Method and device for processing backlog, computing equipment and storage medium

Abstract

The invention provides a to-do list processing method, which comprises the following steps: acquiring target user input which represents a to-do list processing request initiated by a target user; based on the target user input, identifying a target processing intention of a target user for a to-do list by using a first agent; based on the target processing intention, determining an application programming interface for executing the processing request by using a second agent; on the basis of the determined application programming interface, acquiring required processing parameters by using a third agent; calling the application programming interface by utilizing the processing parameters to obtain a calling result; and on the basis of the calling result, generating at least one processing option for the to-do list by utilizing a fourth agent, so that the target user can execute the to-do list represented by the selected option by selecting the option in the at least one processing option.

Description

Technical Field

[0001] The present disclosure relates to the technical field of computers, and in particular to a method and apparatus for processing a to-do list, a computing device, and a storage medium. Background Art

[0002] At present, to-do processing systems usually use traditional GUI (Graphical User Interface) interactions, which have a certain learning threshold and require training for target users. In addition, it is difficult to balance different user habits, resulting in poor user experience. On the other hand, the to-do center has many levels of pages, and users need to click multiple times to complete to-do processing, query and other operations, resulting in low efficiency of to-do processing. Summary of the invention

[0003] In view of this, the present disclosure provides a method and apparatus for processing a to-do list, a computing device, and a storage medium, in an effort to overcome some or all of the above-mentioned deficiencies and other possible deficiencies.

[0004] According to a first aspect of the present disclosure, a method for processing a to-do list is provided, comprising: obtaining target user input, wherein the target user input represents a processing request for the to-do list initiated by the target user; based on the target user input, using a first agent to identify the target user's target processing intention for the to-do list; based on the target processing intention, using a second agent to determine an application programming interface for executing the processing request; based on the determined application programming interface, using a third agent to obtain required processing parameters; using the processing parameters to call the application programming interface to obtain a calling result; based on the calling result, using a fourth agent to generate at least one processing option for the to-do list, so that the target user can execute the to-do list represented by the selected option by selecting an option from the at least one processing option.

[0005] In some embodiments, the target user input is the voice of the target user, and wherein, based on the target user input, the first agent is used to identify the target user's target processing intention for the to-do items, including: converting the voice into text; based on the text, using the first agent to identify the target user's target processing intention for the to-do items.

[0006] In some embodiments, the target user input is text input by the target user, and based on the target user input, the target user's target processing intention for the to-do items is identified using the first agent, including vectorizing the text to obtain a first embedding vector; using the first embedding vector, the first agent is used to identify multiple processing intentions from a processing intention library, and each of the multiple similarities between the intention vectors corresponding to the multiple processing intentions and the first embedding vector is greater than a similarity threshold, wherein the processing intention library includes multiple processing intentions and the intention vectors corresponding to the multiple processing intentions. The processing intention corresponding to the maximum similarity among the multiple similarities is determined as the target processing intention for the to-do items.

[0007] In some embodiments, based on the target user input, a first agent is used to identify the target user's target processing intention for to-do items, including: obtaining the context of the target user input; obtaining multiple user inputs to be trained and multiple response data corresponding to the multiple user inputs to be trained from the context, wherein the response data is intention data characterizing the intentions of the multiple user inputs to be trained obtained by performing intent recognition on the multiple user inputs to be trained using a first deep learning network; determining multiple matching degrees between the multiple response data and the multiple user inputs to be trained; determining the user input to be trained corresponding to a matching degree greater than a matching degree threshold among the multiple matching degrees as training data; marking the training data with a processing intention flag; training the first deep learning network with the training data and the processing intention flag to obtain the first agent; based on the target user input, using the first agent to identify the target user's target processing intention for to-do items.

[0008] In some embodiments, a first deep learning network is trained using the training data and the processing intention flag to obtain the first intelligent agent, including: extracting semantic features and syntactic features associated with the semantic features from the training data; using the semantic features and syntactic features as inputs of the first deep learning network and the processing intention flag as outputs of the first deep learning network, and training the first deep learning network to obtain the first intelligent agent.

[0009] In some embodiments, based on the determined application programming interface, using a third agent to obtain the required processing parameters includes: presenting a user interface to request parameter input related to the parameters; based on the determined application programming interface, using a third agent to obtain the required processing parameters from the parameter input.

[0010] In some embodiments, based on the call result, a fourth agent is used to generate at least one processing option for the to-do item, including: based on the call result and the context of the target user input, a fourth agent is used to generate at least one processing option for the to-do item.

[0011] According to a second aspect of the present disclosure, there is provided a device for processing a to-do list, comprising: an input acquisition module configured to acquire target user input, wherein the target user input represents a processing request for the to-do list initiated by the target user; an intention recognition module configured to identify the target user's target processing intention for the to-do list using a first agent based on the target user input; an application programming interface determination module configured to determine an application programming interface for executing the processing request using a second agent based on the target processing intention; a parameter acquisition module configured to acquire required processing parameters using a third agent based on the determined application programming interface; a calling module configured to call the application programming interface using the processing parameters to obtain a calling result; and a processing option generation module configured to generate at least one processing option for the to-do list using a fourth agent based on the calling result, so that the target user can execute the to-do list represented by the selected option by selecting an option from the at least one processing option.

[0012] According to a third aspect of the present disclosure, a computing device is provided, comprising: a memory configured to store computer-executable instructions; and a processor configured to perform any one of the methods described above when the computer-executable instructions are executed by the processor.

[0013] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, which stores computer-executable instructions. When the computer-executable instructions are executed, any one of the methods described above is executed.

[0014] According to a fifth aspect of the present disclosure, a computer program product is provided, characterized in that the computer program product comprises computer executable instructions, and the computer executable instructions implement any of the methods described above when executed.

[0015] In the to-do list processing method and device claimed for protection in the present disclosure, after obtaining the user input, the first agent is first used to identify the target user's target processing intention for the to-do list; then, based on the target processing intention, the second agent is used to determine the application programming interface for executing the processing request, and based on the determined application programming interface, the third agent is used to obtain the required processing parameters; after calling the application programming interface with the parameters, the fourth agent can be used to generate at least one processing option for the to-do list based on the call result and optionally based on the context. In this way, on the basis of accurately understanding the user's processing intention, the to-do processing flow is split into a multi-stage decision-making and execution process, and each stage is processed by a dedicated agent, which greatly improves the accuracy and efficiency of to-do list processing, while avoiding multiple clicks and other operations, and improving the user's interactive experience.

[0016] These and other advantages of the disclosure will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Embodiments of the present disclosure will now be described in more detail and with reference to the accompanying drawings, in which:

[0018] Figure 1 An exemplary application scenario in which the technical solution according to the embodiments of the present disclosure can be implemented is illustrated;

[0019] Figure 2 A schematic flow chart of a method for processing a to-do list according to an embodiment of the present disclosure is illustrated;

[0020] Figure 3 An exemplary flowchart of a method for using a first agent to identify a target user's target processing intention for a to-do item according to an embodiment of the present disclosure is illustrated;

[0021] Figure 4 An exemplary structural block diagram of a to-do list processing device according to an embodiment of the present disclosure is illustrated;

[0022] Figure 5 An example system is illustrated that includes an example computing device that represents one or more systems and / or devices that may implement the various techniques described herein. DETAILED DESCRIPTION

[0023] The following description provides specific details of various embodiments of the present disclosure so that those skilled in the art can fully understand and implement the various embodiments of the present disclosure. It should be understood that the technical solution of the present disclosure can be implemented without some of these details. In some cases, the present disclosure does not show or describe in detail some well-known structures or functions to avoid these unnecessary descriptions from obscuring the description of the embodiments of the present disclosure. The terms used in the present disclosure should be understood in their broadest reasonable manner, even if they are used in conjunction with specific embodiments of the present disclosure.

[0024] Figure 1 FIG. 1 illustrates an exemplary application scenario 100 in which the technical solution according to an embodiment of the present disclosure can be implemented. Figure 1 As shown, the application scenario shown includes a terminal 110 and a server 120 , and the terminal 110 is communicatively coupled with the server 120 via a network 130 .

[0025] The terminal 110 may be an intelligent terminal device with web page access capability. As an example, the to-do processing application 140 may be run on the terminal 110. The target user may input on the to-do processing application to initiate a processing request for the to-do items to the server 120.

[0026] Server 120 can obtain target user input, and based on the target user input, use the first agent to identify the user's target processing intention for the to-do item; then based on the target processing intention, use the second agent to determine the application programming interface for executing the processing request; then, based on the determined application programming interface, use the third agent to obtain the required processing parameters, and use the processing parameters to call the application programming interface to obtain the calling result; finally, based on the calling result, use the fourth agent to generate at least one processing option for the to-do item, and the processing option can be presented on terminal 110, so that the user can execute the to-do item represented by the selected option by selecting an option from the at least one processing option.

[0027] It should be noted that the terminal 110 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, an intelligent speaker, a smart watch, etc., but is not limited thereto. The server 120 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application is not limited here. The network 130 can be, for example, a wide area network (WAN), a local area network (LAN), a wireless network, a public telephone network, an intranet, and any other type of network known to those skilled in the art.

[0028] The scenario described above is merely an example in which the embodiments of the present disclosure may be implemented and is not limiting.

[0029] Figure 2 A schematic flow chart of a method 200 for processing a to-do list according to an embodiment of the present disclosure is shown. The method may be used, for example, in Figure 1 The server 120 shown is implemented, of course, this is not restrictive, and it can also be implemented independently on the terminal 110 or other third-party entities. Figure 2 As shown, the method 200 includes the following steps.

[0030] In step 210, a target user input is obtained, wherein the target user input represents a processing request for a to-do item initiated by the target user. The target user input may be a text or a voice. For example, the target user input may be "I want to know my to-do list".

[0031] In step 220, based on the target user input, the first agent is used to identify the user's target processing intention for the to-do items. The agents described here and below can be various trained deep learning models or large language models. The processing intention represents the specific processing operation that the target user wants to initiate for the to-do items, such as querying the to-do items, creating a new to-do item, deleting the to-do items, approving the to-do items, etc. For example, when the target user input is "I want to know my to-do list", the target processing intention at the identification point is "query the to-do list".

[0032] In some embodiments, the target user input may be the target user's voice. In this case, when the first agent is used to identify the target user's target processing intention for the to-do items, the voice may be converted into text; then, based on the text, the first agent is used to identify the target user's target processing intention for the to-do items. As an example, the voice may be converted into text in any suitable manner (e.g., by calling existing software development kits for WeChat or various input methods). This can improve the processing efficiency of the to-do items.

[0033] In some embodiments, the target user input is text input by the target user. In this case, when using the first agent to identify the target user's target processing intention for the to-do items, the text can be first vectorized to obtain a first embedding vector. As an example, the BERT model can be used to vectorize the text. BERT is a language representation model that stands for Bidirectional Encoder Representations from Transformers. Then, using the first embedding vector, the first agent is used to identify multiple processing intentions from the processing intention library, and each of the multiple similarities between the intention vectors corresponding to the multiple processing intentions and the first embedding vector is greater than a similarity threshold, wherein the processing intention library includes multiple processing intentions and the intention vectors corresponding to the multiple processing intentions. Finally, the processing intention corresponding to the maximum similarity among the multiple similarities is determined as the target processing intention for the to-do items. As an example, the intention vector corresponding to the first processing intention among the multiple processing intentions has the largest similarity with the first embedding vector, and the first processing intention can be determined as the target processing intention for the to-do items.

[0034] In step 230, based on the target processing intent, the second agent is used to determine an application programming interface for executing the processing request. The application programming interface can be called to complete the processing request for the to-do item. The functions of the application programming interface can be pre-defined and designed, and the application programming interface can be stored in a one-to-one correspondence with the processing intent. As an example, when the target processing intent is "query to-do list", it can be determined that the application programming interface to be called is GetTodoListAPI, which can be used to query the to-do list.

[0035] In step 240, based on the determined application programming interface, a third agent is used to obtain the required processing parameters. As an example, for the application programming interface GetTodoListAPI, the processing parameters that need to be obtained are the user's ID (e.g., user name, etc.) or other identity authentication parameters (e.g., password, ID card, gender, age, etc.). In some embodiments, obtaining the required processing parameters using a third agent may include: presenting a user interface to request parameter input related to the parameters; and, based on the determined application programming interface, obtaining the required processing parameters from the parameter input using a third agent. This allows the requesting user to input the required processing parameters. In some embodiments, the required processing parameters can also be obtained directly from the target user input.

[0036] In step 250, the application programming interface is called using the processing parameters to obtain a call result. As an example, the call result may be "todoList": ["Approve the aforementioned item 2"; "Attend the meeting"; "Approve leave matters"].

[0037] In step 260, based on the call result, a fourth agent is used to generate at least one processing option for the to-do item, so that the user can execute the to-do item represented by the selected option by selecting an option from the at least one processing option. As an example, when the call result is "todoList": ["Approve the aforementioned Item 2"; "Attend the meeting"; "Approve leave"]", the generated processing options may be "You have the following to-do items: "Approve the aforementioned Item 2"; "Attend the meeting"; "Approve leave". Is there anything I can do for you?". Of course, at least one processing option for the to-do item may be presented in any suitable manner.

[0038] In some embodiments, the first agent, the second agent, the third agent, and the fourth agent are independent agents, which realizes the modular design of to-do processing, improves the flexibility and adaptability of to-do processing, and facilitates the independent upgrade and maintenance of each module.

[0039] In some embodiments, using a fourth agent to generate at least one processing option for the to-do item may include: based on the call result and the context input by the target user, using a fourth agent to generate at least one processing option for the to-do item. For example, the "previously mentioned item 2" may be specifically interpreted as "approving the document" in combination with the context.

[0040] In the method for processing to-do items claimed in the present disclosure, after obtaining user input, the first agent is first used to identify the target user's target processing intention for to-do items; then, based on the target processing intention, the second agent is used to determine the application programming interface for executing the processing request, and based on the determined application programming interface, the third agent is used to obtain the required processing parameters; after calling the application programming interface with the parameters, the fourth agent can be used to generate at least one processing option for the to-do items based on the call result and optionally based on the context. In this way, based on the accurate understanding of the user's processing intention, the to-do processing flow is split into a multi-stage decision-making and execution process, and each stage is processed by a dedicated agent, which greatly improves the accuracy and efficiency of to-do processing, while avoiding multiple clicks and other operations, and improving the user's interactive experience.

[0041] Figure 3 The exemplary flowchart of a method 300 for using a first agent to identify a target user's target processing intention for a to-do item according to an embodiment of the present disclosure is shown. The method 300 may be used to implement a reference Figure 2 Step 220 described above. Figure 3 As shown, the method 300 includes the following steps.

[0042] In step 310, the context of the target user input is obtained.

[0043] In step 320, a plurality of user inputs to be trained and a plurality of response data corresponding to the plurality of user inputs to be trained are obtained from the context. The response data here is the intent data representing the intent of the plurality of user inputs to be trained obtained by performing intent recognition on the plurality of user inputs to be trained using the first deep learning network.

[0044] In step 330, multiple matching degrees between the multiple response data and the multiple user inputs to be trained are determined. Matching here can be understood as the degree to which the response data conforms to the intention of the user input to be trained, which can be obtained by evaluating the satisfaction of the response data.

[0045] In step 340, the user input to be trained corresponding to the matching degree greater than the matching degree threshold among the multiple matching degrees is determined as training data.

[0046] In step 350, the training data is annotated with a processing intention flag. The intention flag here can be used as a label for training the first deep network.

[0047] In step 360, the first deep learning network is trained using the training data and the processing intention flag to obtain the first agent. In some embodiments, when training the first deep learning network, semantic features and syntactic features associated with the semantic features can be first extracted from the training data; then, the semantic features and syntactic features are used as inputs of the first deep learning network, and the processing intention flag is used as outputs of the first deep learning network to train the first deep learning network to obtain the first agent. The semantic features here refer to the semantic connotations or semantic elements of a word in a sentence that can be distinguished from other words. Syntactic features refer to the syntactic functions or syntactic roles of words in a sentence, such as the position and role of words in a sentence. In this way, a first agent with more accurate intent recognition can be obtained.

[0048] In step 370, based on the target user input, the first agent is used to identify the target user's target processing intention for the to-do items.

[0049] By using the method 300 of using the first agent to identify the target user's target processing intention for the to-do items, the target user's target processing intention for the to-do items can be more accurately identified, thereby improving the accuracy and efficiency of processing the to-do items.

[0050] Figure 4 FIG. 4 is a block diagram of an exemplary structure of a to-do list processing device 400 according to an embodiment of the present disclosure. Figure 4 As shown, the to-do list processing device 400 includes an input acquisition module 410, an intention recognition module 420, an application programming interface determination module 430, a parameter acquisition module 440, a calling module 450, and a processing option generation module 460.

[0051] The input acquisition module 410 is configured to acquire a target user input, where the target user input represents a processing request for a to-do item initiated by a target user.

[0052] The intention recognition module 420 is configured to use the first agent to recognize the target user's target processing intention for the to-do items based on the target user input.

[0053] The application programming interface determination module 430 is configured to determine, based on the target processing intention, an application programming interface for executing the processing request using a second agent.

[0054] The parameter acquisition module 440 is configured to acquire required processing parameters using a third agent based on the determined application programming interface.

[0055] The calling module 450 is configured to call the application programming interface using the processing parameters to obtain a calling result.

[0056] The processing option generation module 460 is configured to generate at least one processing option for the to-do item based on the call result using the fourth agent, so that the target user can execute the to-do item represented by the selected option by selecting an option from the at least one processing option.

[0057] In the to-do list processing device claimed for protection in the present disclosure, after obtaining the user input, the first agent is first used to identify the target user's target processing intention for the to-do list; then, based on the target processing intention, the second agent is used to determine the application programming interface for executing the processing request, and based on the determined application programming interface, the third agent is used to obtain the required processing parameters; after calling the application programming interface with the parameters, the fourth agent can be used to generate at least one processing option for the to-do list based on the call result and optionally based on the context. In this way, on the basis of accurately understanding the user's processing intention, the to-do processing flow is split into a multi-stage decision-making and execution process, and each stage is processed by a dedicated agent, which greatly improves the accuracy and efficiency of to-do list processing, while avoiding multiple clicks and other operations, and improving the user's interactive experience.

[0058] Figure 5 An example system 500 is illustrated, which includes an example computing device 510 that represents one or more systems and / or devices that can implement the various techniques described herein. Computing device 510 can be, for example, a server of a service provider, a device associated with a server, a system on a chip, and / or any other suitable computing device or computing system. Figure 4 The depicted backlog processing apparatus 400 may take the form of a computing device 510. Alternatively, the backlog processing apparatus 400 may be implemented as a computer program in the form of an application 516.

[0059] The example computing device 510 as shown includes a processing system 511, one or more computer-readable media 512, and one or more I / O interfaces 513 that are communicatively coupled to each other. Although not shown, the computing device 510 may also include a system bus or other data and command transmission system that couples various components to each other. The system bus may include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and / or a processor or local bus utilizing any one of a variety of bus architectures. Various other examples are also contemplated, such as control and data lines.

[0060] Processing system 511 represents the functionality of performing one or more operations using hardware. Thus, processing system 511 is illustrated as including hardware elements 514 that may be configured as processors, functional blocks, and the like. This may include other logic devices implemented in hardware as application specific integrated circuits or formed using one or more semiconductors. Hardware elements 514 are not limited by the materials from which they are formed or the processing mechanisms employed therein. For example, a processor may be composed of (multiple) semiconductors and / or transistors (e.g., electronic integrated circuits (ICs)). In such a context, processor executable instructions may be electronic executable instructions.

[0061] Computer-readable media 512 is illustrated as including memory / storage 515. Memory / storage 515 represents memory / storage capacity associated with one or more computer-readable media. Memory / storage 515 may include volatile media (such as random access memory (RAM)) and / or non-volatile media (such as read-only memory (ROM), flash memory, optical disks, magnetic disks, etc.). Memory / storage 515 may include fixed media (e.g., RAM, ROM, fixed hard drives, etc.) and removable media (e.g., flash memory, removable hard drives, optical disks, etc.). Computer-readable media 512 may be configured in various other ways as further described below.

[0062] One or more I / O interfaces 513 represent functionality that allows a user to input commands and information to the computing device 510 using various input devices and optionally also allows information to be presented to the user and / or other components or devices using various output devices. Examples of input devices include a keyboard, a cursor control device (e.g., a mouse), a microphone (e.g., for voice input), a scanner, touch functionality (e.g., a capacitive or other sensor configured to detect physical touch), a camera (e.g., that can detect motion that does not involve touch as gestures using visible or invisible wavelengths (such as infrared frequencies), etc.). Examples of output devices include a display device (e.g., a monitor or projector), a speaker, a printer, a network card, a tactile response device, etc. Thus, the computing device 510 can be configured in various ways as further described below to support user interaction.

[0063] Computing device 510 also includes application 516. Application 516 may be, for example, a software instance of to-do processing apparatus 400 and, in combination with other elements in computing device 510, implement the techniques described herein.

[0064] Various techniques may be described herein in the general context of software hardware elements or program modules. Generally, these modules include routines, programs, objects, elements, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The terms "module", "function" and "component" as used herein generally represent software, firmware, hardware or a combination thereof. The features of the techniques described herein are platform-independent, meaning that these techniques can be implemented on a variety of computing platforms with a variety of processors.

[0065] An implementation of the described modules and techniques may be stored on or transmitted across some form of computer-readable media. Computer-readable media may include various media accessible by computing device 510. By way of example and not limitation, computer-readable media may include “computer-readable storage media” and “computer-readable signal media.”

[0066] In contrast to a simple signal transmission, carrier wave, or signal itself, "computer-readable storage medium" refers to a medium and / or device capable of persistently storing information, and / or a tangible storage device. Therefore, a computer-readable storage medium refers to a non-signal-bearing medium. Computer-readable storage media include hardware such as volatile and non-volatile, removable and non-removable media and / or storage devices implemented in a method or technology suitable for storing information (such as computer-readable instructions, data structures, program modules, logic elements / circuits, or other data). Examples of computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage device, hard disk, cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or other storage device, tangible medium, or article of manufacture suitable for storing desired information and accessible by a computer.

[0067] "Computer-readable signal media" refers to signal-bearing media that is configured to send instructions to the hardware of the computing device 510, such as via a network. Signal media typically can embody computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, data signal, or other transport mechanism. Signal media also include any information transfer media. The term "modulated data signal" refers to a signal that has one or more of its characteristics set or changed so as to encode information into the signal. By way of example and not limitation, communication media include wired media such as a wired network or direct connection and wireless media such as acoustic, RF, infrared, and other wireless media.

[0068] As previously described, hardware elements 514 and computer-readable media 512 represent instructions, modules, programmable device logic, and / or fixed device logic implemented in hardware form, which in some embodiments can be used to implement at least some aspects of the technology described herein. Hardware elements can include integrated circuits or systems on a chip, application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), and other implementations in silicon or components of other hardware devices. In this context, hardware elements can be used as processing devices for executing program tasks defined by instructions, modules, and / or logic embodied by hardware elements, as well as hardware devices for storing instructions for execution, such as the computer-readable storage media described previously.

[0069] The aforementioned combinations may also be used to implement the various techniques and modules described herein. Therefore, software, hardware or program modules and other program modules may be implemented as one or more instructions and / or logic embodied on some form of computer-readable storage medium and / or by one or more hardware elements 514. The computing device 510 may be configured to implement specific instructions and / or functions corresponding to the software and / or hardware modules. Therefore, for example, by using a computer-readable storage medium and / or hardware element 514 of a processing system, the module may be implemented as a module executable by the computing device 510 as software, at least in part, in hardware. Instructions and / or functions may be executable / operable by one or more articles (e.g., one or more computing devices 510 and / or processing systems 511) to implement the techniques, modules and examples described herein.

[0070] In various embodiments, computing device 510 can be implemented in various configurations. For example, computing device 510 can be implemented as a computer-type device including a personal computer, a desktop computer, a multi-screen computer, a laptop computer, a netbook, etc. Computing device 510 can also be implemented as a mobile device-type device including mobile devices such as mobile phones, portable music players, portable game devices, tablet computers, multi-screen computers, etc. Computing device 510 can also be implemented as a television-type device, which includes a device with or connected to a generally larger screen in a casual viewing environment. These devices include televisions, set-top boxes, game consoles, etc.

[0071] The techniques described herein may be supported by these various configurations of computing device 510 and are not limited to the specific examples of the techniques described herein. Functionality may also be implemented in whole or in part on the "cloud" 520 by using a distributed system, such as through platform 522 as described below.

[0072] Cloud 520 includes and / or represents a platform 522 for resources 524. Platform 522 abstracts the underlying functionality of the hardware (e.g., servers) and software resources of cloud 520. Resources 524 may include applications and / or data that may be used when executing computer processing on a server remote from computing device 510. Resources 524 may also include services provided over the Internet and / or over a subscriber network such as a cellular or Wi-Fi network.

[0073] The platform 522 can abstract resources and functionality to connect the computing device 510 with other computing devices. The platform 522 can also be used to abstract the hierarchy of resources to provide a hierarchy of corresponding levels of demand encountered for resources 524 implemented via the platform 522. Therefore, in an interconnected device embodiment, the implementation of the functionality described herein can be distributed throughout the system 500. For example, the functionality can be implemented in part on the computing device 510 and through the platform 522 that abstracts the functionality of the cloud 520.

[0074] The present disclosure provides a computer-readable storage medium on which computer-readable instructions are stored. When the computer-readable instructions are executed, any of the above methods is implemented.

[0075] The present disclosure provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computing device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computing device executes any method provided in the above-mentioned various optional implementations.

[0076] It should be understood that, for the sake of clarity, embodiments of the present disclosure are described with reference to different functional units. However, it will be apparent that, without departing from the present disclosure, the functionality of each functional unit can be implemented in a single unit, in multiple units, or as a part of other functional units. For example, the functionality that is described as being performed by a single unit can be performed by multiple different units. Therefore, reference to a specific functional unit is only considered as a reference to a suitable unit for providing the described functionality, rather than indicating a strict logical or physical structure or organization. Therefore, the present disclosure can be implemented in a single unit, or can be physically and functionally distributed between different units and circuits.

[0077] It will be understood that although the first, second, third, etc. terms may be used to describe various devices, elements, parts or portions in this article, these devices, elements, parts or portions should not be limited by these terms. These terms are only used to distinguish one device, element, part or portion from another device, element, part or portion.

[0078] Although the present disclosure has been described in conjunction with some embodiments, it is not intended to be limited to the specific forms set forth herein. On the contrary, the scope of the present disclosure is limited only by the appended claims. Additionally, although individual features may be included in different claims, these may possibly be advantageously combined, and inclusion in different claims does not imply that the combination of features is not feasible and / or advantageous. The order of features in the claims does not imply any specific order in which the features must work. Furthermore, in the claims, the word "comprising" does not exclude other elements, and the term "one" or "an" does not exclude a plurality. The figure marks in the claims are provided only as clear examples and should not be interpreted as limiting the scope of the claims in any way.

Claims

1. A method for processing a to-do list, comprising: Obtaining a target user input, where the target user input represents a processing request for a to-do item initiated by the target user; Based on the target user input, using the first agent to identify the target user's target processing intention for the to-do items; Based on the target processing intent, determining, using a second agent, an application programming interface for executing the processing request; Based on the determined application programming interface, using a third agent to obtain required processing parameters; Calling the application programming interface using the processing parameters to obtain a calling result; Based on the calling result, a fourth agent is used to generate at least one processing option for the to-do item, so that the target user can execute the to-do item represented by the selected option by selecting an option from the at least one processing option.

2. The method according to claim 1, wherein: The target user input is a speech of the target user, and wherein, based on the target user input, using the first agent to identify the target user's target processing intention for the to-do items comprises: converting the speech into text; Based on the text, the first agent is used to identify the target user's target processing intention for the to-do items.

3. The method according to claim 2, wherein: The target user input is text input by the target user, and based on the target user input, the first agent is used to identify the target user's target processing intention for the to-do item, including Vectorizing the text to obtain a first embedding vector; Using the first embedding vector, a first intelligent agent is used to identify multiple processing intentions from a processing intention library, and each of the multiple similarities between the intention vectors corresponding to the multiple processing intentions and the first embedding vector is greater than a similarity threshold, wherein the processing intention library includes multiple processing intentions and the intention vectors corresponding to the multiple processing intentions. The processing intention corresponding to the maximum similarity among the multiple similarities is determined as the target processing intention for the to-do item.

4. The method according to claim 1, wherein: Based on the target user input, using the first agent to identify the target user's target processing intention for the to-do items, including: Obtaining the context input by the target user; Acquire multiple user inputs to be trained and multiple response data corresponding to the multiple user inputs to be trained from the context, wherein the response data is intention data representing the intentions of the multiple user inputs to be trained obtained by performing intention recognition on the multiple user inputs to be trained using a first deep learning network; Determining a plurality of matching degrees between the plurality of response data and the plurality of user inputs to be trained; Determine the user input to be trained corresponding to the matching degree greater than the matching degree threshold among the multiple matching degrees as training data; Marking the training data with a processing intention flag; Using the training data and the processing intention flag to train a first deep learning network to obtain the first intelligent agent; Based on the target user input, the first agent is used to identify the target user's target processing intention for the to-do items.

5. The method according to claim 4, wherein: Training a first deep learning network using the training data and the processing intention flag to obtain the first agent includes: Extracting semantic features and syntactic features associated with the semantic features from the training data; The semantic features and syntactic features are used as inputs of a first deep learning network, and the processing intention flag is used as output of the first deep learning network. The first deep learning network is trained to obtain the first intelligent agent.

6. The method according to claim 1, wherein: Based on the determined application programming interface, using a third agent to obtain required processing parameters includes: Presenting a user interface to request parameter input associated with the parameter; Based on the determined application programming interface, a third agent is utilized to obtain required processing parameters from the parameter input.

7. The method according to claim 1, wherein: Based on the call result, using a fourth agent to generate at least one processing option for the to-do item, including: Based on the call result and the context of the target user input, a fourth agent is used to generate at least one processing option for the to-do item.

8. A device for processing a to-do list, comprising: An input acquisition module is configured to acquire a target user input, wherein the target user input represents a processing request for a to-do item initiated by the target user; an intention recognition module configured to recognize the target user's target processing intention for the to-do items using the first agent based on the target user input; An application programming interface determination module is configured to determine an application programming interface for executing the processing request using a second agent based on the target processing intention; a parameter acquisition module configured to acquire required processing parameters using a third agent based on the determined application programming interface; A calling module, configured to call the application programming interface using the processing parameters to obtain a calling result; The processing option generation module is configured to generate at least one processing option for the to-do item based on the call result using the fourth agent, so that the target user can execute the to-do item represented by the selected option by selecting an option from the at least one processing option.

9. A computing device comprising a memory configured to store computer-executable instructions; A processor, which is configured to perform the method according to any one of claims 1 to 7 when the computer executable instructions are executed by the processor.

10. A computer-readable storage medium storing computer-executable instructions, wherein when the computer-executable instructions are executed, the method according to any one of claims 1 to 7 is executed.

11. A computer program product, characterized in that The computer program product comprises computer executable instructions which, when executed, implement the method according to any one of claims 1 to 7.

Images