CN118838526A - Interaction method and device applied to intelligent assistant, electronic equipment and storage medium - Google Patents

Abstract

The disclosure relates to an interaction method, an interaction device, an interaction electronic device and an interaction storage medium applied to an intelligent assistant, relates to the field of computer application, and is designed for improving convenience in selecting a proper large model application from a plurality of model applications and effectively reducing use cost. The interaction method applied to the intelligent assistant comprises the following steps: acquiring the service requirement of a user through a dialogue interactive interface; determining a large model application adapted to the service demand according to the service demand of the user; invoking the determined large model application to execute the business requirement; and displaying the execution result of the service requirement through the dialogue interactive interface. The present disclosure may be used in a software platform product integrating multiple large model applications.

Description

Interaction method, device, electronic device and storage medium applied to intelligent assistant

Technical Field

The present disclosure relates to the field of computer technology, and more specifically, to an interaction method, device, electronic device, and storage medium applied to an intelligent assistant.

Background Art

With the rise of big model technology, more and more companies and individuals have joined the ranks of using big models. At present, many software platforms are equipped with big model applications, which can, for example, communicate with users and help companies and individuals solve some problems in work and daily life.

There are usually several large model applications configured on the software platform. The functions of each large model application, that is, the tasks that can be performed, are different. For example, some are used for image processing, some are used for knowledge questions and answers, and some are used for content creation. If a user needs to perform a specific task, he or she must first find the corresponding application entrance. Only through the correct application entrance can the large model application accurately respond to the user's needs. If the wrong application is selected, the results of the question and the answer may be very different.

However, faced with a large number of large-scale model applications that are suitable for performing different tasks, it is cumbersome, time-consuming, labor-intensive, and costly for users to accurately find the required refined applications.

Summary of the invention

In view of this, the present disclosure provides an interactive method, device, electronic device and storage medium applied to an intelligent assistant, thereby improving the convenience of selecting a suitable large model application from multiple model applications and effectively reducing the cost of use.

In a first aspect, the present disclosure provides an interaction method applied to an intelligent assistant, comprising: obtaining a user's business needs through a dialogue interaction interface; determining a large model application that is adapted to the business needs based on the user's business needs; calling the determined large model application to execute the business needs; and displaying the execution results of the business needs through the dialogue interaction interface.

Optionally, in an implementation manner, a dialogue input box is provided on the dialogue interaction interface, and obtaining the user's business requirements through the dialogue interaction interface includes: obtaining the business requirements input by the user through the dialogue input box.

Optionally, in one implementation, determining the large model application adapted to the business demand according to the business demand of the user includes: identifying the user intent corresponding to the business demand of the user;

According to the identified user intent, a large model application corresponding to the user intent is determined.

Furthermore, in one embodiment, determining the big model application corresponding to the user intent based on the identified user intent includes: obtaining the confidence level of the match between a preset big model application and the user intent based on the identified user intent; and determining the big model application with the highest confidence level as the big model application corresponding to the user intent.

Optionally, in one embodiment, determining the big model application that is compatible with the business needs based on the business needs of the user includes: obtaining the big model application specified in the business needs of the user, and determining the big model application specified in the business needs of the user as the big model application that is compatible with the business needs.

Optionally, in one embodiment, before determining the big model application that is compatible with the business needs, the method further includes: monitoring the input content of the dialog input box, and if it is detected that the user has entered a preset big model application summoning symbol, providing a first large model application list, wherein at least two preset big model application options are displayed in the first large model application list; determining the big model application that is compatible with the business needs based on the user's business needs includes: in response to the user's selection operation on the big model application option, determining the big model application selected by the selection operation as the big model application that is compatible with the business needs.

Optionally, in one embodiment, the method further includes: providing a re-answer control at a predetermined position near the execution result; in response to a user operation on the re-answer control, calling other large model applications to re-execute the business requirement, and displaying the execution result of re-executing the business requirement through the dialogue interaction interface.

Optionally, in one embodiment, an application setting control is also provided at a predetermined position of the dialogue interaction interface, and the method further includes: in response to a user operation on the application setting control, providing a large model setting window, wherein a second large model application list is displayed in the large model setting window, wherein the second large model application list displays preset currently available large model application options, and each of the currently available large model application options corresponds to a start-stop switch; in response to a user operation on the start-stop switch, enabling or disabling the large model application corresponding to the operated start-stop switch.

In a second aspect, the present disclosure provides an interactive device applied to an intelligent assistant, comprising: an acquisition unit, used to acquire a user's business needs through a dialogue interaction interface; a determination unit, used to determine a large model application adapted to the business needs based on the user's business needs; a calling unit, used to call the determined large model application to execute the business needs; and a display unit, used to display the execution results of the business needs through the dialogue interaction interface.

Optionally, in one implementation, a dialogue input box is provided on the dialogue interaction interface; and the acquisition unit is specifically used to: acquire the business demand input by the user through the dialogue input box.

Optionally, in one embodiment, the determination unit includes: an identification module for identifying the user intent corresponding to the user's business needs; and a determination module for determining a large model application corresponding to the user intent based on the identified user intent.

Furthermore, in one embodiment, the determination module is used to: obtain the confidence level of the match between a preset big model application and the user intent based on the identified user intent; and determine the big model application with the highest confidence level as the big model application corresponding to the user intent.

Optionally, in one implementation, the determination module is used to: obtain the large model application specified in the business requirement of the user, and determine the large model application specified in the business requirement of the user as the large model application adapted to the business requirement.

Optionally, in one embodiment, the device further includes: a monitoring unit, configured to monitor the input content of the dialog input box, and if it is detected that the user has input a preset large model application summoning symbol, provide a first large model application list, wherein the first large model application list displays at least two preset large model application options; the determination unit is specifically configured to: in response to the user's selection operation on the large model application option, determine the large model application selected by the selection operation as a large model application adapted to the business needs.

Optionally, in one embodiment, the display unit is further used to: provide a re-answer control at a predetermined position near the execution result; the calling unit is further used to: in response to a user operation on the re-answer control, call other large model applications to re-execute the business requirement; the display unit is further used to: display the execution result of re-executing the business requirement through the dialogue interaction interface.

Optionally, in one embodiment, the display unit is also used to: provide an application setting control at a predetermined position of the dialogue interaction interface, and provide a large model setting window in response to the user's operation on the application setting control, wherein a second large model application list is displayed in the large model setting window, wherein the second large model application list displays preset currently available large model application options, and each of the currently available large model application options corresponds to a start-stop switch; the device also includes a start-stop unit for enabling or disabling the large model application corresponding to the operated start-stop switch in response to the user's operation on the start-stop switch.

In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a housing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is placed inside a space enclosed by the housing, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to various circuits or devices of the above-mentioned electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the interaction method applied to the intelligent assistant described in the first aspect above.

In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the interaction method applied to an intelligent assistant as described in the first aspect above.

The interactive method, device, electronic device and storage medium for an intelligent assistant provided by the embodiments of the present disclosure obtain the user's business needs through a dialogue interaction interface, determine the big model application that is compatible with the business needs based on the business needs, and call the big model application to execute the business needs, so that the user only needs to input the business needs, and the user does not need to search for the required big model application among a large number of big model applications that are suitable for executing different tasks. The user operation is simple and fast, which can significantly improve the convenience of selecting a suitable big model application from multiple model applications, and effectively reduce the cost of using the big model application.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

FIG1 is a flow chart of an interaction method applied to an intelligent assistant provided in an embodiment of the present disclosure;

FIG. 2 is an exemplary schematic diagram of a dialog interaction interface in the interaction method provided in FIG. 1 ;

FIG3 is an exemplary schematic diagram of a dialog interaction interface in the interaction method provided in FIG1 ;

FIG4 is an exemplary schematic diagram of a dialog interaction interface in the interaction method provided in FIG1 ;

FIG5 is an exemplary schematic diagram of a dialog interaction interface in the interaction method provided in FIG1 ;

FIG6 is a schematic diagram of the structure of an interactive device applied to an intelligent assistant provided in an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

DETAILED DESCRIPTION

In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation methods described in the following examples do not represent all implementation methods consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the attached claims.

It should be noted that the phrase "at least one of the items" in the present disclosure includes three types of parallel situations: "any one of the items", "a combination of any number of the items", and "all of the items". For example, "including at least one of A and B" includes the following three types of parallel situations: (1) including A; (2) including B; (3) including A and B. Another example is "executing at least one of step 1 and step 2" which means the following three types of parallel situations: (1) executing step 1; (2) executing step 2; (3) executing step 1 and step 2.

With the rise of artificial general intelligence (AI) and big model technology, in order to better help enterprises and individuals solve some problems in work and daily life, many software platforms are equipped with a large number of big model applications with different functions, such as the "Chinese Painting Master" application for creating Chinese paintings, and the "Intelligent Writing" application for generating text works. In addition, some software platforms also provide the function of creating big model applications. Users can create their own big model applications on the platform as needed, such as the "Conference Room Reservation" application for conference room reservation. Since several big model applications are integrated in the platform, usually, the software platform mostly provides the entrance of each big model application in the form of tiling, list, multi-level menu, etc. Users need to select the big model application they need from them. On the one hand, due to the large number of big model applications and the limited understanding of each application by users, users need to spend a certain amount of time and energy to find the appropriate big model application entrance. For example, users need to search, turn pages, view the details of the big model application, etc. Moreover, if the wrong application is selected, it cannot accurately respond to the user's needs. Users also need to return to search for the big model application again. The operation is very cumbersome, time-consuming and labor-intensive, and the cost of use is high.

In view of this, the present disclosure provides an interactive method applied to an intelligent assistant, which automatically matches the required large model applications for users in the form of an intelligent assistant, significantly improves the convenience of selecting a suitable large model application from multiple model applications, and effectively reduces the cost of use.

First of all, it should be noted that the intelligent assistant mentioned in this disclosure is essentially an application, and specifically an application based on big model technology, that is, a big model application, which can communicate with users, for example, can talk with users, can understand users' business needs, and then determine the big model application (specifically, it can be an external application programming interface API) that is adapted to user needs to help users complete work tasks. The intelligent assistant can be an independent software product or embedded in a software system as a functional module therein.

The interactive method disclosed in the present invention can be applied to a terminal running an intelligent assistant and executed by the intelligent assistant, such as a smart phone, a PDA, a tablet computer, a wearable device with a display screen, a desktop computer, a laptop computer, an all-in-one machine, a smart home device, etc. The intelligent assistant can exist independently or be embedded in a business system. If it is embedded in a business system, an entrance to the intelligent assistant can be set in the page of the business system, and the user can access the intelligent assistant by clicking on the entrance or the like.

FIG1 is a flow chart of an interactive method applied to an intelligent assistant provided by an embodiment of the present disclosure. As shown in FIG1 , the interactive method applied to an intelligent assistant of the present disclosure includes:

Step 101: Obtain the user's business needs through a dialogue interaction interface.

The present disclosure provides a task interaction interface for users, and the interface is used to interact with users in the form of dialogue, etc., so as to obtain the business needs of users, and then execute corresponding tasks to achieve the business needs of users.

The business needs of the present disclosure refer to a certain purpose that the user needs to achieve, such as "booking a conference room" or "conducting model training". The present disclosure does not limit this. For example, it can be any purpose or demand that needs to be implemented by calling a large model application.

The user can express business needs in the form of text, voice, document, etc. Specifically, the text, voice, document, etc. can be input through the dialogue interaction interface. In this step, the user's business needs will be obtained based on the user's input.

As an implementation mode, in the disclosed embodiment, the user can communicate with the intelligent assistant in a dialogue mode, inform the intelligent assistant of the business needs, and when the intelligent assistant has doubts about the user's business needs, it can confirm with the user and ask the user to modify and supplement the business needs. Therefore, the user and the intelligent assistant can have a single round or multiple rounds of dialogue. For users, the dialogue mode is simple and fast to express business needs, and the experience is better.

Specifically, in one embodiment, a dialogue input box is provided in the dialogue interaction interface, and the user issues a task start instruction by inputting text in the dialogue input box. Referring to FIG. 2, FIG. 2 is a schematic diagram of an exemplary dialogue interaction interface. When the user accesses the smart assistant, for example, the access entrance of the smart assistant is set on the main page or a sub-page of the platform, which can be an icon, button or other control. When the user selects the access entrance, for example, when clicking the "smart assistant" button, the dialogue interaction interface is entered. A dialogue input box 20 is provided below the dialogue interaction interface, and the user can enter the dialogue content through the dialogue input box 20. In addition, when entering the dialogue interaction page for the first time, a smart assistant prompt can be provided in the dialogue interaction interface to describe the function and/or usage of the smart assistant, so as to guide and prompt the user. The prompt is, for example: "Hi, I am a super assistant. As your smart partner, I can help you answer questions and solve doubts, and assist you in quickly completing some tasks. You can also @ me to specify a model for question and answer. Welcome to ask me questions."

It should be noted that, for ease of understanding, some components in FIG. 2 to FIG. 5 are circled with dotted lines.

Step 102: Determine a large model application that is compatible with the business needs based on the user's business needs.

In the present disclosure, according to the business needs of users, a suitable big model application that can meet the business needs is automatically matched from several pre-set big model applications, without the need for manual search by users. This can effectively improve the convenience of selecting a suitable big model application from multiple model applications and effectively reduce the user's cost of using big model applications.

Specifically, in one implementation, user intent recognition may be first performed for the business needs input by the user to identify the user intent corresponding to the user's business needs, and then a large model application corresponding to the user intent may be determined based on the identified user intent.

In the embodiments of the present disclosure, the user intent corresponding to the business demand can be identified by a variety of methods, and the present disclosure does not limit this. For example, in one example, the business demand can be provided to a preset intent recognition model to obtain the user intent output by the intent recognition model. Optionally, the intent recognition model can be an artificial intelligence model built based on various algorithms, such as a large language model, a deep learning model, etc. For example, in another example, keywords in the business demand can be extracted and confirmed based on the keywords and the user intent.

After identifying the user's intention, the big model application corresponding to the user's intention can also be determined in a variety of ways, which are not limited in the present disclosure. For example, the pre-set big model applications are all provided with description information, such as the main functions of the application, the data format requirements for processing, etc. The user's intention and description information can be used to perform keyword comparison, rule comparison, etc. to find the big model application corresponding to the user's intention. In one embodiment, the confidence of the preset big model application matching the user's intention can be obtained based on the identified user's intention, and then the big model applications can be sorted according to the confidence, and the big model application with the highest confidence can be determined as the big model application corresponding to the user's intention. Specifically, a pre-set confidence prediction model can be used to input the user's intention and the description information of the big model application into the confidence prediction model to obtain the confidence output by the confidence prediction model, and then according to the confidence, the big model application with the highest confidence is selected as the big model application that matches the user's needs. Among them, confidence refers to the model's confidence in the large model application and user intent configuration. The higher the confidence, the higher the confidence level, that is, the higher the accuracy probability of the large model and user intent configuration, so that the large model application can be selected more accurately and quickly.

It can be understood that any method in the prior art can be selected for identifying user intent and determining the large model application corresponding to the user intent. Those skilled in the art can make the selection, and this disclosure will not elaborate on this.

In the case where the user has clearly identified the large model application that needs to be used, in order to improve the convenience of user operation, in the embodiment of the present disclosure, the user can directly specify the large model application in the business demand. In this step, the large model application specified in the user's business demand will be obtained, and the large model application specified in the user's business demand will be determined as a large model application adapted to the business demand. For example, the business demand may be: please ask the visitor reservation assistant to make a visitor reservation, then the "visitor reservation assistant" specified by the user will be determined as a large model application adapted to the business demand. Specifically, the large model application specified in the user input content can be obtained during the process of monitoring the user inputting the business demand. As a preferred implementation, in order to enable the intelligent assistant to quickly and accurately identify the large model application specified in the business demand, a special large model application summoning symbol can be pre-defined. When the user enters the special summoning symbol, it means that the content entered by the user after the special summoning symbol is the large model application specified by the user. When the intelligent assistant recognizes the special summoning symbol, it can quickly and accurately identify the large model application specified by the user. The feature summoning symbol is not limited, for example, it can be "@", and the business demand entered by the user can be: @Visitor Reservation Assistant, please make a visitor reservation.

As an optimization method, in order to facilitate the user's selection and specification and reduce the user's input operation, in one embodiment, the intelligent assistant can monitor the user's input content, specifically, monitor the user's input content in the dialogue input box. If it is detected that the user has entered a preset large model application summoning symbol, a first large model application list is automatically provided. The first large model application list displays at least two preset large model application options to facilitate user selection. After the user selects a large model application option, in response to the user's selection operation on the large model application option, the large model application selected by the selection operation is determined as a large model application adapted to the business needs. Exemplarily, referring to FIG. 3, when it is detected that the user enters the summoning symbol 32 "@" in the dialogue input box, the first large model application list 30 pops up, including multiple large model application options 31. The user can select a large model application by clicking on an option, and the name of the large model application is automatically added to "@" without the user having to enter it again.

Step 103: Call the determined large model application to execute the business requirements.

Step 104: Display the execution result of the business requirement through the dialogue interaction interface.

After the big model application is determined, the determined big model application is called to execute the business requirements, and the execution results are displayed in the dialogue interaction interface. Referring to Figure 4, after the business requirements are executed, the user will be informed of the execution results in a dialogue, for example, "The appointment data has been generated for you..."

The interactive method for an intelligent assistant provided by the disclosed embodiment obtains the user's business needs through a dialogue interaction interface, determines a big model application that is compatible with the business needs based on the business needs, and calls the big model application to execute the business needs, so that the user only needs to input the business needs, and the user does not need to search for the required big model application among a large number of big model applications that are suitable for executing different tasks. The user operation is simple and fast, which can significantly improve the convenience of selecting a suitable big model application from multiple model applications, and effectively reduce the cost of using the big model application.

Optionally, in one embodiment of the present disclosure, after the large model application is automatically determined and the user's needs are executed, the large model application may be inappropriate, resulting in inaccurate execution results, and the user may be dissatisfied with the answer of the intelligent assistant, i.e., the execution result. For this reason, in the present disclosure, a re-answer control may be provided at a predetermined position close to the execution result. When the user operates the control, in response to the user's operation of the re-answer control, other large model applications are called to re-execute the business needs, and the execution results of the re-execution of the business needs are displayed through the dialogue interaction interface. Referring to FIG. 4, a "switch assistant to re-answer" button 40 is provided below the execution result. If the user is dissatisfied with the answer of the assistant, he can click the "switch assistant to re-answer" button. After clicking, the system will automatically switch to another large model application to re-answer the question for the user, i.e., re-execute the business needs. This intelligent assistant switching function can provide more accurate and satisfactory execution results and enhance the user's experience. Specifically, the replaced large model application can refer to the matching method of step 102, for example, re-matching the intent, or replacing the large model application with the second highest confidence. This application is not limited to this and will not be further described here.

Optionally, in order to provide users with more convenient model response control, in one embodiment of the present disclosure, an application setting control may also be provided at a predetermined position of the dialogue interaction interface. In response to the user's operation on the application setting control, a large model setting window is provided, and a second large model application list is displayed in the large model setting window. The second large model application list displays all preset currently available large model application options, and each currently available large model application option corresponds to a start-stop switch. In response to the user's operation of the start-stop switch, the large model application corresponding to the operated start-stop switch is enabled or disabled, so that the user can freely enable or disable a certain large model application according to their needs, thereby achieving more personalized application management.

As shown in Figure 4, a setting button 41 is provided in the upper right corner of the dialogue interaction interface. After the user clicks the setting button, a large model setting window 50 will pop up as shown in Figure 5. The large model setting window displays a list of all currently available large model applications. Each large model application in the list corresponds to a start-stop switch 51. The user can enable or disable the large model application by controlling the start-stop switch as needed, and the intelligent assistant will only determine the large model application that executes the business needs based on the enabled large model application range.

FIG6 is a schematic diagram of a device structure provided by an embodiment of the present disclosure. As shown in FIG6 , the device of this embodiment may include:

An acquisition unit 60 is used to acquire the user's business needs through the dialogue interaction interface;

A determination unit 61 is used to determine a large model application adapted to the business demand according to the business demand of the user;

A calling unit 62, configured to call the determined large model application to execute the business requirement;

The display unit 63 is used to display the execution result of the business requirement through the dialogue interaction interface.

The interactive device applied to the intelligent assistant provided by the embodiment of the present disclosure obtains the user's business needs through a dialogue interaction interface, determines the big model application adapted to the business needs according to the business needs, and calls the big model application to execute the business needs, so that the user only needs to input the business needs, and the user does not need to search for the required big model application among a large number of big model applications that are suitable for executing different tasks. The user operation is simple and fast, which can significantly improve the convenience of selecting a suitable big model application from multiple model applications, and effectively reduce the cost of using the big model application.

Optionally, in one embodiment, a dialogue input box is provided on the dialogue interaction interface; the acquisition unit 60 is specifically used to: acquire the business demand input by the user through the dialogue input box.

Optionally, in one embodiment, the determining unit 61 includes:

An identification module, used to identify the user intention corresponding to the user's business needs;

A determination module is used to determine a large model application corresponding to the user intention based on the identified user intention.

Furthermore, in one embodiment, the determining module is used to:

According to the identified user intent, obtaining a confidence level that a preset large model application matches the user intent;

The large model application with the highest confidence is determined as the large model application corresponding to the user intention.

Furthermore, in one embodiment, the determining module is used to:

The large model application specified in the business requirement of the user is obtained, and the large model application specified in the business requirement of the user is determined as the large model application adapted to the business requirement.

Optionally, in one embodiment, the device further comprises:

A monitoring unit (not shown in the figure) is used to monitor the input content of the dialogue input box, and if it is detected that the user has input a preset large model application summoning symbol, provide a first large model application list, wherein the first large model application list displays at least two preset large model application options;

The determining unit 61 is specifically configured to: in response to a selection operation of the user on the large model application option, determine the large model application selected by the selection operation as the large model application adapted to the business requirement.

Optionally, in one embodiment, the display unit 63 is further configured to: provide a re-answer control at a predetermined position close to the execution result;

The calling unit 62 is further used to: in response to the user's operation on the re-answer control, call other large model applications to re-execute the business requirement;

The display unit 63 is further used to display the execution result of re-executing the business requirement through the dialogue interaction interface.

Optionally, in one embodiment, the display unit 63 is further used to: provide an application setting control at a predetermined position of the dialog interaction interface, and provide a large model setting window in response to a user operation on the application setting control, wherein a second large model application list is displayed in the large model setting window, wherein the second large model application list displays preset currently available large model application options, and each currently available large model application option corresponds to a start/stop switch;

The device further includes a start-stop unit configured to enable or disable the large model application corresponding to the operated start-stop switch in response to a user's operation of the start-stop switch.

The device of this embodiment can be used to execute the technical solution of the method embodiment shown in Figure 1. Its implementation principle and technical effects are similar and will not be repeated here.

Correspondingly, a device provided in an embodiment of the present disclosure can also be implemented with another structure. FIG7 is a schematic diagram of the structure of an electronic device embodiment provided in the present disclosure, which can implement the process of the embodiment shown in FIG1 of the present disclosure. As shown in FIG7, the above-mentioned electronic device may include: a housing 71, a processor 72, a memory 73, a circuit board 74 and a power supply circuit 75, wherein the circuit board 74 is arranged inside the space surrounded by the housing 71, and the processor 72 and the memory 73 are arranged on the circuit board 74; the power supply circuit 75 is used to supply power to each circuit or device of the above-mentioned electronic device; the memory 73 is used to store executable program code; the processor 72 runs the program corresponding to the executable program code by reading the executable program code stored in the memory 73, so as to execute the method described in the above-mentioned embodiment.

The specific execution process of the processor 72 for the above steps and the steps further executed by the processor 72 by running the executable program code can be found in the description of the embodiment shown in FIG. 1 of the present disclosure, which will not be repeated here.

The electronic device is a device that provides computing services. The electronic device consists of a processor, hard disk, memory, system bus, etc. The electronic device is similar to the general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, manageability, etc.

It should be noted that, in this article, terms such as "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

The logic and/or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or in conjunction with such instruction execution system, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, apparatus or device, or in conjunction with such instruction execution system, apparatus or device.

More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.

In the above embodiments, multiple steps or methods may be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it may be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

For the convenience of description, the above device is described by dividing the functions into various units/modules. Of course, when implementing the present disclosure, the functions of each unit/module can be implemented in the same or multiple software and/or hardware.

It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present disclosure can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present disclosure or certain parts of the embodiments.

Claims (10)

1. An interaction method applied to an intelligent assistant, comprising:

acquiring the service requirement of a user through a dialogue interactive interface;

determining a large model application adapted to the service demand according to the service demand of the user;

Invoking the determined large model application to execute the business requirement;

And displaying the execution result of the service requirement through the dialogue interactive interface.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

The dialogue interactive interface is provided with a dialogue input box, and the obtaining the business requirement of the user through the dialogue interactive interface comprises the following steps:

and acquiring the business requirement input by the user through the dialogue input box.

3. The method of claim 1, wherein said determining a large model application that adapts to the business needs of the user based on the business needs comprises:

identifying user intention corresponding to the business requirement of the user;

And determining a large model application corresponding to the user intention according to the identified user intention.

4. A method according to claim 3, wherein said determining a large model application corresponding to said user intent based on said identified user intent comprises:

Acquiring the confidence degree of matching the preset large model application with the user intention according to the identified user intention;

and determining the large model application with the highest confidence as the large model application corresponding to the user intention.

5. The method of claim 1, wherein said determining a large model application that adapts to the business needs of the user based on the business needs comprises:

and acquiring the large model application specified in the business requirement of the user, and determining the large model application specified in the business requirement of the user as the large model application matched with the business requirement.

6. The method of claim 2, wherein prior to said determining a large model application that is adapted to the business needs, the method further comprises:

Monitoring the input content of the dialogue input box, and providing a first large model application list if the user is monitored to input a preset large model application calling symbol, wherein at least two preset large model application options are displayed in the first large model application list;

the determining the large model application adapted to the service requirement according to the service requirement of the user comprises the following steps:

And responding to the selection operation of the large model application options by a user, and determining the large model application selected by the selection operation as the large model application matched with the business requirement.

7. The method according to claim 1, wherein the method further comprises:

Providing a re-answer control at a predetermined location proximate to the execution result;

and responding to the operation of the user on the re-answer control, calling other large model applications to re-execute the service requirement, and displaying an execution result of re-executing the service requirement through the dialogue interactive interface.

8. An interactive apparatus for an intelligent assistant, comprising:

The acquisition unit is used for acquiring the service requirement of the user through the dialogue interactive interface;

The determining unit is used for determining a large model application adapted to the service requirement according to the service requirement of the user;

the calling unit is used for calling the determined large model application to execute the service requirement;

And the display unit is used for displaying the execution result of the service requirement through the dialogue interactive interface.

9. An electronic device, the electronic device comprising: the device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged in a space surrounded by the shell, and the processor and the memory are arranged on the circuit board; a power supply circuit for supplying power to each circuit or device of the electronic apparatus; the memory is used for storing executable program codes; a processor executes a program corresponding to the executable program code by reading the executable program code stored in the memory for performing the method of any of the preceding claims 1-7.

10. Computer can the storage medium is read and the data is read, the computer-readable storage medium stores one or more programs, the one or more programs being executable by one or more processors for implementing the method of any of the preceding claims 1-7.