 9 The electronic device 900 shown can be used to implement Figure 1 The terminal device 110 or Figure 8 The device 800 is shown.
[0103] like Fig. 9 As shown, the electronic device 900 is in the form of a general electronic device. The components of the electronic device 900 may include, but are not limited to, one or more processors or processing units 910, a memory 920, a storage device 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. The processing unit 910 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 920. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 900.
[0104] The electronic device 900 typically includes a plurality of computer storage media. Such media can be any available media accessible to the electronic device 900, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 920 can be a volatile memory (e.g., register, cache, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory) or some combination thereof. The storage device 930 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, which can be used to store information and / or data and can be accessed within the electronic device 900.
[0105] The electronic device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Fig. 9 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. Memory 920 may include a computer program product 925 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.
[0106] The communication unit 940 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 900 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 900 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.
[0107] The input device 950 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 960 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 900 may also communicate with one or more external devices (not shown) through the communication unit 940 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 900, or communicate with any device that allows the electronic device 900 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).
[0108] 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.
[0109] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0110] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0111] 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, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0112] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square 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.
[0113] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.
Claims
1. A method for task processing, include: In an interaction between a user and a digital assistant, determining a task processing requirement associated with a target application from interaction information from the user; Generate a prompt word for a model based at least on the interaction information using a first plug-in, the first plug-in corresponding to at least one functional component in the target application; Obtaining a model output by providing the prompt word to the model, wherein the model output at least includes parameters required when calling a first functional component in the at least one functional component to implement the task processing requirement; as well as The first plug-in is used to call the first functional component in the target application based on the parameters to generate at least a partial processing result of the task processing requirement.
2. The method according to claim 1, wherein the first plug-in is selected by the user during the interaction between the user and the digital assistant.
3. The method according to claim 1, further comprising: include: Obtaining at least part of the processing result from the target application; as well as A reply to the interaction information is determined based on at least part of the processing result to present to the user.
4. The method according to claim 1, wherein the prompt word comprises at least one of the following: descriptive information related to the at least one functional component in the target application, Task description information related to the task processing requirements, At least one example.
5. The method according to claim 1, wherein the model output comprises an executable code snippet for the first functional component, the executable code snippet comprises the parameter, and the executable code snippet is generated based on at least a code template corresponding to the first functional component; or wherein the model output includes the parameters, and the method further include: The executable code snippet for the first functional component is generated by filling the parameter into the code template corresponding to the first functional component. The method according to claim 1 , wherein the first plug-in comprises an application programming interface (API) for the at least one functional component in the target application.
7. The method according to claim 1, wherein the target application comprises a project management application, and / or The first plug-in corresponds to at least one of a search component and a filter component in the project management application.
8. The method according to claim 7, wherein the parameters required when calling the search component to implement the task processing requirement include at least one of the following: view type, view name and search keyword, and / or The parameters required when calling the screening component to implement the task processing requirement include at least one of the following: view type, view name and at least one screening condition.
9. A device for task processing, include: a requirement determination module configured to determine, in an interaction between a user and a digital assistant, a task processing requirement associated with a target application from interaction information from the user; A prompt word generation module is configured to generate prompt words for the model based on at least the interaction information using a first plug-in, wherein the first plug-in corresponds to at least one functional component in the target application; A model calling module is configured to obtain a model output by providing the prompt word to the model, wherein the model output at least includes parameters required when calling a first functional component in the at least one functional component to realize the task processing requirement; as well as The function component calling module is configured to use the first plug-in to call the first function component in the target application based on the parameters to generate at least a partial processing result of the task processing requirement.
10. An electronic device, include: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 9 when executed by the at least one processing unit.
11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 9.
Citation Information
Patent Citations
Session-based interaction processing method and device, equipment, medium and program product
CN113934832A
Code generation method and device, storage medium and electronic equipment
CN116166271A
Task processing method and automatic question answering method
CN116595154A
Session data processing method and device, equipment and storage medium
CN116644145A
Social project management system and marketplace
US20140007038A1
Cited By
Plug-in-based AI digital human capability expansion method
CN120010948A
Plug-in-based AI digital human capability extension method
CN120010948B
Task processing method and device, equipment and storage medium
CN120409681A
Method and device for generating object, equipment, medium and program product
CN120669881A
Interaction method and device, equipment and storage medium
CN120973276A
