Man-machine interaction method and device based on large model

Abstract

The invention provides a man-machine interaction method and device based on a large model, and relates to the technical field of computers, in particular to the field of artificial intelligence. According to the specific implementation scheme, input information of a user is obtained, and a user intention is determined based on the input information through a large model; determining a to-be-called target processing component according to the user intention; calling a target processing component to generate a target file based on the user intention, and displaying the target file and an editing control corresponding to the target file on a current interface; and in response to the monitored selection operation of the user on the editing control, executing online editing logic corresponding to the editing control on a target file.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, particularly to the field of artificial intelligence, and specifically to a human-computer interaction method and device based on a large model. Background Art

[0002] With the rapid development of Artificial Intelligence (AI) technology, AI assistant products have been widely used globally. Currently, most domestic and foreign AI assistant products are in the stage of assisting creation, and most of the content generated by existing AI assistants is static text. Users usually need to download the generated content to a local file and then use third-party tools for further editing and modification. Summary of the Invention

[0003] The present disclosure provides a human-computer interaction method, device, equipment, and storage medium based on a large model.

[0004] According to one aspect of the present disclosure, a human-computer interaction method based on a large model is provided. The method includes: obtaining input information of a user, and determining a user intention based on the input information through a large model; determining a target processing component to be invoked according to the user intention; invoking the target processing component to generate a target file based on the user intention, and displaying the target file and an editing control corresponding to the target file on a current interface; and in response to detecting a selection operation of the user on the editing control, performing an online editing logic corresponding to the editing control on the target file.

[0005] This application can reduce the operation complexity of users by capturing the user input information and directly generating a target file according to the intention; improve the user experience by directly delivering the file to the user without the need for the user to combine third-party software for file generation; and provide an editing control after generating the target file to enable the user to perform an online editing operation, thereby improving user satisfaction.

[0006] According to another aspect of the present disclosure, a human-computer interaction device based on a large model is provided, including: an obtaining module, configured to obtain input information of a user, and determine a user intention based on the input information through a large model; a determining module, configured to determine a target processing component to be invoked according to the user intention; an invoking module, configured to invoke the target processing component to generate a target file based on the user intention, and display the target file and an editing control corresponding to the target file on a current interface; and an interaction module, configured to perform an online editing logic corresponding to the editing control on the target file in response to detecting a selection operation of the user on the editing control.

[0007] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the above-mentioned large model-based human-computer interaction method.

[0008] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the above-mentioned large model-based human-computer interaction method.

[0009] According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, which implements the above-mentioned large model-based human-computer interaction method when executed by a processor.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understandable through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0012] Figure 1 is a schematic diagram of an exemplary implementation manner of a large model-based human-computer interaction method according to an exemplary embodiment of the present disclosure.

[0013] Figure 2 is a schematic diagram of an exemplary implementation manner of a large model-based human-computer interaction method according to an exemplary embodiment of the present disclosure.

[0014] Figure 3 is a schematic diagram showing the display of a current interface according to an exemplary embodiment of the present disclosure.

[0015] Figure 4 is a schematic diagram of an exemplary implementation manner of a large model-based human-computer interaction method according to an exemplary embodiment of the present disclosure.

[0016] Figure 5 is a schematic diagram showing the display of an editing interface according to an exemplary embodiment of the present disclosure.

[0017] Figure 6 is a schematic diagram of an exemplary implementation manner of a large model-based human-computer interaction method according to an exemplary embodiment of the present disclosure.

[0018] Figure 7It is a schematic diagram of a human-computer interaction device based on a large model according to an exemplary embodiment of the present disclosure.

[0019] Figure 8 It is a schematic diagram of an electronic device according to an exemplary embodiment of the present disclosure. Detailed implementation manners

[0020] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well-known functions and structures are omitted below for clarity and conciseness.

[0021] Artificial Intelligence (AI for short) is a discipline that studies how to make a computer simulate certain thinking processes and intelligent behaviors of humans (such as learning, reasoning, thinking, planning, etc.). It has technologies at both the hardware and software levels. Artificial intelligence hardware technologies generally include several aspects such as computer vision technology, speech recognition technology, natural language processing technology, machine learning / deep learning, big data processing technology, and knowledge graph technology.

[0022] In the technical solutions of the present disclosure, the acquisition, storage, and application of the user's personal information, etc., all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0023] Figure 1 It is a schematic diagram of an exemplary implementation manner of a human-computer interaction method based on a large model shown in this application. As Figure 1 shown, the human-computer interaction method based on a large model includes the following steps:

[0024] S101, obtain the input information of the user, and determine the user intention based on the input information through a large model.

[0025] Obtain the information input and sent by the user in the input box as the input information. Among them, the input information can include various types of content such as text, pictures, and files.

[0026] After obtaining the input information of the user, perform intention recognition on the input information through a large model to obtain the user intention.

[0027] Among them, the large model can adopt existing inference and thinking models, and in this application, the inference, thinking, etc. processes of the large model will be displayed on the display interface.

[0028] Exemplarily, the user's input information can be "Help me write an internship experience about a chemical plant." After the large model identifies the intention of the input information, it can be known that the user wants to obtain a word file about the internship experience of a chemical plant.

[0029] S102, Determine the target processing component to be called according to the user's intention.

[0030] After obtaining the user's intention above, determine the target processing component to be called according to the user's intention. Among them, the target processing component can include a target retrieval component and a target creation component.

[0031] Among them, the target retrieval component is used to retrieve the materials needed for creating the file required by the user from the database.

[0032] Among them, the target creation component is used to create the target file required by the user based on the retrieved reference materials and the previously determined user intention.

[0033] In this application, considering the different forms of files required by the user, multiple creation components are set. Exemplarily, a word creation component required for generating a word file, a PPT creation component required for generating a PPT file, a picture creation component required for generating a picture file, a mind map creation component required for generating a mind map file, a research report creation component required for generating a research report file, a poster creation component required for generating a poster, a code creation component required for generating a code file, an excel creation component required for generating an excel file, etc. can be set. Each file type can respectively correspond to 1 creation component.

[0034] Exemplarily, assuming that the user ultimately wants to obtain a word file, the target creation component is the word creation component required for generating a word file.

[0035] Among them, in addition to traditional components, a retrieval agent can also be used as the target retrieval component.

[0036] Among them, in addition to traditional components, a creation agent can also be used as the target creation component.

[0037] S103, Call the target processing component to generate the target file based on the user's intention, and display the target file and the corresponding editing control on the current interface.

[0038] After determining the target processing component to be called above, the large model is used to call the target processing component to generate the target file based on the user's intention, and the target file is displayed on the current interface.

[0039] Among them, the target file is displayed in the form of a file.

[0040] In addition to displaying the target file on the current interface, an editing control corresponding to the target file is also displayed on the current interface in this application. The user can jump to the online editing interface to perform online editing on the target file by clicking the editing control.

[0041] Furthermore, in addition to displaying the editing control, the current interface can also display a download control for downloading the target file, an export control for exporting the target file, a format conversion control for converting the format of the target file, a sharing control for sharing the target file, a template conversion control for converting the template of the target file, and so on.

[0042] S104, in response to detecting the user's selection operation on the editing control, execute the online editing logic corresponding to the editing control on the target file.

[0043] Exemplarily, if the target file is a PPT file, an editing control corresponding to the PPT file is displayed on the current interface. If the user clicks the editing control, they will jump to the online editing interface for PPT content, where the user can perform online editing on the PPT content.

[0044] An embodiment of this application proposes a human-computer interaction method based on a large model, including: obtaining the user's input information, and determining the user's intention based on the input information through the large model; determining the target processing component to be called according to the user's intention; calling the target processing component to generate a target file based on the user's intention, and displaying the target file and the editing control corresponding to the target file on the current interface; in response to detecting the user's selection operation on the editing control, execute the online editing logic corresponding to the editing control on the target file. By capturing the user's input information and directly generating the target file according to their intention, this application can reduce the operation complexity of the user; by directly delivering the file to the user, there is no need for the user to combine third-party software for file generation, improving the user experience; and, after generating the target file, an editing control is provided to enable the user to perform online editing operations, improving user satisfaction.

[0045] Figure 2 is a schematic diagram of an exemplary embodiment of a human-computer interaction method based on a large model shown in this application, as Figure 2 shown, this human-computer interaction method based on a large model includes the following steps:

[0046] S201, obtain the user's input information, and determine the user's intention based on the input information through the large model.

[0047] Specifically, considering that the user's input information may include more than one content type. For example, the user may input both pictures and text. In this application, the large model splits the input information into at least one sub-information according to the content type; obtains the content processing component corresponding to the sub-information; calls the content processing component corresponding to the sub-information to analyze and process the sub-information, and obtains the sub-information processing result; determines the user intention based on the sub-information processing result. In this way, the user can input various types of content to express their needs, and the large model can also more intelligently and comprehensively understand the user input based on the input information, so as to obtain a complete and accurate user intention.

[0048] Exemplarily, assuming that the user inputs both pictures and text, the large model splits the input information into picture sub-information and text sub-information, then determines a picture processing component dedicated to analyzing the picture sub-information, and, determines a text processing component dedicated to analyzing the text sub-information. Based on the picture processing component and the text processing component, the picture sub-information and the text sub-information are respectively analyzed and processed to obtain the sub-information processing results corresponding to them, and the user intention is determined by combining the sub-information processing results corresponding to them.

[0049] S202, screen out the target retrieval library from the candidate retrieval libraries according to the user intention.

[0050] In this application, the set candidate retrieval libraries are at least one of the whole network public domain database, user private domain database, document and literature database, and user historical interaction database.

[0051] Furthermore, the target retrieval library is also at least one of the whole network public domain database, user private domain database, document and literature database, and user historical interaction database.

[0052] Among them, the whole network public domain database may include various types of content on the entire Internet, such as news, blogs, documents, etc.

[0053] Among them, the user private domain database may include the materials saved by the user personally. For example, the user private domain database can be the materials saved in the user's network disk account.

[0054] Among them, the document and literature database may include professional documents or literatures, such as academic papers and periodical databases.

[0055] Among them, the user historical interaction database may include the materials input by the user before, and may also include the materials generated and delivered to the user before.

[0056] In this application, the input information of the user may include a target retrieval library specified by the user. For example, if the input information of the user is "Please generate a PPT of my internship experience in combination with the internship experience in my network disk", it can be known through analysis of the input information that the user has specified the database of their network disk account as the target retrieval library.

[0057] In this application, the input information of the user may not specify a target retrieval library, but the target retrieval library is determined intelligently according to the user's intention. For example, if the user's intention is "Help me generate a professional journal content", the document literature database can be intelligently determined as the target retrieval library.

[0058] This application proposes multiple retrieval libraries, making the determination of the target retrieval library more flexible, reducing information loss or errors caused by the limitations of a single database, and creatively proposing a user's private domain database, enabling the user to flexibly choose to generate a target file directly based on their private domain data, improving user satisfaction.

[0059] S203. Determine the target retrieval component corresponding to the target retrieval library.

[0060] Among them, the whole network public domain database, the user's private domain database, the document literature database, and the user's historical interaction database can each correspond to a retrieval component respectively. After determining the target retrieval library as described above, the retrieval component corresponding to the target retrieval library is used as the target retrieval component.

[0061] S204. Determine the target creation component according to the user's intention.

[0062] In this application, considering the different forms of files required by the user, multiple creation components are set. Exemplarily, there may be a word creation component required to generate a word file, a PPT creation component required to generate a PPT file, a picture creation component required to generate a picture file, a mind map creation component required to generate a mind map file, a research report creation component required to generate a research report file, a poster creation component required to generate a poster, a code creation component required to generate a code file, an excel creation component required to generate an excel file, etc. Each file type can respectively correspond to 1 creation component.

[0063] Exemplarily, assuming that what the user ultimately wants to obtain is a word file, the target creation component is the word creation component required to generate a word file.

[0064] S205. For any target retrieval library, call the target retrieval component corresponding to the target retrieval library to screen out the target data from the target retrieval library according to the user's intention.

[0065] Determine the retrieval keywords based on the user's intention. Then, for any target retrieval library, call the target retrieval component corresponding to the target retrieval library to screen out the target materials from the target retrieval library according to the retrieval keywords.

[0066] S206, call the target creation component to generate a target file by combining the target materials and the user's intention.

[0067] As an implementable method, obtain the user's historical interaction information; determine the user's preference information based on the historical interaction information, such as the preferred style, the preferred word - using habit, the preferred template, etc.; then call the target creation component to generate a target file by combining the target materials, the user's intention and the preference information. In this way, a target file that makes the user more satisfied can be generated by combining the user's preference information.

[0068] S207, display the target file and the editing control corresponding to the target file on the current interface.

[0069] Figure 3 is a schematic diagram of the display of a current interface shown in this application. As Figure 3 shown, the user - intention recognition process, the target - material retrieval process, the document - creation process, and the finally generated target file delivered to the user can be displayed on the current interface. In addition, the editing control corresponding to the target file is also displayed on the current interface. Figure 3 In addition to displaying the editing control, sharing controls, download controls, copy controls and other controls are also displayed for user interaction.

[0070] Among them, the target materials retrieved can also be displayed on the current interface, and the user can click on the target materials for further detailed browsing.

[0071] S208, in response to detecting the user's selection operation on the editing control, execute the online - editing logic corresponding to the editing control on the target file.

[0072] Exemplarily, if the target file is a PPT file, display the editing control corresponding to the PPT file on the current interface. If the user clicks on the editing control, then jump to the online - editing interface of the PPT content, and the user can perform online editing on the PPT content.

[0073] In the embodiments of this application, by capturing the user - input information and directly generating a target file according to the user's intention, the operation complexity of the user can be reduced; by directly delivering the file to the user, the user does not need to combine with a third - party software for file generation, improving the user experience; multiple retrieval libraries are proposed, making the determination of the target retrieval library more flexible and reducing the information loss or error caused by the limitation of a single retrieval library; and after generating the target file, an editing control is provided to enable the user to perform online - editing operations, improving the user's satisfaction.

[0074] Figure 4 It is a schematic diagram of an exemplary implementation manner of a human-computer interaction method based on a large model shown in this application. As Figure 4 shown, the human-computer interaction method based on a large model includes the following steps:

[0075] S401, Obtain the input information of the user, and determine the user intention based on the input information through the large model.

[0076] S402, Screen out the target retrieval library from the candidate retrieval libraries according to the user intention.

[0077] S403, Determine the target retrieval component corresponding to the target retrieval library.

[0078] S404, Determine the target creation component according to the user intention.

[0079] S405, For any target retrieval library, call the target retrieval component corresponding to the target retrieval library to screen out the target materials from the target retrieval library according to the user intention.

[0080] S406, Call the target creation component to generate the target file by combining the target materials and the user intention.

[0081] S407, Display the target file and the editing control corresponding to the target file on the current interface.

[0082] Regarding the specific implementation manners of steps S401 to S407, reference can be made to the specific introduction of the relevant parts in the above embodiments, and details will not be elaborated here.

[0083] S408, In response to detecting the selection operation of the user on the editing control, jump from the current interface to the editing interface corresponding to the editing control, and display the target content included in the target file on the editing interface.

[0084] S409, In response to detecting the content selection operation of the user on the target content, obtain the content to be edited selected by the user, and display the candidate optimization control corresponding to the content to be edited on the editing interface.

[0085] Figure 5 It is a schematic diagram of the display of an editing interface shown in this application. If the user selects the editing control, then jump from the current interface to the editing interface corresponding to the editing control, and display the target content included in the target file on the editing interface.

[0086] As Figure 5 shown, assume that the user selects "Harvest: Deeply understood that environmental protection is a cause that humans need to continuously carry out" in the target content as the content to be edited. After the user selects the content to be edited, the candidate optimization control corresponding to the content to be edited will be displayed on the editing interface. Figure 5Taking the AI-based polishing optimization control, expansion optimization control, abbreviation optimization control, continuation writing optimization control, and tone-changing optimization control as examples of candidate optimization controls.

[0087] S410, in response to detecting the user's selection operation on the candidate optimization control, obtain the target optimization control selected by the user.

[0088] S411, execute the processing logic corresponding to the target optimization control to optimize the content to be edited, and obtain the optimized target content.

[0089] Continuing with Figure 5 as an example, if after the user selects the content to be edited, it is detected that the user selects the expansion optimization control as the target optimization control, then optimize the content to be edited based on the processing logic corresponding to the expansion optimization control, and obtain the optimized target content.

[0090] Furthermore, after obtaining the optimized target content, display the candidate interaction controls corresponding to the target content on the editing interface; in response to detecting the user's selection operation on the candidate interaction controls, execute the processing logic corresponding to the target interaction control selected by the user on the target content. In this way, even after online editing of the target file, it is still possible to perform post-link operations on the target content based on the control selected by the user, such as downloading or exporting, etc.

[0091] Exemplarily, the candidate interaction controls corresponding to the target content displayed on the editing interface may include an export control for exporting, a convert-to-PDF control for converting to the PDF format, and so on. After obtaining the optimized target content as described above, assuming the user selects the convert-to-PDF control, then generate a PDF file based on the target content; assuming the user selects the export control, then generate a word document based on the target content and save it locally.

[0092] The embodiment of the present application can reduce the operation complexity of the user by capturing the user input information and directly generating the target file according to the user's intention; improve the user experience by directly delivering the file to the user without the user having to combine with third-party software for file generation; and introduce in detail the process of the user performing online editing on the target file based on the AI control, without the user having to perform manual input editing, but can achieve various different optimization functions with the help of the AI control, thus improving the user satisfaction.

[0093] Figure 6 is a schematic diagram of an exemplary embodiment of a large model-based human-computer interaction method shown in the present application. As Figure 6 shown, the large model-based human-computer interaction method includes the following steps:

[0094] S601, Obtain the input information of the user, and determine the user intention based on the input information through a large model.

[0095] S602, Screen out the target retrieval library from the candidate retrieval libraries according to the user intention.

[0096] S603, Determine the target retrieval component corresponding to the target retrieval library.

[0097] S604, Determine the target creation component according to the user intention.

[0098] S605, For any target retrieval library, call the target retrieval component corresponding to the target retrieval library to screen out the target materials from the target retrieval library according to the user intention.

[0099] S606, Call the target creation component to generate the target file by combining the target materials and the user intention.

[0100] S607, Display the target file and the corresponding editing control on the current interface.

[0101] S608, In response to detecting the user's selection operation on the editing control, jump from the current interface to the editing interface corresponding to the editing control, and display the target content included in the target file on the editing interface.

[0102] Regarding the specific implementation manners of steps S601 to S608, reference may be made to the specific introductions in the relevant parts of the above embodiments, and details will not be elaborated herein.

[0103] S609, In response to detecting the user's content selection operation on the target content, obtain the content to be edited selected by the user.

[0104] S610, In response to detecting the user's input operation, obtain the replacement content input by the user.

[0105] In this application, the user can manually input content as the replacement content for the content to be edited.

[0106] S611, Replace the content to be edited based on the replacement content to obtain the replaced target content.

[0107] Further, after obtaining the replaced target content as described above, candidate interaction controls corresponding to the target content are displayed on the editing interface; in response to detecting the user's selection operation on the candidate interaction controls, the processing logic corresponding to the target interaction control selected by the user is executed on the target content. In this way, even after online editing of the target file, post-link operations can still be performed on the target content based on the controls selected by the user, such as downloading or exporting.

[0108] Exemplarily, the candidate interaction controls corresponding to the target content displayed on the editing interface may include an export control for exporting, a convert-to-PDF control for converting to the PDF format, and so on. After obtaining the replaced target content as described above, assuming the user selects the convert-to-PDF control, a PDF file is generated based on the target content; assuming the user selects the export control, a word document is generated based on the target content and saved locally.

[0109] In the embodiment of the present application, by capturing the user input information and directly generating the target file according to the intention, the operation complexity of the user can be reduced; by directly delivering the file to the user, the user does not need to combine with a third-party software for file generation, improving the user experience; the process of the user manually inputting content to perform online editing on the target file is introduced, and the content of the target file can be quickly corrected according to the user's idea, improving the user satisfaction.

[0110] Figure 7 is a schematic diagram of a human-computer interaction device based on a large model shown in the present application, as Figure 7 shown, the human-computer interaction device 700 based on the large model includes an acquisition module 701, a determination module 702, a call module 703, and an interaction module 704, where:

[0111] The acquisition module 701 is configured to acquire the user input information and determine the user intention based on the input information through the large model.

[0112] The determination module 702 is configured to determine the target processing component to be called according to the user intention.

[0113] The call module 703 is configured to call the target processing component to generate the target file based on the user intention, and display the target file and the editing control corresponding to the target file on the current interface.

[0114] The interaction module 704 is configured to execute the online editing logic corresponding to the editing control on the target file in response to monitoring the selection operation of the user on the editing control.

[0115] This device can reduce the operation complexity of the user by capturing the user input information and directly generating the target file according to the intention; by directly delivering the file to the user, the user does not need to combine with a third-party software for file generation, improving the user experience; and after generating the target file, an editing control is provided to enable the user to perform online editing operations, improving the user satisfaction.

[0116] Further, the determination module 702 is further configured to: screen out the target retrieval library from the candidate retrieval library according to the user intention; determine the target retrieval component corresponding to the target retrieval library; and determine the target creation component according to the user intention.

[0117] Furthermore, the target search database is at least one of a public domain database of the entire network, a user private domain database, a document and literature database, and a user history interaction database.

[0118] Furthermore, the calling module 703 is also used to: for any target retrieval library, call the target retrieval component corresponding to the target retrieval library to filter out the target data from the target retrieval library according to the user's intention; call the target creation component to generate a target file based on the target data and the user's intention.

[0119] Furthermore, the calling module 703 is also used to: obtain the user's historical interaction information; determine the user's preference information based on the historical interaction information; and call the target creation component to generate a target file in combination with the target data, user intention and preference information.

[0120] Furthermore, the interaction module 704 is also used to: jump from the current interface to the editing interface corresponding to the editing control, and display the target content contained in the target file on the editing interface; in response to monitoring the user's content selection operation on the target content, obtain the content to be edited selected by the user, and display the candidate optimization control corresponding to the content to be edited on the editing interface; in response to monitoring the user's selection operation on the candidate optimization control, obtain the target optimization control selected by the user; execute the processing logic corresponding to the target optimization control to optimize the content to be edited to obtain the optimized target content.

[0121] Furthermore, the interaction module 704 is also used to: jump from the current interface to the editing interface corresponding to the editing control, and display the target content contained in the target file on the editing interface; in response to monitoring the user's content selection operation on the target content, obtain the content to be edited selected by the user; in response to monitoring the user's input operation, obtain the replacement content input by the user; replace the content to be edited based on the replacement content to obtain the replaced target content.

[0122] Furthermore, the interaction module 704 is also used to: display candidate interaction controls corresponding to the target content on the editing interface; and in response to monitoring the user's selection operation on the candidate interaction control, execute the processing logic corresponding to the target interaction control selected by the user on the target content.

[0123] Furthermore, the acquisition module 701 is also used to: split the input information into at least one sub-information according to the content type through the large model; obtain the content processing component corresponding to the sub-information; call the content processing component corresponding to the sub-information to analyze and process the sub-information to obtain the sub-information processing result; and determine the user intention based on the sub-information processing result.

[0124] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0125] Figure 8 FIG. shows a schematic block diagram of an exemplary electronic device 800 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0126] As Figure 8 shown, the device 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0127] Multiple components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0128] The computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 executes the various methods and processes described above, such as the human-computer interaction method based on large models. For example, in some embodiments, the human-computer interaction method based on large models can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the human-computer interaction method based on large models described above can be executed. Alternatively, in other embodiments, the computing unit 801 can be configured to execute the human-computer interaction method based on large models in any other suitable manner (e.g., by means of firmware).

[0129] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0133] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0134] A computer system can include a client and a server. The client and the server are generally far apart from each other and typically interact through a communication network. The client-server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, can also be a server of a distributed system, or a server incorporating a blockchain.

[0135] It should be understood that the various forms of processes shown above can be used, with steps reordered, added or deleted. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitation is imposed herein.

[0136] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A human-computer interaction method based on a large model, comprising: Obtaining user input information, and determining the user intention based on the input information through a large model; Determine a target processing component to be called according to the user intention; Calling the target processing component to generate a target file based on the user intention, and displaying the target file and the editing control corresponding to the target file on the current interface; In response to monitoring the user's selection operation on the editing control, the online editing logic corresponding to the editing control is executed on the target file.

2. The method according to claim 1, wherein The target processing component includes a target retrieval component and a target creation component, and the target processing component to be called according to the user intention is determined to include: Filtering a target search library from the candidate search libraries according to the user intention; Determine the target retrieval component corresponding to the target retrieval library; A target authoring component is determined based on the user intent.

3. The method according to claim 2, wherein, The target retrieval database is at least one of a public domain database of the entire network, a user private domain database, a document and literature database, and a user history interaction database.

4. The method according to claim 3, wherein, The calling of the target processing component to generate a target file based on the user intention includes: For any of the target search libraries, calling the target search component corresponding to the target search library to filter out target data from the target search library according to the user intention; The target creation component is called to generate the target file in combination with the target data and the user intention.

5. The method according to claim 4, wherein The calling of the target creation component to generate the target file in combination with the target data and the user intention includes: Acquire historical interaction information of the user; Determining preference information of the user based on the historical interaction information; The target creation component is called to generate the target file in combination with the target data, the user intention and the preference information.

6. The method according to claim 5, wherein Executing the online editing logic corresponding to the editing control on the target file includes: Jump from the current interface to the editing interface corresponding to the editing control, and display the target content contained in the target file on the editing interface; In response to monitoring the user's content selection operation on the target content, acquiring the content to be edited selected by the user, and displaying candidate optimization controls corresponding to the content to be edited on the editing interface; In response to monitoring the user's selection operation on the candidate optimization control, obtaining the target optimization control selected by the user; The processing logic corresponding to the target optimization control is executed to optimize the content to be edited to obtain the optimized target content.

7. The method according to claim 5, wherein, Executing the online editing logic corresponding to the editing control on the target file includes: Jump from the current interface to the editing interface corresponding to the editing control, and display the target content contained in the target file on the editing interface; In response to monitoring the user's content selection operation on the target content, acquiring the content to be edited selected by the user; In response to monitoring the input operation of the user, obtaining replacement content input by the user; The content to be edited is replaced based on the replacement content to obtain the replaced target content.

8. The method according to claim 6 or 7, wherein After obtaining the optimized target content or the replaced target content, the method further includes: displaying candidate interaction controls corresponding to the target content on the editing interface; responding to the detected selection operation of the user on the candidate interaction control, and executing the processing logic corresponding to the target interaction control selected by the user on the target content.

9. The method according to claim 1, wherein The step of determining the user intention by the large model based on the input information includes: splitting the input information into at least one sub-information by the large model according to the content type; obtaining a content processing component corresponding to the sub-information; invoking the content processing component corresponding to the sub-information to analyze and process the sub-information to obtain a sub-information processing result; determining the user intention based on the sub-information processing result.

10. A human-computer interaction device based on a large model, comprising: an acquisition module configured to acquire input information of a user and determine a user intention by a large model based on the input information; a determination module configured to determine a target processing component to be invoked according to the user intention; a call module configured to call the target processing component to generate a target file based on the user intention, and display the target file and display an editing control corresponding to the target file on the current interface; an interaction module configured to, in response to detecting a selection operation of the user on the editing control, execute online editing logic corresponding to the editing control on the target file.

11. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-9.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

13. A computer program product, comprising a computer program, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1-9.

Images