Method and device for generating image, equipment, medium and product

Abstract

The embodiment of the invention provides a method and device for generating an image, equipment, a storage medium and a computer program product. The method includes obtaining raw data and an image generation request for the raw data. The method further includes determining adjusted raw data according to the image generation request, the adjusted raw data being at least partially identical to the raw data. The method further includes generating a set of images based on the image generation request and / or the adjusted raw data. According to the method provided by the embodiment of the invention, the original data is adjusted, so that the generated image set can meet the diversified requirements of the user and can be directly used, thereby improving the image generation efficiency and improving the user experience.

Description

TECHNICAL FIELD

[0001] The present disclosure relates generally to the field of computers, and more specifically to a method, apparatus, device, computer-readable storage medium, and computer program product for generating an image. BACKGROUND

[0002] Currently, the development of machine learning models is evolving at a high speed, continuously expanding the application boundaries and upper limits of capabilities in the process of technical iteration. Among them, the machine learning technology represented by language models, through the synergistic support of large-scale data training and deep neural network architecture, has built a technology system with high-order language understanding and generation capabilities.

[0003] For example, machine learning models can handle cross-domain, multi-level user queries, showing strong capabilities from daily information consultation to professional knowledge answering. Through technology enhancement such as dynamic prompt word optimization and external knowledge retrieval integration, machine learning models can accurately understand user intent and output structured and high-accuracy responses, and have been widely applied to intelligent customer service, educational question answering, professional consultation, and other scenarios. In addition, machine learning models can automatically integrate multi-source data based on input requirements, generate standardized citation formats, and build logically coherent text frameworks, covering academic papers, industry analysis reports, technical reviews, and other types. SUMMARY

[0004] According to an example embodiment of the present disclosure, a method, apparatus, device, computer storage medium, and computer program product for generating an image are provided.

[0005] In a first aspect of the present disclosure, a method for generating an image is provided, the method comprising obtaining original data and an image generation request for the original data. The method further comprises determining adjusted original data according to the image generation request, the adjusted original data being at least partially identical to the original data. The method further comprises generating a set of images based on the image generation request and / or the adjusted original data.

[0006] In a second aspect of the present disclosure, an apparatus for generating an image is provided, the apparatus comprising an original data obtaining module configured to obtain original data and an image generation request for the original data. The apparatus further comprises an original data adjusting module configured to determine adjusted original data according to the image generation request, the adjusted original data being at least partially identical to the original data. The apparatus further comprises a set of images generating module configured to generate a set of images based on the image generation request and / or the adjusted original data.

[0007] In a third aspect of the disclosure, there is provided an electronic device comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform the method described according to the first aspect of the disclosure.

[0008] In a fourth aspect of the disclosure, there is provided a computer-readable storage medium having stored thereon machine executable instructions, which when executed by a device, cause the device to perform the method described according to the first aspect of the disclosure.

[0009] In a fifth aspect of the disclosure, there is provided a computer program product comprising computer executable instructions, wherein the computer executable instructions, when executed by a processor, implement the method described according to the first aspect of the disclosure.

[0010] The summary is provided to introduce a selection of concepts that are further described in the detailed description below. It is not intended to identify key or essential features of the disclosure or to delineate the scope of the disclosure. Other features of the disclosure will be apparent from review of the disclosure herein. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1A A schematic diagram showing an example environment in which embodiments of the disclosure can be implemented;

[0012] Figure 1B A schematic diagram showing the effect of generating a set of images according to embodiments of the disclosure;

[0013] Figure 1C A schematic diagram showing an adjustment scheme editing page according to embodiments of the disclosure;

[0014] Figure 2 A flowchart showing a method for generating images according to embodiments of the disclosure;

[0015] Figure 3 A schematic diagram showing a process of reducing the number of words according to embodiments of the disclosure;

[0016] Figure 4 A schematic diagram showing a process of expanding original data according to embodiments of the disclosure;

[0017] Figure 5A A schematic diagram showing functional components according to embodiments of the disclosure;

[0018] Figure 5BA schematic diagram illustrating another functional component according to an embodiment of the present disclosure is shown;

[0019] Figure 6 A schematic block diagram illustrating an example apparatus according to some embodiments of the present disclosure is shown; and

[0020] Figure 7 A block diagram of an example apparatus that can be used to implement an embodiment of the present disclosure is shown.

[0021] In all the drawings, same or similar reference numerals can represent same or similar elements. DETAILED DESCRIPTION

[0022] The names of messages or information exchanged between the plurality of apparatuses in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information. It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of personal information involved in the present disclosure, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained by a proper way according to the relevant laws and regulations.

[0023] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will need to obtain and use the personal information of the user. Thus, the user can autonomously select whether to provide the personal information to the software or hardware such as an electronic device, an application program, a server or a storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information. As an optional but not limited implementation manner, the way of sending the prompt information to the user in response to receiving the active request of the user may, for example, be a pop-up window manner, and the prompt information may, for example, be presented in the form of text in the pop-up window. In addition, the pop-up window may, for example, carry a selection control for the user to select “agree” or “disagree” to provide the personal information to the electronic device.

[0024] It can be understood that the above notification and obtaining of the authorization of the user are only illustrative, and do not limit the implementation manners of the present disclosure, and other manners meeting the relevant laws and regulations can also be applied to the implementation manners of the present disclosure.

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the protection scope of the present disclosure.

[0026] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0027] Typically, users need to adjust the presentation of raw data, such as converting raw data containing text and images into individual images for use and sharing on various social media platforms. In practice, because users cannot predict the amount of information each image can carry, the converted image set may not meet their needs, for example, containing too many or too few images, and therefore cannot be used directly.

[0028] To address this issue, this disclosure proposes a method for generating images. This method adaptively adjusts the original data before converting it into an image set, wherein the adjusted original data is at least partially identical to the original data, and an image set is generated based on the adjusted original data. By adjusting the original data, the generated image set can meet diverse user needs and be used directly, thereby improving the efficiency of image generation and enhancing the user experience.

[0029] The embodiments of this disclosure will now be described in further detail with reference to the accompanying drawings, wherein... Figure 1A A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Example environment 100 includes an application 110 on a user device and a server. The server may be deployed with models (such as multimodal machine learning models), which are trained models capable of generating content in response to user requests. In some embodiments, the user device and the server communicate via a network. The network may include a wired network, a wireless network, or a combination thereof, for providing communication between the user device and the server. In some embodiments, the user device may be connected to the server via a data cable; the present disclosure does not limit the connection method between the user device and the server. In this embodiment, the methods of embodiments of the present disclosure are performed by application 110.

[0030] like Figure 1AAs shown, in application 110, a user can communicate with a model deployed on a server. In some embodiments, the user can provide user input 112 in application 110: "Provide a report or document introducing the characteristics of buildings in various countries." After receiving user input 112, application 110 transmits it to the server. Upon receiving the request, the server's internally deployed model initiates a workflow, performing deep semantic analysis and logical processing on the user input based on its powerful algorithms and training results, thereby generating a response (i.e., an example of the original data). In some embodiments, application 110 can obtain and display the response "Introduction to the characteristics of buildings in various countries" to user input 112. For example, application 110 can display an identifier for the response in a dialog box on the left and display the specific content of the response in a preview interface on the right. In some embodiments, when the user clicks the "Multiple Images" button in the preview interface, application 110 can obtain the image generation request and prepare to convert the response into an image set. The images in the image set can be presented, for example, in the form of cards, which contain a portion of the content in the response. In this embodiment, the response has a very large number of words (e.g., three thousand words), so the generated image set includes, for example, thirty images. In some embodiments, when there are too many images, users can view different images by dragging the scroll wheel below the image collection.

[0031] When the number of characters in a reply exceeds the character limit (i.e., the first threshold), application 110 can display a prompt 114 to reduce the reply. The pop-up window contains a description of the problem and operation options. For example, prompt 114 could be "This reply has too many characters and will be converted into 30 images. Do you want to reduce the number of characters in your reply?" Below this, there are "Yes" and "No" buttons. For example, the limit could be 800 characters.

[0032] In some embodiments, application 110 can obtain an adjusted response based on an image generation request, wherein the adjusted response is determined by the server's model based on the response and user input and is at least partially identical to the response. For example, if a confirmation is received for a prompt (e.g., the user clicked the "Yes" button), a reduced response is obtained as the adjusted response, wherein the reduced response has fewer characters than the upper limit. In some embodiments, application 110 sends an adjustment request to the server, the request parameters including: the full text of the response, user input 112, target character limit (800 characters), and reduction strategy preference (reducing all chapters). After receiving the request, the server-side model, based on the core requirements of the user input (by country, representative buildings, and style features), uses a text summarization algorithm to semantically compress the response, retaining the top three representative buildings for each country, removing secondary cases, removing redundant descriptions (such as the specific year of construction, non-core process details), retaining key information such as name, style, and core features, and performing logical verification on the compressed text to ensure complete chapter structure and fluent sentences, ultimately generating an adjusted response of 780 characters (character count ≤ 800 characters). The server will return the adjusted response and adjustment log (such as "12 cases removed, 23 descriptions simplified") to application 110.

[0033] In some embodiments, application 110 may generate a set of images based on an image generation request and / or an adjusted response. For example, the model may reduce a previously generated response to adjust the response and display the adjusted response in the chat box for the user to view different versions of the response. Figure 1B A schematic diagram illustrating the effect of generating an image set according to an embodiment of the present disclosure is shown. After a user clicks the "Multiple Images" button, an image set can be generated based on the adjusted original data. This image set includes images 116, 118, 120, 122, and 124, which can still be presented in card format. In this embodiment, the number of images in the image set is controlled to 5, adapting to the single-share limit of mainstream social media platforms, eliminating the need for batch operations. Furthermore, users do not need to repeatedly adjust the number of characters in their replies or repeatedly convert images, solving the problem of high trial-and-error costs and improving the efficiency of image generation.

[0034] Furthermore, when adjusting raw data such as responses, recommended adjustment schemes can be provided to the user. In some embodiments, application 110 can generate at least one data adjustment scheme for the raw data based on the image generation request, and display the at least one data adjustment scheme. These data adjustment schemes can be user-defined data adjustment schemes, data adjustment schemes used by the user in historical operations, or data adjustment schemes preset by application 110. These data adjustment schemes can have different characteristics; for example, the data adjustment scheme can be a "scheme suitable for platform A," a "scheme suitable for platform B," etc., and can also be various types of data adjustment schemes such as "multiple image styles," "multiple text styles," "multiple emoji styles," "simplified style," "comprehensive style," etc.

[0035] In some embodiments, if a user selects a specific data adjustment scheme (i.e., a first data adjustment scheme) from at least one data adjustment scheme (i.e., a first operation), the adjusted original data is determined. After the user selects a specific data adjustment scheme displayed, application 110 can adjust the original data based on the content of the selected data adjustment scheme to obtain the adjusted original data.

[0036] In some embodiments, if a user selects a specific data adjustment scheme, an adjustment scheme editing page is displayed. Application 110 can provide a more specific adjustment scheme editing page after the user makes a selection. This page can display one or more adjustment parameters, such as the number of images, the number of characters, the number of images in the generated image set, the text style, etc. The user can modify the specific data adjustment scheme by setting these adjustment parameters. Figure 1C A schematic diagram of an adjustment scheme editing page according to an embodiment of the present disclosure is shown. Application 110 can display multiple scheme options, such as "First Scheme," "Second Scheme," "Third Scheme," etc. After the user clicks on one of the schemes, an adjustment scheme editing page 130 pops up. This adjustment scheme editing page 130 specifically displays the settings of various adjustment parameters corresponding to that scheme. Users can modify these adjustment parameters on the adjustment scheme editing page 130 to meet their diverse needs.

[0037] In some embodiments, if a user confirmation operation (i.e., a second operation) is received on the adjustment scheme editing page, the adjusted original data is determined. After user confirmation, application 110 can adjust the original data according to the modified data adjustment scheme. This embodiment, by recommending data adjustment schemes and providing an editing page for the data adjustment schemes, can improve user processing efficiency and meet diverse user needs, thereby enhancing the user experience.

[0038] In some embodiments, when adjusting raw data such as a response, application 110 can determine image generation parameters based on an image generation request and determine adjusted raw data based on the image generation parameters. For example, application 110 can provide multiple options, each corresponding to a different image-to-text ratio, such as 10:0, 5:1, 2:3, etc. A user can select from multiple options, for example, selecting the option with an image-to-text ratio of 1:5. This selection operation generates an image generation request, where the image-to-text ratio is the image generation parameter of that request. Upon receiving the image generation request, application 110 can adjust the raw data according to the image-to-text configuration, for example, by supplementing the number of images or the volume of text in the raw data to match the image generation parameters of the request. In other examples, the image generation parameters can be other types of parameters, such as the absolute number of images (e.g., 5 images), the absolute number of text, etc.

[0039] In some embodiments, the image generation parameters include at least a data modality corresponding to the image generation request. When the original data modality in the original data differs from the data modality in the image generation parameters, data in the data modality of the image generation parameters is generated based on the original data, and adjusted original data is determined based on the original data and the generated data. This data modality can be, for example, a text modality or an image modality. The data modality in the image generation parameters can be determined in various ways. For example, a user can specify the data modality as "image" in the image generation parameters of the image generation request. Assuming the original data is plain text data, the original data modality of the original data is "text." In this case, the original data modality "text" of the original data differs from the data modality "image" in the image generation parameters. Application 110 can then supplement the original data with a suitable image by understanding the semantics of the original data and integrate it into the original data, thereby obtaining adjusted original data. Assuming the original data is plain text data and the data modality in the image generation parameters is "text," it can be determined that the original data modality "text" of the original data is the same as the data modality "text" in the image generation parameters. Therefore, no adjustment to the original data is required in this aspect of the parameter. However, this does not prevent the raw data from being adjusted based on other parameters in the image generation request.

[0040] In some alternative embodiments, application 110 may provide an input interface from which a user can input data as supplementary data. Application 110 may receive data from a data modality that is included in the image generation parameters input by the user. Application 110 also determines adjusted original data based on the original data and the data from the data modality. For example, if a user inputs three images into the input interface, application 110 may supplement the original data with these three images to obtain adjusted original data.

[0041] It should be understood that a server instance can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. Servers can be connected directly or indirectly through wired or wireless communication methods, and this application does not impose any restrictions.

[0042] The user device can be any type of mobile computing device, including mobile computers (e.g., personal digital assistants, laptops, notebooks, tablets, netbooks, etc.), mobile phones (e.g., cellular phones, smartphones, etc.), wearable computing devices (e.g., smartwatches, head-mounted devices, including smart glasses, etc.) or other types of mobile devices. In some embodiments, the user device can also be a fixed computing device, such as a desktop computer, game console, smart TV, etc. It should be understood that the above operations can be performed jointly by the user device and the server.

[0043] It should be understood that the architecture and functionality in the example environment are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. Embodiments of this disclosure can also be applied to other environments with different structures and / or functionalities.

[0044] The processes according to embodiments of this disclosure will be described in detail below with reference to other accompanying drawings. For ease of understanding, the specific data mentioned in the following description are exemplary and not intended to limit the scope of this disclosure. It will be understood that the embodiments described below may also include additional actions not shown and / or actions shown may be omitted, and the scope of this disclosure is not limited in this respect.

[0045] Figure 2 A flowchart of a method 200 for generating an image according to certain embodiments of the present disclosure is shown. In this embodiment, it can be generated by... Figures 1A-1C This method is executed using an embodiment of the present invention. In block 202, raw data and an image generation request for the raw data are obtained. The raw data may be, for example, data generated by a model (e.g., a response) or data uploaded by a user; this embodiment does not limit this. The image generation request is a request to generate a set of images, and this request may be obtained based on a visual control. For example, a specific button may be displayed on the interface, and the user clicking the specific button will obtain the image generation request. This specific button may, for example, be associated with specific generation parameters or generation schemes; this embodiment does not limit this. The raw data may, for example, include at least one of audio data, video data, text data, or image data.

[0046] In box 204, adjusted original data is determined based on the image generation request. The adjusted original data is at least partially identical to the original data. This adjusted original data may be, for example, content generated by a model based on the original data through semantic compression, information augmentation, key point extraction, etc., and is at least partially identical to the original data. This adjustment can be in any aspect, such as data volume or data style. In some embodiments, the adjusted original data differs from the original data in the number of images it contains.

[0047] In box 206, an image set is generated based on the image generation request and / or adjusted raw data. For example, the raw data can be directly converted into an image set based on the image generation request. This results in an image set that more closely matches the content of the original data. Alternatively, an image set can be generated based on adjusted raw data, utilizing previous adjustments to meet diverse user needs. Another example is generating an image set based on both the image generation request and adjusted raw data. This example further incorporates personalized parameters from the image generation request into the adjusted raw data to achieve more accurate image generation. This image set could, for example, be... Figure 1A and Figure 1C The diagram shows multiple cards. In this operation, for example, the adjusted original data can be split into a combination of multiple images according to preset rules (such as maximum number of characters per image, content integrity, and format adaptation). Each image carries a portion of the content, and the whole image completely covers all the information of the adjusted original data.

[0048] According to an embodiment of the present disclosure, the method adaptively adjusts the original data before converting it into an image set, wherein the adjusted original data is at least partially identical to the original data, and an image set is generated based on the adjusted original data. By adjusting the original data, the generated image set can meet the diverse needs of users and can be used directly, thereby improving the efficiency of image generation and enhancing the user experience.

[0049] In some embodiments, image generation requests correspond to a preset strategy, and if the original data does not conform to the preset strategy, the original data is adjusted based on the preset strategy. This preset strategy may be, for example, a strategy based on data volume, a strategy based on data style, and so on. Different image generation requests from a user may correspond to the same fixed preset strategy, or they may correspond to different preset strategies. For example, one image generation request (e.g., selecting "Platform A") corresponds to a strategy associated with Platform A, and another image generation request (e.g., selecting "Platform B") corresponds to a strategy associated with Platform B.

[0050] In some embodiments, if the preset strategy includes a limitation on data volume, the original data can be adjusted based on that limitation. Data volume refers to the size of the content of the original data, which can be the number of characters, images, paragraphs, chapters, etc. Figure 3 A schematic diagram illustrating the word count reduction process according to an embodiment of this disclosure is shown. In this embodiment, the limitation on data volume includes an upper limit on the number of words. At point 302, after the application obtains the raw data returned by the server, it performs word count through a built-in text parsing module. This module supports multilingual character recognition (including Chinese and English, numbers, and punctuation marks) and can automatically filter redundant tags (such as HTML format tags and knowledge base reference tags) in the raw data to ensure that the statistical result is "valid content word count". For example, for the "Report on the Characteristics of Buildings in Various Countries" mentioned above, the text parsing module first removes hidden format tags in the raw data, then counts the valid character count as 3000 words, and synchronizes the statistical result to the top of the application's preview interface (displaying "Word Count: 3000") for the user to view intuitively.

[0051] At position 304, the system checks if the character count exceeds the upper limit. The application compares the character count of the original data with the upper limit. This comparison is performed locally and in real-time, without secondary interaction with the server, improving response speed. In some embodiments, if the character count of the original data is less than or equal to the upper limit (e.g., the user input is "introduce the architectural features of building B in country A", and the generated original data has 750 characters), the system proceeds directly to position 306 and initiates the image conversion process. In some embodiments, the content is split into optimal portions of 120-180 characters per image, ensuring balanced information per image and no cross-image splitting, ultimately generating 5-6 images (750 characters ÷ 150 characters / image = 5 images), with image format, resolution, and other parameters configured by default. In some embodiments, a "one-click sharing" entry is automatically generated after conversion, adapting to mainstream social media platforms.

[0052] In some embodiments, if the original data has more characters than the upper limit, the reduced original data is used as the adjusted original data, where the reduced original data has fewer characters than the upper limit. That is, the application can directly reduce the original data without prompting. In some embodiments, if the original data has more characters than the upper limit, the application proceeds to position 308 and presents a prompt for reducing the original data. In some embodiments, the original data includes multiple sections, where the prompt includes reasons for retaining certain sections, generated by a model. For example, for a user input of 112, the prompt might include the following: Retained sections: Country C, Country D, Country E, Country F. Reason for retention: Each section covers your requirements for "various countries" and "representative buildings." Retaining these sections will fully present the top three landmark buildings from Country C to Country F. The reduced version is estimated to have 780 characters and will generate 5 images, suitable for sharing scenarios.

[0053] At point 310, it determines whether the user confirms the prompt. If the prompt is ignored, for example, the user clicks the "ignore" or "no" button, proceed to point 306 and directly generate the image set based on the original data. If the prompt is confirmed, proceed to point 312 and obtain the reduced original data as the adjusted original data, where the number of characters in the reduced original data is less than the upper limit. Several methods for reducing the original data are shown below the figure.

[0054] In some embodiments, the original data comprises multiple chapters, and at point 314, a subset of these chapters is retained as the reduced original data. In some embodiments, this subset of chapters is determined based on multiple relevance measures of the chapters relative to the original data, which are determined by a model. That is, the model selects the most relevant chapters from the multiple chapters to form the core framework of the reduced original data, discarding chapters with lower relevance. The relevance measure indicates the degree of correlation between the corresponding chapter and the original data. Reducing the word count of the original data by retaining more relevant chapters can improve the user experience.

[0055] There are various methods for calculating relevance metrics, such as calculating relevance metrics based on the frequency of keyword occurrences. In some embodiments, keywords are obtained, where keywords are determined by the model based on the original data. For example, the model can mine high-frequency core words (such as "landmark building," "style," "feature," "landmark," etc.) from the original data as keywords to ensure coverage of the core semantics of the original data.

[0056] In some embodiments, multiple frequencies of keywords appearing across multiple chapters are determined. For example, the frequency of each keyword in each chapter is counted (e.g., in the chapter on Country C, "style" appears 8 times, "feature" appears 6 times, and "landmark" appears 5 times, for a total frequency of 19 times; in the chapter on Country D, "style" appears 7 times, "feature" appears 5 times, and "landmark" appears 4 times, for a total frequency of 16 times). In some embodiments, multiple relevance measures are determined based on these multiple frequencies. For example, the total frequency of keywords in each chapter is converted to a relative frequency, and the result of dividing the total frequency of keywords in that chapter by the sum of the total frequencies of keywords in all chapters is used as the relevance measure.

[0057] In some embodiments, by extracting high-frequency core words from the original data and statistically analyzing the frequency of occurrence of keywords in each chapter and calculating the relative frequency, the relevance of chapters is transformed from a qualitative judgment into a quantitative indicator, which solves the problems of subjectivity and ambiguity in traditional relevance assessment and makes the assessment results quantifiable.

[0058] In some embodiments, the reduced original data is obtained by reducing the content of one or more chapters from a plurality of chapters. For example, at 316, the plurality of chapters includes a first chapter, which is replaced with a summary of the first chapter, generated by the model, and the summary has fewer words than the first chapter. For example, if a chapter of the original data (such as the C country section) has too many words (originally 800 words), the model replaces that chapter (the first chapter) with a summary of that chapter, and the summary has significantly fewer words than the original chapter (e.g., 800 words reduced to 180 words).

[0059] At point 318, multiple chapters include a first chapter and a second chapter. The merged chapter is determined by merging the first and second chapters, and the reduced original data is obtained by shortening the merged chapter. In this embodiment, by merging some similar chapters and reducing the word count of the merged chapter, the chapters can be more distinguishable, which can improve the user experience while reducing the word count.

[0060] In some embodiments, multiple chapters of the raw data are identified. For example, the multiple chapters can be identified by their titles or by font size (chapter titles typically have larger fonts). In some embodiments, multiple coupling measures between the multiple chapters are determined. A coupling measure is a quantitative indicator that measures the degree of correlation between two chapters. In some embodiments, a model can be used to determine the core semantics of each chapter (e.g., a paragraph summarizing a chapter). These core semantics can be represented, for example, by features, and then the distance between these core semantics in a multidimensional space is calculated as a coupling measure.

[0061] In some embodiments, the first and second chapters are determined based on multiple coupling metrics. For example, all chapters are paired to form chapter pairs (e.g., 5 chapters form 10 chapter pairs), sorted in descending order by coupling metrics, and the chapter pairs with the highest ranking are selected for merging.

[0062] This embodiment achieves the dual goals of precise word count control and optimized information density: by merging similar chapters, the total word count of the original data is kept within the upper limit while avoiding information fragmentation caused by reducing a single chapter. The method of merging followed by reduction efficiently compresses redundant content (such as repetitive statements and minor examples), increases the information density of a single chapter, and ensures a reasonable number of generated images (reducing cross-chapter image splitting). This eliminates the need for manual adjustments and trial and error by the user, improving image generation efficiency and user experience.

[0063] In some cases, when the original data is too long, two image sets can be generated based on the original data, and different titles can be generated for these two image sets. In some embodiments, a first chapter set and a second chapter set are determined by grouping multiple chapters, serving as the reduced original data. For example, the title of each chapter can be determined, and the semantic distance between each title can be calculated. These titles are then divided into two groups based on these semantic distances, resulting in the first chapter set and the second chapter set.

[0064] In some embodiments, when converting to an image set, a first image set is generated based on a first chapter set, and a second image set is generated based on a second chapter set. This operation can perform two image conversions to obtain two image sets. This allows users to use the first image set and the second image set separately, thereby improving the user experience.

[0065] In some cases, excessive word count can lead to a mismatch between the word count and the number of images included in the original data. To address this, in some embodiments, the original data includes images and text. Data volume limitations include a second threshold and a third threshold for images. The number of images is the first threshold, and the number of text words is the second threshold. When adjusting the original data, if the ratio of the first threshold (i.e., the number of images) to the second threshold (i.e., the number of text words) is less than a text-image ratio threshold (i.e., the second threshold), supplementary original data is obtained by adding additional images to the original data. This text-image ratio threshold is a reasonable ratio between the total number of words in the original data and the number of images included in the original data (e.g., a text-image ratio threshold of 1:150, meaning one image for every 150 words is optimal). If the actual ratio is less than the text-image ratio threshold (e.g., the original data of 3000 words includes only one image), it is considered an imbalance, and additional images can be added to the original data to generate supplementary original data. The supplementary images must be strongly related to the content of the original data. For example, if the original data is "Architectural Characteristics of Various Countries," the supplementary images could include architectural style classification diagrams, etc.

[0066] In some embodiments, if the number of images is less than a preset threshold (i.e., a third threshold), supplementary original data is obtained by adding additional images to the original data. Besides ratio-based judgment, the number of images inherent in the original data can also be directly verified using a preset threshold, which is the minimum number of images required to ensure a good browsing experience. If the statistical result is less than the preset threshold, the additional image supplementation process is directly triggered to obtain supplementary original data.

[0067] In some embodiments, the limitation on data volume includes a lower limit on the number of words (i.e., a fourth threshold). If the number of words in the original data is less than the lower limit, expanded original data is obtained as adjusted original data, wherein the number of words in the expanded original data is greater than the lower limit. For example, in some cases, the original data generated by the model has a small number of words, such as real-time original data of a communicative nature. Thus, if the user also wants to convert it into a collection of images, it may be necessary to expand the original data.

[0068] Figure 4A schematic diagram illustrating the process of expanding raw data according to an embodiment of this disclosure is shown. At 402, after the application obtains the raw data returned by the server, it performs word count. This is similar to the operation at 302 and will not be described again. At 404, a lower limit is determined based on a preset type set. This preset type set may include types such as technology, education, entertainment, and stories, where the lower limit for educational raw data is 300 words, for entertainment raw data it is 200 words, for story raw data it is 500 words, for technology raw data it is 400 words, and for comprehensive raw data used for other types it is 350 words. In some embodiments, the type of the raw data is obtained, wherein the type is determined by the model from the preset type set based on the raw data. In some embodiments, the type of the raw data is determined by the server-side model by analyzing the semantics of the raw data. For example, the model may extract the topic from the raw data, calculate the distance between the topic and each type, and output the type with the highest confidence from the preset type set. If the confidence is lower than the threshold (e.g., the raw data content spans multiple types), it is defaulted to the comprehensive type, corresponding to a lower limit of 350 words.

[0069] At point 406, a lower limit corresponding to the type is selected, for example, by choosing a threshold from the threshold set that corresponds to the type. For example, the application can determine the word count lower limit for the original data type from the mapping table mentioned above based on the original data type determined by the model. For example, if the type of the original data is determined to be technical, then the lower limit is 400 words. At point 408, it is determined whether the word count of the original data is less than the lower limit. If not, proceed to point 410 to generate an image set based on the original data. If the word count of the original data is greater than the lower limit, proceed to point 412 to present a prompt for expanding the original data. This prompt can be similar to a prompt for reducing the word count, for example, including reasons for expansion, which will not be elaborated further.

[0070] At point 414, determine if the user confirms the prompt. If not, proceed to point 410 and generate an image set based on the original data. Although the number of characters is small, if the user wants to generate images based on this original data, it can be directly converted into an image set. If confirmation of the prompt is received, proceed to point 416 and obtain the expanded original data as the adjusted original data, where the number of characters in the expanded original data is greater than the lower limit, to obtain the expanded original data.

[0071] In this embodiment, by pre-setting coverage categories such as technology, education, entertainment, and stories, differentiated word count limits are matched to different categories. This ensures that the word count standard deeply matches users' needs for information detail in various scenarios, thereby improving user experience. Furthermore, by expanding the original data to reach the corresponding category's word count limit, the generated image set is ensured to have a reasonable quantity, avoiding the problem of sparse text in single images due to insufficient word count (e.g., short original data with less than 200 words generates only one image, resulting in monotonous content and poor visual presentation). The expanded original data is more complete and logically coherent, and the generated image set is suitable for usage habits in scenarios such as social sharing and document insertion, while also improving the readability and dissemination of the content.

[0072] In this disclosure, the methods used to expand the word count and the methods used to reduce the word count can be combined with each other, and there is no limitation on this. For example, expanding the word count can be done by expanding the content of each chapter, or by expanding the content of one or more chapters with high relevance.

[0073] In some embodiments, the preset strategy includes restrictions on the data style of the original data, and the original data is adjusted based on these restrictions when it is adjusted. The data style can be a design paradigm related to formatting and layout, such as, but not limited to, elements like font type, font size, paragraph hierarchy, line spacing, image size specifications, and chart layout. In some embodiments, the original data includes a first portion, and the restrictions on the data style include restrictions on font size. These restrictions include a fifth threshold (i.e., an upper limit for font size, such as a 24-point font), and if the font size of the first portion of the original data (e.g., actually a 32-point font) exceeds the fifth threshold, the font size of the first portion is reduced. This avoids generating too many images due to excessively large fonts.

[0074] In some embodiments, restrictions on data style include restrictions on font size. These restrictions include a sixth threshold, and if the font size of the first part of the original data is smaller than the sixth threshold (i.e., the lower limit of the font size, for example, set to 10-point font), the font size of the first part is increased. When it is detected that the font size of the first part of the original data is lower than the sixth threshold (e.g., actually 8-point font), to prevent users from being unable to clearly identify the data content due to excessively small font size, a font enlargement adjustment mechanism will be automatically activated to enlarge the font size of that part of the content (adjusting it to 10-point font) until it meets the standard size requirement corresponding to the sixth threshold, ensuring the effective transmission of data information.

[0075] In some embodiments, restrictions on data style include restrictions on image size, which include a seventh threshold (e.g., restrictions on image height and width). If the image size of the first image in the original data exceeds the seventh threshold, the image size of the first image is reduced. Considering that excessively large image sizes may affect the number of generated images, when the size parameters (such as width and height) of the first image (a certain image to be processed) contained in the original data are detected to exceed the aforementioned seventh threshold, the first image is reduced in size. This process can reduce the size of the first image to the range corresponding to the seventh threshold by means of proportional scaling, pixel compression, etc., while ensuring that the core image information is not lost.

[0076] In some embodiments, restrictions on data style include restrictions on image size, which include an eighth threshold (e.g., restrictions on image height and width). If the image size of the first image in the original data is smaller than the eighth threshold, the image size of the first image is increased. If the size of the first image in the original data is smaller than the eighth threshold, it will affect the usability of the image. Therefore, an image enlargement adjustment process is triggered. Through techniques such as image interpolation and resolution enhancement, the size of the first image is enlarged to the standard size corresponding to the eighth threshold, ensuring that the image information can be presented completely and clearly, while ensuring that the image clarity is not significantly affected.

[0077] Figure 5A A schematic diagram of functional components according to embodiments of the present disclosure is shown. In some embodiments, a rich set of functional components can be provided in the preview interface to meet diverse user needs. In some embodiments, a "Select Template" button 512 can be provided on the right side of the preview interface. Users can click the "Select Template" button 512, and the application can display multiple templates below, such as "Simple Basic," "Black and White Minimalist," and a "View More" control. After clicking the "View More" control, a list including other templates can be displayed. After selecting a specific template, the user can apply the selected template to one or more images in the image set. That is, the granularity of template operation can be at the image level, and different templates can be applied to each image in the image set to meet diverse user needs. For example, if a user clicks on an image in the image set to select it (e.g., highlight the border), and then selects a specific template, the template will only be applied to the selected image, while the other images will retain their original style.

[0078] To enhance ease of use, the preview interface also features a real-time preview function. In some embodiments, when a user hovers their mouse over a template, the system will automatically apply the template temporarily to the currently selected image, demonstrating the actual effects of the font, background, and layout. Once the user confirms their satisfaction, they can click the template to complete the settings; if not, they can directly switch to another template without repeatedly undoing the changes. Furthermore, the application supports custom template saving. Users can save adjusted template parameters (such as custom fonts, background colors, and line spacing) as "My Templates" for later use, avoiding repetitive settings.

[0079] Figure 5B A schematic diagram of another functional component according to an embodiment of this disclosure is shown. Considering that some users may not need the system to automatically determine the threshold, but instead wish to actively control the word count of the original data based on their own usage scenarios (such as image quantity limits on a specific platform, content simplification requirements), the application adds a "Reduce Word Count" button 514 on the right side of the preview interface, giving users more flexible operational control. In some embodiments, users can manually choose whether to reduce the word count. For example, a "Reduce Word Count" button 514 is displayed on the right side of the application's preview interface. When a user clicks this button, the application can display an option list below, where each option represents a way to reduce the word count, such as "Keep Chapter," "Summarize Chapter," "Merge Chapter," etc. After the user selects a method, the application sends the processing logic related to that method (see the above embodiment) to the model for processing to obtain the reduced original data, and generates an image set based on the reduced original data. In this embodiment, instead of comparing the word count of the original data with a threshold, the user can actively choose whether to reduce the word count of the original data, which can improve the user experience. This functional component offers the following benefits: the reduction logic is entirely user-driven, without relying on system threshold judgments, and it can adapt to more personalized scenarios.

[0080] Figure 6 A schematic block diagram of an example device 600 according to some embodiments of the present disclosure is shown. Device 600 can be implemented by software, hardware, or a combination of both. Figure 6 As shown, the device 600 includes a raw data acquisition module 610, a raw data adjustment module 620, and an image set generation module 630.

[0081] In some embodiments, the raw data acquisition module 610 may be configured to acquire raw data and an image generation request for the raw data. The raw data adjustment module 620 may be configured to determine adjusted raw data based on the image generation request, wherein the adjusted raw data is at least partially identical to the raw data. The image set generation module 630 may be configured to generate an image set based on the image generation request and / or the adjusted raw data.

[0082] In some embodiments, the original data adjustment module 620 includes: a scheme generation module configured to generate and display at least one data adjustment scheme for the original data based on an image generation request, wherein the at least one data adjustment scheme includes a first data adjustment scheme; and a first operation module configured to determine the adjusted original data in response to a first operation by a user on the first data adjustment scheme.

[0083] In some embodiments, the first operation module includes: an editing page display module configured to display an adjustment scheme editing page in response to a user's first operation on the first data adjustment scheme; and a second operation module configured to determine the adjusted original data in response to a user's second operation on the adjustment scheme editing page.

[0084] In some embodiments, the original data adjustment module 620 includes: a parameter determination module configured to determine image generation parameters according to an image generation request; and a second adjustment module configured to determine adjusted original data based on the image generation parameters.

[0085] In some embodiments, the image generation parameters include at least a data modality corresponding to the image generation request; and the second adjustment module includes a data generation module configured to generate data of the data modality in the image generation parameters based on the original data in response to a difference between the original data modality in the original data and the data modality in the image generation parameters; and a third adjustment module configured to determine adjusted original data based on the original data and the generated data; or the second adjustment module includes a receiving module configured to receive data of the data modality from the user, wherein the data of the data modality is included in the image generation parameters input by the user; and a fourth adjustment module configured to determine adjusted original data based on the original data and the data of the data modality.

[0086] In some embodiments, the image generation request corresponds to a preset strategy, and the original data adjustment module 620 includes: a first detection module configured to adjust the original data based on the preset strategy in response to the original data not conforming to the preset strategy.

[0087] In some embodiments, the preset strategy includes a limitation on the amount of data, and the first detection module includes a data volume limitation module configured to adjust the original data based on the limitation on the amount of data.

[0088] In some embodiments, the limitation on data volume includes a first threshold for the number of characters, and the data volume limitation module includes: a first character count detection module configured to present a prompt for reducing the original data in response to the number of characters in the original data being greater than the first threshold; and a first character count adjustment module configured to obtain the reduced original data as adjusted original data in response to receiving confirmation of the prompt, wherein the number of characters in the reduced original data is less than the first threshold.

[0089] In some embodiments, the original data includes images and text, the number of images being a first number and the number of characters in the text being a second number. The data volume limitation includes a second threshold and a third threshold for images, and the data volume limitation module includes: a ratio detection module configured to obtain supplementary original data by adding additional images to the original data in response to the ratio of the first number to the second number being less than the second threshold; and an image detection module configured to obtain supplementary original data by adding additional images to the original data in response to the first number being less than the third threshold.

[0090] In some embodiments, the limitation on data volume includes a fourth threshold for the number of characters, and the data volume limitation module includes: a second character count detection module configured to present a prompt for expanding the original data in response to the number of characters in the original data being less than the fourth threshold; and a second character count adjustment module configured to obtain the expanded original data as adjusted original data in response to receiving confirmation of the prompt, wherein the number of characters in the expanded original data is greater than the fourth threshold.

[0091] In some embodiments, the preset strategy includes restrictions on data styles, and the first detection module includes a style adjustment module configured to adjust the original data based on the restrictions on data styles.

[0092] In some embodiments, the restrictions on data style include restrictions on font size, the restrictions on font size include a fifth threshold, the original data includes a first portion, and the style adjustment module includes: a font size detection module configured to reduce the font size of the first portion in response to the font size of the first portion exceeding the fifth threshold.

[0093] In some embodiments, the limitation on data style includes a limitation on font size, the limitation on font size includes a sixth threshold, and the style adjustment module includes: a sixth threshold module configured to increase the font size of the first part in response to the font size of the first part of the original data being less than the sixth threshold.

[0094] In some embodiments, the data style restriction includes a font size restriction, the data style restriction includes an image size restriction, the image size restriction includes a seventh threshold, and the style adjustment module includes: a seventh threshold module configured to reduce the image size of the first image in response to the image size of the first image of the original data exceeding the image size restriction.

[0095] In some embodiments, the limitation on data style includes a limitation on image size, the limitation on image size includes an eighth threshold, and the style adjustment module includes: an eighth threshold module configured to increase the image size of the first image in response to the image size of the first image of the original data being less than the eighth threshold.

[0096] In some embodiments, the raw data includes at least one of audio data, video data, text data, or image data.

[0097] The division of modules or units in the embodiments of this disclosure is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the disclosed embodiments may be integrated into one unit, exist as separate physical entities, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0098] Figure 7 A block diagram of an example device 700 that can be used to implement embodiments of the present disclosure is shown. It should be understood that... Figure 7 The device 700 shown is merely an example and should not be construed as limiting the functionality and scope of the implementation described herein. For example, device 700 may correspond to the implementation described herein. Figures 1A-1C The user equipment described above can be used to perform the above-described... Figures 1A to 4 The process. For example, device 700 may correspond to the electronic device of the third aspect of the invention.

[0099] like Figure 7 As shown, device 700 is in the form of a general-purpose computing device. Components of device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage devices 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of device 700.

[0100] Device 700 typically includes multiple computer storage media. Such media can be any available media accessible to device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 730 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data (e.g., training data for training) and accessible within device 700.

[0101] Device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not specified in the original text... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various implementations of this disclosure.

[0102] The communication unit 740 enables communication with other computing devices via a communication medium. Additionally, the functionality of the components of device 700 can be implemented as a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0103] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Device 700 can also communicate as needed with one or more external devices (not shown) via communication unit 740. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with device 700, or with any device that enables device 700 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0104] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is provided that stores a computer program thereon, which, when executed by a processor, implements the methods described above.

[0105] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0106] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0107] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0108] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0109] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating an image, comprising: Obtain raw data and an image generation request based on the raw data; The adjusted original data is determined based on the image generation request, and the adjusted original data is at least partially the same as the original data; as well as Generate an image set based on the image generation request and / or the adjusted original data.

2. The method of claim 1, wherein determining the adjusted original data according to the image generation request comprises: Based on the image generation request, at least one data adjustment scheme is generated for the original data and displayed, wherein the at least one data adjustment scheme includes a first data adjustment scheme; as well as In response to the user's first operation on the first data adjustment scheme, the adjusted original data is determined.

3. The method of claim 2, wherein determining the adjusted original data in response to a user's first operation on the first data adjustment scheme includes: In response to the user's first operation on the first data adjustment scheme, the adjustment scheme editing page is displayed; as well as In response to the user's second action on the adjustment scheme editing page, the adjusted original data is determined.

4. The method of claim 1, wherein determining the adjusted original data according to the image generation request comprises: Determine the image generation parameters based on the image generation request; as well as The adjusted original data is determined based on the image generation parameters.

5. The method according to claim 4, wherein the image generation parameters include at least a data modality corresponding to the image generation request; The process of determining the adjusted original data based on the image generation parameters includes: In response to the fact that the original data modality in the original data is different from the data modality in the image generation parameters, data of the data modality in the image generation parameters is generated based on the original data; as well as Based on the original data and the generated data, the adjusted original data is determined; or Data is received from the user in the data modality, wherein the data in the data modality is included in the image generation parameters input by the user; as well as The adjusted original data is determined based on the original data and the data modality.

6. The method of claim 1, wherein the image generation request corresponds to a preset strategy, and determining the adjusted original data based on the image generation request includes: In response to the original data not conforming to the preset strategy, the original data is adjusted based on the preset strategy.

7. The method of claim 6, wherein the preset strategy includes a limitation on the amount of data, and adjusting the original data based on the preset strategy includes: The original data is adjusted based on the aforementioned limitations on data volume.

8. The method of claim 7, wherein the limitation on data volume includes a first threshold for word count, and adjusting the original data based on the limitation on data volume includes: In response to the original data having a word count greater than the first threshold, a prompt is displayed to reduce the original data; as well as In response to receiving confirmation of the prompt, the reduced original data is obtained as the adjusted original data, wherein the number of words in the reduced original data is less than the first threshold.

9. The method of claim 7, wherein the original data comprises images and text, the number of images is a first number, the number of characters in the text is a second number, the limitation on the data volume includes a second threshold and a third threshold for images, and adjusting the original data based on the limitation on the data volume comprises: In response to the ratio of the first number to the second number being less than the second threshold, supplementary original data is obtained by adding additional images to the original data; as well as In response to the first number being less than the third threshold, the supplemented original data is obtained by adding the additional image to the original data.

10. The method of claim 7, wherein the limitation on data volume includes a fourth threshold for the number of words, and adjusting the original data based on the limitation on data volume includes: In response to the original data having fewer characters than the fourth threshold, a prompt is displayed to expand the original data; as well as In response to receiving confirmation of the prompt, the expanded original data is obtained as the adjusted original data, wherein the number of words in the expanded original data is greater than the fourth threshold.

11. The method of claim 6, wherein the preset strategy includes restrictions on data styles, and adjusting the original data based on the preset strategy includes: The original data is adjusted based on the aforementioned restrictions on the data style.

12. The method of claim 11, wherein the restriction on data style includes a restriction on font size, the restriction on font size includes a fifth threshold, the original data includes a first portion, and adjusting the original data based on the restriction on data style includes: In response to the font size of the first part exceeding the fifth threshold, the font size of the first part is reduced.

13. An apparatus for generating an image, comprising: The raw data acquisition module is configured to acquire raw data and an image generation request based on the raw data; The original data adjustment module is configured to determine the adjusted original data based on the image generation request, wherein the adjusted original data is at least partially the same as the original data; as well as An image set generation module is configured to generate an image set based on the image generation request and / or the adjusted original data.

14. An electronic device, comprising: At least one processing unit; At least one memory is coupled to the at least one processing unit and stores operations to be performed by the at least one processing unit, the operations causing the electronic device to perform the method according to any one of claims 1 to 12 when performed by the at least one processing unit.

15. A computer program product having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images