WO2025200591A1 - 用于创建数字助手的方法、装置、设备和介质 - Google Patents
用于创建数字助手的方法、装置、设备和介质Info
- Publication number
- WO2025200591A1 WO2025200591A1 PCT/CN2024/138824 CN2024138824W WO2025200591A1 WO 2025200591 A1 WO2025200591 A1 WO 2025200591A1 CN 2024138824 W CN2024138824 W CN 2024138824W WO 2025200591 A1 WO2025200591 A1 WO 2025200591A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- digital assistant
- trigger
- event
- setting
- response
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
- G06F9/453—Help systems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
Definitions
- Exemplary implementations of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for creating digital assistants.
- Digital assistants are provided to assist users in various task processing needs in different applications and scenarios.
- Digital assistants can usually call various built-in or third-party tools to perform tasks.
- Digital assistants usually have intelligent dialogue and task processing capabilities.
- Digital assistants can be called in response to user input. For example, in the process of interacting with a digital assistant, the user inputs an interactive message, and the digital assistant provides a reply message in response to the user input.
- the digital assistant can provide feedback on the input based on the user's input in real time. However, the user may expect to automatically call the digital assistant when certain events are detected.
- a method for creating a digital assistant includes: presenting a settings area in a creation page of the digital assistant, the settings area being used to set a trigger for the digital assistant, the trigger specifying an event source for receiving a trigger event and an action corresponding to the trigger event, the trigger event being an event from an application other than the digital assistant; in response to receiving a setting request for the settings area, setting the trigger based on the setting request; and creating the digital assistant based on the trigger, so that the created digital assistant performs an action in response to receiving the trigger event.
- a device for creating a digital assistant includes: a setting area presentation module configured to present a setting area in a creation page of the digital assistant, the setting area being used to set a trigger for the digital assistant, the trigger specifying an event source for receiving a trigger event and an action corresponding to the trigger event, the trigger event being an event from an application other than the digital assistant; a trigger setting module configured to, in response to receiving a setting request for the setting area, set a trigger based on the setting request; and a digital assistant publishing module configured to create a digital assistant based on the trigger, so that the created digital assistant performs an action in response to receiving the trigger event.
- an electronic device in a third aspect of the present disclosure, includes: at least one processing unit; and 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, when executed by the at least one processing unit, causing the electronic device to perform the method according to the first aspect of the present disclosure.
- a computer-readable storage medium on which a computer program is stored.
- the processor implements the method according to the first aspect of the present disclosure.
- a computer program product comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.
- FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented
- FIG2 shows a schematic diagram of an example of creating and applying a digital assistant according to some embodiments of the present disclosure
- FIG3 shows a schematic diagram of an example page according to some embodiments of the present disclosure
- FIG9 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented.
- the term “including” and similar terms should be understood as open inclusion, i.e., “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.
- executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
- 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 the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.
- a digital assistant is invoked in response to user input. For example, a user may enter an interactive message, and the digital assistant provides a reply message in response to the user input. However, the user may desire to automatically invoke the digital assistant when certain events occur. In this case, it is desirable to provide a more convenient and flexible way to create a digital assistant, and enable the digital assistant to be automatically invoked when predetermined events occur, thereby meeting more user needs.
- an application environment of the present disclosure is described, which shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented.
- the environment 100 involves an assistant creation platform 110 and an assistant application platform 130 .
- the assistant creation platform 110 can provide a digital assistant creation and publishing environment for users 105.
- the assistant creation platform 110 can be a low-code platform that provides a collection of tools for creating digital assistants.
- the assistant creation platform 110 can support the visual development of digital assistants, so that developers can skip the manual coding process and speed up the development cycle and cost of applications.
- the assistant creation platform 110 can support any appropriate platform for users to develop digital assistants and other types of applications, for example, it can include a platform based on Application Platform as a Service (aPaaS). Such a platform can support users to efficiently develop applications and realize operations such as application creation and application function adjustment.
- aPaaS Application Platform as a Service
- the assistant creation platform 110 can be deployed locally on the terminal device of the user 105, and/or can be supported by a remote server.
- the terminal device of the user 105 can run a client of the assistant creation platform 110, which can support the interaction between the user and the assistant creation platform 110.
- the assistant creation platform 110 runs locally on the user's terminal device, the user 105 can directly use the client to interact with the local assistant creation platform 110.
- the server-side device can realize the supply of services to the client running in the terminal device based on the communication connection between the server and the terminal device.
- the assistant creation platform 110 can present a corresponding page 122 to the user 105 based on the operation of the user 105 to output and/or receive information to the user 105 and/or receive information from the user 105.
- the assistant creation platform 110 can be associated with a corresponding database, which stores the data or information required for the digital assistant creation process supported by the assistant creation platform 110.
- the database can store the code and description information corresponding to the various functional modules that make up the digital assistant.
- the assistant creation platform 110 can also perform operations such as calling, adding, deleting, and updating on the functional modules in the database.
- the database can also store operations that can be performed on different functional modules. For example, in a scenario where a digital assistant is to be created, the assistant creation platform 110 can call the corresponding functional blocks from the database to build a digital assistant.
- a user 105 can create a digital assistant 120 as needed on an assistant creation platform 110 and publish the digital assistant 120.
- the digital assistant 120 can be published to any appropriate assistant application platform 130, as long as the assistant application platform 130 can support the operation of the digital assistant 120.
- the digital assistant 120 can be used for dialogue interaction with the user 135.
- the client of the assistant creation platform 110 can present an interactive window 132 of the digital assistant 120, such as a conversation window, in the client interface.
- the digital assistant 120 has intelligent dialogue and information processing capabilities.
- the user 140 can enter a conversation message in the conversation window, and the digital assistant 120 can determine the reply message based on the created configuration information and present it to the user in the interaction window 132.
- the interactive message with the digital assistant 120 may include messages in multimodal form, such as text messages (e.g., natural language text), voice messages, image messages, video messages, and the like.
- the assistant creation platform 110 and/or the assistant application platform 130 can run on appropriate electronic devices.
- the electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices.
- the terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio/video players, digital cameras/camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.
- PCS personal communication systems
- PDAs personal digital assistants
- audio/video players digital cameras/camcorders
- positioning devices television receivers, radio broadcast receivers, e-book devices, gaming devices or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.
- the assistant creation platform 110 can obtain the interaction information between the user 140 and the digital assistant 120 in the conversation window (including conversation messages from the user and reply messages from the digital assistant 120). In some embodiments, the assistant creation platform 110 can use the model to understand the user's conversation messages and determine the next operation to be performed. The assistant creation platform 110 can interact with the model to provide model input to the model and obtain corresponding model output from the model.
- the model can run locally on the assistant creation platform 110 or on a remote server.
- the model can be a machine learning model, a deep learning model, a learning model, a neural network, etc.
- the model can be based on a language model (LM), especially a large language model (LLM).
- LLM large language model
- the language model can have question-and-answer capabilities by learning from a large amount of corpus.
- the model can also be based on other appropriate models.
- digital assistants can usually provide feedback on the user's input in real time. That is, digital assistants rely on real-time interaction with users, and they cannot handle tasks that need to be performed when specific events occur. For example, a user may want the digital assistant to automatically reply "received" in response to determining that a new email has been received in a specified mailbox, and so on.
- existing digital assistants do not support being triggered by specific events, which greatly limits the functions and application areas of digital assistants. At this point, it is expected that complex tasks triggered by specific events can be handled in a more flexible and effective way.
- an improved scheme for creating a digital assistant is proposed.
- a setting area is presented in the creation page of the digital assistant.
- the setting area is used to set the trigger of the digital assistant.
- the trigger specifies the event source for receiving the trigger event and the action corresponding to the trigger event, and the trigger event is an event from an application other than the digital assistant.
- the trigger is set based on the setting request.
- the digital assistant is created based on the trigger so that the created digital assistant performs an action in response to receiving the trigger event.
- triggers for digital assistants can be configured, and digital assistants with trigger functions can be created so that the created digital assistants can perform actions in response to trigger events. This helps to improve the applicability and flexibility of digital assistants and supports digital assistants in handling more complex tasks.
- Figure 2 shows a schematic diagram of an example 200 of creating and applying a digital assistant according to some embodiments of the present disclosure.
- the assistant creation platform 110 presents a setting area in the creation page of the digital assistant (e.g., digital assistant 120), and the setting area is used to set the trigger (Trigger) 210 of the digital assistant.
- Trigger Trigger
- the trigger 210 specifies the event source 211 for receiving the trigger event (which may include an event source customized by the user 105 (e.g., a webhook notification), an event template provided by the assistant creation platform 110 (e.g., a reference event source, etc.), etc.) and the action 212 corresponding to the trigger event (the type of action may include, for example, a query type, a plug-in type, a workflow type, etc.), and the trigger event is an event from an application other than the digital assistant.
- the assistant creation platform 110 can receive a setting request for the setting area from the user 105 via the setting area.
- the lower portion of FIG2 shows the application process after the digital assistant is released.
- the assistant application platform 130 can provide guidance information 240 about the digital assistant to the user 135.
- the guidance information 240 can be used to indicate the functions and uses of the digital assistant.
- the digital assistant can perform an action 250 according to the configuration.
- Example 300 includes an area 310 for setting event tasks, which is also a setting area for setting trigger 210.
- At least one event task that has been created (for example, Task D to Task E shown in the figure) can be presented in area 310.
- Each event task can correspond to a triggering event (in this article, event tasks and triggering events can be used interchangeably), that is, corresponds to a trigger.
- the number of at least one event task should be less than or equal to a predetermined number (for example, any appropriate number such as 5, 10, 15, etc.).
- the assistant creation platform 110 can present a prompt message of "Create up to XX tasks".
- Emailbox is merely a specific example of an application corresponding to the application event type.
- events from other applications may also be received. For example, new messages from instant messaging applications may be received, new notifications from shopping applications may be received, and so on.
- the assistant creation platform 110 may determine that the type of the trigger event is an instant message type and present an input box 420.
- the assistant creation platform 110 may receive a configuration for the trigger event (e.g., an event source) via the input box 420.
- the assistant creation platform 110 may generate a trigger event based on the digital assistant and the message data from the event source.
- the assistant creation platform 110 can determine that the type of the trigger event is an application event type.
- the assistant creation platform 110 can also present an input box for receiving authentication information.
- the assistant creation platform can receive authentication information for logging into the application via the input box.
- the digital assistant can use the authentication information to log into the application in order to receive message data, and generate a trigger event based on the message data.
- the user can set a token in the assistant creation platform so that the digital assistant can use the token to obtain the corresponding notification message.
- the assistant creation platform 110 may also specify a validity period for the authentication information.
- the assistant creation platform 110 may specify that the validity period for the authentication information is 30 days (or other lengths of time).
- the digital assistant may obtain a trigger event.
- the assistant creation platform 110 can also present area 440, for example.
- the assistant creation platform 110 can receive a configuration for the format of the message data from the event source via area 440.
- the assistant creation platform 110 can receive the JSON format followed by the message data via area 440, and the triggering event will perform subsequent actions based on the format message.
- example 400 also includes a control 450, and the assistant creation platform 110 can present a configuration page for the action in response to the control 450 being triggered.
- the type of action can include, for example, a query type, a plug-in type, and a workflow type.
- the assistant creation platform 110 can receive a setting request for the action from the user 105 via the configuration page of the action.
- the assistant creation platform 110 can determine the type of action based on the setting request, and set an action that matches the type of action based on the setting request.
- Example 500A includes an input box 510.
- the assistant creation platform 110 can receive settings for a prompt word template via the input box 510.
- message data can be extracted from the triggering event, and query prompt words can be generated based on the message data and the prompt word template (i.e., the prompt word template received via the input box 510), so that the created digital assistant performs the corresponding action based on the query prompt word.
- the prompt word can be, for example, a model input for interacting with a model (e.g., a language model), which is used to guide the model to give a corresponding model output based on the learned knowledge.
- the assistant creation platform 110 may also present an example 600 as shown in FIG6 in response to the action type being set.
- Example 600 includes a control 610.
- the assistant creation platform 110 may create an event task (i.e., create a trigger) based on the above setting request.
- control 610 the terminal user (i.e., user 135) is allowed to start/stop event tasks in the conversational page. For example, if user 135 wishes to stop event task "AAA" (execute the auto-answer email task), they can enter "Please turn off event task AAA" in the conversational page. In this case, the auto-answer email task will be turned off, and no automatic responses will be provided for new emails received. User 135 can enter "Please start event task AAA" in the conversational page, and the auto-answer email task will be started. Assuming that control 610 is not set, the terminal user is not allowed to start/stop event tasks in the conversational page.
- the assistant creation platform 110 can store a trigger in response to receiving a user interaction. If the trigger is shared with other users, other users can also load the trigger in another creation page of another digital assistant. Another digital assistant can be created based on the trigger so that the created other digital assistant performs an action in response to detecting a trigger event. In this way, the sharing of triggers can be achieved, and a trigger created by one user can be shared with other users for use, that is, a trigger can be shared by multiple digital assistants, thereby improving the applicability and flexibility of the trigger.
- the assistant creation platform 110 can also perform a test 220 on the digital assistant in response to receiving a test request for testing the digital assistant, and the user 105 can publish 230 the digital assistant after passing the test.
- the assistant creation platform 110 can obtain a trigger event for simulating an event source (for example, assuming that a Webhook-URL is received, or an email is received).
- the assistant creation platform 110 can provide the execution result of the digital assistant performing the action (for example, it can include normal execution and the occurrence of an exception).
- the execution result can be provided, for example, in the conversational page of the digital assistant.
- the assistant creation platform 110 can also switch the working state of the trigger in response to receiving a switching request in the conversational page. For example, the assistant creation platform 110 can switch the XX trigger from an enabled state to a disabled state in response to receiving a session "Close XX trigger" in the conversational page.
- the created digital assistant can detect a trigger event, and in response to detecting the trigger event, the created digital assistant can perform an action corresponding to the trigger event based on its own configuration. Creation can include various forms. For example, a digital assistant can be created during the testing phase, and the digital assistant can be used by user 105 in the assistant creation platform 110. For another example, after the digital assistant that calls the trigger is tested, it can be published to the assistant application platform 130. At this point, the created digital assistant can be used by more users (for example, multiple users 135).
- the assistant application platform 130 can provide user 135 with guidance information about the digital assistant.
- This guidance information can be used to indicate the functions and uses of the digital assistant.
- the digital assistant can use specified authentication information (e.g., an email account and password) to log in to the email server. If a new email is received in the email account, the digital assistant can automatically reply to the new email, and so on.
- triggers for digital assistants can be configured.
- the digital assistant can perform actions based on triggering events, thereby enabling the digital assistant to perform corresponding actions based on events from other applications. This helps improve the applicability and flexibility of the digital assistant and enables the digital assistant to collaborate with other applications to perform more complex tasks.
- FIG7 shows a flowchart of a process 700 for creating a digital assistant according to some embodiments of the present disclosure.
- the process 700 can be implemented at the assistant creation platform 110.
- the process 700 is described below with reference to FIG1.
- a setting area is presented in the creation page of the digital assistant.
- the setting area is used to set the trigger of the digital assistant.
- the trigger specifies the event source for receiving the trigger event and the action corresponding to the trigger event.
- the trigger event is an event from an application other than the digital assistant.
- the trigger in response to receiving a setting request for the setting area, the trigger is set based on the setting request.
- the digital assistant is created based on the trigger so that the created digital assistant performs an action in response to receiving the trigger event.
- generating the trigger event further comprises: setting authentication information for receiving message data via the event source.
- the type of trigger event includes an application event type
- setting the trigger based on the setting request includes: setting authentication information for logging into the application; using the authentication information to log into the application to receive message data; and generating a trigger event based on the message data.
- setting the authentication information further includes: specifying a validity period of the authentication information.
- setting the trigger based on the setting request includes: determining a type of action based on the setting request; and setting an action that matches the type of action based on the setting request.
- the process 700 further includes: extracting message data from the triggering event in response to determining that the type of action indicates a query type; and generating query prompt words based on the message data and the prompt word template so that the created digital assistant performs the action based on the query prompt words.
- the process 700 further includes: in response to determining the type of action indicating the plug-in type, selecting a plug-in integrated by the digital assistant based on the setting request; and extracting message data from the triggering event so that the created digital assistant calls the plug-in to perform the action based on the message data.
- the process 700 further includes: in response to determining that the type of action indicates a workflow type, selecting a workflow integrated by the digital assistant based on a setting request; and extracting message data from the triggering event so that the created digital assistant calls the workflow to perform the action based on the message data.
- the process 700 further includes: in response to receiving a test request for testing the digital assistant, obtaining a trigger event for simulating an event source; and providing an execution result of the action performed by the digital assistant.
- the process 700 digital assistant provides the execution result in a conversational page, and the process 700 further includes: switching the working state of the trigger in response to receiving a switching request in the conversational page.
- the process 700 further includes: detecting, by the created digital assistant, a triggering event; and performing, by the created digital assistant, an action in response to detecting the triggering event.
- the process 700 further includes: storing the trigger in response to receiving a user interaction; loading the trigger in another creation page of another digital assistant; and creating another digital assistant based on the trigger so that the created another digital assistant performs an action in response to detecting a trigger event.
- FIG 8 shows a schematic structural block diagram of an apparatus 800 for creating a digital assistant according to some embodiments of the present disclosure.
- the apparatus 800 can be included in the assistant creation platform 110 in Figure 1, for example.
- the various modules/components in the apparatus 800 can be implemented by hardware, software, firmware, or any combination thereof.
- the device 800 includes a setting area presentation module 810, which is configured to present a setting area in the creation page of the digital assistant.
- the setting area is used to set the trigger of the digital assistant.
- the trigger specifies the event source for receiving the trigger event and the action corresponding to the trigger event.
- the trigger event is an event from an application other than the digital assistant.
- the device 800 also includes a trigger setting module 820, which is configured to set the trigger based on the setting request in response to receiving a setting request for the setting area.
- the device 800 also includes a digital assistant publishing module 830, which is configured to create a digital assistant based on the trigger, so that the created digital assistant performs an action in response to receiving the trigger event.
- the type of trigger event includes an instant message type
- the trigger setting module is further configured to: generate a trigger event based on the digital assistant and the message data from the event source.
- the trigger setting module is further configured to: specify a validity period of the authentication information.
- the device further includes: a workflow selection module, configured to indicate a workflow type in response to determining the type of action, and select a workflow integrated by the digital assistant based on a setting request; and a workflow calling module, configured to extract message data from the triggering event so that the created digital assistant calls the workflow to perform the action based on the message data.
- a workflow selection module configured to indicate a workflow type in response to determining the type of action, and select a workflow integrated by the digital assistant based on a setting request
- a workflow calling module configured to extract message data from the triggering event so that the created digital assistant calls the workflow to perform the action based on the message data.
- the device further includes: an acquisition module configured to acquire a trigger event for simulating an event source in response to receiving a test request for testing the digital assistant; and a providing module configured to provide an execution result of the action performed by the digital assistant.
- the digital assistant provides the execution result in a conversational page
- the device further includes: a switching module configured to switch the working state of the trigger in response to receiving a switching request in the conversational page.
- the device further includes: a detection module configured to detect a triggering event by the created digital assistant; and an execution module configured to execute an action by the created digital assistant in response to detecting the triggering event.
- the units and/or modules included in the device 800 can be implemented in various ways, including software, hardware, firmware, or any combination thereof.
- one or more units and/or modules can be implemented using software and/or firmware, such as machine executable instructions stored on a storage medium.
- some or all of the units and/or modules in the device 800 can be implemented at least in part by one or more hardware logic components.
- exemplary types of hardware logic components include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.
- an appropriate electronic device or combination of electronic devices may include, for example, the assistant creation platform 110 and/or the assistant application platform 130 in FIG. 1 .
- FIG9 shows a block diagram of an electronic device 900 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 900 shown in FIG9 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 900 shown in FIG9 can be used to implement the assistant creation platform 110, the assistant application platform 130 of FIG1 , and/or the apparatus 800 of FIG8 .
- the electronic device 900 typically includes a plurality of computer storage media. Such media can be any accessible media that the electronic device 900 can access, 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., 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 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 that can be used to store information and/or data and can be accessed within the electronic device 900.
- 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 900.
- the electronic device 900 may further include additional removable/non-removable, volatile/non-volatile storage media.
- a disk drive for reading or writing from a removable, non-volatile disk e.g., a “floppy disk”
- an optical drive for reading or writing from a removable, non-volatile optical disk may be provided.
- each drive may be connected to a bus (not shown) by one or more data media interfaces.
- the memory 920 may include a computer program product 925 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.
- the communication unit 940 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 900 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, 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.
- PC network personal computer
- the input device 950 may be one or more input devices, such as a mouse, keyboard, or trackball.
- the output device 960 may be one or more output devices, such as a display, a speaker, or a printer.
- 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, or the like, with one or more devices that allow a user to interact with the electronic device 900, or 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).
- I/O input/output
- a computer-readable storage medium on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above.
- 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.
- 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, such that when these instructions are executed by the processing unit 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.
- 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.
- 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.
- 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.
- 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.
- 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.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Computer Security & Cryptography (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Information Transfer Between Computers (AREA)
Abstract
根据本公开的实施例,提供了用于创建数字助手的方法、装置、设备和介质。该方法包括:在数字助手的创建页面中呈现设置区域,设置区域用于设置数字助手的触发器,触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件;响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器;以及基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。由此,可以提升数字助手的应用性和灵活性。
Description
本申请要求2024年03月29日递交的、标题为“用于创建数字助手的方法、装置、设备和介质”、申请号为202410383220.0的中国发明专利申请的优先权,该申请的全部内容通过引用结合在本申请中。
本公开的示例性实现方式总体涉及计算机领域,特别地涉及用于创建数字助手的方法、装置、设备和计算机可读存储介质。
机器学习技术已经被广泛地用于多种技术领域。在现有技术中,数字助手被提供用于协助用户在不同应用、场景下的各类任务处理需求。数字助手通常可以调用各种内置或第三方的工具来执行任务。数字助手通常具有智能对话和任务处理能力。数字助手可以响应于用户输入而被调用。例如,在与数字助手的交互过程中,用户输入交互消息,并且数字助手响应于用户输入来提供回复消息。通常,数字助手可以实时地基于用户的输入来提供针对该输入的反馈。然而,用户可能期望在检测到某些事件的情况下自动调用数字助手。
在本公开的第一方面,提供了一种用于创建数字助手的方法。该方法包括:在数字助手的创建页面中呈现设置区域,设置区域用于设置数字助手的触发器,触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件;响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器;以及基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。
在本公开的第二方面,提供了一种用于创建数字助手的装置。该装置包括:设置区域呈现模块,被配置为在数字助手的创建页面中呈现设置区域,设置区域用于设置数字助手的触发器,触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件;触发器设置模块,被配置为响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器;以及数字助手发布模块,被配置为基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。
在本公开的第三方面,提供了一种电子设备。该电子设备包括:至少一个处理单元;以及至少一个存储器,至少一个存储器被耦合到至少一个处理单元并且存储用于由至少一个处理单元执行的指令,指令在由至少一个处理单元执行时使电子设备执行根据本公开第一方面的方法。
在本公开的第四方面,提供了一种计算机可读存储介质,其上存储有计算机程序,计算机程序在被处理器执行时使处理器实现根据本公开第一方面的方法。
根据本公开的第五方面,提供了一种计算机程序产品,包括计算机程序,其中计算机程序被处理器执行时实现根据本公开的第一方面的方法。
应当理解,本内容部分中所描述的内容并非旨在限定本公开的实现方式的关键特征或重要特征,也不用于限制本公开的范围。本公开的其它特征将通过以下的描述而变得容易理解。
在下文中,结合附图并参考以下详细说明,本公开各实现方式的上述和其他特征、优点及方面将变得更加明显。在附图中,相同或相似的附图标注表示相同或相似的元素,其中:
结合附图并参考以下详细说明,本公开各实施例的上述和其他特征、优点及方面将变得更加明显。在附图中,相同或相似的附图标记表示相同或相似的元素,其中:
图1示出了本公开的实施例能够在其中实现的示例环境的示意图;
图2示出了根据本公开的一些实施例的创建和应用数字助手的示例的示意图;
图3示出了根据本公开的一些实施例的示例页面的示意图;
图4示出了根据本公开的另一些实施例的示例页面的示意图;
图5A至5C示出了根据本公开的一些实施例的动作的示例配置页面的示意图;
图6示出了根据本公开的一些实施例的预定任务的示例创建页面的示意图;
图7示出了根据本公开的一些实施例的用于创建数字助手的过程的流程图;
图8示出了根据本公开的一些实施例的用于创建数字助手的装置的示意性结构框图;以及
图9示出了其中可以实现本公开的一个或多个实施例的电子设备的框图。
下面将参照附图更详细地描述本公开的实施例。虽然附图中示出了本公开的某些实施例,然而应当理解的是,本公开可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例,相反,提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是,本公开的附图及实施例仅用于示例性作用,并非用于限制本公开的保护范围。
在本公开的实施例的描述中,术语“包括”及其类似用语应当理解为开放性包含,即“包括但不限于”。术语“基于”应当理解为“至少部分地基于”。术语“一个实施例”或“该实施例”应当理解为“至少一个实施例”。术语“一些实施例”应当理解为“至少一些实施例”。下文还可能包括其他明确的和隐含的定义。
在本文中,除非明确说明,“响应于A”执行一个步骤并不意味着在“A”之后立即执行该步骤,而是可以包括一个或多个中间步骤。
可以理解的是,本技术方案所涉及的数据(包括但不限于数据本身、数据的获得、使用、存储或删除)应当遵循相应法律法规及相关规定的要求。
可以理解的是,在使用本公开各实施例公开的技术方案之前,均应当根据相关法律法规通过适当的方式对本公开所涉及信息的类型、使用范围、使用场景等告知相关用户并获得相关用户的授权,其中,相关用户可以包括任何类型的权利主体,例如个人、企业、团体。
例如,在响应于接收到用户的主动请求时,向相关用户发送提示信息,以明确地提示相关用户,其请求执行的操作将需要获得和使用到相关用户的信息,从而使得相关用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用程序、服务器或存储介质等软件或硬件提供信息。
作为一种可选的但非限制性的实施例,响应于接收到相关用户的主动请求,向相关用户发送提示信息的方式,例如可以是弹出窗口的方式,弹出窗口中可以以文字的方式呈现提示信息。此外,弹出窗口中还可以承载供用户选择“同意”或“不同意”向电子设备提供信息的选择控件。
可以理解的是,上述通知和获得用户授权过程仅是示意性的,不对本公开的实施例构成限定,其他满足相关法律法规的方式也可应用于本公开的实施例中。
如本文中所使用的,术语“模型”可以从训练数据中学习到相应的输入与输出之间的关联关系,从而在训练完成后可以针对给定的输入,生成对应的输出。模型的生成可以基于机器学习技术。深度学习是一种机器学习算法,通过使用多层处理单元来处理输入和提供相应输出。神经网络模型是基于深度学习的模型的一个示例。在本文中,“模型”也可以被称为“机器学习模型”、“学习模型”、“机器学习网络”或“学习网络”,这些术语在本文中可互换地使用。
数字助手可以作为人们有效工作、学习、生活的工具。通常,数字助手的开发与一般应用的开发类似,需要由具有编程能力的开发人员通过编写复杂代码来定义数字助手的各项能力,并在适当运行平台上部署数字助手,以便用户能够下载、安装和使用数字助手。
随着应用场景多元化、机器学习技术的可用性越来越强,期望开发出更多具有不同能力的数字助手,以支持在各个细分领域中的任务处理,或者满足不同用户的个性化需求。然而,受限于编程能力和对数字助手的底层实现逻辑的有限理解,用户无法自由、方便地创建不同的数字助手。目前已经提供了多种低代码编程平台,并且用户可以以更为方便并且灵活的方式来创建数字助手。
数字助手响应于用户输入而被调用,例如,用户可以输入交互消息,并且数字助手响应于用户输入来提供回复消息。然而,用户可能期望在出现某些事件的情况下自动调用数字助手。此时,期望能够提供对数字助手的更方便、灵活的创建途径,并且使得该数字助手能够在出现预定的事件下被自动调用,进而满足用户的更多需求。
示例环境
参见图1描述本公开的应用环境,该图1示出了本公开的实施例能够在其中实现的示例环境100的示意图。环境100涉及助手创建平台110和助手应用平台130。
如图1所示,助手创建平台110可以为用户105提供数字助手的创建和发布环境。在一些实施例中,助手创建平台110可以是低代码平台,其提供数字助手创建的工具合集。助手创建平台110可以支持对数字助手的可视化开发,从而使开发人员可以跳过手工编码的过程,加快应用的开发周期和成本。助手创建平台110可以支持用户开发数字助手和其他类型的应用的任何适当平台,例如可以包括基于应用平台即服务(aPaaS)的平台。这样的平台能够支持用户对应用进行高效开发,实现应用创建、应用功能调整等操作。
助手创建平台110可以被部署在用户105的终端设备本地,和/或可以由远程服务器来支持。例如,用户105的终端设备可以运行有助手创建平台110的客户端,该客户端可以支持用户与助手创建平台110的交互。在助手创建平台110运行在用户的终端设备本地的情况下,用户105可以直接利用客户端与本地的助手创建平台110进行交互。在助手创建平台110运行在服务端设备的情况下,服务端设备可以基于与终端设备之间的通信连接,实现对终端设备中运行的客户端的服务的供应。助手创建平台110可以基于用户105的操作而向用户105呈现相应的页面122,以向用户105输出和/或从用户105接收信息。
在一些实施例中,助手创建平台110可以关联到相应的数据库,其中存储助手创建平台110所支持的数字助手创建过程所需的数据或信息。例如,数据库可以存储用于组成数字助手的各个功能模块对应的代码和描述信息等。助手创建平台110还可以对数据库中的功能模块执行调用、增加、删除、更新等操作。数据库还可以存储对不同功能模块可执行的操作。示例性地,在要创建数字助手的场景,助手创建平台110可以从数据库中调用相应的功能块来搭建数字助手。
在本公开的实施例中,用户105可以在助手创建平台110上根据需要创建数字助手120,并发布数字助手120。数字助手120可被发布到任一适当的助手应用平台130,只要助手应用平台130能够支持数字助手120的运行。在发布后,数字助手120可以用于与用户135的对话交互。助手创建平台110的客户端可以在客户端界面中呈现数字助手120的交互窗口132,例如会话窗口。数字助手120作为一种智能助手,具有智能对话和信息处理能力。用户140可以在会话窗口中输入会话消息,数字助手120可以基于所创建的配置信息,来确定回复消息并在交互窗口132中呈现给用户。在一些实施例中,取决于数字助手120的配置,与数字助手120的交互消息可以包括多模态形式的消息,诸如文本消息(例如,自然语言文本)、语音消息、图像消息、视频消息,等等。
助手创建平台110和/或助手应用平台130可以运行在适当的电子设备。这里的电子设备可以是任何类型的具有计算能力的设备,包括终端设备或服务端设备。终端设备可以是任何类型的移动终端、固定终端或便携式终端,包括移动手机、台式计算机、膝上型计算机、笔记本计算机、上网本计算机、平板计算机、媒体计算机、多媒体平板、个人通信系统(PCS)设备、个人导航设备、个人数字助手(PDA)、音频/视频播放器、数码相机/摄像机、定位设备、电视接收器、无线电广播接收器、电子书设备、游戏设备或者前述各项的任何组合,包括这些设备的配件和外设或者其任何组合。服务端设备例如可以包括计算系统/服务器,诸如大型机、边缘计算节点、云环境中的计算设备,等等。在一些实施例中,助手创建平台110和/或助手应用平台130可以基于云服务来实现。
应当理解,仅出于示例性的目的描述环境100的结构和功能,而不暗示对于本公开的范围的任何限制。
助手创建平台110可以获取用户140与数字助手120在会话窗口中的交互信息(包括来自用户的会话消息以及来自数字助手120的回复消息)。在一些实施例中,助手创建平台110可以借助模型来理解用户的会话消息,以及确定要执行的下一步操作。助手创建平台110可以与模型进行交互,以向模型提供模型输入,并从模型获得对应的模型输出。模型可以运行在助手创建平台110的本地或者在远端服务器。在一些实施例中,模型可以是机器学习模型、深度学习模型、学习模型、神经网络等。在一些实施例中,模型可以基于语言模型(LM)尤其是基于大语言模型(LLM)。语言模型通过从大量语料中学习,能够具备问答能力。模型也可以基于其他适当的模型。
如前文所简要提及的,数字助手可以通常可以实时地基于用户的输入来提供针对该输入的反馈。也即数字助手依赖与用户的实时交互,其无法处理那些需要在出现特定事件下执行的任务。例如,用户可能希望数字助手:响应于确定指定邮箱接收到新邮件,自动回复“已收到”,等等。然而,已有数字助手并不支持在特定事件下被触发,这在很大程度上限制了数字助手的功能和应用领域。此时,期望可以更为灵活并且有效的方式来处理由特定事件触发的复杂任务。
创建数字助手的概要
为了至少部分地解决现有技术中的不足,根据本公开的一个示例性实现方式,提出了一种用于创建数字助手的改进方案。根据该方案,在数字助手的创建页面中呈现设置区域。设置区域用于设置数字助手的触发器。触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件。响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器。基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。
以此方式,在本公开的实施例中,可以配置数字助手的触发器,并且创建具有触发器功能的数字助手,以便创建的数字助手可以响应于触发事件而执行动作。这有助于提升数字助手的应用性和灵活性,并且支持数字助手处理更为复杂的任务。以下进一步结合附图来详细描述该方案的各种示例实现。
创建数字助手的详细过程
图2示出了根据本公开的一些实施例的创建和应用数字助手的示例200的示意图。在本公开的实施例中,如图2上部所示,助手创建平台110在数字助手(例如数字助手120)的创建页面中呈现设置区域,该设置区域用于设置数字助手的触发器(Trigger)210。触发器210指定用于接收触发事件的事件来源211(其可以包括用户105自定义的事件来源(例如,webhook通知)、助手创建平台110提供的事件模板(例如参考事件来源,等)等等)以及对应于触发事件的动作212(动作的类型例如可以包括查询类型、插件类型、工作流类型等等),触发事件是来自数字助手以外的应用的事件。助手创建平台110可以经由设置区域接收用户105对设置区域的设置请求。
图2下部示出了在数字助手被发布后的应用过程,助手应用平台130可以向用户135提供关于数字助手的引导信息240,该引导信息240例如可以用于指示数字助手的功能和用途。继而,数字助手可以根据配置执行动作250。
参考图3描述创建数字助手的更多细节,该图3示出了根据本公开的一些实施例的示例页面300(也可以简称为示例300)的示意图。示例300包括用于设置事件任务的区域310,区域310也即用于设置触发器210的设置区域。区域310中可以呈现已创建的至少一个事件任务(例如图中所示的任务D至任务E)。每个事件任务可以对应于一个触发事件(在本文中,事件任务和触发事件可以交替地被使用),也即对应于一个触发器。在一些实施例中,至少一个事件任务的数目应小于等于预定数目(例如5,10,15等任意适当的数目)。在已创建的至少一个事件任务的数目达到预定数目,且再次接收到创建新的事件任务的请求时,助手创建平台110可以呈现“最多创建XX个任务”的提示消息。
区域310包括控件320,助手创建平台110可以响应于接收到对控件320的用户操作,呈现事件任务的创建页面。区域310包括用于呈现针对每个事件任务的多个操作控件的子区域330。助手创建平台110可以响应于接收到针对子区域330中的目标操作控件的用户操作,来执行相应的动作,例如可以分享任务、复制任务或者删除任务。在一些实施例中,助手创建平台110还可以响应于接收到对区域310中某个已创建的事件任务的选择操作,呈现对该事件任务的编辑页面。助手创建平台110可以经由这个编辑页面接收用户105对事件任务的编辑请求。
区域310上方区域示出了设置预定任务的页面,用户可以设置在某个时间点触发的预定任务A、B和C。例如,可以指定早8点的闹钟任务,或者指定早9点获取天气预报的任务,等等。
图4示出了根据本公开的另一些实施例的示例页面400(也可以简称为示例400)的示意图。示例400例如示出了事件任务的创建页面的示例,和/或,事件任务的编辑页面的示例。示例400包括取消控件401,助手创建平台110还可以响应于接收到对取消控件401的用户操作,取消呈现示例400(助手创建平台110例如可以返回呈现示例300)。
示例400还包括用于设置事件任务的类型的选择控件410。事件任务的类型(也即触发事件的类型)例如可以包括即时信息类型,和/或,应用事件类型。在此,即时信息类型例如可以表示应用之间实时传输信息的方式,例如“Webhook”方式。助手创建平台110可以响应于接收到对选择控件410的用户操作,呈现窗口412。窗口412可以呈现分别对应于即时信息类型和应用事件类型的选项,例如,选项“Webhook”可以对应于即时信息类型,选项“邮箱”可以对应于应用事件类型。应当理解,“邮箱”仅仅是与应用事件类型相对应的应用的具体示例,备选地和/或附加地,还可以接收来自其他应用的事件。例如,可以接收来自即时消息应用中的新消息,可以接收来自购物应用中的新通知,等等。
如果选项“Webhook”被选择,助手创建平台110可以确定触发事件的类型为即时信息类型,并呈现输入框420。助手创建平台110可以经由输入框420接收针对触发事件的配置(例如事件来源)。在一些实施例中,助手创建平台110可以基于数字助手和来自事件来源的消息数据,生成触发事件。
示例性地,助手创建平台110可以基于数字助手的标识(例如数字助手的ID)和来自事件来源的消息数据,生成Webhook URL。备选地或者附加地,助手创建平台110还可以基于用户105的标识(例如用户105的用户ID)、数字助手的标识(例如数字助手的ID)和来自事件来源的消息数据,生成Webhook URL。由此,可以保证Webhook URL的唯一性,避免出现混乱。助手创建平台110还可以呈现输入框430。助手创建平台110可以经由输入框430接收用于经由事件来源接收消息数据的鉴权信息(也可以被理解为密码)。进一步,创建的数字助手可以在鉴权信息与事件来源相匹配的情况下,接收消息数据。
如果选项“邮箱”被选择,助手创建平台110可以确定触发事件的类型为应用事件类型。助手创建平台110例如同样可以呈现用于接收鉴权信息的输入框。助手创建平台可以经由该输入框接收用于登录应用的鉴权信息。数字助手可以利用鉴权信息登录应用以便接收消息数据,并基于消息数据,生成触发事件。例如,用户可以在助手创建平台中设置令牌,以便数字助手利用该令牌获得相应的通知消息。
在一些实施例中,助手创建平台110还可以指定鉴权信息的有效期。例如,助手创建平台110可以指定鉴权信息的有效期为30天(或者其他时间长度)。数字助手被发布后,可以响应于确定鉴权信息的使用满足有效期(例如响应于当前日期距离上次获取到鉴权信息的日期的间隔未达到30天),由数字助手获取触发事件。可以响应于确定鉴权信息的使用不满足有效期(例如响应于当前日期距离上次获取到鉴权信息的日期的间隔达到30天),向应用数字助手的用户(例如用户135)呈现用于输入鉴权信息的输入控件,并利用经由输入控件接收的鉴权信息登录应用以便获取触发事件。
继续以选项“Webhook”为例,助手创建平台110例如还可以呈现区域440。助手创建平台110可以经由区域440接收针对来自事件来源的消息数据的格式的配置。例如,助手创建平台110可以经由区域440接收消息数据遵循的JSON格式,触发事件将基于该格式消息执行后续动作。在一些实施例中,示例400还包括控件450,助手创建平台110可以响应于控件450被触发,呈现针对动作的配置页面。动作的类型例如可以包括查询类型、插件类型和工作流类型。助手创建平台110可以经由动作的配置页面接收用户105对动作的设置请求。助手创建平台110可以基于设置请求来确定动作的类型,并基于设置请求来设置与动作的类型相匹配的动作。
示例性地,助手创建平台110可以响应于接收到对控件450的用户操作,呈现图5A至图5C所示的示例500A至示例500C。图5A至图5C示出了根据本公开的一些实施例的动作的示例配置页面(也即示例500A至示例500C)的示意图。配置页面包括三个选项,分别对应于查询类型、插件类型和工作流类型这三个类型。如果动作的类型指示查询类型,助手创建平台110可以呈现示例500A。在示例500A中,选项“查询”处于被选择状态。查询类型例如可以表示调用数字助手的查询功能来执行的动作,也即基于接收到的消息数据生成提示词,进而使得数字助手输出针对该提示词的应答。
示例500A包括输入框510。助手创建平台110可以经由输入框510接收对提示词模板的设置。在确定动作的类型指示查询类型的情况下,可以从触发事件中提取消息数据,并基于消息数据和提示词模板(也即经由输入框510接收到的提示词模板)生成查询提示词,以使得创建的数字助手基于查询提示词来执行相应的动作。提示词例如可以为用于向模型(例如语言模型)进行交互的模型输入,其用于引导模型根据学习到的知识来给出对应的模型输出。
如果动作的类型指示插件类型,助手创建平台110可以呈现示例500B。在示例500B中,选项“插件”处于被选择状态。示例500B包括区域520。助手创建平台110可以经由区域520来接收用户105的设置请求,并基于接收到的设置请求来选择由被集成在数字助手中的插件。在确定动作的类型指示插件类型的情况下,可以从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用插件以执行相应的动作。
应当理解,在此的插件是能够被集成至数字助手的多种插件。例如,搜索插件可以由搜索应用和/或搜索网页提供,并且可以调用该搜索插件来执行由消息数据指定的搜索任务。又例如,订票插件可以由订票应用和/或订票网页提供,并且可以调用该订票插件来执行由消息数据指定的订票任务,等等。
如果动作的类型指示工作流类型,助手创建平台110可以呈现示例500C。在示例500C中,选项“工作流”处于被选择状态。示例500C包括区域530。助手创建平台110可以经由区域530来接收用户105的设置请求,并基于接收到的设置请求来选择被集成在数字助手中的工作流(其可以包括自定义的工作流,例如自动回复邮件对应的工作流)。
应当理解,在此的工作流是指将被集成至数字助手中的包括多个预定节点的序列。用户可以自行定义工作流中的各个节点的具体配置和各个节点之间的数据流关系,以便完成较为复杂的任务。在确定动作的类型指示工作流类型的情况下,可以从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用工作流以执行相应的动作。
在一些实施例中,助手创建平台110还可以响应于动作类型被设置,呈现如图6所示的示例600。示例600包括控件610。助手创建平台110可以响应于接收到针对创建控件610的用户操作,基于上述设置请求来创建事件任务(也即创建触发器)。
假设控件610被设置,则允许终端用户(即,用户135)在对话式页面中启动/关闭事件任务。例如,如果用户135希望关闭事件任务“AAA”(执行自动应答邮件任务),则可以在对话式页面中输入“请关闭事件任务AAA”。此时,自动应答邮件任务将被关闭,并且不会针对接收到的新邮件提供自动应答。用户135可以在对话式页面中输入“请启动事件任务AAA”,此时自动应答邮件任务将被启动。假设控件610未被设置,则不允许终端用户在对话式页面中启动/关闭事件任务。
在一些实施例中,助手创建平台110可以响应于接收到用户交互,存储触发器。如果该触发器被分享给其他用户,其他用户同样可以在另一数字助手的另一创建页面中,加载触发器。可以基于触发器来创建另一数字助手以使得创建的另一数字助手响应于检测到触发事件而执行动作。由此,可以实现触发器的共享,一个用户创建的触发器可以被分享给其他用户使用,也即一个触发器可以被多个数字助手共享,由此可以提升触发器的应用性和灵活性。
返回图2,触发器被创建后,助手创建平台110还可以响应于接收到用于测试数字助手的测试请求,执行对数字助手的测试220,在通过测试之后用户105可以发布230数字助手。助手创建平台110可以获取用于模拟来自事件来源的触发事件(例如假设接收到一个Webhook-URL,或者收到一封邮件)。助手创建平台110可以提供数字助手执行动作的执行结果(例如可以包括正常执行和出现异常)。该执行结果例如可以被提供在数字助手的对话式页面中。在一些实施例中,为避免频繁接收到不同触发事件所对应的执行结果,助手创建平台110还可以响应于在对话式页面中接收到切换请求,切换触发器的工作状态。例如,助手创建平台110可以响应于在对话式页面中接收到会话“关闭XX触发器”,将XX触发器由启用状态切换至禁止状态。
数字助手被创建之后,创建的数字助手可以检测触发事件,并响应于检测到触发事件,创建的数字助手可以基于自身的配置来执行与触发事件对应的动作。创建可以包括多种形式,例如,在测试阶段可以创建数字助手,该数字助手可以在助手创建平台110中由用户105使用。又例如,调用触发器的数字助手被测试完成后,可以被发布至助手应用平台130。此时,创建的数字助手可以被更多用户(例如,多个用户135)使用。
数字助手被发布后,助手应用平台130可以向用户135提供关于数字助手的引导信息,该引导信息例如可以用于指示数字助手的功能和用途。具体地,假设数字助手包括执行自动应答邮件任务的触发器,则该数字助手可以利用指定的鉴权信息(例如,邮件账户和密码)登录邮件服务器。如果该邮件账户中接收到新邮件,则可以自动答复该新邮件,等等。
综上所述,根据本公开的实施例,可以配置数字助手的触发器。此时,数字助手可以基于触发事件而执行动作,由此支持数字助手基于来自其他应用的事件来执行相应的动作。这有助于提升数字助手的应用性和灵活性,并且使得数字助手可以与其他应用协作进而执行更为复杂的任务。
示例过程
图7示出了根据本公开的一些实施例的用于创建数字助手的过程700的流程图。过程700可以被实现在助手创建平台110处。下面参考图1描述过程700。
如图7所示,在框710处,在数字助手的创建页面中呈现设置区域,设置区域用于设置数字助手的触发器,触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件。在框720处,响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器。在框730处,基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。
在一些实施例中,触发事件的类型包括即时信息类型,并且基于设置请求来设置触发器包括:基于数字助手和来自事件来源的消息数据,生成触发事件。
在一些实施例中,生成触发事件进一步包括:设置用于经由事件来源接收消息数据的鉴权信息。
在一些实施例中,触发事件的类型包括应用事件类型,并且基于设置请求来设置触发器包括:设置用于登录应用的鉴权信息;利用鉴权信息登录应用以便接收消息数据;以及基于消息数据,生成触发事件。
在一些实施例中,设置鉴权信息进一步包括:指定鉴权信息的有效期。
在一些实施例中,基于设置请求来设置触发器包括:基于设置请求来确定动作的类型;以及基于设置请求来设置与动作的类型相匹配的动作。
在一些实施例中,该过程700进一步包括:响应于确定动作的类型指示查询类型,从触发事件中提取消息数据;以及基于消息数据和提示词模板生成查询提示词,以使得创建的数字助手基于查询提示词来执行动作。
在一些实施例中,该过程700进一步包括:响应于确定动作的类型指示插件类型,基于设置请求来选择由数字助手所集成的插件;以及从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用插件以执行动作。
在一些实施例中,该过程700进一步包括:响应于确定动作的类型指示工作流类型,基于设置请求来选择由数字助手所集成的工作流;以及从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用工作流以执行动作。
在一些实施例中,该过程700进一步包括:响应于接收到用于测试数字助手的测试请求,获取用于模拟来自事件来源的触发事件;以及提供数字助手执行动作的执行结果。
在一些实施例中,该过程700数字助手在对话式页面中提供执行结果,并且该过程700进一步包括:响应于在对话式页面中接收到切换请求,切换触发器的工作状态。
在一些实施例中,该过程700进一步包括:由创建的数字助手检测触发事件;以及响应于检测到触发事件,由创建的数字助手执行动作。
在一些实施例中,检测触发事件包括以下至少任一项:响应于确定鉴权信息的使用满足有效期,由数字助手获取触发事件;以及响应于确定鉴权信息的使用不满足有效期,呈现用于输入鉴权信息的输入控件;以及利用经由输入控件接收的鉴权信息登录应用以便获取触发事件。
在一些实施例中,该过程700进一步包括:响应于接收到用户交互,存储触发器;在另一数字助手的另一创建页面中,加载触发器;以及基于触发器来创建另一数字助手以使得创建的另一数字助手响应于检测到触发事件而执行动作。
示例装置和设备
本公开的实施例还提供了用于实现上述方法或过程的相应装置。图8示出了根据本公开的一些实施例的用于创建数字助手的装置800的示意性结构框图。装置800例如可以被包括在图1中助手创建平台110中。装置800中的各个模块/组件可以由硬件、软件、固件或者它们的任意组合来实现。
如图所示,装置800包括设置区域呈现模块810,被配置为在数字助手的创建页面中呈现设置区域,设置区域用于设置数字助手的触发器,触发器指定用于接收触发事件的事件来源以及对应于触发事件的动作,触发事件是来自数字助手以外的应用的事件。装置800还包括触发器设置模块820,被配置为响应于接收到针对设置区域的设置请求,基于设置请求来设置触发器。装置800还包括数字助手发布模块830,被配置为基于触发器来创建数字助手,以使得创建的数字助手响应于接收到触发事件而执行动作。
在一些实施例中,触发事件的类型包括即时信息类型,并且触发器设置模块进一步被配置用于:基于数字助手和来自事件来源的消息数据,生成触发事件。
在一些实施例中,触发器设置模块进一步被配置为:设置用于经由事件来源接收消息数据的鉴权信息。
在一些实施例中,触发事件的类型包括应用事件类型,并且触发器设置模块进一步被配置为:设置用于登录应用的鉴权信息;利用鉴权信息登录应用以便接收消息数据;以及基于消息数据,生成触发事件。
在一些实施例中,触发器设置模块进一步被配置为:指定鉴权信息的有效期。
在一些实施例中,触发器设置模块进一步被配置为:基于设置请求来确定动作的类型;以及基于设置请求来设置与动作的类型相匹配的动作。
在一些实施例中,该装置进一步包括:提取模块,被配置为响应于确定动作的类型指示查询类型,从触发事件中提取消息数据;以及生成模块,被配置为基于消息数据和提示词模板生成查询提示词,以使得创建的数字助手基于查询提示词来执行动作。
在一些实施例中,该装置进一步包括:插件选择模块,被配置为响应于确定动作的类型指示插件类型,基于设置请求来选择由数字助手所集成的插件;以及插件调用模块,被配置为从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用插件以执行动作。
在一些实施例中,该装置进一步包括:工作流选择模块,被配置为响应于确定动作的类型指示工作流类型,基于设置请求来选择由数字助手所集成的工作流;以及工作流调用模块,被配置为从触发事件中提取消息数据,以使得创建的数字助手基于消息数据,调用工作流以执行动作。
在一些实施例中,该装置进一步包括:获取模块,被配置为响应于接收到用于测试数字助手的测试请求,获取用于模拟来自事件来源的触发事件;以及提供模块,被配置为提供数字助手执行动作的执行结果。
在一些实施例中,数字助手在对话式页面中提供执行结果,并且装置进一步包括:切换模块,被配置为响应于在对话式页面中接收到切换请求,切换触发器的工作状态。
在一些实施例中,该装置进一步包括:检测模块,被配置为由创建的数字助手检测触发事件;以及执行模块,被配置为响应于检测到触发事件,由创建的数字助手执行动作。
在一些实施例中,检测模块进一步被配置为:响应于确定鉴权信息的使用满足有效期,由数字助手获取触发事件。
在一些实施例中,检测模块进一步被配置为:响应于确定鉴权信息的使用不满足有效期,呈现用于输入鉴权信息的输入控件;以及利用经由输入控件接收的鉴权信息登录应用以便获取触发事件。
在一些实施例中,该装置进一步包括:存储模块,被配置为响应于接收到用户交互,存储触发器;加载模块,被配置为在另一数字助手的另一创建页面中,加载触发器;以及创建模块,被配置为基于触发器来创建另一数字助手以使得创建的另一数字助手响应于检测到触发事件而执行动作。
装置800中所包括的单元和/或模块可以利用各种方式来实现,包括软件、硬件、固件或其任意组合。在一些实施例中,一个或多个单元和/或模块可以使用软件和/或固件来实现,例如存储在存储介质上的机器可执行指令。除了机器可执行指令之外或者作为替代,装置800中的部分或者全部单元和/或模块可以至少部分地由一个或多个硬件逻辑组件来实现。作为示例而非限制,可以使用的示范类型的硬件逻辑组件包括现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准品(ASSP)、片上系统(SOC)、复杂可编程逻辑器件(CPLD),等等。
应当理解,以上方法中的一个或多个步骤可以由适当的电子设备或电子设备的组合来执行。这样的电子设备或电子设备的组合例如可以包括图1中的助手创建平台110和/或助手应用平台130。
图9示出了其中可以实施本公开的一个或多个实施例的电子设备900的框图。应当理解,图9所示出的电子设备900仅仅是示例性的,而不应当构成对本文所描述的实施例的功能和范围的任何限制。图9所示出的电子设备900可以用于实现图1的助手创建平台110,助手应用平台130,和/或,图8的装置800。
如图9所示,电子设备900是通用电子设备的形式。电子设备900的组件可以包括但不限于一个或多个处理器或处理单元910、存储器920、存储设备930、一个或多个通信单元940、一个或多个输入设备950以及一个或多个输出设备960。处理单元910可以是实际或虚拟处理器并且能够根据存储器920中存储的程序来执行各种处理。在多处理器系统中,多个处理单元并行执行计算机可执行指令,以提高电子设备900的并行处理能力。
电子设备900通常包括多个计算机存储介质。这样的介质可以是电子设备900可访问的任何可以获取的介质,包括但不限于易失性和非易失性介质、可拆卸和不可拆卸介质。存储器920可以是易失性存储器(例如寄存器、高速缓存、随机访问存储器(RAM))、非易失性存储器(例如,只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、闪存)或它们的某种组合。存储设备930可以是可拆卸或不可拆卸的介质,并且可以包括机器可读介质,诸如闪存驱动、磁盘或者任何其他介质,其可以能够用于存储信息和/或数据并且可以在电子设备900内被访问。
电子设备900可以进一步包括另外的可拆卸/不可拆卸、易失性/非易失性存储介质。尽管未在图9中示出,可以提供用于从可拆卸、非易失性磁盘(例如“软盘”)进行读取或写入的磁盘驱动和用于从可拆卸、非易失性光盘进行读取或写入的光盘驱动。在这些情况中,每个驱动可以由一个或多个数据介质接口被连接至总线(未示出)。存储器920可以包括计算机程序产品925,其具有一个或多个程序模块,这些程序模块被配置为执行本公开的各种实施例的各种方法或动作。
通信单元940实现通过通信介质与其他电子设备进行通信。附加地,电子设备900的组件的功能可以以单个计算集群或多个计算机器来实现,这些计算机器能够通过通信连接进行通信。因此,电子设备900可以使用与一个或多个其他服务器、网络个人计算机(PC)或者另一个网络节点的逻辑连接来在联网环境中进行操作。
输入设备950可以是一个或多个输入设备,例如鼠标、键盘、追踪球等。输出设备960可以是一个或多个输出设备,例如显示器、扬声器、打印机等。电子设备900还可以根据需要通过通信单元940与一个或多个外部设备(未示出)进行通信,外部设备诸如存储设备、显示设备等,与一个或多个使得用户与电子设备900交互的设备进行通信,或者与使得电子设备900与一个或多个其他电子设备通信的任何设备(例如,网卡、调制解调器等)进行通信。这样的通信可以经由输入/输出(I/O)接口(未示出)来执行。
根据本公开的示例性实现方式,提供了一种计算机可读存储介质,其上存储有计算机可执行指令,其中计算机可执行指令被处理器执行以实现上文描述的方法。根据本公开的示例性实现方式,还提供了一种计算机程序产品,计算机程序产品被有形地存储在非瞬态计算机可读介质上并且包括计算机可执行指令,而计算机可执行指令被处理器执行以实现上文描述的方法。
这里参照根据本公开实现的方法、装置、设备和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解,流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合,都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理单元,从而生产出一种机器,使得这些指令在通过计算机或其他可编程数据处理装置的处理单元执行时,产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中,这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作,从而,存储有指令的计算机可读介质则包括一个制造品,其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
可以把计算机可读程序指令加载到计算机、其他可编程数据处理装置、或其他设备上,使得在计算机、其他可编程数据处理装置或其他设备上执行一系列操作步骤,以产生计算机实现的过程,从而使得在计算机、其他可编程数据处理装置、或其他设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实现的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分,模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实现,上述说明是示例性的,并非穷尽性的,并且也不限于所公开的各实现。在不偏离所说明的各实现的范围和精神的情况下,对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择,旨在最好地解释各实现的原理、实际应用或对市场中的技术的改进,或者使本技术领域的其他普通技术人员能理解本文公开的各个实现方式。
Claims (18)
- 一种用于创建数字助手的方法,包括:在所述数字助手的创建页面中呈现设置区域,所述设置区域用于设置所述数字助手的触发器,所述触发器指定用于接收触发事件的事件来源以及对应于所述触发事件的动作,所述触发事件是来自所述数字助手以外的应用的事件;响应于接收到针对所述设置区域的设置请求,基于所述设置请求来设置所述触发器;以及基于所述触发器来创建所述数字助手,以使得创建的所述数字助手响应于接收到所述触发事件而执行所述动作。
- 根据权利要求1所述的方法,其中所述触发事件的类型包括即时信息类型,并且基于所述设置请求来设置所述触发器包括:基于所述数字助手和来自所述事件来源的消息数据,生成所述触发事件。
- 根据权利要求2所述的方法,其中生成所述触发事件进一步包括:设置用于经由所述事件来源接收所述消息数据的鉴权信息。
- 根据权利要求1所述的方法,其中所述触发事件的类型包括应用事件类型,并且基于所述设置请求来设置所述触发器包括:设置用于登录所述应用的鉴权信息;利用所述鉴权信息登录所述应用以便接收消息数据;以及基于所述消息数据,生成所述触发事件。
- 根据权利要求4所述的方法,其中设置所述鉴权信息进一步包括:指定所述鉴权信息的有效期。
- 根据权利要求1所述的方法,其中基于所述设置请求来设置所述触发器包括:基于所述设置请求来确定所述动作的类型;以及基于所述设置请求来设置与所述动作的类型相匹配的动作。
- 根据权利要求6所述的方法,进一步包括:响应于确定所述动作的所述类型指示查询类型,从所述触发事件中提取消息数据;以及基于所述消息数据和提示词模板生成查询提示词,以使得创建的所述数字助手基于所述查询提示词来执行所述动作。
- 根据权利要求6所述的方法,进一步包括:响应于确定所述动作的所述类型指示插件类型,基于所述设置请求来选择由所述数字助手所集成的插件;以及从所述触发事件中提取消息数据,以使得创建的所述数字助手基于所述消息数据,调用所述插件以执行所述动作。
- 根据权利要求6所述的方法,进一步包括:响应于确定所述动作的所述类型指示工作流类型,基于所述设置请求来选择由所述数字助手所集成的工作流;以及从所述触发事件中提取消息数据,以使得创建的所述数字助手基于所述消息数据,调用所述工作流以执行所述动作。
- 根据权利要求1所述的方法,进一步包括:响应于接收到用于测试所述数字助手的测试请求,获取用于模拟来自所述事件来源的所述触发事件;以及提供所述数字助手执行所述动作的执行结果。
- 根据权利要求10所述的方法,其中所述数字助手在对话式页面中提供所述执行结果,并且所述方法进一步包括:响应于在所述对话式页面中接收到切换请求,切换所述触发器的工作状态。
- 根据权利要求5所述的方法,进一步包括:由创建的所述数字助手检测所述触发事件;以及响应于检测到所述触发事件,由创建的所述数字助手执行所述动作。
- 根据权利要求12所述的方法,其中检测所述触发事件包括以下至少任一项:响应于确定所述鉴权信息的使用满足所述有效期,由所述数字助手获取所述触发事件;以及响应于确定所述鉴权信息的使用不满足所述有效期,呈现用于输入所述鉴权信息的输入控件;以及利用经由所述输入控件接收的鉴权信息登录所述应用以便获取所述触发事件。
- 根据权利要求1所述的方法,进一步包括:响应于接收到用户交互,存储所述触发器;在另一数字助手的另一创建页面中,加载所述触发器;以及基于所述触发器来创建另一数字助手以使得创建的所述另一数字助手响应于检测到所述触发事件而执行所述动作。
- 一种用于创建数字助手的装置,包括:设置区域呈现模块,被配置为在所述数字助手的创建页面中呈现设置区域,所述设置区域用于设置所述数字助手的触发器,所述触发器指定用于接收触发事件的事件来源以及对应于所述触发事件的动作,所述触发事件是来自所述数字助手以外的应用的事件;触发器设置模块,被配置为响应于接收到针对所述设置区域的设置请求,基于所述设置请求来设置所述触发器;以及数字助手创建模块,被配置为基于所述触发器来创建所述数字助手,以使得创建的所述数字助手响应于接收到所述触发事件而执行所述动作。
- 一种电子设备,包括:至少一个处理单元;以及至少一个存储器,所述至少一个存储器被耦合到所述至少一个处理单元并且存储用于由所述至少一个处理单元执行的指令,所述指令在由所述至少一个处理单元执行时使所述电子设备执行根据权利要求1至14中任一项所述的方法。
- 一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序可由处理器执行以实现根据权利要求1至14中任一项所述的方法。
- 一种计算机程序产品,包括计算机程序,其中所述计算机程序在被处理器执行时实现根据权利要求1至14中任一项所述的方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410383220.0 | 2024-03-29 | ||
| CN202410383220.0A CN120743397A (zh) | 2024-03-29 | 2024-03-29 | 用于创建数字助手的方法、装置、设备和介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025200591A1 true WO2025200591A1 (zh) | 2025-10-02 |
Family
ID=97175813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/138824 Pending WO2025200591A1 (zh) | 2024-03-29 | 2024-12-12 | 用于创建数字助手的方法、装置、设备和介质 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20250310282A1 (zh) |
| CN (1) | CN120743397A (zh) |
| WO (1) | WO2025200591A1 (zh) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110785970A (zh) * | 2017-04-14 | 2020-02-11 | 脸谱公司 | 使网页的机器人创建自动化的技术 |
| US10608966B1 (en) * | 2017-04-17 | 2020-03-31 | Facebook, Inc. | Techniques to customize bot messaging behavior |
| US20230121261A1 (en) * | 2021-10-04 | 2023-04-20 | Qualtrics, Llc | Providing a sequence-builder-user interface for generating a digital action sequence |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5809492A (en) * | 1996-04-09 | 1998-09-15 | At&T Corp. | Apparatus and method for defining rules for personal agents |
| US11128627B2 (en) * | 2018-03-13 | 2021-09-21 | Microsoft Technology Licensing, Llc | Triggering and controlling workflows across applications and services used in cloud computing systems |
| US11086696B2 (en) * | 2019-08-01 | 2021-08-10 | Microsoft Technology Licensing, Llc | Parallel cloned workflow execution |
| US11727213B2 (en) * | 2020-09-09 | 2023-08-15 | Servicenow, Inc. | Automatic conversation bot generation using input form |
| CN120980535A (zh) * | 2021-05-09 | 2025-11-18 | 华为技术有限公司 | 一种通信方法及装置 |
| US12282752B2 (en) * | 2022-11-28 | 2025-04-22 | International Business Machines Corporation | Automatic detection of robotic process automation trigger events |
| US20250131359A1 (en) * | 2023-10-23 | 2025-04-24 | Expensify, Inc. | Augmenting chat-based workflows with large language models |
-
2024
- 2024-03-29 CN CN202410383220.0A patent/CN120743397A/zh active Pending
- 2024-07-10 US US18/768,181 patent/US20250310282A1/en active Pending
- 2024-12-12 WO PCT/CN2024/138824 patent/WO2025200591A1/zh active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110785970A (zh) * | 2017-04-14 | 2020-02-11 | 脸谱公司 | 使网页的机器人创建自动化的技术 |
| US10608966B1 (en) * | 2017-04-17 | 2020-03-31 | Facebook, Inc. | Techniques to customize bot messaging behavior |
| US20230121261A1 (en) * | 2021-10-04 | 2023-04-20 | Qualtrics, Llc | Providing a sequence-builder-user interface for generating a digital action sequence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120743397A (zh) | 2025-10-03 |
| US20250310282A1 (en) | 2025-10-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2024240105A1 (zh) | 用于信息处理的方法、装置、设备和存储介质 | |
| WO2025086565A1 (zh) | 用于管理工作流的方法、装置、设备和介质 | |
| WO2025223030A1 (zh) | 信息处理方法、装置、设备和存储介质 | |
| WO2026001060A1 (zh) | 信息处理方法、装置、设备和存储介质 | |
| WO2024240149A1 (zh) | 用于应用处理的方法、装置、设备和存储介质 | |
| WO2024240100A1 (zh) | 用于测试用例生成的方法、装置、设备和存储介质 | |
| WO2025026189A1 (zh) | 用于提示词管理的方法、装置、设备和存储介质 | |
| EP4722893A1 (en) | Method and apparatus for application processing, and device and storage medium | |
| WO2025200591A1 (zh) | 用于创建数字助手的方法、装置、设备和介质 | |
| CN118197305A (zh) | 语音控制方法、装置和电子设备 | |
| CN119002745B (zh) | 用于会话交互的方法、装置、设备和存储介质 | |
| US12242742B1 (en) | Storing data in a digital assistant | |
| US20260050494A1 (en) | Method, device and storage medium for function invocation | |
| US20260086825A1 (en) | Method, apparatus, device, storage medium and program product for request processing | |
| US20250307040A1 (en) | Managing data output of a workflow | |
| CN119088437B (zh) | 应用配置方法、装置、设备和存储介质 | |
| US20260003583A1 (en) | Interface processing | |
| WO2026040535A1 (zh) | 用于应用创建的方法、装置、设备、介质和程序产品 | |
| WO2025091733A1 (zh) | 用于数字助手交互的方法、装置、设备和存储介质 | |
| CN119312393A (zh) | 数据处理的方法、装置、设备、存储介质和程序产品 | |
| WO2025092386A1 (zh) | 用于处理任务的方法、装置、设备和存储介质 | |
| CN120409681A (zh) | 用于任务处理方法、装置、设备和存储介质 | |
| CN120806144A (zh) | 大模型应用的提示词风险评估方法、装置、设备和存储介质 | |
| CN119088438A (zh) | 信息处理和应用配置方法、装置、设备、存储介质和产品 | |
| WO2026077043A1 (zh) | 任务处理的方法、装置、设备、存储介质和程序产品 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24931738 Country of ref document: EP Kind code of ref document: A1 |