Information generation method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses an information generation method and device, a storage medium and electronic equipment, and the method comprises the steps: obtaining at least one piece of demonstration information of a target demonstration activity, employing a first artificial intelligence content generation model based on the at least one piece of demonstration information, and obtaining demonstration structured information, and generating activity display information for the target demonstration activity by adopting a second artificial intelligence content generation model based on the demonstration structured information. By adopting the method, the additional remark content which is generated in the demonstration activity and belongs to the initial demonstration file can be integrated with the initial demonstration file, so that the demonstration structured information with comprehensive content is obtained, and then the demonstration structured information with the comprehensive content is converted into the activity display information displayed to the user; therefore, the user who participates in the demonstration activity does not need to specially record the activity content, and the efficiency of recording the activity content is improved while the complete activity content is ensured to be recorded.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information generation method, device, storage medium and electronic device. Background Art

[0002] With the development of information technology, more and more smart devices have rich presentation functions. Therefore, smart devices are widely used in multi-person meetings or multi-person activities. In addition to display and recording functions, some smart devices also have writing and drawing functions, which support participants to write and draw content in electronic presentation files during the presentation, greatly increasing the interactivity between users and electronic presentation files. Summary of the invention

[0003] The embodiments of the present application provide an information generation method, device, storage medium and electronic device, and the technical solution is as follows:

[0004] In a first aspect, an embodiment of the present application provides an information generation method, the method comprising:

[0005] Obtain at least one kind of demonstration information of a target demonstration activity;

[0006] Based on the at least one demonstration information, a first artificial intelligence content generation model is used to obtain demonstration structured information;

[0007] Based on the demonstration structured information, a second artificial intelligence content generation model is adopted to generate activity display information for the target demonstration activity.

[0008] In a feasible implementation manner, the obtaining demonstration structured information by using a first artificial intelligence content generation model based on the at least one demonstration information includes:

[0009] Performing model prompt information generation processing based on the at least one demonstration information to obtain content integration prompt information;

[0010] The content integration prompt information is input into the first artificial intelligence content generation model to obtain demonstration structured information.

[0011] In a feasible implementation manner, the generating process of the model prompt information based on the at least one demonstration information to obtain the content integration prompt information includes:

[0012] generating content extraction prompt information for a demonstration note object in the at least one demonstration information;

[0013] Generate structure integration prompt information for the presentation note object and the initial presentation file object in the at least one presentation information;

[0014] Content integration prompt information is determined based on the content extraction prompt information and the structure integration prompt information.

[0015] In a feasible implementation manner, the generating activity display information for the target demonstration activity by using a second artificial intelligence content generation model based on the demonstration structured information includes:

[0016] Performing model prompt information generation processing based on the demonstration structured information to obtain information conversion prompt information;

[0017] The information conversion prompt information is input into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity.

[0018] In a feasible implementation manner, the step of generating model prompt information based on the demonstration structured information to obtain information conversion prompt information includes:

[0019] Determine a specified display form type set corresponding to the target demonstration activity;

[0020] Generate information conversion prompt information based on the specified display form type set and the demonstration structured information.

[0021] In a feasible implementation manner, determining a specified display form type set corresponding to the target demonstration activity includes:

[0022] Obtaining a display type mapping relationship between a plurality of preset reference demonstration activity types and reference display form types corresponding to the reference demonstration activity types;

[0023] Determining a target demonstration activity type corresponding to the target demonstration activity based on the at least one demonstration information;

[0024] The target display form type corresponding to the target demonstration activity type is searched in the display type mapping relationship, and a designated display form type set corresponding to the target demonstration activity is determined based on the target display form type.

[0025] In a feasible implementation manner, determining the designated display form type set corresponding to the target demonstration activity based on the target display form type includes:

[0026] Determine the priority level corresponding to the target display format type;

[0027] A designated presentation format type set corresponding to the target demonstration activity is generated based on the priority level and the target presentation format type.

[0028] In a feasible implementation manner, determining a specified display form type set corresponding to the target demonstration activity includes:

[0029] The demonstration structured information is input into a display type recognition model to obtain a specified display form type set corresponding to the target demonstration activity, and the display type recognition model is trained by display form type labels corresponding to the labeled demonstration structured information.

[0030] In a feasible implementation manner, after the second artificial intelligence content generation model is used based on the demonstration structured information to generate the activity display information for the target demonstration activity, the method further includes:

[0031] The activity display information is sent to at least one designated terminal.

[0032] In a feasible implementation manner, after sending the activity display information to at least one designated terminal, the method further includes:

[0033] Obtaining update information for the activity display information sent by the target designated terminal;

[0034] The activity display information is updated based on the update information to obtain target activity display information for the target demonstration activity;

[0035] The target activity display information is synchronized to the at least one designated terminal.

[0036] In a feasible implementation manner, the method further includes:

[0037] Acquire a basic artificial intelligence content generation model, and create an initial first artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0038] Acquire at least one kind of sample demonstration information in the sample demonstration activity, wherein the sample demonstration information at least includes sample demonstration picture information and sample demonstration voice information;

[0039] Based on the sample demonstration picture information and the sample demonstration voice information, at least one round of model training is performed on the initial first artificial intelligence content generation model to obtain a first artificial intelligence content generation model after model training.

[0040] In a feasible implementation manner, the method further includes:

[0041] Acquire a basic artificial intelligence content generation model, and create an initial second artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0042] Get the sample demonstration structured information corresponding to the sample demonstration activity;

[0043] Based on the sample demonstration structured information, at least one round of model training is performed on the initial second artificial intelligence content generation model to obtain a second artificial intelligence content generation model after model training.

[0044] In a second aspect, an embodiment of the present application provides an information generating device, the device comprising:

[0045] An information acquisition module, used to acquire at least one kind of demonstration information of a target demonstration activity;

[0046] A first processing module, configured to obtain presentation structured information by using a first artificial intelligence content generation model based on the at least one presentation information;

[0047] The second processing module is used to generate activity display information for the target demonstration activity by adopting a second artificial intelligence content generation model based on the demonstration structured information.

[0048] In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0049] In a fourth aspect, an embodiment of the present application provides an electronic device, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0050] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0051] In one or more embodiments of the present application, at least one demonstration information of the target demonstration activity is obtained, and then the first artificial intelligence content generation model can be used to obtain the demonstration structured information according to the at least one demonstration information, and then the second artificial intelligence content generation model can be used to obtain the activity display information for the above target demonstration activity according to the demonstration structured information. Using this method, the additional notes generated in the demonstration activity outside the initial demonstration file and the initial demonstration file can be integrated to obtain the comprehensive demonstration structured information, and then the comprehensive demonstration structured information is converted into the activity display information displayed to the user, so that the users participating in the demonstration activity do not need to record the activity content intentionally, while ensuring the complete recording of the activity content, the efficiency of recording the activity content is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 It is a flowchart of an information generation method provided in an embodiment of the present application;

[0054] Figure 2 This is a schematic diagram of a scenario for carrying out a target demonstration activity provided by an embodiment of the present application;

[0055] Figure 3 This is another schematic diagram of a scenario for carrying out a target demonstration activity provided by an embodiment of the present application;

[0056] Figure 4 It is a flowchart of another information generation method provided in an embodiment of the present application;

[0057] Figure 5 It is a structural schematic diagram of an information generating device provided in an embodiment of the present application;

[0058] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] In the description of the present application, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood in specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are an "or" relationship.

[0061] In the related art, smart devices are widely used in multi-person meetings or multi-person activities due to their rich presentation functions. During the presentation of a meeting or activity, the presenter can record, write, and draw content on the smart device. When the presenter adds content on the smart device, the participants can use methods such as taking photos, screenshots, and handwriting to record the content added by the presenter. Of course, the participants can also record the video of the entire activity. However, recording content by taking photos, screenshots, handwriting, and recording videos requires manual recording of the activity content, and even requires manual further improvement of the activity content based on these recorded contents after the activity is over, which takes up a lot of time of the activity recorder and affects the efficiency of recording the activity content.

[0062] The present application is described in detail below with reference to specific embodiments.

[0063] In one embodiment, Figure 1 As shown, a method for generating information is proposed, which can be realized by a computer program and can be run on an information generating device based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0064] Specifically, the information generating method includes:

[0065] S101: Acquire at least one kind of demonstration information of a target demonstration activity.

[0066] It is easy to understand that a target demonstration activity can refer to a purposeful discussion activity held offline or online. Whether it is a target demonstration activity held online or offline, it uses an electronic device with a demonstration function to display the demonstration file. The demonstration file can refer to the electronic file displayed in the process of carrying out the target demonstration activity. The types of electronic files can include but are not limited to documents, tables, slides, pictures, etc.

[0067] Demonstration information may refer to information of a certain type of demonstration used to display relevant information of the target demonstration activity during the process of carrying out the target demonstration activity. The demonstration type may include but is not limited to the image demonstration type, voice demonstration type, and other types. Image demonstration type information may refer to image information displayed with the aid of an electronic device. Voice demonstration type information may refer to voice information played with the aid of an electronic device, or may refer to voice information narrated manually.

[0068] Specifically, the demonstration information of the embodiments of the present application may include, but is not limited to, demonstration screen information, demonstration voice information and other information. Among them, the demonstration screen information may refer to the screen information displayed by the electronic device during the process of carrying out the target demonstration activity. The demonstration screen information may include a demonstration file with annotation traces, or a demonstration file without annotation traces. A demonstration file with annotation traces refers to a file obtained after an annotation operation is performed on the original demonstration file during the activity. A demonstration file with annotation traces may contain the original demonstration file and the marking information added to the original demonstration file. A demonstration file without annotation traces refers to the original demonstration file during the activity, and no annotation operation is performed on the original demonstration file during the entire activity. A demonstration file without annotation traces may contain the original demonstration file and does not contain any marking information.

[0069] The demonstration voice information may refer to the voice information of the activity personnel collected during the process of carrying out the target demonstration activity. The demonstration voice information may include the voice information of the activity speaker and the voice information of the non-activity speaker.

[0070] See also Figure 2 A schematic diagram of a scenario for carrying out a target demonstration activity is shown in FIG. Figure 2 As shown, the target demonstration activity is an offline demonstration activity, the demonstration screen information is obtained by recording the screen displayed on the smart device screen, and the demonstration voice information is obtained by recording the voice at the event site.

[0071] See also Figure 3 Another scenario diagram for carrying out target demonstration activities is shown in FIG. Figure 3As shown, the target demonstration activity is a demonstration activity held online, and the target demonstration activity is implemented with the help of a conference platform, and all participants in the target demonstration activity must participate in the activity through the conference platform. Among them, the conference platform can be a software, applet, web page or other tool with the function of holding online multi-person activities. In the target demonstration activity, there are main demonstration devices and slave demonstration devices, and the demonstration file is mainly initiated by the main demonstration device. The editing authority of the demonstration file can be only owned by the main demonstration device, or by the main demonstration device and some slave demonstration devices. When the main demonstration device or the slave demonstration device edits the demonstration file, the edited demonstration file can be synchronously displayed to all demonstration devices. In this scenario, the demonstration screen information can be the screen content displayed on the screen of the main demonstration device recorded with the help of the conference platform, and the demonstration screen information can be saved on the main demonstration device; the demonstration voice information can be the voice content output by all demonstration devices recorded with the help of the conference platform, and the demonstration voice information can be saved on the main demonstration device.

[0072] In some embodiments, when the method is applied to a scenario where the electronic device is a demonstration device, obtaining at least one demonstration information of the target demonstration activity may specifically include: obtaining demonstration screen information and / or demonstration voice information from the local storage of the electronic device, the demonstration screen information may be obtained by recording the screen on the electronic device, and the demonstration voice information may be obtained by recording the sound during the activity. Among them, the demonstration device may refer to a device that displays the demonstration file during the target demonstration activity, which may specifically be Figure 2 The smart device in the scene shown or Figure 3 The main demonstration device in the scene shown.

[0073] In some other embodiments, when the method is applied to a scenario where the electronic device is not a demonstration device, obtaining at least one demonstration information of the target demonstration activity may specifically include: the electronic device may obtain the demonstration screen information and / or demonstration voice information by receiving a data packet containing demonstration screen information and / or demonstration voice information sent by the demonstration device, and the demonstration screen information and demonstration voice information are collected by the demonstration device; or, the electronic device may download a data packet containing demonstration screen information and / or demonstration voice information from the cloud to obtain the demonstration screen information and / or demonstration voice information, and the data packet containing demonstration screen information and / or demonstration voice information stored in the cloud may be a data packet uploaded by the demonstration device, and the demonstration screen information and / or demonstration voice information are collected by the demonstration device. Among them, the demonstration device may specifically be Figure 2 The smart device in the scene shown or Figure 3 The main demonstration device in the scene shown.

[0074] S102: Using a first artificial intelligence content generation model based on at least one demonstration information to obtain demonstration structured information.

[0075] It is easy to understand that the first artificial intelligence content generation model can be a content generation model based on artificial intelligence generated content (Artificial Intelligence Generated Content, AIGC for short) technology. In a broad sense, AIGC technology can be regarded as an AI technology that has the ability to generate and create like humans, that is, generative AI, which can autonomously generate and create new texts, images, music, videos, 3D interactive content and other forms of content and data based on training data and generation algorithm models. The first artificial intelligence generation model used in the embodiment of the present application may be a model for a specific field implemented based on AIGC technology. The embodiment of the present application uses the first artificial intelligence content generation model in order to generate demonstration structured information. Therefore, the first artificial intelligence content generation model may be a model for the field of demonstration structured information generation implemented based on AIGC technology.

[0076] Demonstration structured information may refer to structured information obtained by organizing the original data according to a predefined structure after classifying, marking, and other processing of the original data. The original data may refer to the demonstration screen information and the demonstration voice information in the embodiment of the present application. Specifically, the original data may include a demonstration file with annotation traces in the demonstration screen information and the voice information of the activity participants in the demonstration voice information. The predefined structure may refer to a structure with different functional levels divided according to functions. For example, the predefined structure is generally divided into several description function areas of the same level. In each description function area of ​​the same level, at least one sub-function area may be interspersed, such as a point description sub-function area, a special mark sub-function area, and a note sub-function area.

[0077] In some embodiments, before executing this step, a first artificial intelligence content generation model can be trained to facilitate direct use when executing this step. Following the interpretation of demonstration information in S101, when at least one demonstration information obtained includes demonstration picture information and demonstration voice information, the implementation process of this step can be specifically: first, obtain a structure integration prompt template, extract the original demonstration file and additional note information from the demonstration picture information and the demonstration voice information, then add the original demonstration file and additional note information to the structure integration prompt template to obtain the structure integration prompt information, and finally, input the structure integration prompt information into the pre-trained first artificial intelligence content generation model to obtain the demonstration structured information output by the first artificial intelligence content generation model. Among them, the additional note information refers to the note information obtained by performing note operations on the original demonstration file, such as marking important data, adding new content, and expressing supplementary content in language.

[0078] Among them, the structural integration prompt template refers to a reusable prompt word template used to guide the model to perform content integration processing. The structural integration prompt information is used to guide the first artificial intelligence content generation model to generate demonstration structured information for the demonstration screen information and demonstration voice information of the target demonstration activity. Optionally, the structural integration prompt template can be generated using prompt templates such as PromptTemplates, ChatPrompt Templates, Example Selectors, OutputParsers, etc.

[0079] S103: Generate activity display information for the target demonstration activity using a second artificial intelligence content generation model based on the demonstration structured information.

[0080] It is easy to understand that the second artificial intelligence content generation model can be another content generation model based on AIGC technology. The second artificial intelligence content generation model used in the embodiment of the present application can be a model for the field of activity display information generation based on AIGC technology. The second artificial intelligence content generation model and the first artificial intelligence content generation model are models applied to different content generation fields.

[0081] Activity display information may refer to display content with one or more display form types. Display form types may include but are not limited to text form, mind map form, flow chart form, statistical table form and composite forms obtained by combining these forms. The display content in text form may be a content summary for the target demonstration activity, which may include at least one of the following contents: basic information, purpose, content overview, discussion results, follow-up plans, etc. The display content in the form of a mind map may be the content of the relationship between ideas, concepts, and structures involved in the target demonstration activity drawn using different graphics such as arrows, shapes, and frame lines. The display content in the form of a flow chart may be multiple steps for executing a certain transaction involved in the target demonstration activity. The display content in the form of a statistical table may be a statistical table of certain statistical data involved in the target demonstration activity.

[0082] In some embodiments, before executing this step, a second artificial intelligence content generation model can be trained to facilitate direct use when executing this step. The implementation process of this step can be specifically: first, obtain an activity display prompt template, then add the demonstration structured information to the activity display prompt template to obtain activity display prompt information, and finally, input the activity display prompt information into the pre-trained second artificial intelligence content generation model to obtain the activity display information output by the second artificial intelligence content generation model.

[0083] The activity display prompt template refers to a reusable prompt word template, which is a prompt word template used to guide the second artificial intelligence content to generate activity display information for different demonstration activities. The activity display prompt information is used to guide the second artificial intelligence content generation model to generate activity display information for demonstration structured information.

[0084] In one or more embodiments of the present application, at least one demonstration information of the target demonstration activity is obtained, and then the first artificial intelligence content generation model can be used to obtain the demonstration structured information according to the at least one demonstration information, and then the second artificial intelligence content generation model can be used to obtain the activity display information for the above target demonstration activity according to the demonstration structured information. Using this method, the additional notes generated in the demonstration activity outside the initial demonstration file and the initial demonstration file can be integrated to obtain the comprehensive demonstration structured information, and then the comprehensive demonstration structured information is converted into the activity display information displayed to the user, so that the users participating in the demonstration activity do not need to record the activity content intentionally, while ensuring the complete recording of the activity content, the efficiency of recording the activity content is improved.

[0085] See also Figure 4 , Figure 4 This is a flow chart of another embodiment of an information generation method proposed in this application. Specifically:

[0086] S401: Acquire at least one kind of demonstration information of a target demonstration activity.

[0087] Specifically, see Figure 1 The explanation of S101 in the illustrated embodiment will not be repeated here.

[0088] S402: Perform model prompt information generation processing based on at least one demonstration information to obtain content integration prompt information.

[0089] It is easy to understand that the content integration prompt information may refer to prompt information used to guide the model to generate presentation structured information for different presentation activities. Optionally, the content integration prompt information may be a composite prompt template, that is, it may be composed of multiple sub-prompt templates.

[0090] Optionally, when at least one demonstration information includes demonstration screen information and demonstration voice information, the step of performing model prompt information generation processing based on at least one demonstration information to obtain content integration prompt information is the step of performing model prompt information generation processing based on the demonstration screen information and the demonstration voice information to obtain content integration prompt information, which may specifically include the following steps:

[0091] A1: Generate content extraction prompt information for the demonstration note object in the demonstration screen information and the demonstration voice information;

[0092] Since the demonstration screen information not only includes the original demonstration file, but also includes the written annotation information obtained by annotation operations on the original demonstration file, such as marking important data and adding new content, and the demonstration voice information includes voice annotation information supplemented by language expression, the demonstration annotation object refers to the written annotation information and voice annotation information in the demonstration screen information.

[0093] Content extraction prompt information can be used to guide the model to extract presentation note objects, namely written note information and voice note information, based on the input.

[0094] Specifically, the first information feature corresponding to the remark information can be determined, and the first information feature may include color marking features, font marking features, font size marking features, writing features and other features; the second information feature of the voice remark information can be determined, and the second information feature may include sentences and / or words with supplementary or emphasis functions; further, the first information feature and the second information feature are added to the first preset prompt template to obtain content extraction prompt information.

[0095] A2: Generate structural integration prompt information for the demonstration note object and the initial demonstration file object in the demonstration screen information and the demonstration voice information;

[0096] The original presentation file object refers to the original presentation file in the presentation screen.

[0097] The structural integration prompt information can be used to guide the model to integrate the presentation note object and the initial presentation file object according to the predefined structure.

[0098] Specifically, the predefined structure corresponding to the target demonstration activity can be obtained, the first description information of the demonstration note object and the second description information of the initial demonstration file object can be obtained, and the predefined structure, the first description information, and the second description information can be written into the second preset prompt template to obtain the structural integration prompt information. The model integrates the aforementioned extracted demonstration note object and the initial demonstration file object according to the structural integration prompt information.

[0099] A3: Determine the content integration prompt information based on the content extraction prompt information and the structure integration prompt information.

[0100] Specifically, the first priority of the content extraction prompt information can be set, and the second priority of the structure integration prompt information can be set. The first priority is higher than the second priority. The content extraction prompt information carrying the first priority and the structure integration prompt information carrying the second priority are spliced ​​to obtain the content integration prompt information.

[0101] S403: Input the content integration prompt information into the first artificial intelligence content generation model to obtain demonstration structured information.

[0102] It should be noted that before executing this step, for example, before executing S401, training can be performed to obtain a first artificial intelligence content generation model, which can be specifically: obtaining a basic artificial intelligence content generation model, and creating an initial first artificial intelligence content generation model based on the basic artificial intelligence content generation model; obtaining at least one kind of sample demonstration information in the sample demonstration activity, the sample demonstration information at least including sample demonstration picture information and sample demonstration voice information; performing at least one round of model training on the initial first artificial intelligence content generation model based on the sample demonstration picture information and the sample demonstration voice information, to obtain the first artificial intelligence content generation model after model training.

[0103] Among them, the basic artificial intelligence content generation model may refer to a language model that has the ability to understand natural language and generate specified natural language text. The basic artificial intelligence content generation model can complete multiple types of text generation tasks. Optionally, the basic artificial intelligence content generation model may be a generative pre-trained transformer model (Chat Generative Pre-trained Transformer, ChatGPT), a Wenxinyiyan model, and the like. Creating an initial first artificial intelligence content generation model based on the basic artificial intelligence content generation model can be understood as adjusting the preset model parameters in the basic artificial intelligence content generation model until the model meets the function of completing a single type of content generation task, thereby obtaining the initial first artificial intelligence content generation model. The single type of content generation task that can be completed by the initial first artificial intelligence content generation model may be a task of generating demonstration structured information based on input.

[0104] Based on the sample demonstration picture information and the sample demonstration voice information, at least one round of model training is performed on the initial first artificial intelligence content generation model to obtain the first artificial intelligence content generation model after model training, which can be specifically:

[0105] First, sample data acquisition: acquiring a large amount of sample data, which is sample content integrated prompt information obtained by performing model prompt information generation processing based on sample demonstration screen information and sample demonstration voice information in each sample demonstration activity;

[0106] Second, sample data annotation: that is, based on the needs of the demonstration structured information generation scenario, an expert-side service is introduced to manually annotate the sample data (sample content integrated with prompt information) with corresponding sample labels. The sample labels include demonstration structured information labels for each sample data.

[0107] Third, model training: that is, inputting sample data into the initial first artificial intelligence content generation model for at least one round of model training to obtain predicted demonstration structured information, using the model loss function to determine the model loss value based on the predicted demonstration structured information and the sample data label (demonstration structured information label), and adjusting the model parameters of the initial first artificial intelligence content generation model based on the model loss value until the model training end conditions are met to obtain the first artificial intelligence content generation model. Optionally, the model end training conditions of the model may include, for example, the value of the loss function is less than or equal to a preset loss function threshold, the number of iterations reaches a preset number threshold, etc. The specific model end training conditions can be determined based on actual conditions and are not specifically limited here.

[0108] Specifically, according to the content integration prompt information described in step A3 in S402, the process of the first artificial intelligence content generation model outputting demonstration structured information according to the content integration prompt information can be: the first artificial intelligence content generation model can respond to the content extraction prompt information with a higher priority (first priority) to obtain a demonstration notes object; and then respond to the structure integration prompt information with a lower priority (second priority), that is, integrate the demonstration notes object and the initial demonstration file object according to a predefined structure to obtain demonstration structured information.

[0109] The predefined structure may refer to a structure with different functional levels divided according to functions. For example, the predefined structure is generally divided into several description function areas of the same level, and in each description function area of ​​the same level, there may be interspersed point description sub-function areas, special mark sub-function areas, and remark sub-function areas. The presentation structured information generated according to the predefined structure may generally include several description information of the same level, and in each description information of the same level, there may be interspersed at least one sub-description information, such as point description information, special mark description information, and remark description information.

[0110] S404: Perform model prompt information generation processing based on the demonstration structured information to obtain information conversion prompt information.

[0111] It is easy to understand that the information conversion prompt information may refer to prompt information used to guide the model to generate activity display information for different demonstration activities. Optionally, the information conversion prompt information may be generated based on a preset conversion prompt template.

[0112] Specifically, when the model prompt information generation process based on the demonstration structured information is performed to obtain the information conversion prompt information, it can be:

[0113] B1: Determine the set of specified display form types corresponding to the target demonstration activity;

[0114] In a feasible implementation, determining a set of designated display form types corresponding to a target demonstration activity may be: obtaining a display type mapping relationship between a plurality of preset reference demonstration activity types and reference display form types corresponding to the reference demonstration activity types; determining a target demonstration activity type corresponding to the target demonstration activity based on at least one demonstration information; searching for a target display form type corresponding to the target demonstration activity type in the display type mapping relationship, and determining a set of designated display form types corresponding to the target demonstration activity based on the target display form type.

[0115] The presentation type mapping relationship may be stored in a local memory of the electronic device, and thus the presentation type mapping relationship may be obtained from the local memory.

[0116] Reference demonstration activity types may include but are not limited to regular types, special types, strategic types, voting types, analysis types, recording types, training types, and other types. Regular demonstration activities may be delivered by the host, and participants may also throw out their own opinions, suggestions, and views, and answer and discuss them in order to determine the purpose of the activity, propose solutions, and make other decisions. Special demonstration activities may refer to activities centered on a specific topic or a specific problem. The purpose of the activity is to focus on discussing the specific topic or specific problem and propose feasible solutions. Strategy demonstration activities may refer to activities used to formulate strategic action plans. Voting demonstration activities may refer to activities that vote by voting. Analysis demonstration activities may refer to activities that focus on specific problems and scenarios, convene experts or experienced professionals for discussions, and analyze problems and predict developments. Recording demonstration activities may refer to activities that focus on recording, collecting, organizing, and editing. Training demonstration activities may refer to activities that improve professional knowledge and skills through training.

[0117] When at least one demonstration information includes demonstration picture information and demonstration voice information, the target demonstration activity type corresponding to the target demonstration activity is determined based on the at least one demonstration information, that is, the target demonstration activity type corresponding to the target demonstration activity is determined based on the demonstration picture information and the demonstration voice information. Specifically, keyword extraction can be performed on the text in the demonstration picture information and the demonstration voice information to determine the target demonstration activity type corresponding to the target demonstration activity.

[0118] Specifically, determining the designated display form type set corresponding to the target demonstration activity based on the target display form type can be understood as: determining the priority level corresponding to the target display form type; generating the designated display form type set corresponding to the target demonstration activity based on the priority level and the target display form type. Since a target demonstration activity type can correspond to at least two target display form types in the display type mapping relationship, the display content of some display form types can be generated on the basis of the display content of a certain display form type, that is, the display content of some display form types can be generated by using the display content of a certain display form type generated previously. In this scenario, the priority level corresponding to the target display form type can be determined, and then a plurality of target display form types can be stored in the designated display form type set in the form of target display form type plus priority level. This is convenient for the subsequent model to generate activity display information, and improve the efficiency of the model in generating display content of multiple display form types.

[0119] In another feasible implementation, determining the specified display form type set corresponding to the target demonstration activity can be: inputting the demonstration structured information into a display type recognition model to obtain the specified display form type set corresponding to the target demonstration activity, wherein the display type recognition model is trained by display form type labels corresponding to the labeled demonstration structured information.

[0120] Specifically, the model training process of the display type recognition model is explained as follows:

[0121] Model creation: Create an initial display type recognition model for display type recognition scenarios based on the machine learning model;

[0122] Sample data acquisition: Acquire a large amount of sample data. The sample data is sample demonstration structured information obtained through content integration processing based on sample demonstration picture information and sample demonstration voice.

[0123] Sample data labeling: Based on the needs of display type identification scenarios, expert services are introduced to manually label the sample data with corresponding sample labels. The sample labels include a set of labels for the display type of each sample data.

[0124] Model training process: input sample data into the initial display type recognition model for at least one round of model training to obtain a set of predicted display form types, use the model loss function to determine the model loss value based on the predicted display form type set and the sample data label (display form type set label), and adjust the model parameters of the initial display type recognition model based on the model loss value until the model training end conditions are met to obtain the display type recognition model. Optionally, the model end training conditions of the model may include, for example, the value of the loss function is less than or equal to a preset loss function threshold, the number of iterations reaches a preset number threshold, etc. The specific model end training conditions can be determined based on actual conditions and are not specifically limited here.

[0125] It should be noted that the machine learning models involved in the embodiments of the present application include but are not limited to the fitting of one or more machine learning models such as convolutional neural network (CNN) model, deep neural network (DNN) model, recurrent neural network (RNN) model, embedding model, gradient boosting decision tree (GBDT) model, logistic regression (LR) model, etc.

[0126] B2: Generate information conversion prompt information based on the specified display format type set and demonstration structured information.

[0127] Specifically, a preset information conversion prompt template can be obtained, and the specified display form type set and the demonstration structured information are respectively filled in the corresponding positions in the preset information conversion prompt template to obtain information conversion prompt information. Among them, the preset information conversion prompt template is a reusable prompt word template used to guide the model to perform information conversion processing. Therefore, by filling the corresponding information in the preset information conversion prompt template, that is, the specified display form type set and the demonstration structured information, the information conversion prompt information can be obtained.

[0128] S405: Input the information conversion prompt information into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity.

[0129] It should be noted that before executing this step, for example, before executing S401, a second artificial intelligence content generation model can be trained, which can be specifically: obtaining a basic artificial intelligence content generation model, and creating an initial second artificial intelligence content generation model based on the basic artificial intelligence content generation model; obtaining sample demonstration structured information corresponding to the sample demonstration activity; and performing at least one round of model training on the initial second artificial intelligence content generation model based on the sample demonstration structured information to obtain a second artificial intelligence content generation model after model training.

[0130] Creating an initial second artificial intelligence content generation model based on the basic artificial intelligence content generation model can be understood as adjusting the preset model parameters in the basic artificial intelligence content generation model until the model meets the function of completing a single type of content generation task, thereby obtaining the initial second artificial intelligence content generation model. The single type of content generation task that can be completed by the initial second artificial intelligence content generation model can be generating activity display information based on input.

[0131] Based on the sample demonstration structured information, at least one round of model training is performed on the initial second artificial intelligence content generation model to obtain the second artificial intelligence content generation model after model training. Specifically, it can be: since the sample data, that is, the sample demonstration structured information, has been obtained previously, the next step is to label the sample data, that is, to introduce the expert end service based on the needs of the activity display information generation scenario to manually label the sample data (sample demonstration structured information) with the corresponding sample label, and the sample label includes the activity display information label for each sample data; the next step is to perform model training, that is, to input the sample data into the initial second artificial intelligence content generation model for at least one round of model training to obtain the predicted activity display information, and to determine the model loss value based on the predicted activity display information and the sample data label (activity display information label), and to adjust the model parameters of the initial second artificial intelligence content generation model based on the model loss value until the model training end condition is met to obtain the second artificial intelligence content generation model. Optionally, the model training end condition of the model may include, for example, the value of the loss function is less than or equal to the preset loss function threshold, the number of iterations reaches the preset number threshold, etc. The specific model training end condition can be determined based on the actual situation, and is not specifically limited here.

[0132] Specifically, according to the specified display form type set described in step B1 in S404, the process of the second artificial intelligence content generation model outputting activity display information according to the information conversion prompt information can be: the second artificial intelligence content generation model can convert the demonstration structure information into display content of different display form types in order of priority levels in the specified display form type set, and finally the display contents of all display form types constitute the activity display information of the target demonstration activity.

[0133] refer to Figure 1 In the description of the display format type in the illustrated embodiment, the activity display information may include, but is not limited to, display content in text form, display content in the form of a mind map, display content in the form of a flowchart, display content in the form of a statistical table, and the like. Display content in text form may be a common display content, which mainly uses text to summarize the key information of the activity, such as the purpose of the activity, the problems to be solved, the solutions to the problems to be solved, and the like. Display content in the form of a mind map may be content that describes the relationship between the ideas, concepts, and structures involved in the activity. Display content in the form of a flowchart may be multiple steps involved in the execution of a certain transaction in the activity. Display content in the form of a statistical table may be the original statistical table extracted from the demonstration screen information, or may be a statistical table generated for certain statistical data involved in the demonstration screen information, or may be a statistical table generated for certain statistical data described in the voice in the demonstration voice information.

[0134] S406: Send the activity display information to at least one designated terminal.

[0135] Specifically, after the activity display information is generated, the activity display information can be sent to a designated terminal of at least one designated user. The designated user can be a participant who participates in the target demonstration activity. In this way, the participants do not need to record the activity content individually, and can directly obtain the activity record by receiving the activity display information. The method of sending the activity display information may include but is not limited to instant messaging software, email, etc.

[0136] S407: Acquire update information for the activity display information sent by the target designated terminal.

[0137] The target user corresponding to the target designated terminal may be a user with editing authority for the activity display information. Specifically, when the target user edits and updates the activity display information, the update information for the activity display information may be sent to the electronic device through the target designated terminal, so that the electronic device may obtain the update information. The update information may include the location of the updated content, the original content before the update, and the new content after the update.

[0138] S408: Update the activity display information based on the update information to obtain target activity display information for the target demonstration activity.

[0139] Specifically, after receiving the update information for the activity display information, the activity display information may be updated according to the update information, so as to obtain the target activity display information with the latest content.

[0140] S409: Synchronize the target activity display information to at least one designated terminal.

[0141] Specifically, after the activity display information is updated to obtain the target activity display information, the target activity display information with the latest content can be sent to the at least one designated terminal, so that the designated terminal can obtain the target activity display information with the latest content in a timely manner to ensure the accuracy and consistency of the activity display information obtained by each designated terminal.

[0142] In an embodiment of the present application, after obtaining the demonstration screen information and demonstration voice information of the target demonstration activity, by generating content integration prompt information, the content integration prompt information is then input into the first artificial intelligence content generation model to obtain demonstration structured information, and then information conversion prompt information is generated through the demonstration structured information, and the information conversion prompt information is input into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity, so as to improve the efficiency and accuracy of recording the activity content. In addition, the activity display information is also sent to the designated terminal, so that all participants can obtain the key information of the activity in a timely manner and ensure the consistency of information acquisition. The update information of the activity display information of the target designated terminal can also be received, so that the designated participants can modify the content in the activity display information at any time, ensuring the flexibility of recording the activity content.

[0143] The following will be combined Figure 5 , the information generating device provided in the embodiment of the present application is introduced in detail. It should be noted that, Figure 5 The information generating device shown is used to execute the present application Figure 1 and Figure 4 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 and Figure 4 The embodiment shown.

[0144] See also Figure 5 , which shows a schematic diagram of the structure of the information generating device of an embodiment of the present application. The information generating device 1 can be implemented as all or part of the device through software, hardware or a combination of both. According to some embodiments, the information generating device 1 includes an information acquisition module 11, a first processing module 12 and a second processing module 13, which are specifically used to:

[0145] An information acquisition module 11 is used to acquire at least one kind of demonstration information of a target demonstration activity;

[0146] A first processing module 12, configured to obtain presentation structured information by using a first artificial intelligence content generation model based on the at least one presentation information;

[0147] The second processing module 13 is used to generate activity display information for the target demonstration activity by adopting a second artificial intelligence content generation model based on the demonstration structured information.

[0148] Optionally, the first processing module 12 includes:

[0149] A first processing unit, configured to perform model prompt information generation processing based on the at least one demonstration information to obtain content integration prompt information;

[0150] The second processing unit is used to input the content integration prompt information into the first artificial intelligence content generation model to obtain demonstration structured information.

[0151] Optionally, the first processing unit is configured to:

[0152] generating content extraction prompt information for a demonstration note object in the at least one demonstration information;

[0153] Generate structure integration prompt information for the presentation note object and the initial presentation file object in the at least one presentation information;

[0154] Content integration prompt information is determined based on the content extraction prompt information and the structure integration prompt information.

[0155] Optionally, the second processing module 13 includes:

[0156] A third processing unit is used to perform model prompt information generation processing based on the demonstration structured information to obtain information conversion prompt information;

[0157] The fourth processing unit is used to input the information conversion prompt information into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity.

[0158] Optionally, the third processing unit includes:

[0159] A set generation subunit, used to determine a set of designated display form types corresponding to the target demonstration activity;

[0160] The information generating subunit is used to generate information conversion prompt information based on the specified display form type set and the demonstration structured information.

[0161] Optionally, the collection generation subunit includes:

[0162] A first generating subunit is used to obtain a display type mapping relationship between a plurality of preset reference demonstration activity types and reference display form types corresponding to the reference demonstration activity types;

[0163] A second generating subunit is used to determine a target demonstration activity type corresponding to the target demonstration activity based on the at least one demonstration information;

[0164] The third generating subunit is used to search the target display form type corresponding to the target demonstration activity type in the display type mapping relationship, and determine the specified display form type set corresponding to the target demonstration activity based on the target display form type.

[0165] Optionally, the third generation subunit is used to:

[0166] Determine the priority level corresponding to the target display format type;

[0167] A designated presentation format type set corresponding to the target demonstration activity is generated based on the priority level and the target presentation format type.

[0168] Optionally, a collection generation subunit is used to:

[0169] The demonstration structured information is input into a display type recognition model to obtain a specified display form type set corresponding to the target demonstration activity, and the display type recognition model is trained by display form type labels corresponding to the labeled demonstration structured information.

[0170] Optionally, the information generating device is further used for:

[0171] Sending the activity display information to at least one designated terminal;

[0172] Optionally, the information generating device is further used for:

[0173] Obtaining update information for the activity display information sent by the target designated terminal;

[0174] The activity display information is updated based on the update information to obtain target activity display information for the target demonstration activity;

[0175] The target activity display information is synchronized to the at least one designated terminal.

[0176] Optionally, the information generating device is further used for:

[0177] Acquire a basic artificial intelligence content generation model, and create an initial first artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0178] Acquire at least one kind of sample demonstration information in the sample demonstration activity, wherein the sample demonstration information at least includes sample demonstration picture information and sample demonstration voice information;

[0179] Based on the sample demonstration picture information and the sample demonstration voice information, at least one round of model training is performed on the initial first artificial intelligence content generation model to obtain a first artificial intelligence content generation model after model training.

[0180] Optionally, the information generating device is further used for:

[0181] Acquire a basic artificial intelligence content generation model, and create an initial second artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0182] Get the sample demonstration structured information corresponding to the sample demonstration activity;

[0183] Based on the sample demonstration structured information, the initial second artificial intelligence content generation model is trained for at least one round of model training to obtain a second artificial intelligence content generation model after model training.

[0184] It should be noted that when the information generating device provided in the above embodiment executes the information generating method, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the information generating device provided in the above embodiment and the information generating method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0185] The present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 1 and Figure 4 The information generation method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 and Figure 4 The specific description of the illustrated embodiment will not be repeated here.

[0186] The present application also provides a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor as described above. Figure 1 and Figure 4 The information generation method of the embodiment shown in the figure can be found in the specific execution process. Figure 1 and Figure 4 The specific description of the illustrated embodiment will not be repeated here.

[0187] Please refer to Figure 6 , is a structural block diagram of an electronic device provided in an embodiment of this specification. The electronic device in this specification may include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 may be connected via a bus 150.

[0188] The processor 110 may include one or more processing cores. The processor 110 uses various interfaces and lines to connect various parts of the entire terminal, and executes various functions and processes data of the terminal 100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Optionally, the processor 110 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 110 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 110, but may be implemented separately through a communication chip.

[0189] The memory 120 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, codes, code sets, or instruction sets.

[0190] The input device 130 is used to receive input commands or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone, or a touch device. The output device 140 is used to output commands or data, and the output device 140 includes but is not limited to a display device and a speaker. In the embodiment of this specification, the input device 130 may be a temperature sensor for obtaining the operating temperature of the terminal. The output device 140 may be a speaker for outputting audio signals.

[0191] In addition, those skilled in the art will appreciate that the structure of the terminal shown in the above drawings does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown, or combine certain components, or arrange the components differently. For example, the terminal also includes a radio frequency circuit, an input unit, a sensor, an audio circuit, a wireless fidelity (WIFI) module, a power supply, a Bluetooth module, and other components, which will not be described in detail here.

[0192] In the embodiments of this specification, the execution subject of each step may be the terminal described above. Optionally, the execution subject of each step is the operating system of the terminal. The operating system may be an Android system, an IOS system, or other operating systems, which is not limited in the embodiments of this specification.

[0193] exist Figure 6 In the electronic device, the processor 110 may be used to call the program of the information generation method stored in the memory 120, and the processor 110 may be used to call the program of the information generation method stored in the memory 120, and specifically perform the following operations:

[0194] Obtain at least one kind of demonstration information of a target demonstration activity;

[0195] Based on the at least one demonstration information, a first artificial intelligence content generation model is used to obtain demonstration structured information;

[0196] Based on the demonstration structured information, a second artificial intelligence content generation model is adopted to generate activity display information for the target demonstration activity.

[0197] In one embodiment, when the processor 110 performs the step of using the first artificial intelligence content generation model based on the at least one demonstration information to obtain the demonstration structured information, the processor 110 specifically performs the following operations:

[0198] Performing model prompt information generation processing based on the at least one demonstration information to obtain content integration prompt information;

[0199] The content integration prompt information is input into the first artificial intelligence content generation model to obtain demonstration structured information.

[0200] In one embodiment, when the processor 110 performs the model prompt information generation process based on the at least one demonstration information to obtain the content integration prompt information, the processor 110 specifically performs the following operations:

[0201] generating content extraction prompt information for a demonstration note object in the at least one demonstration information;

[0202] Generate structure integration prompt information for the presentation note object and the initial presentation file object in the at least one presentation information;

[0203] Content integration prompt information is determined based on the content extraction prompt information and the structure integration prompt information.

[0204] In one embodiment, when the processor 110 generates the activity display information for the target demonstration activity by using the second artificial intelligence content generation model based on the demonstration structured information, the processor 110 specifically performs the following operations:

[0205] Performing model prompt information generation processing based on the demonstration structured information to obtain information conversion prompt information;

[0206] The information conversion prompt information is input into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity.

[0207] In one embodiment, when the processor 110 performs the model prompt information generation process based on the demonstration structured information to obtain the information conversion prompt information, the processor 110 specifically performs the following operations:

[0208] Determine a specified display form type set corresponding to the target demonstration activity;

[0209] Generate information conversion prompt information based on the specified display form type set and the demonstration structured information.

[0210] In one embodiment, when the processor 110 determines the specified display form type set corresponding to the target demonstration activity, the processor 110 specifically performs the following operations:

[0211] Obtaining a display type mapping relationship between a plurality of preset reference demonstration activity types and reference display form types corresponding to the reference demonstration activity types;

[0212] Determining a target demonstration activity type corresponding to the target demonstration activity based on the at least one demonstration information;

[0213] The target display form type corresponding to the target demonstration activity type is searched in the display type mapping relationship, and a designated display form type set corresponding to the target demonstration activity is determined based on the target display form type.

[0214] In one embodiment, when the processor 110 determines the designated presentation form type set corresponding to the target demonstration activity based on the target presentation form type, the processor 110 specifically performs the following operations:

[0215] Determine the priority level corresponding to the target display format type;

[0216] A designated presentation format type set corresponding to the target demonstration activity is generated based on the priority level and the target presentation format type.

[0217] In one embodiment, when the processor 110 determines the specified display form type set corresponding to the target demonstration activity, the processor 110 specifically performs the following operations:

[0218] The demonstration structured information is input into a display type recognition model to obtain a specified display form type set corresponding to the target demonstration activity, and the display type recognition model is trained by display form type labels corresponding to the labeled demonstration structured information.

[0219] In one embodiment, after executing the step of using the second artificial intelligence content generation model based on the demonstration structured information to generate activity presentation information for the target demonstration activity, the processor 110 further performs the following operations:

[0220] The activity display information is sent to at least one designated terminal.

[0221] In one embodiment, after executing the step of sending the activity display information to at least one designated terminal, the processor 110 further performs the following operations:

[0222] Obtaining update information for the activity display information sent by the target designated terminal;

[0223] The activity display information is updated based on the update information to obtain target activity display information for the target demonstration activity;

[0224] The target activity display information is synchronized to the at least one designated terminal.

[0225] In one embodiment, the processor 110 further performs the following operations:

[0226] Acquire a basic artificial intelligence content generation model, and create an initial first artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0227] Acquire at least one kind of sample demonstration information in the sample demonstration activity, wherein the sample demonstration information at least includes sample demonstration picture information and sample demonstration voice information;

[0228] Based on the sample demonstration picture information and the sample demonstration voice information, at least one round of model training is performed on the initial first artificial intelligence content generation model to obtain a first artificial intelligence content generation model after model training.

[0229] In one embodiment, the processor 110 further performs the following operations:

[0230] Acquire a basic artificial intelligence content generation model, and create an initial second artificial intelligence content generation model based on the basic artificial intelligence content generation model;

[0231] Get the sample demonstration structured information corresponding to the sample demonstration activity;

[0232] Based on the sample demonstration structured information, at least one round of model training is performed on the initial second artificial intelligence content generation model to obtain a second artificial intelligence content generation model after model training.

[0233] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0234] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for generating information, characterized in that: The method comprises: Obtain at least one kind of demonstration information of a target demonstration activity; Based on the at least one demonstration information, a first artificial intelligence content generation model is used to obtain demonstration structured information; Based on the demonstration structured information, a second artificial intelligence content generation model is used to generate activity display information for the target demonstration activity.

2. The method according to claim 1, characterized in that The step of using a first artificial intelligence content generation model based on the at least one demonstration information to obtain demonstration structured information includes: Performing model prompt information generation processing based on the at least one demonstration information to obtain content integration prompt information; The content integration prompt information is input into the first artificial intelligence content generation model to obtain demonstration structured information.

3. The method according to claim 2, characterized in that The step of generating model prompt information based on the at least one demonstration information to obtain content integration prompt information includes: generating content extraction prompt information for a demonstration note object in the at least one demonstration information; Generating structure integration prompt information for the presentation note object and the initial presentation file object in the at least one presentation information; Content integration prompt information is determined based on the content extraction prompt information and the structure integration prompt information.

4. The method according to claim 1, characterized in that The step of using a second artificial intelligence content generation model based on the demonstration structured information to generate activity display information for the target demonstration activity includes: Performing model prompt information generation processing based on the demonstration structured information to obtain information conversion prompt information; The information conversion prompt information is input into the second artificial intelligence content generation model to generate activity display information for the target demonstration activity.

5. The method according to claim 4, characterized in that The generating process of model prompt information based on the demonstration structured information to obtain information conversion prompt information includes: Determine a specified display form type set corresponding to the target demonstration activity; Information conversion prompt information is generated based on the specified display form type set and the demonstration structured information.

6. The method according to claim 5, characterized in that The step of determining a specified display form type set corresponding to the target demonstration activity includes: Obtaining a display type mapping relationship between a plurality of preset reference demonstration activity types and reference display form types corresponding to the reference demonstration activity types; Determining a target demonstration activity type corresponding to the target demonstration activity based on the at least one demonstration information; The target display form type corresponding to the target demonstration activity type is searched in the display type mapping relationship, and a designated display form type set corresponding to the target demonstration activity is determined based on the target display form type.

7. The method according to claim 6, characterized in that The step of determining a designated display form type set corresponding to the target demonstration activity based on the target display form type includes: Determine the priority level corresponding to the target display format type; A designated presentation format type set corresponding to the target demonstration activity is generated based on the priority level and the target presentation format type.

8. An information generating device, characterized in that: The device comprises: An information acquisition module, used to acquire at least one kind of demonstration information of a target demonstration activity; A first processing module, configured to obtain presentation structured information by using a first artificial intelligence content generation model based on the at least one presentation information; The second processing module is used to generate activity display information for the target demonstration activity by adopting a second artificial intelligence content generation model based on the demonstration structured information.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 7.

Images