CN117171315A

CN117171315A - Task processing method and device, electronic equipment and storage medium

Info

Publication number: CN117171315A
Application number: CN202311092198.6A
Authority: CN
Inventors: 柳金杜; 王保卫; 王海威; 邹宗尧; 和为
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-08-28
Filing date: 2023-08-28
Publication date: 2023-12-05

Abstract

The disclosure provides a task processing method and device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and particularly relates to the technical fields of natural language processing, man-machine conversation, intelligent office and the like. The implementation scheme is as follows: determining a target task to be executed based on dialogue information input by a user in a dialogue interface, wherein the target task comprises at least one parameter to be configured; extracting initial values of the at least one parameter from the dialogue information; generating a form corresponding to the target task based on the initial values of the at least one parameter; displaying the form in the dialogue interface; responding to the operation of a user on the form, and obtaining the respective confirmation value of the at least one parameter; and executing the target task based on the respective confirmation values of the at least one parameter.

Description

Task processing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular, to the technical fields of natural language processing, man-machine conversation, intelligent office, etc., and more particularly, to a task processing method and apparatus, an electronic device, a computer readable storage medium, and a computer program product.

Background

Artificial intelligence (Artificial Intelligence, AI) is the discipline of studying the process of making a computer to simulate certain mental processes and intelligent behaviors of a person (e.g., learning, reasoning, thinking, planning, etc.), both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology, a natural language processing technology and the like.

Man-machine conversation refers to a technique for a machine to understand and use natural language to implement man-machine communication.

The task type dialog is a man-machine dialog for the purpose of completing a task. Task-oriented dialog systems are used to assist users in completing specific tasks in specific areas, such as weather queries, flight reservations, restaurant reservations, and the like.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been recognized in any prior art unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a task processing method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a task processing method, including: determining a target task to be executed based on dialogue information input by a user in a dialogue interface, wherein the target task comprises at least one parameter to be configured; extracting initial values of the at least one parameter from the dialogue information; generating a form corresponding to the target task based on the initial values of the at least one parameter; displaying the form in the dialogue interface; responding to the operation of a user on the form, and obtaining the respective confirmation value of the at least one parameter; and executing the target task based on the respective confirmation values of the at least one parameter.

According to an aspect of the present disclosure, there is provided a task processing device including: a determining module configured to determine a target task to be executed based on dialogue information input by a user in a dialogue interface, wherein the target task includes at least one parameter to be configured; an extracting module configured to extract initial values of each of the at least one parameter from the dialogue information; the generation module is configured to generate a form corresponding to the target task based on the initial values of the at least one parameter; a first presentation module configured to present the form in the dialog interface; an obtaining module configured to obtain respective confirmation values of the at least one parameter in response to a user operation on the form; and an execution module configured to execute the target task based on the respective validation values of the at least one parameter.

According to an aspect of the present disclosure, there is provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described above.

According to an aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the above-described method.

According to an aspect of the present disclosure, there is provided a computer program product comprising computer program instructions which, when executed by a processor, implement the above-described method.

According to one or more embodiments of the present disclosure, task processing efficiency of a dialog system can be improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings illustrate exemplary embodiments and, together with the description, serve to explain exemplary implementations of the embodiments. The illustrated embodiments are for exemplary purposes only and do not limit the scope of the claims. Throughout the drawings, identical reference numerals designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, in accordance with an embodiment of the present disclosure;

FIG. 2 illustrates a flow chart of a task processing method according to an embodiment of the present disclosure;

FIG. 3 illustrates a schematic diagram of a dialog interface, according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of a task processing procedure according to an embodiment of the present disclosure;

FIG. 5 shows a block diagram of a task processing device according to an embodiment of the present disclosure; and

fig. 6 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, the use of the terms "first," "second," and the like to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, unless otherwise indicated, and such terms are merely used to distinguish one element from another element. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on the description of the context.

The terminology used in the description of the various illustrated examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, the elements may be one or more if the number of the elements is not specifically limited. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items. "plurality" means two or more.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

In the related art, when a dialog system executes a complex task, it is generally necessary to repeatedly ask or confirm execution parameters of the task to a user, which results in a large number of dialogues, long time consumption, and low task processing efficiency.

For example, in a task of creating a meeting schedule, the dialog system asks or confirms information of a participant, a meeting time, a meeting place, and the like to the user through the following multi-turn dialog:

the user: please help me with a meeting of about 8 days in Ming dynasty.

Dialog system: please ask Zhang Xiaoming or Li Xiaoming?

The user: li Xiaoming.

Dialog system: please ask 8 am or 8 pm?

The user: 8 am.

Dialog system: please ask whether an online meeting or an offline meeting?

The user: offline.

Dialog system: please ask where the meeting place is?

The user: conference room 101.

Dialog system: good, you have reserved the meeting.

In the above example, the user successfully creates the meeting schedule through five rounds of conversations. The interaction times of the user and the dialogue system are large, the interaction time is long, the operation is complex, and the task processing efficiency is low.

In view of the above problems, embodiments of the present disclosure provide a task processing method. And automatically identifying a target task which is intended to be executed by the user according to the dialogue information of the user, extracting the initial value of the parameter of the target task from the dialogue information, generating a form, and displaying the generated form to the user through a dialogue interface. The user can obtain the confirmation values of all parameters by operating the form and only performing one-round dialogue with the dialogue system without repeatedly performing multiple rounds of dialogue with the dialogue system, so that the interaction times and interaction time consumption of the user and the dialogue system are greatly reduced, and the task processing efficiency is improved.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, in accordance with an embodiment of the present disclosure. Referring to fig. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the client devices 101, 102, 103, 104, 105, and 106 and the server 120 may run one or more services or software applications that enable execution of the task processing methods.

In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof that are executable by one or more processors. A user operating client devices 101, 102, 103, 104, 105, and/or 106 may in turn utilize one or more client applications to interact with server 120 to utilize the services provided by these components. It should be appreciated that a variety of different system configurations are possible, which may differ from system 100. Accordingly, FIG. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The client devices 101, 102, 103, 104, 105, and/or 106 may provide interfaces that enable a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that the present disclosure may support any number of client devices.

Client devices 101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, vehicle-mounted devices, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and the like. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, appli os, UNIX-like operating systems, linux, or Linux-like operating systems; or include various mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, windows Phone, android. Portable handheld devices may include cellular telephones, smart phones, tablet computers, personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays (such as smart glasses) and other devices. The gaming system may include various handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. For example only, the one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, wi-Fi), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture that involves virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. Server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of client devices 101, 102, 103, 104, 105, and/or 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and/or 106.

In some implementations, the server 120 may be a server of a distributed system or a server that incorporates a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. The cloud server is a host product in a cloud computing service system, so as to solve the defects of large management difficulty and weak service expansibility in the traditional physical host and virtual private server (VPS, virtual Private Server) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of databases 130 may be used to store information such as audio files and video files. Database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. Database 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve the databases and data from the databases in response to the commands.

In some embodiments, one or more of databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key value stores, object stores, or conventional stores supported by the file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

Fig. 2 illustrates a flow chart of a task processing method 200 according to an embodiment of the present disclosure. The subject of execution of method 200 is generally a client device, such as client devices 101-106 shown in FIG. 1. In some embodiments, the execution subject of method 200 may also be a server, such as server 120 shown in fig. 1.

As shown in fig. 2, the method 200 includes steps S210-S260.

In step S210, a target task to be executed is determined based on dialogue information input by a user in a dialogue interface, wherein the target task includes at least one parameter to be configured.

In step S220, initial values of the at least one parameter are extracted from the dialogue information.

In step S230, a form corresponding to the target task is generated based on the initial values of the at least one parameter.

In step S240, the form is presented in the dialog interface.

In step S250, respective confirmation values of the at least one parameter are obtained in response to a user operation on the form.

In step S260, the target task is performed based on the respective confirmation values of the at least one parameter.

According to the embodiment of the disclosure, a target task which is intended to be executed by a user is automatically identified based on dialogue information of the user, an initial value of a parameter of the target task is extracted from the dialogue information, a form is generated, and the generated form is displayed to the user through a dialogue interface. The user can obtain the confirmation values of all parameters by operating the form and only performing one-round dialogue with the dialogue system without repeatedly performing multiple rounds of dialogue with the dialogue system, so that the interaction times and interaction time consumption of the user and the dialogue system are greatly reduced, and the task processing efficiency is improved.

In step S210, the user may input dialogue information by means of text or voice.

According to some embodiments, a trained intent recognition model may be utilized to recognize a user's intent, i.e., to recognize a target task that the user intends to perform. The intention recognition model may be a lightweight classification model or a large language model (Large Language Model, LLM, simply referred to as a large model).

In the embodiment of the disclosure, the parameters of the target task are complex (such as a large number of parameters, various data types, etc.), the requirement on accuracy is high, or sensitive information is involved, so that the target task cannot be executed immediately after the task parameters are extracted from the target task, but after the task parameters are extracted from the target task, the task parameters need to be sent to a user for confirmation, and after the user confirms that the task parameters are correct, the target task is executed based on the task parameters. The target tasks may be tasks in an office scenario, including creating a calendar (including meetings, interviews with clients, etc.), submitting vacation applications, submitting financial reimbursement applications, etc.; and the tasks in the living scene can also be tasks including online shopping, spot takeaway and the like.

It will be appreciated that different tasks have different parameters. For example, for a task that creates a meeting schedule, its parameters include meeting title, participant, meeting time, etc. For the take-out task, the parameters include merchant name, meal name, receiver name, contact, receiving address, etc.

According to some embodiments, a parameter set corresponding to each task may be preset, that is, a correspondence relationship between the task and the parameter set may be preset. Accordingly, after the target task is determined in step S210, a parameter set corresponding to the target task may be determined based on the preset correspondence, so as to obtain at least one parameter to be configured of the target task.

In step S220, for each parameter of the target task, an initial value of the parameter is extracted from the dialogue information.

According to some embodiments, a named entity recognition algorithm may be used to extract the entity word corresponding to each parameter from the dialogue information as an initial value for the parameter. In some cases, the dialogue information entered by the user may not be complete for the target task, and the entity words of certain parameters cannot be extracted from the dialogue information, i.e., the values of certain parameters are missing. In this case, the value of the missing parameter may be set to a default value (or referred to as a "default value").

According to some embodiments, a large language model may be utilized to extract initial values for parameters from dialog information.

According to some embodiments, step S220 may include steps S222 and S224.

In step S222, for any one of the at least one parameter of the target task, an information piece corresponding to the parameter is cut out from the dialogue information.

In step S224, the information piece of the parameter is processed based on the preset format of the parameter to obtain the initial value of the parameter.

According to the embodiment, the information fragments of the parameter are processed by using the preset format of the parameter to obtain the initial value of the parameter, so that the formatting of the parameter value can be realized, and the accuracy of the parameter value in form is ensured. Therefore, the success rate of task execution can be improved, and task execution failure caused by the format problem of parameter values is avoided.

According to some embodiments, the target task is executed by invoking an interface to which the target task corresponds. Accordingly, the at least one parameter is a request parameter of the interface. It will be appreciated that the request parameters of the interface typically need to be entered in a specific data structure, otherwise the interface may throw exceptions. According to the embodiment, the information input by the user can be converted into the data format required by the interface, so that the success rate of interface calling is improved, namely, the success rate of task execution is improved.

For example, the dialogue information input by the user is "help me about the meeting at 10 am in the Ming day", and the target task that the dialogue information is intended to perform is "create a meeting schedule" by performing intention recognition on the dialogue information. Parameters for creating a meeting calendar task include meeting title, participant, and meeting start time. The dialogue information of the user is understood by using a large language model, the information fragment corresponding to the participant is intercepted as I'm and Xiaoming, and the information fragment corresponding to the meeting starting time is 10 am on tomorrow.

The preset format of the participant is, for example, a person identification (i.e., ID) in digital form, so that the pieces of information "me" and "min" need to be converted into IDs (e.g., by looking up an address book or analyzing a history chat record), respectively, and the converted IDs are used as initial values of the participant. The participant's default format may also be the person's formal, complete name (i.e., including both last and first names), thus requiring the conversion of the pronoun "me" and nickname "small" to formal names "Li Hua" and "Wang Ming" (e.g., by looking up an address book or analyzing a historical chat record).

The preset format of the meeting starting time is YYYY-MM-DD HH: MM, wherein Y, M, D, H, m respectively represents year, month, day, time and minute. Therefore, it is necessary to acquire the current date, for example, 2023, 6, 8, and then format-convert the information piece "10 am on tomorrow" based on the current date, resulting in an initial value of "2023-06-09 10:00" of the meeting start time.

In the dialogue information "help me about 10 am in the small Ming day", the value of the meeting title is missing. In this case, the initial value of the meeting header may be set to a default value of "xxx-initiated meeting", where xxx is the name of the user, i.e., the name of "me". For example, the user name is "Li Hua", and the initial value of the conference title is "Li Hua-initiated conference".

According to some embodiments, the method 200 further comprises steps S272 and S274.

In step S272, the initial values of the at least one parameter are each checked.

In step S274, in response to the failure of the initial value verification of any one of the at least one parameter, a hint message is added to the form to indicate that the parameter is incorrect.

According to the embodiment, the correctness of the parameter value in the content can be ensured by checking the initial value of the parameter, so that the success rate of task execution is ensured, and the task execution failure caused by the parameter value error is avoided. When the parameter value verification fails, a possible parameter error is prompted to a user, so that the user can modify the parameter value conveniently, the correctness of the parameter value is improved, and the success rate of task execution is improved.

According to some embodiments, for step S272, a verification rule of the initial value may be set as needed. For example, in a target task of creating a conference schedule, for a participant parameter, whether an initial value of the participant is correct can be verified by searching an address book of a user; for the conference time parameter, whether the current conference conflicts with the existing conference in time or not can be judged by comparing the initial value of the conference time parameter with the existing conference time of the participant; etc.

According to some embodiments, in the case that verification of an initial value of a certain parameter fails, in addition to adding a prompt message for indicating that the parameter is wrong in a form, a possible correction value of the initial value may be further given, so as to facilitate quick modification of the value of the parameter by a user.

According to some embodiments, step S230 may include steps S232 and S234.

In step S232, a form template corresponding to the target task is acquired. The form template comprises at least one control to be filled, and the at least one control corresponds to the at least one parameter respectively.

In step S234, initial values of at least one parameter are respectively filled into the corresponding controls, so as to generate a form corresponding to the target task.

According to the embodiment, the form template can provide a unified visual effect for the forms of the same type of tasks, so that a user can conveniently acquire the information of interest in the forms and operate the forms.

According to some embodiments, a form template corresponding to each task may be preset, that is, a correspondence relationship between the task and the form template may be preset. Accordingly, in step S232, a form template corresponding to the target task may be obtained based on the above correspondence.

The form template includes at least one control to be populated, such as a text entry box, a drop down selection box, a list selector, a time selector, a people selector, and the like. Each control comprises a control style and control data, wherein the control data is an initial value of a parameter corresponding to the control. And filling the initial value of each parameter into the corresponding control, so that a form corresponding to the target task can be generated.

After the form of the target task is generated, the form is used as the response information of the dialogue information input by the user and is fed back to the user through the dialogue interface.

The user may operate on the forms in the dialog interface. According to some embodiments, the user's operation on the form includes a form validation operation and a modification operation for any of the at least one parameter. Accordingly, step S250 may include steps S252 and S254.

In step S252, initial values of the respective parameters are modified in response to the modification operation.

In response to the form validation operation, the form is submitted to determine the respective current value of at least one parameter in the form as the respective validation value of the at least one parameter in step S254.

According to the above embodiment, the user can modify the values of the respective parameters in the form. After the values of the parameters are confirmed without errors, the form is submitted through a confirmation operation. Therefore, the values of all parameters can be confirmed through only one round of dialogue, multiple rounds of dialogue do not need to be repeatedly conducted with the dialogue system, the interaction times and the interaction time consumption with the dialogue system are greatly reduced, and the task processing efficiency is improved.

It will be appreciated that in step S252, the user may modify the initial value of the parameter one or more times to obtain a modified parameter value.

According to some embodiments, the parameter value after each modification by the user may be checked with reference to steps S272 and S274 described above, so as to ensure correctness of the modified parameter value in content, thereby ensuring success rate of task execution.

According to some embodiments, step S260 may include: and calling an interface corresponding to the target task based on the respective confirmation value of the at least one parameter so as to execute the target task.

According to the embodiment, the corresponding task is executed by calling the interface, so that the task execution capacity of the dialogue system is conveniently expanded.

According to some embodiments, the method 200 further comprises steps SS282 and S284.

In step S282, the task processing result returned by the interface is received.

In step S284, the task processing result is presented in the dialogue interface.

According to the embodiment, the user can conveniently know the task processing condition and perform subsequent operation.

Fig. 3 shows a schematic diagram of a dialog interface 300 according to an embodiment of the disclosure. As shown in fig. 3, a user Li Hua (simply referred to as "hua" in fig. 3) enters dialog information 310 "help me about 10 am in the small open morning" in dialog interface 300.

A conversation robot (i.e., a conversation system, abbreviated as "machine" in fig. 3) uses a large language model to identify intent of a user's conversation information 310, and determines that the task that he intends to perform is to create a meeting schedule. Further, the large language model extracts initial values of title, participant, start time, end time parameters from the dialogue information 310, and formats the initial values. The formatted initial values are filled into corresponding controls of a form template corresponding to the meeting schedule task to generate a form 320, and the generated form 320 is fed back to the user in the dialogue interface 300.

As shown in FIG. 3, form 320 includes a title control 330, a participant control 340, a start time control 350, an end time control 360, a reminder control 370, and a button 380.

Title control 330 includes text input box 332. An initial value "Li Hua initiated meeting" of the title is displayed in the text input box 332. The user may modify the current title "Li Hua initiated meeting" by operating the text input box 332.

The participant control 340 displays the initial values "Wang Ming, li Hua" of the participant and includes the person selector 342. The user may modify the current participant "Wang Ming, li Hua" by operating the people selector 342. For example, the user may open his address book by clicking on the people selector 342 and select one or more people from the address book as participants.

The start time control 350 displays an initial value of "2023-06-09 10:00" of the start time of the meeting, and includes a time selector 352. The user may modify the current start time "2023-06-09 10:00" by operating the time selector 352. For example, the user may open a calendar and clock and set a date and time by clicking on the time selector 352.

The end time control 360 displays an initial value of "2023-06-09 11:00" of the end time of the meeting and includes a time selector 362. The user may modify the current end time "2023-06-09 11:00" by operating the time selector 362. For example, the user may open a calendar and clock and set a date and time by clicking on the time selector 362.

The reminder component 370 displays a reminder message "06-09 10:00-11:00 Wang Ming, li Hua that there is a meeting conflict" indicating that one of the two has a meeting reservation for that period of time. And, the prompt component 370 recommends three possible meeting time options 372 to the user. The user may quickly modify the meeting time by selecting meeting time option 372. It will be appreciated that if the user is not satisfied with the recommended three meeting time options 372, then the meeting time may be manually set by operating the time selectors 352 and 362.

After confirming the value of each parameter, the user clicks the button 380 to submit the current form 320. The conversation robot invokes an external interface for creating a meeting schedule based on the values of the various parameters in the current form 320 to perform the task of creating the meeting schedule.

Subsequently, the conversation robot presents the task execution results 390 in the conversation interface 300. As shown by task execution result 390, the meeting calendar has been successfully created. Task execution results 390 include buttons 392. The user can quickly join the meeting by clicking on button 392.

Fig. 4 shows a schematic diagram of a task processing procedure 400 according to an embodiment of the disclosure. As shown in fig. 4, the task processing procedure 400 includes steps S401 to S407.

In step S401, a user inputs a natural language instruction in a dialogue interface.

In step S402, the large model parses the user instruction, and extracts pieces of information corresponding to the respective parameters, i.e., semi-finished product parameters, from the user instruction.

In step S403, the smart work card robot (i.e., dialog system, dialog robot) receives the semi-finished parameters after the large model processing, further processes, formats these parameters, and converts them into presentation controls and control data on the work card (i.e., form).

In step S404, the smart workcard robot renders the workcard 410 in the dialog interface.

In step S405, the user performs operations such as modification, confirmation, and the like on the work card 410. Taking creating a meeting schedule as an example, a user may adjust meeting time, add a participant, etc.

In step S406, after the user confirms the work card, the work card generates a callback event, and returns the parameter value confirmed by the user to the smart work card service.

In step S407, the smart workcard service receives and processes this callback and invokes the external interface to complete the task.

Compared with a common large-model robot, the intelligent work card robot has the advantages that intelligent work card services are added, and the interaction mode of the robot is expanded. As shown in fig. 4, the smart workcard service includes the following modules:

1. the template management module manages the template of each work card and controls used on the template, such as text input boxes, drop-down selection boxes, list selectors, time selectors, personnel selectors and the like.

2. And the card generation module is used for generating complete work card configuration data by combining the corresponding work card template according to the input parameters in the user instruction understood by the large model robot.

3. And the card sending module is used for sending the generated work card to a dialogue interface of the user and rendering the work card.

4. And the event callback module is used for processing user operation on the work card, for example, after the user clicks the submit confirmation form, the data of the user on the form is required to be collected and tidied, and finally, an external interface is called.

5. The interface calling module is responsible for processing the calling logic and organizing the returned data results, mapping them to the results interface of the work card for the user's use and secondary operations (e.g., joining a meeting by clicking on button 392 as shown in fig. 3).

In the embodiment of the disclosure, the intelligent work card robot is a general AI native application solution, and the existing application in the enterprise office environment can be quickly transformed into the intelligent work card robot only by providing a corresponding interface and a work card template.

According to the embodiment of the disclosure, a user can directly communicate with the intelligent work card robot by using natural language and issue instructions. The intelligent work card robot will return to the work card (i.e., form) after parsing the instruction and pre-populate the work card directly with data that the large language model understands from the instruction. The user can quickly confirm the data in the work card, if inaccurate and unidentified data is found, the user can directly modify and edit the data on the card, and when the user confirms the data without errors, the form is submitted, and the intelligent work card robot can call the third-party interface.

Task instructions in large model products typically require the invocation of external interface capabilities that require defined data structures as input, otherwise the interface throws exceptions. However, the interaction between the user and the large model product is in a natural language form, the large model is required to accurately identify key information input by the natural language of the user, and the key information is required to be converted into a data format required by an interface, and if the process is completely given to the large model, the performance is poor, the time is long, and the accuracy is difficult to ensure. For example, a scene of creating a meeting schedule, the user inputs "help me meeting at 10 am on the small Ming Sunday", and the large model needs to recognize the user's intention and obtain key information about personnel, time, place, etc., and then convert it into data required for the interface, such as user ID, time stamp, etc. There are also cases where the user input is ambiguous, such as "Tuesday" refers to "Tuesday" or? If the identification is wrong, the schedule is directly created, and the loss of the user experience is caused.

The intelligent work card robot can match and convert the parameters analyzed by the large model according to the interface data format, and if the result which cannot be converted can be directly transmitted to a user through the work card for confirmation, so that various problems caused by semantic ambiguity are avoided.

Still taking the above scenario of creating a meeting schedule as an example, when the semantics of the user input are ambiguous, a better quality large model can be identified and ask the user a question of "what is you needed to reserve a meeting for tuesday or for the next tuesday? "do you need to reserve an online meeting or an offline meeting? ". However, when more parameters are required for the interface, the number of queries increases, so that the overall interaction period becomes long.

According to the intelligent working card robot disclosed by the embodiment of the disclosure, parameter data understood by the large model can be directly filled into the working card form control, if the data formats cannot be matched, the data are directly reserved for the user to confirm and modify, and the whole process only needs one large model interaction, so that the repeated confirmation process is greatly reduced, and the success rate of interface calling is improved.

Large model products typically return data in text format, sometimes in some simple format arrangement, such as lists, tables, etc., that result in a presentation that satisfies most simple content creation scenarios. However, such returned results are not interactable and cannot be modified by the user. While the task class often needs to keep pace, this requires the results to be modified again. For example, a user creates a meeting schedule, and it is necessary to allow the user to easily modify the time, place, participant, etc. of the schedule.

The intelligent work card robot of the embodiment of the disclosure can utilize the work card in the form of a graphical user interface (Graphical User Interface, GUI) to enable a user to modify task information conveniently.

According to an embodiment of the present disclosure, there is also provided a task processing device. Fig. 5 shows a block diagram of a task processing device 500 according to an embodiment of the present disclosure. As shown in fig. 5, the apparatus 500 includes a determining module 510, an extracting module 520, a generating module 530, a first presentation module 540, an obtaining module 550, and an executing module 560.

The determining module 510 is configured to determine a target task to be performed based on dialogue information entered by a user in a dialogue interface, wherein the target task comprises at least one parameter to be configured.

The extraction module 520 is configured to extract respective initial values of the at least one parameter from the dialogue information.

The generating module 530 is configured to generate a form corresponding to the target task based on the respective initial values of the at least one parameter.

The first presentation module 540 is configured to present the form in the dialog interface.

The obtaining module 550 is configured to obtain respective confirmation values of the at least one parameter in response to a user operation on the form.

The execution module 560 is configured to execute the target task based on the respective validation values of the at least one parameter.

According to some embodiments, the extraction module 520 comprises: an intercepting unit configured to intercept, for any one of the at least one parameter, an information piece corresponding to the parameter from the dialogue information; and a formatting unit configured to process the information piece based on a preset format of the parameter to obtain an initial value of the parameter.

According to some embodiments, the generating module 530 includes: the acquisition unit is configured to acquire a form template corresponding to the target task, wherein the form template comprises at least one control to be filled, and the at least one control corresponds to the at least one parameter respectively; and the filling unit is configured to fill the initial values of the at least one parameter into the corresponding controls respectively so as to generate a form corresponding to the target task.

According to some embodiments, the apparatus 500 further comprises: a verification module configured to verify initial values of the at least one parameter respectively; and a prompt module configured to add a prompt message indicating that the parameter is wrong in the form in response to failure of initial value verification of any one of the at least one parameter.

According to some embodiments, the operations include a form validation operation and a modification operation for any of the at least one parameter, and wherein the obtaining module 550 includes: a modifying unit configured to modify initial values of the respective parameters in response to the modifying operation; and a submitting unit configured to submit the form in response to the form confirmation operation, to determine the current value of each of at least one parameter in the form as the confirmation value of each of the at least one parameter.

According to some embodiments, the execution module 560 is further configured to: and calling an interface corresponding to the target task based on the respective confirmation value of the at least one parameter so as to execute the target task.

According to some embodiments, the apparatus 500 further comprises: the receiving module is configured to receive a task processing result returned by the interface; and a second display module configured to display the task processing result in the dialogue interface.

It should be appreciated that the various modules and units of the apparatus 500 shown in fig. 5 may correspond to the various steps in the method 200 described with reference to fig. 2. Thus, the operations, features and advantages described above with respect to method 200 are equally applicable to apparatus 500 and the modules and units comprising the same. For brevity, certain operations, features and advantages are not described in detail herein.

Although specific functions are discussed above with reference to specific modules, it should be noted that the functions of the various modules discussed herein may be divided into multiple modules and/or at least some of the functions of the multiple modules may be combined into a single module.

It should also be appreciated that various techniques may be described herein in the general context of software hardware elements or program modules. The various elements described above with respect to fig. 5 may be implemented in hardware or in hardware in combination with software and/or firmware. For example, the units may be implemented as computer program code/instructions configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units may be implemented as hardware logic/circuitry. For example, in some embodiments, one or more of the modules 510-560 may be implemented together in a System on Chip (SoC). The SoC may include an integrated circuit chip including one or more components of a processor (e.g., a central processing unit (Central Processing Unit, CPU), microcontroller, microprocessor, digital signal processor (Digital Signal Processor, DSP), etc.), memory, one or more communication interfaces, and/or other circuitry, and may optionally execute received program code and/or include embedded firmware to perform functions.

There is also provided, in accordance with an embodiment of the present disclosure, an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor, the memory storing instructions executable by the at least one processor to enable the at least one processor to perform the task processing methods of the embodiments of the present disclosure.

According to an embodiment of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the task processing method of the embodiment of the present disclosure.

There is also provided, in accordance with an embodiment of the present disclosure, a computer program product comprising computer program instructions which, when executed by a processor, implement the task processing method of the embodiments of the present disclosure.

Referring to fig. 6, a block diagram of an electronic device 600 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 can also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

A number of components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, the input unit 606 may receive input numeric or character information and generate key signal inputs related to user settings and/or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and/or a remote control. The output unit 607 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. Storage unit 608 may include, but is not limited to, magnetic disks, optical disks. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices through a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, 802.11 devices, wi-Fi devices, wiMAX devices, cellular communication devices, and/or the like.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. One or more of the steps of the method 200 described above may be performed when a computer program is loaded into RAM 603 and executed by the computing unit 601. Alternatively, in other embodiments, computing unit 601 may be configured to perform method 200 by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the foregoing methods, systems, and apparatus are merely illustrative embodiments or examples and that the scope of the present disclosure is not limited by these embodiments or examples but only by the claims following the grant and their equivalents. Various elements of the embodiments or examples may be omitted or replaced with equivalent elements thereof. Furthermore, the steps may be performed in a different order than described in the present disclosure. Further, various elements of the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the disclosure.

Claims

1. A task processing method, comprising:

determining a target task to be executed based on dialogue information input by a user in a dialogue interface, wherein the target task comprises at least one parameter to be configured;

Extracting initial values of the at least one parameter from the dialogue information;

generating a form corresponding to the target task based on the initial values of the at least one parameter;

displaying the form in the dialogue interface;

responding to the operation of a user on the form, and obtaining the respective confirmation value of the at least one parameter; and

and executing the target task based on the respective confirmation values of the at least one parameter.

2. The method of claim 1, wherein the extracting initial values of the at least one parameter from the dialog information comprises:

for any one of the at least one parameter, intercepting an information fragment corresponding to the parameter from the dialogue information; and

and processing the information fragment based on the preset format of the parameter to obtain the initial value of the parameter.

3. The method according to claim 1 or 2, wherein the generating a form corresponding to the target task based on the respective initial values of the at least one parameter comprises:

acquiring a form template corresponding to the target task, wherein the form template comprises at least one control to be filled, and the at least one control corresponds to the at least one parameter respectively; and

And filling initial values of the at least one parameter into corresponding controls respectively to generate a form corresponding to the target task.

4. A method according to any one of claims 1-3, further comprising:

verifying the initial values of the at least one parameter; and

and in response to failure of initial value verification of any one of the at least one parameter, adding a prompt message for indicating parameter errors in the form.

5. The method of any of claims 1-4, wherein the operations include a form validation operation and a modification operation for any of the at least one parameter, and wherein the obtaining, in response to a user operation on the form, respective validation values for the at least one parameter comprises:

modifying initial values of the corresponding parameters in response to the modifying operation; and

submitting the form in response to the form validation operation to determine a current value of each of at least one parameter in the form as a validation value of each of the at least one parameter.

6. The method of any of claims 1-5, wherein the performing the target task based on the respective acknowledgement values of the at least one parameter comprises:

And calling an interface corresponding to the target task based on the respective confirmation value of the at least one parameter so as to execute the target task.

7. The method of claim 6, further comprising:

receiving a task processing result returned by the interface; and

and displaying the task processing result in the dialogue interface.

8. A task processing device comprising:

a determining module configured to determine a target task to be executed based on dialogue information input by a user in a dialogue interface, wherein the target task includes at least one parameter to be configured;

an extracting module configured to extract initial values of each of the at least one parameter from the dialogue information;

the generation module is configured to generate a form corresponding to the target task based on the initial values of the at least one parameter;

a first presentation module configured to present the form in the dialog interface;

an obtaining module configured to obtain respective confirmation values of the at least one parameter in response to a user operation on the form; and

and an execution module configured to execute the target task based on the respective confirmation values of the at least one parameter.

9. The apparatus of claim 8, wherein the extraction module comprises:

an intercepting unit configured to intercept, for any one of the at least one parameter, an information piece corresponding to the parameter from the dialogue information; and

and the formatting unit is configured to process the information fragment based on the preset format of the parameter so as to obtain the initial value of the parameter.

10. The apparatus of claim 8 or 9, wherein the generating module comprises:

the acquisition unit is configured to acquire a form template corresponding to the target task, wherein the form template comprises at least one control to be filled, and the at least one control corresponds to the at least one parameter respectively; and

and the filling unit is configured to fill the initial values of the at least one parameter into the corresponding controls respectively so as to generate a form corresponding to the target task.

11. The apparatus of any of claims 8-10, further comprising:

a verification module configured to verify initial values of the at least one parameter respectively; and

and the prompting module is configured to respond to failure of initial value verification of any parameter in the at least one parameter and add a prompting message for indicating parameter errors in the form.

12. The apparatus of any of claims 8-11, wherein the operations comprise a form validation operation and a modification operation for any of the at least one parameter, and wherein the obtaining module comprises:

a modifying unit configured to modify initial values of the respective parameters in response to the modifying operation; and

and a submitting unit configured to submit the form in response to the form confirmation operation, so as to determine the current value of each of at least one parameter in the form as the confirmation value of each of the at least one parameter.

13. The apparatus of any of claims 8-12, wherein the execution module is further configured to:

14. The apparatus of claim 13, further comprising:

the receiving module is configured to receive a task processing result returned by the interface; and

and the second display module is configured to display the task processing result in the dialogue interface.

15. An electronic device, comprising:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.

17. A computer program product comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1-7.