Interactive document generation method and device, storage medium and program product

Abstract

The embodiment of the invention provides an interactive document generation method and device, a storage medium and a program product, original input information and a first operation panel are displayed, the first operation panel is configured to have a first operation area, the first operation area is used for displaying an indication identifier, and the position of the indication identifier in the first operation area is displayed; mapping document content features under at least one content dimension; and in response to a first operation for the first operation area, displaying an indication identifier at a target position in the first operation area, generating an output document corresponding to the original input information according to the target position, and matching document contents of the output document with target document content features corresponding to the target position. The document content feature description based on the image user interface is realized, the problems of low and inaccurate description of document content features based on texts are avoided, and the document generation efficiency and the content accuracy are improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of artificial intelligence technology, and in particular, to an interactive document generation method, device, storage medium, and program product. Background Art

[0002] Currently, in a document processing program implemented based on artificial intelligence (AI) technology, the user's intention can be obtained through a conversation, and then document processing tasks such as abstract generation, article polishing, and expansion can be implemented based on the user's intention.

[0003] In the prior art, in a document processing program, it is usually necessary for the user to input an accurate text description, and then perform corresponding document processing tasks based on the text description. However, the above solutions in the prior art have problems of low document generation efficiency and poor content accuracy. Summary of the Invention

[0004] Embodiments of the present disclosure provide an interactive document generation method, device, storage medium, and program product to overcome the problems of low document generation efficiency and poor content accuracy.

[0005] In a first aspect, an interactive document generation method provided by an embodiment of the present disclosure includes:

[0006] Displaying original input information and a first operation panel, the first operation panel being configured to have a first operation area for displaying an indication identifier, the position of the indication identifier within the first operation area mapping document content features in at least one content dimension; in response to a first operation on the first operation area, displaying the indication identifier at a target position within the first operation area, and generating an output document corresponding to the original input information according to the target position, the document content of the output document matching the target document content features corresponding to the target position.

[0007] In a second aspect, an interactive document generation device provided by an embodiment of the present disclosure includes:

[0008] A first interaction unit for displaying original input information and a first operation panel, the first operation panel being configured to have a first operation area for displaying an indication identifier, the position of the indication identifier within the first operation area mapping document content features in at least one content dimension;

[0009] A second interaction unit for, in response to a first operation on the first operation area, displaying the indication identifier at a target position within the first operation area;

[0010] A processing unit for generating an output document corresponding to the original input information according to the target position, wherein the document content of the output document matches the target document content feature corresponding to the target position.

[0011] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0012] The memory stores computer-executable instructions;

[0013] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the interactive document generation method described in the first aspect and various possible designs of the first aspect as above.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When the processor executes the computer-executable instructions, the interactive document generation method described in the first aspect and various possible designs of the first aspect as above is implemented.

[0015] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, and when the computer program is executed by a processor, the interactive document generation method described in the first aspect and various possible designs of the first aspect as above is implemented.

[0016] The interactive document generation method, device, storage medium, and program product provided in this embodiment display the original input information and a first operation panel. The first operation panel is configured to have a first operation area for displaying an indication mark. The position of the indication mark in the first operation area maps the document content features under at least one content dimension. In response to a first operation on the first operation area, an indication mark is displayed at a target position in the first operation area, and an output document corresponding to the original input information is generated according to the target position. The document content of the output document matches the target document content feature corresponding to the target position. By configuring the first operation panel with the first operation area, responding to the user's operation on the first operation area, generating an indication mark, and then characterizing the target document content feature based on the target position of the indication mark in the first operation area, and further generating an output document with the target document content feature, it realizes the description of the document content feature based on the graphical user interface, avoids the problems of low efficiency and inaccuracy caused by describing the document content feature based on text, and improves the document generation efficiency and content accuracy. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a schematic diagram of an application scenario of the interactive document generation method provided by an embodiment of the present disclosure;

[0019] Figure 2 It is a schematic flow chart of the interactive document generation method provided by an embodiment of the present disclosure Figure 1 ;

[0020] Figure 3 It is a schematic diagram of a first operation area provided by an embodiment of the present disclosure;

[0021] Figure 4 It is another schematic diagram of a first operation area provided by an embodiment of the present disclosure;

[0022] Figure 5 It is a flow chart of the specific implementation manner of step S100;

[0023] Figure 6 It is a schematic flow chart of the interactive document generation method provided by an embodiment of the present disclosure Figure 2 ;

[0024] Figure 7 It is Figure 6 a flow chart of the specific implementation manner of step S203 in the illustrated embodiment;

[0025] Figure 8 It is a schematic diagram of the process of generating content parameter data and structure parameter data provided by an embodiment of the present disclosure;

[0026] Figure 9 It is Figure 6 a flow chart of the specific implementation manner of step S205 in the illustrated embodiment;

[0027] Figure 10 It is a schematic diagram of the process of determining a target document template provided by an embodiment of the present disclosure;

[0028] Figure 11 It is a structural block diagram of the interactive document generation device provided by an embodiment of the present disclosure;

[0029] Figure 12 It is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure;

[0030] Figure 13Schematic diagram of the hardware structure of the electronic device provided by the embodiments of the present disclosure. Detailed implementation manners

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some but not all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0032] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties. The collection, use, and processing of relevant data need to comply with relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.

[0033] The application scenarios of the embodiments of the present disclosure will be explained below:

[0034] The interactive document generation method provided by the embodiments of the present disclosure can be applied to an application program (APP, Application) with document processing functions, such as AI assistant application programs, document editing application programs, etc. More specifically, it can be applied to application scenarios such as article expansion, article polishing, and abstract generation. The execution subject of this embodiment can be a terminal device running the above-mentioned application program with document processing functions, or a server deploying the service end corresponding to the above-mentioned application program, or other electronic devices with similar functions. Among them, when the execution subject is a terminal device, the terminal device executes the method provided by this embodiment by running the above-mentioned application program; when the execution subject is a server, the service end of the above-mentioned application program with document processing functions can run partially or entirely on the server and execute the method provided by this embodiment on the server side, while the terminal device runs the client of the application program. Based on the server-client communication between the server and the terminal device, the terminal device can obtain the execution result of the method provided by this embodiment and display it as needed.

[0035] Among them, in some embodiments, the terminal device or the server can implement the interactive document generation method provided in the embodiments of the present disclosure by running various computer-executable instructions or computer programs. For example, the computer-executable instructions can be program-level commands, machine instructions, or software instructions. The computer program can be a native program or a software module in the operating system; it can be a local application, that is, a program that needs to be installed in the operating system to run, or it can be a small program embedded in any APP, that is, a program that runs based on the browser environment. In summary, the above computer-executable instructions can be instructions in any form, and the above computer programs can be application programs, modules, or plugins in any form, and the specific implementation form can be configured according to needs. Further, in the process of implementing the interactive document generation method provided in the embodiments of the present disclosure, the terminal device can execute the method by running the computer-executable instructions or computer programs set locally, or can execute the method by calling the computer-executable instructions or computer programs set in an external server. In some embodiments, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud storage, cloud communication, cloud databases, cloud computing, cloud functions, network services, middleware services, domain name services, security services, content delivery network (Content Delivery Network, CDN), and big data and artificial intelligence platforms. Among them, the cloud service can be an interactive processing service for the terminal device to call.

[0036] Figure 1 FIG. is an application scenario diagram of the interactive document generation method provided in the embodiments of the present disclosure. Refer to Figure 1 As shown in the figure, taking the terminal device as an example, a target application program with document processing functions runs in the terminal device. The target application program is, for example, an AI assistant program. The user inputs or loads one or more of text, pictures, audio, and video through the interaction interface of the target application program as the original input information. Then, the terminal device will process the above original input information by calling a pre-trained document generation model to generate a corresponding output document. For example, as shown in the figure, the original input information is a picture (image P1) and a piece of text (shown as ABC in the figure). After that, after the user further inputs a more detailed intention description (such as article style, writing characteristics) in the interaction interface and clicks the "Process" control, the terminal device processes the above original input information and generates a short story named DEF (the text content is represented by XXX in the figure), and can perform subsequent operations such as return, save, or publish according to the user's needs.

[0037] In the application scenario of document processing based on AI technology, human-computer interaction is usually carried out based on a Conversational User Interface. That is, the AI assistant guides the user to complete the text description of the user's intention in the way of "chat" by imitating the user's conversation. Then, based on the text input by the user, it conducts understanding and reasoning, and finally completes the document processing process based on the user's intention. In the above process, it is required that the user inputs text with accurate meaning to describe the content characteristics of the document. This step has a relatively high operation threshold, resulting in problems such as insufficient and inaccurate expression in the descriptive text of the user's intention. As a result, when performing corresponding document processing tasks based on the text description, there are problems of low document generation efficiency and poor content accuracy.

[0038] The embodiments of the present disclosure provide an interactive document generation method to solve the above problems.

[0039] Refer to Figure 2 , Figure 2 which is the flowchart of the interactive document generation method provided by the embodiments of the present disclosure. Figure 1 The method of this embodiment can be applied to a terminal device or a server. Among them, for the case where the terminal device executes the method provided by this embodiment, in one possible implementation, the terminal device can implement the interactive document generation method provided by this embodiment by executing the program code deployed locally. In another possible implementation, the server can be used to deploy the functional service implemented based on the interactive document generation method provided by this embodiment, and the terminal device can access the above server and call the corresponding functional service to implement the interactive document generation method provided by this embodiment. Exemplarily, the interactive document generation method provided by this embodiment includes:

[0040] Step S101: Display the original input information and the first operation panel. The first operation panel is configured to have a first operation area, and the first operation area is used to display indication identifiers. The position of the indication identifier in the first operation area maps the document content characteristics under at least one content dimension.

[0041] Step S102: In response to the first operation on the first operation area, display the indication identifier at the target position in the first operation area.

[0042] Refer to Figure 1Schematic diagram of the application scenario shown. In this embodiment, the terminal device is used as the execution subject to introduce the provided interactive document generation method. Exemplarily, the terminal device provides a document processing function to the user by running a target application. The user can input and load the original input information through the interaction interface of the target application, or select the information currently displayed on the terminal device as the original input information. Exemplarily, the original input information may include one or more of text, pictures, videos, audios, and information in data format. When or after the terminal device displays the original input information in the interaction interface, it displays a first operation panel. Among them, the first operation panel has a first operation area. After an operation is applied to the first operation area, an indication mark will be displayed at the corresponding operation position. The indication mark can be a circular symbol, a hand-shaped graphic, etc., which are symbols or graphics that can be used to indicate positions. This embodiment does not make any restrictions.

[0043] Furthermore, the position of the indication mark in the first operation area maps the document content features under at least one content dimension. The content dimension can be understood as a certain aspect of the document content features. For example, the content dimension includes a tone dimension, a writing style dimension, a content professionalism dimension, a content expansion degree dimension, etc. Specifically, for example, the document content features under the tone dimension, that is, the features of the document content in terms of tone (such as relaxed or serious); another example is the document content features under the content professionalism dimension, that is, the features of the document content in terms of content professionalism (professional or colloquial). Different content dimensions correspond to the features of the document content in different aspects. Through the document content features under different content dimensions, the control of the document content can be achieved from multiple aspects, thereby meeting the user's more detailed, accurate, and diverse content creation intentions.

[0044] Furthermore, based on the mapping relationship between the position of the indication mark in the first operation area and the document content features under at least one content dimension, the purpose of describing the document content features can be achieved by operating the indication mark. Specifically, after the terminal device receives the first operation on the first operation area, according to the trigger position of the first operation, the target position can be determined, and a corresponding indication mark, that is, the indication mark, will be generated and displayed at the target position. Figure 3 Schematic diagram of a first operation area provided by an embodiment of the present disclosure, as Figure 3As shown, the first operation area within the first operation panel is a long rectangular area, and the indication identifier can be moved and displayed within this area in the left and right directions. Among them, when the user applies a click operation (the first operation) at the P1 point position (i.e., the target position) with respect to this first operation area, a corresponding indication identifier is displayed at the P1 point position, such as the solid circle symbol shown in the figure. And when the user applies a click operation at the P2 point position again, a corresponding indication identifier is displayed at the P2 point position, and at the same time, the indication identifier at the P1 point position disappears. Visually, that is, the solid circle symbol (indication identifier) moves from the P1 point position to the P2 point position. The distance from the P1 point position or the P2 point position to the left area boundary or the right area boundary of the first operation area (i.e., the relatively arranged first area boundary and the second area boundary) can be used to map the document content characteristics under a certain specific content dimension. For example, the document content characteristics under the content professionalism dimension. More specifically, for example, the closer the P1 point position is to the left area boundary, the more professional the document content is, and the closer the P1 point position is to the right area boundary, the more colloquial the document content is. That is to say, in this embodiment, the position of the indication identifier within the first operation area maps the document content characteristics under a content dimension. Optionally, according to needs, the prompt information corresponding to the content dimension mapped by the above first operation area can also be displayed within the first operation panel to guide the user to improve the operation efficiency. For example, the prompt information of "more professional" and "more colloquial" is displayed at both ends of the left area boundary and the right area boundary.

[0045] Figure 4 Another schematic diagram of the first operation area provided by the embodiments of the present disclosure is as Figure 4As shown, the first operation area within the first operation panel is a square area, and the indication mark can move and be displayed in this area in four directions: up, down, left, and right. Among them, when the user applies a click operation (the first operation) at the P1 point position (i.e., the target position) with respect to the first operation area, a corresponding indication mark is displayed at the P1 point position, such as the solid circle symbol shown in the figure. When the user applies a click operation at the P2 point position again, a corresponding indication mark is displayed at the P2 point position, and at the same time, the indication mark at the P1 point position disappears. Visually, that is, the solid circle symbol (indication mark) moves from the P1 point position to the P2 point position. The first distance from the P1 point position or the P2 point position to the left area boundary or the right area boundary of the first operation area (i.e., the relatively set first area boundary and the second area boundary), and the second distance from the P1 point position or the P2 point position to the upper area boundary or the lower area boundary of the first operation area (i.e., the relatively set third area boundary and the fourth area boundary) are respectively used to map the document content features under two content dimensions. For example, the first distance is used to map the document content features under the content professionalism dimension (the first content dimension). More specifically, the greater the first distance, the more professional the document content; the smaller the first distance, the more colloquial the document content. The second distance is used to map the document content features under the content extensiveness dimension (the second content dimension). The greater the second distance, the richer the expansion of the document content; the smaller the second distance, the more focused the document content on the theme. Optionally, as shown in the figure, the prompt information of "more professional" and "more colloquial" is displayed at both ends of the left area boundary and the right area boundary, and the prompt information of "content expansion" and "focus on the theme" is displayed at both ends of the upper area boundary and the lower area boundary to guide the user to operate and improve the interaction efficiency.

[0046] That is to say, in this embodiment, the position of the indication mark within the first operation area maps the document content features under two content dimensions.

[0047] In addition, the implementation manner of the above first operation is exemplary, and it can also be other ways. For example, after the first operation panel is initialized, a default indication mark is displayed within the first operation area, such as Figure 4 the solid circle symbol at the P1 point position shown in the figure. After that, in response to the user's drag operation (another possible first operation), the solid circle symbol is moved from the P1 point position to the P2 point position, and the P2 point position is the target position corresponding to the first operation. That is, another implementation manner of displaying the indication mark at the target position within the first operation area in response to the first operation on the first operation area can be specifically set according to needs and is not limited in this embodiment. Among them, the first operation can include multiple repeated operations, that is, the user determines a final target position by adjusting the position of the indication mark multiple times, and at the same time, an indication mark is displayed at the target position.

[0048] Further, in a possible implementation, optionally, before step S101, it further includes:

[0049] Step S100: Configure the content dimension of the document content features adjusted by the first operation panel.

[0050] Exemplarily, the first operation panel includes a first operation area, and the positions within the first operation area map the document content features under at least one content dimension. That is, the first operation panel can adjust the document content features of the output document in one or more content dimensions through the first operation area. The first operation area maps at least one content dimension, such as the content professionalism dimension, the tone dimension, etc. In a possible implementation, the content dimensions mapped by the first operation area are fixed, that is, the content dimensions of the document content features adjusted by the first operation panel are fixed. Specifically, configure one or more fixed, commonly used content dimensions that are not affected by the type or content semantics of the original input information for the first operation panel, such as the document word count dimension. After that, the user can perform a first operation to determine a target position within the first operation area, thereby controlling the document word count of the output document. In another possible implementation, the content dimensions of the document content features adjusted by the first operation panel are dynamically configured based on the original input information. Exemplarily, as Figure 5 shown, the specific implementation of step S100 includes:

[0051] Step S100A: In response to a first trigger operation, select the original input information within the interaction interface, where the original input information includes at least one of text, picture, and video.

[0052] Step S100B: In response to a second trigger operation, determine a recommended content dimension based on the content of the original input information, and configure the mapping between the operation area of the first operation panel and the recommended content dimension.

[0053] The content dimensions mapped by the first operation area are dynamic, that is, when the types of the original input information are different, the content dimensions mapped by the first operation area are different. For example, when the original input information is a piece of text and the original input information is used to continue writing the text, in this case, the content dimensions mapped by the first operation area include the content professionalism dimension and do not include the tone dimension; when the original input information is a video and the original input information is used to create an article based on the video, in this case, the content dimensions mapped by the first operation area include the tone dimension.

[0054] In this embodiment, by first selecting the original input information required by the user within the interactive interface based on the first trigger operation, and then determining a recommended content dimension that matches it according to the type and / or content semantics of the original input information, and configuring it to the operation area of the first operation panel, the content dimension that the first operation panel can adjust is matched with the original input information actually processed, so as to achieve more reasonable content feature control and improve the quality of the output document. In practical applications, the prompt information corresponding to the recommended content dimension can also be displayed in the first operation panel as needed (for example, display prompt information such as "more professional" and "more colloquial" at both ends of the area boundary), so as to realize the intelligent recommendation of the content dimension controlled by the first operation panel.

[0055] Step S103: Generate an output document corresponding to the original input information according to the target position, and the document content of the output document matches the target document content feature corresponding to the target position.

[0056] Further, after determining the target position of the indication identifier in response to the first operation, for example, this target position, map the corresponding document content feature, that is, determine the target document content feature. Then, based on the target document content feature, call the pre-trained document generation model to process the original input information, complete document processing tasks such as article polishing and article expansion, and finally output a processed document, that is, the output document. Since the target document content feature is referred to (input) during the process of generating the output document in the document generation model, the document content of the generated output document matches the target document content feature corresponding to the target position.

[0057] In a possible implementation manner, the target position is, for example, a two-dimensional coordinate, in the form of, for example, [x, y], where x represents the abscissa within the first operation area, and y represents the abscissa within the first operation area. According to the preset configuration information, this two-dimensional coordinate can be mapped to a feature matrix, feature vector or feature identifier representing the document content under at least one content dimension. Then, by inputting the above feature matrix, feature vector or feature identifier and the original input information into the document generation model, using the document generation ability provided by the document generation model, extract the features of the original input information to obtain the corresponding initial features, and then combine the target document content features to control the content generation direction based on the initial features, and finally generate a document that matches the target document content feature, that is, the output document.

[0058] In this embodiment, by displaying the original input information and the first operation panel, the first operation panel is configured to have a first operation area, and the first operation area is used to display an indication identifier. The position of the indication identifier within the first operation area maps the document content features under at least one content dimension. In response to a first operation on the first operation area, an indication identifier is displayed at a target position within the first operation area, and an output document corresponding to the original input information is generated according to the target position. The document content of the output document matches the target document content features corresponding to the target position. By configuring the first operation panel with the first operation area, responding to the user's operation on the first operation area, generating an indication identifier, and then based on the target position of the indication identifier within the first operation area, characterizing the target document content features, and further generating an output document with the target document content features, the description of the document content features based on the graphical user interface is realized, avoiding the problems of low efficiency and inaccuracy caused by describing the document content features based on text, and improving the document generation efficiency and content accuracy.

[0059] Reference Figure 6 , Figure 6 is a schematic flowchart of an interactive document generation method provided by an embodiment of the present disclosure Figure 2 . This embodiment further refines step S103 on the basis of the embodiment shown in Figure 2 . The interactive document generation method includes:

[0060] Step S201: Display the original input information and the first operation panel. The first operation panel is configured to have a first operation area and a second operation area. The first operation area is used to display an indication identifier. The position of the indication identifier within the first operation area maps the document content features under at least one content dimension. The second operation area is used to determine the document structure features of the output document.

[0061] Step S202: In response to a first operation on the first operation area, display an indication identifier at a target position within the first operation area.

[0062] Step S203: Obtain content parameter data characterizing the target document content features according to the target position.

[0063] Exemplarily, in this embodiment, a first operation area and a second operation area are configured within the first operation panel. Among them, the specific implementation manner of the first operation area has been introduced in detail in the previous embodiment part and will not be elaborated here. Then, according to the target position determined by the first operation, content parameter data characterizing the target document content features is generated. Among them, the content parameter data includes, for example, coordinates characterizing the target position. The coordinates can be one-dimensional coordinates or two-dimensional indexes, or can be serial numbers characterizing the target position.

[0064] Exemplarily, the operation area at least includes a first area boundary and a second area boundary which are oppositely arranged, and a third area boundary and a fourth area boundary which are oppositely arranged. As Figure 7 shown, the specific implementation manner of step S203 includes:

[0065] Step S2031: Obtain a first content parameter according to the distance between the target position and the first area boundary or the second area boundary. The first content parameter characterizes the document content feature in the first content dimension.

[0066] Step S2032: Obtain a second content parameter according to the distance between the target position and the third area boundary or the fourth area boundary. The second content parameter characterizes the document content feature in the second content dimension.

[0067] Step S2033: Obtain content parameter data according to the first content parameter and the second content parameter.

[0068] Exemplarily, in this embodiment, the target position is represented by two-dimensional coordinates. Referring to Figure 4 the schematic diagram of the first operation area shown, the first area boundary and the second area boundary are two vertical boundaries of the rectangular first operation area. Exemplarily, the abscissa corresponding to the first area boundary is 0, and the abscissa corresponding to the second area boundary is 1. Then the first content parameter is a value greater than or equal to 0 and less than or equal to 1. Similarly, the third area boundary and the fourth area boundary are two horizontal boundaries of the rectangular first operation area. The ordinate corresponding to the third area boundary is 0, and the ordinate corresponding to the fourth area boundary is 1. Then the first content parameter is a value greater than or equal to 0 and less than or equal to 1. After that, content parameter data is obtained according to the two-dimensional array composed of the first content parameter and the second content parameter. In this embodiment, the content parameter data composed of the first content parameter and the second content parameter can describe the composite features in two content dimensions, thereby improving the accuracy and efficiency of the description of the document content features.

[0069] Step S204: In response to the second operation on the second operation area, obtain structure parameter data characterizing the target document structure feature.

[0070] Exemplarily, the second operation area is used to determine the document structure features of the output document in response to a user operation. In one possible implementation, option controls are provided in the second operation area, and corresponding options are set through the option controls to determine the document structure features of the output document. The document structure features may include, for example, being compact, logical, etc. The structural parameter data representing the target document structure features can be a specific value, an array, or a matrix, which is not limited here. In another possible implementation, the second operation area is used to determine the document content features under at least one content dimension, that is, the second operation area can be a supplement or basis for the first operation area. For example, the user first operates the second operation area to determine the document content features under a target content dimension, setting a content tone for the finally generated output document. For example, in the scenario of article continuation, whether the content of the generated output document leans towards tragedy or comedy can be set through the second operation area. Then, by operating the first operation area, the content of the output document is fine-tuned in other dimensions, such as the professionalism dimension, the divergence dimension, etc.

[0071] Further, in one possible implementation, before step S204, it further includes: obtaining the semantic information of the original input information; and displaying at least two alternative document structure parameters representing the document structure features in the second operation area according to the semantic information.

[0072] Correspondingly, the specific implementation manner of step S204 includes:

[0073] Step S204A: In response to the second operation on the alternative document structure parameters, determine the target document structure parameters, and generate structural parameter data based on the target document structure parameters.

[0074] Exemplarily, similar to the first operation area, the content displayed in the second operation area can be pre-configured fixed content, that is, similar to the case where the content dimension mapped by the first operation area is fixed. The second operation panel is configured with one or more fixed, commonly used alternative document structure parameters that are not affected by the type or content semantics of the original input information, such as the document word count parameter. Then, the user can perform a second operation to determine the target document structure parameters from multiple alternative document structure parameters, and then use it as the structural parameter data representing the document structure features.

[0075] In another possible implementation, the content configured in the second operation panel, that is, the alternative document structure parameters, are dynamically configured based on the original input information. Specifically, after obtaining the original input information, semantic analysis is performed on the original input information to obtain semantic information representing the semantics of the original input information. Then, based on the semantic information, the corresponding alternative document structure parameters representing the document structure features are determined. For example, if the semantic information indicates that the content semantics of the original input information is a story that needs to be expanded, then according to the above semantic information, the corresponding alternative document structure parameters are determined to include a "structural coherence parameter" (more structured). This parameter is used to control the document generation model to expand the original input information in a more organized and structured manner. For example, it may elaborate on the content in a certain logical order, such as cause-and-effect relationship, chronological order, general-to-specific relationship, etc. It will add more conjunctions and transitional sentences to make the text more hierarchical and the structure more complete, and so on. Another example is that the alternative document structure parameters also include a "content focus parameter" (more focused). This parameter is used to control the document generation model to expand the original input information more closely around the core theme or key information of the original input information, highlighting the key points and avoiding deviating from the theme or adding too much irrelevant content. For example, if the original text is "The application of artificial intelligence in the medical field", after selecting "more focused", the expanded content will mainly focus on the applications of artificial intelligence in specific medical fields such as medical diagnosis, disease prediction, surgical assistance, drug research and development, etc., rather than involving too much the applications of artificial intelligence in other fields such as education and transportation, nor elaborating on irrelevant content such as the basic concepts of artificial intelligence, making the theme of the expanded text more prominent and the content more concentrated.

[0076] Figure 8 FIG. is a schematic diagram of a process for generating content parameter data and structure parameter data provided by an embodiment of the present disclosure. The following will further introduce the above steps with reference to Figure 8 the above, and refer to Figure 8As shown, exemplarily, after the terminal device loads the original input information, it determines the content in the first operation area and the second operation area of the first operation panel according to the content of the original input information and the task type of document processing (such as article expansion). For example, as shown in the figure, in the rectangular first operation area, there are a first area boundary and a second area boundary set vertically corresponding, and a third area boundary and a fourth area boundary set horizontally corresponding. Among them, the first area boundary and the second area boundary correspond to the content expansion degree dimension (the first content dimension). On both sides of the first area boundary and the second area boundary, the corresponding prompt messages "concise" and "expanded" are respectively displayed. The closer the indication mark is to the "concise" side, the more concise and refined the content of the output document is. On the contrary, the closer it is to the "expanded" side, the more expanded and rich the content of the output document is. Similarly, the third area boundary and the fourth area boundary correspond to the professionalism dimension (the second content dimension). On both sides of the third area boundary and the fourth area boundary, the corresponding prompt messages "professional" and "causal" are respectively displayed. The closer the indication mark is to the "professional" side, the more professional the content of the output document is. On the contrary, the closer it is to the "causal" side, the more colloquial the content of the output document is. On the other hand, in the second operation area, the alternative document structure parameters "structured" and "focused" are displayed. After that, in response to the first operation and the second operation of the user, an indication mark is generated at the P1 point position. The horizontal and vertical coordinates of the P1 point are the first content parameter (x) and the second content parameter (y) respectively. And the document structure parameter "structured" is selected as the target document structure parameter, so as to obtain the content parameter data [x, y] and the structure parameter data "structured".

[0077] In this embodiment, by obtaining the semantic information of the original input information, determining the alternative document structure parameters based on the semantic information, and then generating the structure parameter data based on the alternative document structure parameters, the structure parameter data is matched with the semantic information of the original input information, achieving the effect of automatic recommendation of the structure parameter data, reducing the requirements for the user's operation experience, and improving the use efficiency and effect of the document generation model.

[0078] Step S205: Generate an output document according to the content parameter data, the structure parameter data, and the original input information.

[0079] Exemplarily, after the above steps to obtain the content parameter data, structure parameter data, and the original input information, in one possible implementation, directly input the above content parameter data, structure parameter data, and the original input information into the document generation model. The document generation model can directly process the above data and generate an output document that matches the above document content features and document structure features. Among them, the ability of the document generation model to process the above data is obtained during the previous model training process, and the specific implementation principle and process will not be elaborated here.

[0080] Further, exemplarily, the content parameter data includes at least one content parameter, and each content parameter characterizes the content features in a corresponding content dimension, such as Figure 9 As shown, the specific implementation of step S205 includes:

[0081] Step S2051: Generate corresponding document prompt words according to each content parameter;

[0082] Step S2052: Call the document generation model to process each document prompt word and the original input information to generate an output document.

[0083] Exemplarily, in another possible implementation, in the content parameter data, there are respectively content parameters corresponding to multiple content dimensions. For example, the first content parameter characterizing the document content features in the first content dimension, the second content parameter characterizing the document content features in the second content dimension. Optionally, in the structure parameter data, there are also respectively multiple target document structure parameters. The above content parameters and target document structure parameters are all data represented in the form of numerical values, arrays, and matrices. The terminal device uses a pre-configured prompt word engineering module to convert the content parameter data and structure parameter data into corresponding document prompt words respectively, and then inputs the document prompt words and the original input information into the document generation model for processing, and uses the document prompt words corresponding to the content parameter data and structure parameter data as guiding information to control the generation of the document content, so as to achieve the purpose of converting the original input information into an output document. Through the conversion of the prompt word engineering module, the obtained document prompt words can describe the user's intention more accurately, improve the accuracy of the finally generated output document, and at the same time reduce the training difficulty of the document generation model.

[0084] Further, optionally, before step S205, in this embodiment, it further includes:

[0085] Step S206: Obtain a target document template, and the target document template characterizes the layout style of the output document.

[0086] Exemplarily, the layout style refers to information on how the output document arranges the document content and the presentation form of the document content. For example, the interspersed arrangement of "image + chart + text" is a layout style, and the arrangement of "mind map + text" is another layout style. The document template is data used to describe the above layout styles. Among them, the target document template can be a preset fixed template or a dynamic template determined based on the original input information, that is, when the original input information is different, different target document templates are obtained, resulting in different layout styles of the generated output document. It can also be a dynamic template determined based on the document content characteristics and / or document structure characteristics, that is, when the content parameter data and structure parameter data obtained in the above steps are different, corresponding different target document templates will be obtained, thereby resulting in different layout styles of the generated output document.

[0087] Correspondingly, the implementation method of step S205 includes: step S205A: Generate an output document based on the content parameter data, structure parameter data, target document template, and original input information.

[0088] In the steps of this embodiment, by obtaining the target document template, on the basis of step S205, the layout style of the generated output document is further controlled through the target document template. This can further improve the document accuracy and document quality of the generated output document.

[0089] Of course, in another possible implementation, it can be Figure 2 Based on the implementation method of step S103 in the shown embodiment, combined with the target document template, an output document is generated, that is, an output document is generated based on the target position, target document template, and original input information. In this implementation method, the layout style of the output document is controlled based on the target document template, which can also further improve the document accuracy and document quality of the generated output document.

[0090] Further, in a possible implementation, the first operation area includes four sub-operation areas, and the content feature type is a composite feature type jointly determined by the document content features in the first content dimension and the document content features in the second content dimension; among them, the first content dimension is used to indicate the content professionalism of the output document; the second content dimension is used to indicate the content expansion degree of the output document. In this case, exemplarily, the specific implementation method of step S206 includes:

[0091] When the target content feature type is the first composite feature type, a first target document template is obtained, where the first composite feature type corresponds to the first content feature in the first content dimension and the first content feature in the second intention dimension, the first content feature is less than the first threshold, the second content feature is less than the second threshold, and the first target document template is used to generate an abstract card in the output document, and the abstract card is used to display a summary of the text paragraph generated based on the original input information;

[0092] When the target content feature type is the second composite feature type, a second target document template is obtained, where the second composite feature type corresponds to the third content feature in the first content dimension and the fourth content feature in the second intention dimension, the third content feature is greater than the first threshold, the fourth content feature is greater than the second threshold, and the second target document template is used to generate a mind map representing the logical structure of the original input information in the output document.

[0093] Exemplarily, Figure 10 FIG. is a schematic diagram of a process for determining a target document template provided by an embodiment of the present disclosure. The following will further introduce the above process in conjunction with Figure 10 and make a further introduction to the above process, such as Figure 10As shown, within the first operation area of the rectangle, there are a first area boundary and a second area boundary that are vertically corresponding, and a third area boundary and a fourth area boundary that are horizontally corresponding. Among them, the first area boundary and the second area boundary correspond to the content expansion degree dimension (the first content dimension). On both sides of the first area boundary and the second area boundary, the corresponding prompt messages "concise" and "expanded" are respectively displayed. The closer the indication mark is to the "concise" side, the more concise and refined the content of the output document is. On the contrary, the closer it is to the "expanded" side, the more expanded and rich the content of the output document is. Similarly, the third area boundary and the fourth area boundary correspond to the professionalism dimension (the second content dimension). On both sides of the third area boundary and the fourth area boundary, the corresponding prompt messages "professional" and "causal" are respectively displayed. The closer the indication mark is to the "professional" side, the more professional the content of the output document is. On the contrary, the closer it is to the "causal" side, the more colloquial the content of the output document is. Based on the preset first threshold and second threshold (shown as L1 and L2 in the figure), the first operation area is divided into four sub-operation areas, which respectively correspond to 4 types of composite feature types. The first threshold is, for example, half of the distance between the first area boundary and the second area boundary; the second threshold is, for example, half of the distance between the third area boundary and the fourth area boundary. When the target position P1 of the indication mark is within the sub-operation area D1, the target content feature type is the first composite feature type, which can be expressed as the "concise + causal" type. When the target content feature type is this type, the output document to be generated needs to meet the feature requirements of being concise and refined and easy to understand. In this case, the first target document template is used. The first target document template can generate an abstract card in the output document. The abstract card is used to display the summary of the text paragraphs generated based on the original input information. For example, after understanding the original input information, it is divided into several paragraphs according to the content semantics, and a content summary is made for each paragraph to generate a paragraph abstract, and the paragraph abstract is written into the abstract card, so as to meet the above-mentioned feature requirements of being concise and refined and easy to understand. When the target position P2 of the indication mark is within the sub-operation area D2, the target content feature type is the second composite feature type, which can be expressed as the "expanded + professional" type. When the target content feature type is this type, the output document to be generated needs to meet the feature requirements of rich content and high professionalism. In this case, the second target document template is used. The second target document template can generate a mind map representing the logical structure of the original input information in the output document, so as to meet the above-mentioned feature requirements of rich content and high professionalism.

[0094] In this embodiment, the implementation manner of step S202 is the same as that of step S102 in the embodiment Figure 2 shown in the present disclosure, and will not be elaborated here one by one.

[0095] An interactive document generation method corresponding to the above embodiments Figure 11 is a structural block diagram of an interactive document generation device provided by an embodiment of the present disclosure. The method introduced in the above embodiments can be executed by this interactive document generation device, which can be implemented in software and / or hardware, and can be integrated in an electronic device with certain data processing capabilities. Among them, the electronic device may include, but is not limited to, a mobile terminal with big data processing capabilities, and a fixed terminal with big data processing capabilities such as a desktop computer and a supercomputer.

[0096] For the sake of convenience of description, only parts related to the embodiments of the present disclosure are shown. Referring to Figure 11 , the interactive document generation device 3 includes:

[0097] A first interaction unit 31, configured to display original input information and a first operation panel, the first operation panel is configured to have a first operation area, and the first operation area is used to display an indication identifier, and the position of the indication identifier in the first operation area maps document content features under at least one content dimension;

[0098] A second interaction unit 32, configured to display an indication identifier at a target position in the first operation area in response to a first operation on the first operation area;

[0099] A processing unit 33, configured to generate an output document corresponding to the original input information according to the target position, and the document content of the output document matches the target document content features corresponding to the target position,

[0100] According to one or more embodiments of the present disclosure, the processing unit 33 is specifically configured to: obtain content parameter data representing the target document content features according to the target position; generate an output document based on the content parameter data and the original input information.

[0101] According to one or more embodiments of the present disclosure, the operation area at least includes a relatively arranged first area boundary and a second area boundary. When the processing unit 33 obtains content parameter data representing the target document content features according to the target position, it is specifically configured to: obtain a first content parameter according to the distance between the target position and the first area boundary or the second area boundary, and the first content parameter represents the document content features in the first content dimension; obtain content parameter data according to the first content parameter.

[0102] According to one or more embodiments of the present disclosure, the operation area further includes a relatively arranged third area boundary and a fourth area boundary. The processing unit 33 is further configured to: obtain a second content parameter according to the distance between the target position and the third area boundary or the fourth area boundary, where the second content parameter characterizes the document content feature in the second content dimension; when the processing unit 33 obtains the content parameter data according to the first content parameter, it is specifically configured to: obtain the content parameter data according to the first content parameter and the second content parameter.

[0103] According to one or more embodiments of the present disclosure, the first operation panel is configured to have a second operation area for determining the document structure feature of the output document. The processing unit 33 is further configured to: obtain the structure parameter data characterizing the target document structure feature in response to a second operation on the second operation area; when the processing unit 33 generates the output document based on the content parameter data and the original input information, it is specifically configured to: generate the output document according to the content parameter data, the structure parameter data, and the original input information.

[0104] According to one or more embodiments of the present disclosure, the processing unit 33 is further configured to: obtain the semantic information of the original input information; display at least two alternative document structure parameters characterizing the document structure feature in the second operation area according to the semantic information; when the processing unit 33 obtains the structure parameter data characterizing the target document structure feature in response to a second operation on the second operation area, it is specifically configured to: determine the target document structure parameter in response to the second operation on the alternative document structure parameter, and generate the structure parameter data based on the target document structure parameter.

[0105] According to one or more embodiments of the present disclosure, the content parameter data includes at least one content parameter, and each content parameter characterizes the content feature in a corresponding content dimension; when the processing unit 33 generates the output document based on the content parameter data and the original input information, it is specifically configured to: generate corresponding document prompt words according to each content parameter; call a document generation model to process each document prompt word and the original input information to generate the output document.

[0106] According to one or more embodiments of the present disclosure, the first operation area includes at least two sub-operation areas, and the sub-operation areas correspond to the content feature types one by one. The processing unit 33 is further configured to: determine the target sub-operation area where the target position is located; obtain the corresponding target content feature type according to the target sub-operation area; obtain the target document template according to the target content feature type, where the target document template characterizes the layout style of the output document; when the processing unit 33 generates the output document corresponding to the original input information according to the target position, it is specifically configured to: generate the output document according to the target position, the target document template, and the original input information.

[0107] According to one or more embodiments of the present disclosure, the first operation area includes four sub-operation areas, and the content feature type is a composite feature type jointly determined by the document content features in the first content dimension and the document content features in the second content dimension; wherein, the first content dimension is used to indicate the content professionalism of the output document; the second content dimension is used to indicate the content expansion degree of the output document.

[0108] According to one or more embodiments of the present disclosure, when the processing unit 33 obtains the target document template according to the target content feature type, it is specifically configured to: when the target content feature type is the first composite feature type, obtain the first target document template, wherein the first composite feature type corresponds to the first content feature in the first content dimension and the first content feature in the second intention dimension, the first content feature is less than the first threshold, the second content feature is less than the second threshold, and the first target document template is used to generate a summary card in the output document, and the summary card is used to display a summary of the text paragraph generated based on the original input information; when the target content feature type is the second composite feature type, obtain the second target document template, wherein the second composite feature type corresponds to the third content feature in the first content dimension and the fourth content feature in the second intention dimension, the third content feature is greater than the first threshold, the fourth content feature is greater than the second threshold, and the second target document template is used to generate a mind map representing the logical structure of the original input information in the output document.

[0109] According to one or more embodiments of the present disclosure, before displaying the original input information and the first operation panel, the first interaction unit 31 is further configured to: in response to the first trigger operation, select the original input information in the interaction interface, and the original input information includes at least one of text, picture, and video; in response to the second trigger operation, determine the recommended content dimension based on the content of the original input information, and configure the mapping between the operation area of the first operation panel and the recommended content dimension.

[0110] Wherein, the first interaction unit 31, the second interaction unit 32, and the processing unit 33 are connected in sequence. The interactive document generation device 3 provided in this embodiment can execute the technical solutions of the above method embodiments, and its implementation principles and technical effects are similar, which will not be elaborated here in this embodiment.

[0111] Figure 12 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure, as Figure 12 shown, the electronic device 4 includes:

[0112] a processor 41, and a memory 42 communicatively connected to the processor 41;

[0113] The memory 42 stores computer-executable instructions;

[0114] The processor 41 executes computer-executable instructions stored in the memory 42 to implement the interactive document generation method in the embodiments as Figure 2 - Figure 10 shown in the embodiments.

[0115] Optionally, the processor 41 and the memory 42 are connected through a bus 43.

[0116] For related descriptions, reference may be made to Figure 2 - Figure 10 the relevant descriptions and effects corresponding to the steps in the corresponding embodiments for understanding, and details are not elaborated here.

[0117] Embodiments of the present disclosure provide a computer-readable storage medium storing computer-executable instructions, which are used to implement the interactive document generation method provided in any one of the embodiments corresponding to the present disclosure when executed by a processor. Figure 2 - Figure 10 Embodiments of the present disclosure provide a computer program product including a computer program, which implements the interactive document generation method provided in any one of the embodiments corresponding to the present disclosure when executed by a processor.

[0118] Embodiments of the present disclosure provide an electronic device for implementing the above embodiments. Figure 2 - Figure 10 Reference is made to

[0119] which shows a schematic structural diagram of an electronic device 900 suitable for implementing the embodiments of the present disclosure. The electronic device 900 may be a terminal device or a server. Among them, the terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable media players (PMPs), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0120] As shown in Figure 13 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure. Figure 13

[0121] Figure 13 ​​As shown, the electronic device 900 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 901, which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 902 or the program loaded from the storage device 908 into the random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The processing device 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The input / output (I / O) interface 905 is also connected to the bus 904.

[0122] Generally, the following devices may be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 may allow the electronic device 900 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 13 an electronic device 900 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0123] Specifically, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0124] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0125] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately without being assembled into the electronic device.

[0126] The above-mentioned computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to execute the method shown in the above embodiment.

[0127] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0129] The units or modules described in the embodiments of the present disclosure may be implemented in software or in hardware. Among them, the name of the unit or module does not constitute a limitation on the unit itself in some cases.

[0130] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, by way of non-limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0131] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may 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 disk, 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 a first aspect, according to one or more embodiments of the present disclosure, there is provided an interactive document generation method, including:

[0133] Displaying original input information and a first operation panel, the first operation panel being configured to have a first operation area for displaying an indication identifier, the position of the indication identifier within the first operation area mapping document content features under at least one content dimension; in response to a first operation on the first operation area, displaying an indication identifier at a target position within the first operation area, and generating an output document corresponding to the original input information according to the target position, the document content of the output document matching the target document content features corresponding to the target position.

[0134] According to one or more embodiments of the present disclosure, the generating an output document corresponding to the original input information according to the target position includes: obtaining content parameter data characterizing the target document content features according to the target position; generating an output document based on the content parameter data and the original input information.

[0135] According to one or more embodiments of the present disclosure, the operation area at least includes relatively arranged first and second area boundaries, and the obtaining content parameter data characterizing the target document content features according to the target position includes: obtaining a first content parameter according to the distance between the target position and the first area boundary or the second area boundary, the first content parameter characterizing document content features in a first content dimension; obtaining content parameter data according to the first content parameter.

[0136] According to one or more embodiments of the present disclosure, the operation area further includes a relatively arranged third area boundary and a fourth area boundary, and the method further includes: obtaining a second content parameter according to the distance between the target position and the third area boundary or the fourth area boundary, where the second content parameter characterizes the document content feature in the second content dimension; the obtaining content parameter data according to the first content parameter includes: obtaining content parameter data according to the first content parameter and the second content parameter.

[0137] According to one or more embodiments of the present disclosure, the first operation panel is configured to have a second operation area for determining the document structure feature of the output document; the method further includes: obtaining structure parameter data characterizing the target document structure feature in response to a second operation on the second operation area; the generating an output document based on the content parameter data and the original input information includes: generating an output document according to the content parameter data, the structure parameter data, and the original input information.

[0138] According to one or more embodiments of the present disclosure, the method further includes: obtaining the semantic information of the original input information; displaying at least two alternative document structure parameters characterizing the document structure feature in the second operation area according to the semantic information; the obtaining structure parameter data characterizing the target document structure feature in response to a second operation on the second operation area includes: determining the target document structure parameter in response to a second operation on the alternative document structure parameter, and generating structure parameter data based on the target document structure parameter.

[0139] According to one or more embodiments of the present disclosure, the content parameter data includes at least one content parameter, and each content parameter characterizes the content feature in a corresponding content dimension; the generating an output document based on the content parameter data and the original input information includes: generating corresponding document prompt words according to each content parameter; calling a document generation model to process each document prompt word and the original input information to generate an output document.

[0140] According to one or more embodiments of the present disclosure, the first operation area includes at least two sub-operation areas, and the sub-operation areas correspond to content feature types one by one; the method further includes: determining the target sub-operation area where the target position is located; obtaining the corresponding target content feature type according to the target sub-operation area; obtaining a target document template according to the target content feature type, where the target document template characterizes the layout style of the output document; the generating an output document corresponding to the original input information according to the target position includes: generating an output document according to the target position, the target document template, and the original input information.

[0141] According to one or more embodiments of the present disclosure, the first operation area includes four sub-operation areas, and the content feature type is a composite feature type jointly determined by the document content features in the first content dimension and the document content features in the second content dimension; wherein, the first content dimension is used to indicate the content professionalism of the output document; the second content dimension is used to indicate the content expansion degree of the output document.

[0142] According to one or more embodiments of the present disclosure, obtaining a target document template according to the target content feature type includes: when the target content feature type is the first composite feature type, obtaining a first target document template, wherein the first composite feature type corresponds to the first content feature in the first content dimension and the first content feature in the second intention dimension, the first content feature is less than a first threshold, the second content feature is less than a second threshold, and the first target document template is used to generate an abstract card in the output document, and the abstract card is used to display a summary of the text paragraph generated based on the original input information; when the target content feature type is the second composite feature type, obtaining a second target document template, wherein the second composite feature type corresponds to the third content feature in the first content dimension and the fourth content feature in the second intention dimension, the third content feature is greater than the first threshold, the fourth content feature is greater than the second threshold, and the second target document template is used to generate a mind map representing the logical structure of the original input information in the output document.

[0143] According to one or more embodiments of the present disclosure, before displaying the original input information and the first operation panel, it further includes: in response to a first trigger operation, selecting the original input information in the interaction interface, where the original input information includes at least one of text, picture, and video; in response to a second trigger operation, determining a recommended content dimension based on the content of the original input information, and configuring a mapping between the operation area of the first operation panel and the recommended content dimension.

[0144] In a second aspect, according to one or more embodiments of the present disclosure, an interactive document generation device is provided, including:

[0145] A first interaction unit, configured to display the original input information and a first operation panel, the first operation panel is configured to have a first operation area, and the first operation area is used to display an indication identifier, and the position of the indication identifier in the first operation area maps the document content features in at least one content dimension;

[0146] A second interaction unit, configured to display an indication identifier at a target position in the first operation area in response to a first operation on the first operation area;

[0147] A processing unit, configured to generate an output document corresponding to the original input information according to the target position, where the document content of the output document matches the target document content features corresponding to the target position.

[0148] According to one or more embodiments of the present disclosure, the processing unit is specifically configured to: obtain content parameter data characterizing the target document content features according to the target position; and generate an output document based on the content parameter data and the original input information.

[0149] According to one or more embodiments of the present disclosure, the operation area at least includes a relatively arranged first area boundary and a second area boundary. When the processing unit obtains content parameter data characterizing the target document content features according to the target position, it is specifically configured to: obtain a first content parameter according to the distance between the target position and the first area boundary or the second area boundary, where the first content parameter characterizes the document content features in a first content dimension; and obtain content parameter data according to the first content parameter.

[0150] According to one or more embodiments of the present disclosure, the operation area further includes a relatively arranged third area boundary and a fourth area boundary. The processing unit is further configured to: obtain a second content parameter according to the distance between the target position and the third area boundary or the fourth area boundary, where the second content parameter characterizes the document content features in a second content dimension; when the processing unit obtains content parameter data according to the first content parameter, it is specifically configured to: obtain content parameter data according to the first content parameter and the second content parameter.

[0151] According to one or more embodiments of the present disclosure, the first operation panel is configured to have a second operation area, and the second operation area is used to determine the document structure features of the output document; the processing unit is further configured to: in response to a second operation on the second operation area, obtain structure parameter data characterizing the target document structure features; when the processing unit 33 generates an output document based on the content parameter data and the original input information, it is specifically configured to: generate an output document based on the content parameter data, the structure parameter data, and the original input information.

[0152] According to one or more embodiments of the present disclosure, the processing unit is further configured to: obtain semantic information of the original input information; display at least two alternative document structure parameters characterizing document structure features in the second operation area according to the semantic information; when the processing unit obtains structure parameter data characterizing the target document structure features in response to a second operation on the second operation area, it is specifically configured to: determine a target document structure parameter in response to the second operation on the alternative document structure parameters, and generate structure parameter data based on the target document structure parameter.

[0153] According to one or more embodiments of the present disclosure, the content parameter data includes at least one content parameter, and each content parameter characterizes content features in a corresponding content dimension; when the processing unit generates an output document based on the content parameter data and the original input information, it is specifically configured to: generate corresponding document prompt words according to each content parameter; call a document generation model to process each document prompt word and the original input information to generate an output document.

[0154] According to one or more embodiments of the present disclosure, the first operation area includes at least two sub-operation areas, and the sub-operation areas correspond to content feature types one by one; the processing unit is further configured to: determine the target sub-operation area where the target position is located; obtain the corresponding target content feature type according to the target sub-operation area; obtain a target document template according to the target content feature type, and the target document template characterizes the layout style of the output document; when the processing unit generates an output document corresponding to the original input information according to the target position, it is specifically configured to: generate an output document according to the target position, the target document template, and the original input information.

[0155] According to one or more embodiments of the present disclosure, the first operation area includes four sub-operation areas, and the content feature type is a composite feature type jointly determined by document content features in a first content dimension and document content features in a second content dimension; wherein, the first content dimension is used to indicate the content professionalism of the output document; the second content dimension is used to indicate the content expansion degree of the output document.

[0156] According to one or more embodiments of the present disclosure, when obtaining a target document template according to the target content feature type, the processing unit is specifically configured to: when the target content feature type is a first composite feature type, obtain a first target document template, where the first composite feature type corresponds to a first content feature in a first content dimension and a first content feature in a second intention dimension, the first content feature is less than a first threshold, the second content feature is less than a second threshold, and the first target document template is used to generate an abstract card in an output document, and the abstract card is used to display a summary of a text paragraph generated based on original input information; when the target content feature type is a second composite feature type, obtain a second target document template, where the second composite feature type corresponds to a third content feature in a first content dimension and a fourth content feature in a second intention dimension, the third content feature is greater than the first threshold, the fourth content feature is greater than the second threshold, and the second target document template is used to generate a mind map representing the logical structure of the original input information in an output document.

[0157] According to one or more embodiments of the present disclosure, before displaying the original input information and the first operation panel, the first interaction unit is further configured to: in response to a first trigger operation, select the original input information in the interaction interface, where the original input information includes at least one of text, pictures, and videos; in response to a second trigger operation, determine a recommended content dimension based on the content of the original input information, and configure a mapping between an operation area of the first operation panel and the recommended content dimension.

[0158] In a third aspect, according to one or more embodiments of the present disclosure, an electronic device is provided, including: at least one processor and a memory;

[0159] The memory stores computer-executable instructions;

[0160] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the interactive document generation method as described in the first aspect and various possible designs of the first aspect above.

[0161] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, where computer-executable instructions are stored in the computer-readable storage medium, and when a processor executes the computer-executable instructions, the interactive document generation method as described in the first aspect and various possible designs of the first aspect above is implemented.

[0162] Fifth aspect, according to one or more embodiments of the present disclosure, there is provided a computer program product including a computer program which, when executed by a processor, implements the interactive document generation method as described in the first aspect above and various possible designs of the first aspect.

[0163] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0164] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0165] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. An interactive document generation method, characterized in that, Including: Displaying the original input information and a first operation panel, the first operation panel being configured to have a first operation area for displaying an indication identifier, the position of the indication identifier within the first operation area mapping the document content features under at least one content dimension; In response to a first operation on the first operation area, displaying an indication identifier at a target position within the first operation area, and generating an output document corresponding to the original input information according to the target position, the document content of the output document matching the target document content features corresponding to the target position.

2. The method according to claim 1, characterized in that The generating an output document corresponding to the original input information according to the target position includes: Obtaining content parameter data characterizing the target document content features according to the target position; Generating an output document based on the content parameter data and the original input information.

3. The method according to claim 2, characterized in that, The operation area at least includes relatively arranged first area boundaries and second area boundaries. The obtaining content parameter data characterizing the target document content features according to the target position includes: Obtaining a first content parameter according to the distance between the target position and the first area boundary or the second area boundary, the first content parameter characterizing the document content features in a first content dimension; Obtaining content parameter data according to the first content parameter.

4. The method according to claim 3, characterized in that, The operation area further includes relatively arranged third area boundaries and fourth area boundaries. The method further includes: Obtaining a second content parameter according to the distance between the target position and the third area boundary or the fourth area boundary, the second content parameter characterizing the document content features in a second content dimension; The obtaining content parameter data according to the first content parameter includes: Obtaining content parameter data according to the first content parameter and the second content parameter.

5. The method according to claim 2, wherein The first operation panel is configured to have a second operation area for determining the document structure features of the output document. The method further includes: In response to a second operation on the second operation area, obtaining structure parameter data characterizing the target document structure features; The generating an output document based on the content parameter data and the original input information includes: Generating an output document according to the content parameter data, the structure parameter data and the original input information.

6. The method according to claim 5, wherein The method further includes: Obtaining the semantic information of the original input information; Displaying at least two alternative document structure parameters characterizing the document structure features within the second operation area according to the semantic information; The obtaining structure parameter data characterizing the target document structure features in response to a second operation on the second operation area includes: In response to a second operation on the alternative document structure parameters, determining the target document structure parameters and generating structure parameter data based on the target document structure parameters.

7. The method according to claim 2, wherein The content parameter data includes at least one content parameter, and each content parameter characterizes the content features in a corresponding content dimension; The generating an output document based on the content parameter data and the original input information includes: Generate corresponding document prompts according to each of the content parameters; Call a document generation model to process each of the document prompts and the original input information to generate an output document.

8. The method according to claim 1, wherein The first operation area includes at least two sub-operation areas, and the sub-operation areas correspond one-to-one with the content feature types; the method further includes: Determine the target sub-operation area where the target position is located; Obtain a corresponding target content feature type according to the target sub-operation area; Obtain a target document template according to the target content feature type, and the target document template characterizes the layout style of the output document; The generating the output document corresponding to the original input information according to the target position includes: Generate an output document according to the target position, the target document template and the original input information.

9. The method according to claim 8, wherein The first operation area includes four sub-operation areas, The content feature type is a composite feature type jointly determined by the document content features in the first content dimension and the document content features in the second content dimension; Wherein, the first content dimension is used to indicate the content professionalism of the output document; the second content dimension is used to indicate the content expansion degree of the output document.

10. The method according to claim 9, characterized in that, The obtaining the target document template according to the target content feature type includes: When the target content feature type is the first composite feature type, obtain a first target document template, wherein the first composite feature type corresponds to the first content feature in the first content dimension and the first content feature in the second intent dimension, the first content feature is less than a first threshold, the second content feature is less than a second threshold, and the first target document template is used to generate an abstract card in the output document, and the abstract card is used to display a summary of the text paragraphs generated based on the original input information; When the target content feature type is the second composite feature type, obtain a second target document template, wherein the second composite feature type corresponds to the third content feature in the first content dimension and the fourth content feature in the second intent dimension, the third content feature is greater than the first threshold, the fourth content feature is greater than the second threshold, and the second target document template is used to generate a mind map representing the logical structure of the original input information in the output document.

11. The method according to claim 1, characterized in that, Before displaying the original input information and the first operation panel, it further includes: In response to a first trigger operation, select the original input information in the interaction interface, and the original input information includes at least one of text, picture, and video; In response to a second trigger operation, determine a recommended content dimension based on the content of the original input information, and configure the mapping between the operation area of the first operation panel and the recommended content dimension.

12. An interactive document generation device, characterized in that, Includes: A first interaction unit, configured to display the original input information and a first operation panel, the first operation panel is configured to have a first operation area, and the first operation area is used to display an indication identifier, and the position of the indication identifier in the first operation area maps the document content features in at least one content dimension; A second interaction unit, configured to display an indication mark at a target position within the first operation area in response to a first operation on the first operation area; A processing unit, configured to generate an output document corresponding to the original input information according to the target position, where the document content of the output document matches the target document content feature corresponding to the target position.

13. An electronic device, characterized in that, Comprising: A processor and a memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the interactive document generation method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the interactive document generation method according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, the interactive document generation method according to any one of claims 1 to 11 is implemented.

Images