Object diagnosis interaction method and device based on intelligent agent

By deploying the intelligent body area and operation area on the display interface, and using the diagnostic intelligent body to diagnose electronic equipment, the problem of low diagnostic efficiency in the prior art is solved, and efficient diagnostic result output and improved user experience are achieved.

CN119002770APending Publication Date: 2024-11-22LENOVO (BEIJING) LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411218295.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-31
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the prior art, the diagnosis efficiency of electronic device failures is low, and usually depends on manual or remote mail methods, resulting in low diagnostic efficiency and poor user experience.

Method used

By deploying the agent area and the operation area on the display interface, after the diagnostic agent is triggered, the diagnostic agent display window is presented in the agent area, and the diagnostic agent is used to diagnose the target object based on the input data, and the diagnostic result is output to the operation area.

Benefits of technology

It improves the efficiency of object diagnosis, improves user experience, avoids dependence on manual or email methods, and simplifies the diagnosis process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119002770A_ABST
    Figure CN119002770A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent agent-based object diagnosis interaction method and device, and the method comprises the steps: responding to a triggering operation for a diagnosis intelligent agent, and outputting a display window of the diagnosis intelligent agent in an intelligent agent region of a display interface; the diagnosis agent is used for realizing an object diagnosis function; the display interface further comprises an operation area; using the diagnosis agent to diagnose a target object according to input data to obtain the diagnosis result; the input data is obtained through a display window of the diagnostic agent; and outputting the diagnosis result to the operation area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an object diagnosis interaction method and device based on an intelligent agent. Background Art

[0002] Currently, electronic equipment failures are usually checked manually or remotely via email, etc. However, this method has the problem of low diagnostic efficiency. Summary of the invention

[0003] In view of this, the present application provides an agent-based object diagnosis interaction method and device as follows:

[0004] An agent-based object diagnosis interaction method, comprising:

[0005] In response to a trigger operation on a diagnostic agent, a display window of the diagnostic agent is outputted in an agent area of ​​a display interface; the diagnostic agent is used to implement an object diagnosis function; the display interface further includes an operation area;

[0006] Utilizing the diagnostic agent to diagnose the target object according to the input data to obtain the diagnostic result; the input data is obtained through the display window of the diagnostic agent;

[0007] The diagnosis result is output to the operation area.

[0008] In the above method, preferably, the display interface further comprises a menu area, and the menu area is used to output at least one menu option;

[0009] Among them, the trigger operation is: the operation of selecting the intelligent agent option in the menu options; the intelligent agent area is presented in the display interface when the intelligent agent option is triggered, and at least the display window of the diagnostic intelligent agent is presented in the intelligent agent area.

[0010] In the above method, preferably, the agent area is used to present a display window of at least one agent; the display window of the agent has a switch control; when the switch control is triggered, a switch list is output, and the switch list contains at least one to-be-selected identifier; the to-be-selected identifier is used to uniquely represent the corresponding agent;

[0011] The trigger operation includes: an operation in which the candidate identification corresponding to the diagnostic agent is selected.

[0012] In the above method, preferably, when only the to-be-selected identifier corresponding to the diagnosis agent is selected, the display window of the diagnosis agent replaces the display window of the agent where the switching control is located;

[0013] When the to-be-selected identifier corresponding to the diagnosis agent and the to-be-selected identifiers corresponding to other agents are selected, the display window of the diagnosis agent and the display windows of the other agents are presented in the agent area.

[0014] In the above method, preferably, the diagnostic agent diagnoses the target object based on object data; the object data is the operating data of the target object in the target time period;

[0015] Wherein, when the target object is in operation, the object data is provided to the diagnostic agent in a mirroring manner.

[0016] In the above method, preferably, the desktop mirror image in the object data is output in the form of a floating window in the intelligent body area.

[0017] In the above method, preferably, the input data includes data content of at least one data type;

[0018] The data type includes at least one of a character type, a document type, a voice type, an image type, and a video type.

[0019] In the above method, preferably, the input data is obtained by:

[0020] Obtaining input content received by the display window of the diagnostic agent;

[0021] The input content is parsed using the diagnostic agent to obtain the input data.

[0022] The above method, preferably, before outputting the diagnosis result to the operation area, the method further includes:

[0023] Determine whether the operation area is in a hidden state; the operation area enters the hidden state when the display window of the diagnosis agent is presented in the agent area, or the operation area enters the hidden state when a hidden control is triggered;

[0024] If the operation area is in a hidden state, restore the operation area to be presented on the display interface.

[0025] An object diagnosis interaction device based on an intelligent agent, comprising:

[0026] A window output unit, for outputting a display window of the diagnostic agent in the agent area of ​​the display interface in response to a trigger operation on the diagnostic agent; the diagnostic agent is used to implement the object diagnosis function; the display interface also includes an operation area;

[0027] A result obtaining unit, used to use the diagnostic agent to diagnose the target object according to the input data to obtain the diagnostic result; the input data is obtained through the display window of the diagnostic agent;

[0028] The result output unit is used to output the diagnosis result to the operation area.

[0029] It can be seen from the above technical scheme that in the object diagnosis interaction method and device based on the agent disclosed in the present application, by deploying the agent area and the operation area on the display interface, after the diagnostic agent is triggered, the display window of the diagnostic agent can be presented in the agent area, and then the diagnostic agent is used to diagnose the target object according to the input data, and the obtained diagnostic result is output in the operation area. Therefore, in the present application, the target object is diagnosed by the diagnostic agent and the obtained diagnostic result is output through the operation area of ​​the unified interface, and the object diagnosis can be realized without manual or email methods, and there is no need to switch the diagnostic agent and the operation area where the diagnostic result is located, thereby improving the efficiency of object diagnosis and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0031] Figure 1 A flowchart of an agent-based object diagnosis interaction method provided in an embodiment of the present application;

[0032] Figure 2 , Figure 3 , Figure 4 and Figure 5 They are respectively exemplary diagrams of providing diagnostic services to users through operating areas and diagnostic agents in embodiments of the present application;

[0033] Figure 6 This is an example diagram of the menu area in the embodiment of the present application;

[0034] Figure 7 This is an example diagram of a display window in which a display interface outputs multiple agents through an agent area in an embodiment of the present application;

[0035] Figure 8 , Fig. 9 , Fig.10 , Fig.11 , Fig.12 , Fig.13 and Fig.14They are respectively example diagrams of switching agents in the embodiments of the present application;

[0036] Fig.15 This is an example diagram of diagnosing a computer in an embodiment of the present application;

[0037] Fig.16 Another flow chart of an agent-based object diagnosis interaction method provided in an embodiment of the present application;

[0038] Fig.17 and Fig.18 They are respectively example diagrams of hidden operation areas in the embodiments of the present application;

[0039] Fig.19 This is an example diagram of the recovery operation area in the embodiment of the present application;

[0040] Fig. 20 This is an example diagram of dragging a display window of a diagnostic agent in an embodiment of the present application;

[0041] Fig.21 This is an example diagram of adjusting the display window and operation area of ​​the diagnostic intelligent agent in the embodiment of the present application;

[0042] Fig. 22 A schematic diagram of the structure of an agent-based object diagnosis interaction device provided in an embodiment of the present application;

[0043] Fig.23 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0044] Fig.24 , Fig.25 and Fig.26 They are respectively schematic diagrams of realizing computer diagnosis through the interaction between the workbench and the display window of the intelligent body when the present application is applied to a notebook. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] refer to Figure 1 As shown, it is a flowchart of an implementation of an agent-based object diagnosis interaction method provided in an embodiment of the present application, which can be applied to electronic devices equipped with multiple agents, such as mobile phones, tablet computers, notebooks, etc. The technical solution in this embodiment is mainly used to improve the diagnostic efficiency of the object to improve the user experience.

[0047] Specifically, the method in this embodiment may include the following steps:

[0048] Step 101: In response to a trigger operation on a diagnosis agent, a display window of the diagnosis agent is output in an agent area of ​​a display interface.

[0049] The diagnostic agent is used to implement the object diagnosis function. For example, the diagnostic agent is a large model trained with samples, and the diagnostic agent can provide diagnostic results for the diagnosed object, such as the cause of the fault and the way to solve the fault.

[0050] It should be noted that the display interface is the interface output by the electronic device to implement this embodiment, and the display interface also includes an operation area. Figure 2 As shown in , a display window of a diagnosis agent is output in the agent area, and the operation area can be located on the left side of the agent area.

[0051] The trigger operation may be an operation of triggering the diagnostic agent through a menu area, where the menu area is an area presented in the display interface, or the trigger operation may be an operation of triggering the diagnostic agent through other agents.

[0052] Step 102: Utilize the diagnostic agent to diagnose the target object according to the input data to obtain a diagnostic result.

[0053] The input data is obtained through the display window of the diagnostic agent.

[0054] It should be noted that the target object refers to an object to be diagnosed, such as a computer, a person, an animal, a production equipment, an application, and the like. Accordingly, the input data may be data content containing at least one data type. The data types here may include at least one of a character type, a document type, a voice type, an image type, and a video type. Thus, the diagnostic agent may process input data of any one or more data types to achieve object diagnosis based on multimodal input.

[0055] For example, if the target object is a computer, the input data may include: screenshots of computer errors and text of user questions about computer failures. For another example, if the target object is a person, the input data may include: medical images of the person and the user's voice description of illness.

[0056] In one implementation, the input data is data entered by the user in an input box in the display window of the diagnostic agent. Figure 2 As shown in , the user enters “What’s wrong with this computer” in the input box in the display window of the diagnostic agent. At this time, the input data is “What’s wrong with this computer”.

[0057] In another implementation, the input data is: data obtained by processing the content input by the user in the input box in the display window of the diagnostic agent.

[0058] Specifically, the input data can be obtained in the following ways:

[0059] First, the input content received by the display window of the diagnosis agent is obtained, and then the input content is parsed by the diagnosis agent to obtain input data.

[0060] For example, Figure 3 As shown in , the user enters “What’s wrong with this computer” in the input box in the display window of the diagnostic agent. Based on this, the diagnostic agent parses “What’s wrong with this computer” and obtains the input data “Detect computer failure”.

[0061] For example, Figure 4 As shown in , the user enters a screenshot of the computer error in the input box in the display window of the diagnostic agent. Based on this, the diagnostic agent parses the screenshot of the computer error and obtains the input data "Detect computer error failure".

[0062] Step 103: Output the diagnosis result to the operation area.

[0063] The diagnosis result may include the fault description corresponding to the input data, the cause of the fault, and the method for resolving the fault.

[0064] For example, Figure 3 or Figure 4 As shown in , taking the target object as a computer as an example, the diagnosis result may include: an error identifier, a cause of the error, and a detailed solution to the error, etc.

[0065] For example, Figure 5 As shown in , taking the target object as a person, the diagnosis result may include: description of the symptoms of the person, the cause of the symptoms, and treatment plans, etc.

[0066] It can be seen from the above technical scheme that in an object diagnosis interaction method based on an intelligent agent provided in an embodiment of the present application, by deploying an intelligent agent area and an operation area on the display interface, after the diagnostic intelligent agent is triggered, the display window of the diagnostic intelligent agent can be presented in the intelligent agent area, and then the diagnostic intelligent agent is used to diagnose the target object according to the input data, and the obtained diagnostic result is output in the operation area. Therefore, in the present application, the target object is diagnosed by the diagnostic intelligent agent and the obtained diagnostic result is output through the operation area of ​​the unified interface. Object diagnosis can be achieved without manual or email methods, and there is no need to switch the diagnostic intelligent agent and the operation area where the diagnostic result is located, thereby improving the efficiency of object diagnosis and improving the user experience.

[0067] In one implementation, the display interface further includes: a menu area, the menu area is used to output at least one menu option, each menu option corresponds to a function, and an agent option is used to trigger the agent area to be presented on the display interface.

[0068] Based on this, the triggering operation is: the operation of selecting the agent option in the menu option. Based on this, when the agent option in the menu option is triggered, the agent area is presented on the display interface, and when the agent option in the menu option is triggered, the diagnostic agent is started, and accordingly, at least the display window of the diagnostic agent is presented in the agent area.

[0069] At this time, the diagnostic agent is the agent that is started by default in the electronic device when the agent area is initially presented.

[0070] For example, Figure 6 As shown in the figure, the menu area is presented on the left side of the operation area. After the user selects the agent option in the menu options, the agent area is presented on the right side of the operation area. The agent area has a display window of the target agent, namely the diagnosis agent.

[0071] In one implementation, the agent area is used to present a display window of at least one agent. Figure 7 As shown in , in addition to the display window of the diagnosis agent, the agent area may also present a display window of agent 1, and agent 1 may be an agent that provides other intelligent services, such as an agent that provides text and image services.

[0072] There is a switch control in the display window of the agent, and when the switch control is triggered, a switch list is output, and the switch list contains at least one to-be-selected identifier. The to-be-selected identifier is used to uniquely identify the corresponding agent.

[0073] It should be noted that each agent in the agent area has a switch control in its display window. For example, the display window of the diagnosis agent has a switch control, and the display window of agent 1 also has a switch control. The user can click on the switch control in the display window of any agent to trigger the switch control.

[0074] The switch control is used to replace the display window of the agent to which the switch control belongs with the display window of the new agent, or the switch control is used to present the display window of the new agent to the agent area. The user clicks the switch control in the display window to trigger the switch control.

[0075] Specifically, there may be one or more switching controls.

[0076] For example, Figure 8 As shown in , there is a switch control in the display window of agent 1, and the switch control includes: a cross expansion control, a first control, and a second control. The first control is a control corresponding to a single agent, and the second control is a control corresponding to multiple agents. The first control is used to replace the display window of agent 1 with the display window of a new agent, and the second control is used to present the display windows of one or more new agents to the agent area. After clicking the cross expansion control, the user can select the expanded first control or the second control, thereby triggering the switch control.

[0077] For example, Fig. 9 As shown in , there is a switch control in the display window of agent 1, and the user can select the switch control to trigger the switch control.

[0078] Based on this, when the switch control is triggered, a switch list is output, and the switch list contains at least one candidate identifier, which is used to uniquely represent the corresponding intelligent agent, such as the name or function type of the intelligent agent.

[0079] For example, Fig.10 As shown in , when there are multiple switching controls, if the user selects the first control, the switching list corresponding to the first control is output, and the user can select the candidate identification corresponding to a diagnostic agent in the switching list corresponding to the first control; if the user selects the second control, the switching list corresponding to the second control is output, and the user can select the candidate identification corresponding to agent 1 and the candidate identification corresponding to the diagnostic agent in the switching list corresponding to the second control.

[0080] For example, Fig.11As shown in , in the case where there is only one toggle control, if the user selects the toggle control, a toggle list is output, and the user only selects a to-be-selected identifier that is different from agent 1, such as a to-be-selected identifier of a diagnostic agent, on the toggle list, or the user selects multiple to-be-selected identifiers on the toggle list, including a to-be-selected identifier such as a diagnostic agent, which may include a to-be-selected identifier of agent 1 or not include a to-be-selected identifier of agent 1.

[0081] Based on this, the triggering operation in step 101 may be an operation in which the candidate identification corresponding to the diagnostic agent is selected.

[0082] Specifically, when only the to-be-selected identifier corresponding to the diagnosis agent is selected, the display window of the diagnosis agent replaces the display window of the agent where the switching control is located;

[0083] When the to-be-selected identifier corresponding to the diagnosis agent and the to-be-selected identifiers corresponding to other agents are selected, the display window of the diagnosis agent and the display windows of the other agents are presented in the agent area.

[0084] For example, Fig.12 As shown in , if only the to-be-selected identifier corresponding to the diagnosis agent is selected, the display window of the diagnosis agent will replace the display window of agent 1.

[0085] For example, Fig.13 As shown in , if the to-be-selected identifier corresponding to the diagnosis agent and the to-be-selected identifier corresponding to agent 2 are selected, then the display window of the diagnosis agent and the display window of agent 2 are presented in the agent area.

[0086] For example, Fig.14 As shown in , if the candidate identification corresponding to the diagnostic agent and the candidate identification corresponding to agent 1 are selected, since the display window of agent 1 has been presented in the agent area, the display window of the diagnostic agent will be presented in the agent area.

[0087] In one implementation, the diagnostic agent diagnoses the target object based on the object data. The object data is the operation data of the target object in the target time period. The target time period is the historical time period of the target object, such as within 1 hour before the current moment, or within one month before the current moment.

[0088] In this case, when the target object is in operation, the object data is provided to the diagnostic agent in a mirroring manner.

[0089] For example, taking the target object as a computer, the computer's operating data within 1 hour before the current moment is provided to the diagnostic agent in a mirrored manner. The diagnostic agent performs fault diagnosis on the computer based on the mirrored operating data and the input data to obtain a diagnostic result.

[0090] Based on the above implementation, the desktop image in the object data is presented in the agent area in the form of a floating window. At this time, the desktop image can cover part of the display window of any agent in the agent area. The desktop image can assist the diagnostic agent in diagnosing the target object, and can also show the operating status of the target object to the user.

[0091] For example, Fig.15 As shown in the figure, there is a computer desktop mirror image in the upper left corner of the display window of the diagnostic agent. The diagnostic agent diagnoses the computer based on the computer's operating data within 1 hour before the current moment and the input data "What's wrong with this computer" to obtain the computer's diagnostic results. The diagnostic results may include: including: error identification of the fault, the cause of the fault and detailed solutions to the fault, etc. These diagnostic results are output in the operation area on the left. The content output in the operation area can be edited. Based on this, the user can copy these diagnostic results, or adjust the description or layout of these diagnostic results.

[0092] In one implementation, before step 103 in this embodiment, the following processing may also be performed, such as Fig.16 As shown in:

[0093] Step 104: Determine whether the operation area is in a hidden state. If the operation area is in a hidden state, execute step 105; if the operation area is not in a hidden state, execute step 103.

[0094] The operation area enters a hidden state when the display window of the diagnosis agent is presented in the agent area, or the operation area enters a hidden state when a hidden control is triggered.

[0095] It should be noted that when the operation area enters the hidden state, the menu area also enters the hidden state.

[0096] For example, Fig.17 As shown in , there is a hidden control in the upper left corner of the operation area. The user can click the hidden control to trigger the operation area to enter a hidden state. At this time, the display interface only presents the intelligent agent area;

[0097] For example, Fig.18As shown in , after the user clicks the agent option in the menu area, the display window of the diagnostic agent is presented in the agent area. At the same time, the operation area is hidden. At this time, the display interface only presents the agent area and the menu area.

[0098] Step 105: The recovery operation area is presented on the display interface, and step 103 is executed.

[0099] It should be noted that when the operation area is restored to be presented on the display interface, the menu area can also be restored to be presented on the display interface or continue to be hidden.

[0100] For example, Fig.19 As shown in , the operation area in a hidden state is restored to the display interface, so that the operation area can output diagnostic results to the user, such as the error logo of the computer, the cause of the error, and the detailed solution to the error.

[0101] In one implementation, the position of the display window of the diagnostic agent relative to the operating area can be set by the user. For example, the user drags the display window of the diagnostic agent to the top or right of the operating area. Fig. 20 as shown in .

[0102] In another implementation, the position of the display window of the diagnostic agent relative to the operating area may be determined based on the diagnostic result output by the diagnostic agent.

[0103] For example, if the diagnosis results of a large number of faults are long, the display window of the diagnostic agent can be adjusted to the left of the operation area, and the display window of the diagnostic agent can be reduced while the operation area is enlarged, such as Fig.21 As shown in , it is convenient for users to edit the diagnosis results in the operation area.

[0104] refer to Fig. 22 , is a schematic diagram of the structure of an agent-based object diagnosis interaction device provided in an embodiment of the present application, and the device may include the following units:

[0105] The window output unit 2201 is used to output the display window of the diagnostic agent in the agent area of ​​the display interface in response to the trigger operation on the diagnostic agent; the diagnostic agent is used to implement the object diagnosis function; the display interface also includes an operation area;

[0106] The result obtaining unit 2202 is used to use the diagnostic agent to diagnose the target object according to the input data to obtain the diagnostic result; the input data is obtained through the display window of the diagnostic agent;

[0107] The result output unit 2203 is used to output the diagnosis result to the operation area.

[0108] It can be seen from the above technical scheme that in an object diagnosis interaction device based on an intelligent agent provided by an embodiment of the present application, by deploying an intelligent agent area and an operation area on the display interface, after the diagnostic intelligent agent is triggered, the display window of the diagnostic intelligent agent can be presented in the intelligent agent area, and then the diagnostic intelligent agent is used to diagnose the target object according to the input data, and the obtained diagnostic result is output in the operation area. Therefore, in the present application, the target object is diagnosed by the diagnostic intelligent agent and the obtained diagnostic result is output through the operation area of ​​the unified interface, and the object diagnosis can be realized without manual or email methods, and there is no need to switch the diagnostic intelligent agent and the operation area where the diagnostic result is located, thereby improving the efficiency of object diagnosis and improving the user experience.

[0109] In one implementation, the display interface also includes a menu area, which is used to output at least one menu option; wherein the trigger operation is: an operation in which an agent option in the menu options is selected; the agent area is presented on the display interface when the agent option is triggered, and at least a display window of the diagnostic agent is presented in the agent area.

[0110] In one implementation, the agent area is used to present a display window of at least one agent; the display window of the agent has a switch control; when the switch control is triggered, a switch list is output, and the switch list contains at least one to-be-selected identifier; the to-be-selected identifier is used to uniquely represent the corresponding agent; wherein the trigger operation includes: an operation in which the to-be-selected identifier corresponding to the diagnostic agent is selected.

[0111] Among them, when only the to-be-selected identifier corresponding to the diagnostic agent is selected, the display window of the diagnostic agent replaces the display window of the agent where the switching control is located; when the to-be-selected identifier corresponding to the diagnostic agent and the to-be-selected identifiers corresponding to other agents are selected, the display window of the diagnostic agent and the display windows of the other agents are presented in the agent area.

[0112] In one implementation, the diagnostic agent diagnoses the target object based on object data; the object data is the operating data of the target object in a target time period; wherein, when the target object is in an operating state, the object data is provided to the diagnostic agent in a mirroring manner.

[0113] Among them, the desktop mirror image in the object data is output in the form of a floating window in the intelligent body area.

[0114] In one implementation, the input data includes data content of at least one data type; wherein the data type includes: at least one of a character type, a document type, a voice type, an image type, and a video type.

[0115] The input data is obtained in the following manner: obtaining the input content received by the display window of the diagnostic agent; and parsing the input content using the diagnostic agent to obtain the input data.

[0116] In one implementation, before the result output unit 2203 outputs the diagnosis result to the operation area, it is also used to: determine whether the operation area is in a hidden state; the operation area enters a hidden state when the display window of the diagnostic agent is presented in the agent area, or the operation area enters a hidden state when a hidden control is triggered; if the operation area is in a hidden state, restore the operation area to be presented on the display interface.

[0117] It should be noted that the specific implementation method of each unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0118] refer to Fig.23 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, wherein a plurality of intelligent agents are installed on the electronic device, and the intelligent agents are used to provide corresponding intelligent services; the electronic device may include the following structure:

[0119] Memory 2301, used to store computer programs and data generated by the operation of the computer programs;

[0120] Processor 2302 is used to execute a computer program to achieve: in response to a trigger operation on the diagnostic agent, outputting a display window of the diagnostic agent in the agent area of ​​the display interface; the diagnostic agent is used to implement an object diagnosis function; the display interface also includes an operation area; using the diagnostic agent to diagnose the target object according to input data to obtain the diagnosis result; the input data is obtained through the display window of the diagnostic agent; and outputting the diagnosis result to the operation area.

[0121] It can be seen from the above technical solution that in an electronic device provided by an embodiment of the present application, by deploying an agent area and an operation area on the display interface, after the diagnostic agent is triggered, the display window of the diagnostic agent can be presented in the agent area, and then the diagnostic agent is used to diagnose the target object according to the input data, and the obtained diagnostic result is output in the operation area. Therefore, in the present application, the target object is diagnosed by the diagnostic agent and the obtained diagnostic result is output through the operation area of ​​the unified interface, and the object diagnosis can be realized without manual or email methods, and there is no need to switch the diagnostic agent and the operation area where the diagnostic result is located, thereby improving the efficiency of object diagnosis and improving the user experience.

[0122] Taking the electronic device as a notebook as an example, the technical solution of the present application is illustrated below:

[0123] When a user's electronic device has a problem, they can either manually check it step by step, or contact the IT diagnostic support of relevant channels through 400, Email or IM to seek a solution. The IT diagnostic service process mainly relies on manual operation, which has problems such as unclear problem description and complicated solutions. It also has problems such as low diagnostic efficiency and the need for remote operation, which leads to poor user experience and is prone to errors.

[0124] In view of this, this application provides a new interaction and method in an IT diagnosis scenario through multimodal (text, image, voice, video) technical support. It aims to provide interactive innovation of one-stop intelligent IT diagnosis service by integrating natural language processing, computer vision and speech recognition technologies.

[0125] like Fig.24 As shown, the desktop application is divided into three window screens, which are divided into ① menu window screen, i.e. menu area, ② workbench window screen, i.e. operation area, and ③ intelligent body window screen, i.e. intelligent body area according to their functional attributes.

[0126] The specific interaction steps and examples are as follows:

[0127] (1) Fig.25 As shown, the functions of text, voice, and video are completed in the ③ agent window screen. For example, in the first step: click "+" to select voice input, or upload videos / files, and also support direct drag and drop from the folder to upload. After the file is uploaded, the corresponding questions and answers can be conducted through natural language. In the second step, the diagnostic agent can give the corresponding problem description, cause analysis, and solution suggestions based on the uploaded files and text, and output them in the ② workbench window screen.

[0128] (2) Fig.26As shown, the first step is to directly mirror the entire screen by clicking "+" and selecting the screen mirroring button. The second step is to hide the workbench window screen and the menu window screen, that is, the main window is hidden. The third step is for the user to enter the question he wants to ask in the diagnostic agent. The fourth step is for the diagnostic agent to analyze the mirrored screen content and mirrored data such as logs, and give the results of the analysis and solution suggestions on the workbench window screen. Among them, after turning on the screen mirroring, the entire application is minimized, that is, the workbench window screen is hidden, and only the content of the screen mirroring is displayed in the display agent window, and real-time analysis is performed. Furthermore, the user can click the button in the upper left corner of the diagnostic agent to expand the workbench window screen and the menu window screen.

[0129] It can be seen that the technical solution of this application has the following advantages:

[0130] 1. Provide convenient diagnostic methods, reduce dependence on professional technicians, make operation easier, and reduce learning costs.

[0131] 2. Improve diagnostic accuracy, reduce misdiagnosis rate, and provide a more user-friendly and intuitive user experience.

[0132] 3. Multimodal fusion can comprehensively utilize text, image and voice information to enhance the richness and accuracy of information, and help improve the accuracy and reliability of diagnosis.

[0133] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0134] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0136] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An agent-based object diagnosis interaction method, comprising: In response to a trigger operation on the diagnostic agent, outputting a display window of the diagnostic agent in an agent area of ​​the display interface; The diagnostic agent is used to implement the object diagnosis function; the display interface also includes an operation area; Utilizing the diagnostic agent to diagnose the target object according to input data to obtain a diagnostic result; the input data is obtained through a display window of the diagnostic agent; The diagnosis result is output to the operation area.

2. The method according to claim 1, wherein the display interface further comprises a menu area, wherein the menu area is used to output at least one menu option; in, The trigger operation is: the operation in which the agent option in the menu options is selected; the agent area is presented in the display interface when the agent option is triggered, and at least the display window of the diagnostic agent is presented in the agent area.

3. According to the method of claim 1, the agent area is used to present a display window of at least one agent; the display window of the agent has a switch control; when the switch control is triggered, a switch list is output, and the switch list contains at least one to-be-selected identifier; the to-be-selected identifier is used to uniquely represent the corresponding agent; in, The trigger operation includes: an operation in which the to-be-selected identifier corresponding to the diagnostic agent is selected.

4. The method according to claim 3, wherein when only the candidate identification corresponding to the diagnosis agent is selected, the display window of the diagnosis agent replaces the display window of the agent where the switching control is located; When the to-be-selected identifier corresponding to the diagnosis agent and the to-be-selected identifier corresponding to other agents are selected, the display window of the diagnosis agent and the display windows of the other agents are presented in the agent area.

5. The method according to claim 1, wherein the diagnostic agent diagnoses the target object based on object data; the object data is the operating data of the target object in a target time period; in, When the target object is in operation, the object data is provided to the diagnostic agent in a mirroring manner.

6. According to the method of claim 5, the desktop mirror image in the object data is output in the form of a floating window in the agent area.

7. The method according to claim 1, wherein the input data includes data content of at least one data type; in, The data type includes: at least one of a character type, a document type, a voice type, an image type, and a video type.

8. The method according to claim 7, wherein the input data is obtained by: Obtaining input content received by the display window of the diagnostic agent; The input content is parsed using the diagnostic agent to obtain the input data.

9. The method according to claim 1, before outputting the diagnosis result to the operation area, the method further comprises: Determining whether the operation area is in a hidden state; The operation area enters a hidden state when the display window of the diagnosis agent is presented in the agent area, or the operation area enters a hidden state when a hiding control is triggered; If the operation area is in a hidden state, restore the operation area to be presented on the display interface.

10. An object diagnosis interaction device based on an intelligent agent, comprising: A window output unit, for outputting a display window of the diagnostic agent in the agent area of ​​the display interface in response to a trigger operation on the diagnostic agent; the diagnostic agent is used to implement the object diagnosis function; the display interface also includes an operation area; A result obtaining unit, used to use the diagnostic agent to diagnose the target object according to input data to obtain a diagnostic result; the input data is obtained through the display window of the diagnostic agent; The result output unit is used to output the diagnosis result to the operation area.

Citation Information

Cited By

  • Intelligent agent interaction method, electronic equipment and intelligent agent interaction equipment

    CN120406784A