Processing method and device for poster picture generation, computer equipment and storage medium

Abstract

The invention relates to the technical field of image data processing, discloses a poster picture generation processing method, device and equipment and a medium, and aims to solve the problem that the quality of generated poster pictures is low in the prior art. According to the method, a client side communicates with a server side through a network, and the server side receives calling for generating the poster pictures through the client side; the method comprises the following steps: calling a front-end user, acquiring retained user information of the front-end user according to the calling, customizing a current poster copywriting and display characteristics adapted to the front-end user according to the user information, and customizing and displaying a target poster adapted to the front-end user by a front end according to the poster copywriting and the display characteristics. According to the method and the device, the customized and personalized display of the poster picture for the characteristics of the front-end user is realized, the compatibility problem of the poster picture in platforms corresponding to different terminals is solved, the generation quality of the poster picture is improved, and the method and the device can be applied to but not limited to the financial field and the medical health field.

Description

Technical Field

[0001] The present invention relates to image data processing technology and the financial field, and in particular to a processing method, device, computer equipment and storage medium for generating a poster image. Background Art

[0002] Posters are a form of print advertising widely used to promote and convey information, usually attracting public attention through pictures, text and design elements. Poster pictures refer to pictures used for poster purposes.

[0003] With the development of internet technology, especially as more and more businesses are being processed online, poster images are finding increasingly widespread application. In some online user-friendly systems, such as insurance purchases, bank transfers, health checkups, or key milestone events, it's often necessary to design user experiences based on the results of current transactions or user milestones. This requires the use of technical means to depict and create beautiful, user-friendly poster images depicting the user's current actions or milestones, encouraging users to share and forward them, thereby enhancing the user experience and achieving wider dissemination.

[0004] In traditional technology, poster images are generally generated by simply randomly matching fixed information images made by designers and downloading and saving them, or by directly taking screenshots using some single-platform plug-ins. Therefore, the generated poster images are relatively uniform and fixed.

[0005] The inventors realized that traditional poster images, because poster images are relatively simple to produce and are generated based on a single platform, cannot be adaptively generated according to different users and cannot achieve cross-platform compatibility. Therefore, the generated poster images are of low quality, resulting in a poor user experience of the poster images, and in turn resulting in poor publicity and dissemination effects of the poster images.

[0006] Therefore, how to improve the quality of generated poster images has become a technical problem that needs to be urgently solved in online user-oriented interactive systems. Summary of the Invention

[0007] The present invention provides a processing method, device, computer equipment and storage medium for generating poster images, so as to solve the technical problem of low quality of generated poster images in an online user-oriented interactive system.

[0008] In a first aspect, a processing method for generating a poster image applied to a front end is provided, comprising: responding to a start instruction for generating a poster image, generating a call instruction for a preset back end, wherein the call instruction includes a preset front end user identifier corresponding to the front end user; transmitting the call instruction to the preset back end, and then the preset back end customizes the initial poster copy and display features corresponding to the preset front end user identifier according to the call instruction and the preset front end user identifier, and returns the initial poster copy and the display features; obtaining the initial poster copy and the display features, and determining the display environment corresponding to the front end user; determining a target poster copy based on the display environment and according to the initial poster copy and the display features; determining a background image according to the preset front end user identifier, and displaying the target poster copy on the background image to obtain a target poster image.

[0009] In the second aspect, a processing method for generating poster images applied to a back-end is provided, comprising: receiving a call instruction for a preset front-end to generate a poster image, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user; obtaining user information data corresponding to the front-end user based on the preset front-end user identifier; determining information keywords based on the user information data; generating initial poster copy and display features based on the information keywords and a preset deep learning model; returning the initial poster copy and the display features to the preset front-end according to the call instruction, and then the preset front-end customizes and generates a target poster image corresponding to the preset front-end based on the initial poster copy and the display features.

[0010] In a third aspect, a processing device for generating poster images applied to a front end is provided, comprising: a first generation module for responding to a start instruction for generating a poster image and generating a call instruction for a preset back end, wherein the call instruction includes a preset front end user identifier corresponding to the front end user; a transmission module for transmitting the call instruction to the preset back end, and then the preset back end customizes the initial poster copy and display features corresponding to the preset front end user identifier according to the call instruction and the preset front end user identifier, and returns the initial poster copy and the display features; a first acquisition module for acquiring the initial poster copy and the display features, and determining the display environment corresponding to the front end user; a first determination module for determining the target poster copy based on the display environment and according to the initial poster copy and the display features; a first display module for determining a background image according to the preset front end user identifier, and displaying the target poster copy on the background image to obtain a target poster image.

[0011] In a fourth aspect, a processing device for generating poster images applied to a back-end is provided, comprising: a receiving module for receiving a call instruction for a preset front-end to generate a poster image, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user; a second acquisition module for acquiring user information data corresponding to the front-end user based on the preset front-end user identifier; a second determination module for determining information keywords based on the user information data; a first generation module for generating initial poster copy and display features based on the information keywords and based on a preset deep learning model; a return module for returning the initial poster copy and the display features to the preset front-end according to the call instruction, and then the preset front-end customizes and generates a target poster image corresponding to the preset front-end based on the initial poster copy and the display features.

[0012] In a fifth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the processing method for generating the poster image applied to the front end are implemented, or the steps of the processing method for generating the poster image applied to the back end are implemented.

[0013] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the processing method for generating the poster image applied to the front end, or implements the steps of the processing method for generating the poster image applied to the back end.

[0014] In the scheme implemented by the above-mentioned poster image generation processing method, device, computer equipment and storage medium, the method communicates with the server through the network through the client, and the server receives the call to generate the poster image through the client, and obtains the user information of the retained front-end user according to the call, and customizes the poster copy and display features suitable for the current front-end user according to the user information. The front-end then customizes and displays the target poster suitable for the front-end user according to the poster copy and display features, realizes the customization of poster copy according to user information, and customizes the display according to the display environment corresponding to the front-end device, which not only realizes the customization and personalized display of poster images for the front-end user's own characteristics, but also solves the compatibility problem of poster images in the platforms corresponding to different terminals, improves the cross-platform compatibility and adaptability of poster images, improves the generation quality of poster images, and can improve the interactive effect of online user-oriented interactive systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of an application environment of a processing method for generating a poster image in an embodiment of the present invention;

[0017] Figure 2 A flowchart of a method for generating a poster image applied to a front end according to an embodiment of the present invention is provided;

[0018] Figure 3 A flowchart of a method for generating a poster image in a back-end according to an embodiment of the present invention;

[0019] Figure 4 A schematic block diagram of a processing device for generating a poster image at a front end according to an embodiment of the present invention;

[0020] Figure 5 A schematic block diagram of a processing device for generating poster images at the back end provided by an embodiment of the present invention;

[0021] Figure 6 is a structural diagram of a computer device in one embodiment of the present invention;

[0022] Figure 7 FIG. 2 is another structural diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0025] An embodiment of the present invention provides a processing method for generating poster images, which can be applied to computer devices including but not limited to tablet computers, desktop computers, servers, cloud platforms, etc., and can be used when generating poster images based on online user-oriented interactive systems in fields including but not limited to the financial field and medical health field.

[0026] Faced with the technical problem of low quality of poster images generated in traditional technologies, the inventors proposed a processing method for poster image generation in an embodiment of the present invention. The core idea of ​​the embodiment of the present invention is: in a user-oriented interactive system, the front end initiates a call to generate poster images based on the interacting front-end user, and the back end customizes and generates poster copy and display features that are suitable for the current front-end user based on the call and the user information of the front-end user. The front end customizes and displays the target poster image that is suitable for the front-end user based on the poster copy and display features, which can improve the generation quality of the poster image.

[0027] In one embodiment, the poster image generation processing method provided by the embodiment of the present invention can be applied to Figure 1 In an application environment, the client communicates with the server via a network. The server receives a call to generate a poster image through the client, and based on the call, obtains the user information of the retained front-end user, and customizes the poster text and display features that are suitable for the current front-end user based on the user information. The front-end then customizes and displays the target poster that is suitable for the front-end user based on the poster text and display features. In an embodiment of the present invention, the above scheme can be used to generate poster images for application scenarios of online user-oriented interactive systems such as insurance purchase, bank transfer, physical examination activities or important node activities, realizing customized poster text based on user information, and customized display based on the display environment such as the display device corresponding to the front-end device and the front-end user characteristics. This not only realizes the customization and personalized display of the poster image based on the front-end user's own characteristics, but also solves the compatibility problem of the poster image between the platforms corresponding to different terminals, improves the cross-platform compatibility and adaptability of the poster image, and improves the generation quality of the poster image. Among them, the client can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented as an independent server or a server cluster or cloud platform composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0028] The following embodiments of the present invention are described in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0029] See also Figure 2 , Figure 2 This is a flow chart of a processing method for generating poster images applied to a front end according to an embodiment of the present invention. Figure 2 As shown, the method is applied to the front end, and the method includes but is not limited to the following steps S21-S25:

[0030] S21. In response to the start instruction generated by the poster image, generate a preset backend calling instruction, wherein the calling instruction includes a preset front-end user identifier corresponding to the front-end user.

[0031] Explanatory note, in an online user-oriented interactive system, when a front-end user performs a corresponding operation on a front-end device and the generation of a corresponding poster image is set, the operation triggers the generation of a poster image. After the user performs the above operation, the generation of the poster image is started. The front-end device responds to the start instruction for the poster image generation and generates a call instruction for the preset back-end. The call instruction represents the call of the front-end to the back-end. The call instruction can also be called a request, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user. The preset front-end user identifier represents an identifier pre-set by the front-end user. The preset front-end user identifier includes but is not limited to the front-end user's account login account, mobile phone number, email address, and other identifiers that uniquely identify the front-end user. The front end can also be called a terminal, client, or user end. The front end can be but is not limited to various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The back end can also be called a server end or background. The back end can be but is not limited to an independent server, server cluster, or cloud platform.

[0032] For example, in the insurance field, after an insurance user purchases insurance through an online user-oriented insurance interactive system such as an APP or a web page at the front end, a call instruction for the insurance backend is generated in response to the start instruction for generating a poster image to generate a poster image of the insurance user, wherein the call instruction includes a preset insurance user identifier corresponding to the insurance user.

[0033] For example, in the banking field, after a bank user makes a bank transfer through an online user-oriented banking transaction interaction system such as an APP or a web page, the user responds to the startup instruction generated by the poster image and generates a call instruction for the bank's back-end to generate a poster image of the bank user, where the call instruction includes a preset bank user identifier corresponding to the bank user.

[0034] For another example, in the field of medical health, after a physical examination user makes a physical examination appointment or checks the physical examination results through an online user-oriented physical examination interactive system such as an APP or a web page, he or she responds to the start instruction for generating a poster image and generates a call instruction for the back-end of the physical examination service unit to generate a poster image of the physical examination user, wherein the call instruction includes a preset physical examination user identifier corresponding to the physical examination user.

[0035] S22. The calling instruction is transmitted to the preset backend, and the preset backend customizes the initial poster copy and display features corresponding to the preset front-end user identifier according to the calling instruction and the preset front-end user identifier, and returns the initial poster copy and the display features.

[0036] Explanatoryally, a call instruction is transmitted to a preset backend, which then obtains user information of the frontend user corresponding to the preset frontend user identifier based on the call instruction and the preset frontend user identifier. The user information is generally collected by the frontend user through the enterprise's online channels such as enterprise APPs and web pages. The user information includes user profile information, user behavior information, user achievement information, and other front-end user information content. Based on the user information, the initial poster copy and display features corresponding to the preset front-end user identifier are customized and generated, and the initial poster copy and display features are returned to the front-end device. The initial poster copy includes but is not limited to text content such as Chinese and English, numbers, and special characters. The display features represent the display features of the initial poster copy on the generated poster image. The display features include but are not limited to the style features of the copy and user features. The style features are a combination of attributes corresponding to the font, size, color, and style of the copy. The style features include but are not limited to font category, font size, font color, whether to highlight, whether to bold, and whether to italicize. The font categories include but are not limited to Kaiti, Songti, Heiti, and Fangsong. The user features represent but are not limited to features corresponding to the personal portrait of the front-end user, such as the age, gender, and occupation of the front-end user.

[0037] For example, in the insurance field, after an insurance user purchases insurance through an online user-oriented insurance interactive system such as an APP or a web page at the front end, the insurance user responds to the startup instruction generated by the poster image, generates a call instruction for the insurance back end, and transmits the call instruction to the insurance back end. The insurance back end obtains the user information of the insurance user, and customizes and generates the initial poster copy and display features corresponding to the insurance user based on the insurance user information, and returns the initial poster copy and display features to the insurance front end. Then, the insurance front end generates a poster image for the insurance user based on the initial poster copy and display features. In other application scenarios of corresponding online user-oriented interactive systems such as banking or physical examination fields, similar processing methods are adopted and will not be repeated here.

[0038] S23. Obtain the initial poster text and the display features, and determine the display environment corresponding to the front-end user.

[0039] Explanatoryly, the front end obtains the initial poster copy and display features, and determines the display environment corresponding to the front-end user. The display environment shown represents the front-end environment in which the poster copy is displayed. The display environment includes but is not limited to the front-end device type, screen size, screen pixels, system platform, and encoding scheme. The front-end device type includes but is not limited to desktop computers, laptops, smart phones, tablets and portable wearable devices. The system platform includes but is not limited to iOS and Android systems. The relevant factors of different display environments will affect the display effect of the poster image. Generating corresponding poster images according to the display environment corresponding to the front-end user can improve the display effect of the generated poster images, thereby improving the generation quality of the poster images.

[0040] S24. Determine a target poster copy based on the display environment, the initial poster copy, and the display characteristics.

[0041] Explanatory, based on the display environment, and according to the initial poster copy and display features, the initial poster copy including the size of each character is calculated, and the display position of each character is determined based on the size of each character and display factors such as the screen size included in the display environment, thereby determining the target poster copy. The target poster copy represents the final display effect of the poster copy. The target poster copy includes but is not limited to the display position and display style of the poster copy in the poster image.

[0042] S25. Determine a background image according to the preset front-end user identifier, and display the target poster text on the background image to obtain a target poster image.

[0043] Explanatoryly, the background image is determined according to the preset front-end user identifier. The background image can be determined randomly, or the corresponding background image can be matched according to the front-end user characteristics corresponding to the preset front-end user identifier, and the target poster copy is displayed on the background image. For example, the target poster copy is drawn onto the matched background image in the order of traversal using canvas technology, and saved to the front-end device corresponding to the front-end user using a browser or other file saving API to obtain the target poster image, thereby realizing the customization and personalized generation of the poster copy of the target poster image, and the target poster image is cross-platform compatible and adaptive, so that both the content of the poster copy and the display of the poster image are highly consistent with the user's own information characteristics and the front-end device characteristics, thereby improving the generation quality of the poster image.

[0044] In an embodiment of the present invention, a call instruction for a preset backend is generated in response to a start instruction for generating a poster image, wherein the call instruction includes a preset front-end user identifier corresponding to a front-end user. The call instruction is transmitted to the preset backend, and the preset backend customizes an initial poster copy and display features corresponding to the preset front-end user identifier based on the call instruction and the preset front-end user identifier, and returns the initial poster copy and display features. The front end obtains the initial poster copy and display features, and determines a display environment corresponding to the front-end user. Based on the display environment and according to the initial poster copy and display features, a target poster copy is determined. A background image is determined according to the preset front-end user identifier, and the target poster copy is displayed on the background image to obtain a target poster image. This not only achieves customization of the poster copy according to the front-end user, but also determines the target poster copy according to the display environment corresponding to the front-end device, thereby achieving adaptive display of the poster copy. This not only achieves customized and personalized display of the poster image for the front-end user, but also solves the compatibility problem of the poster image on platforms corresponding to different terminals, thereby improving cross-platform compatibility and adaptability of the poster image. Therefore, both the content of the poster copy and the display of the poster image are highly consistent with the user's own information characteristics and the characteristics of the front-end device, thereby improving the generation quality of the poster image.

[0045] In one embodiment, determining a target poster copy based on the display environment and according to the initial poster copy and the display characteristics includes:

[0046] Determining the size of each character included in the initial poster text according to the display environment and the display characteristics, and obtaining the byte size corresponding to each character;

[0047] According to the display environment and the byte size, the display position of the character in the poster image is determined to obtain the target poster copy.

[0048] Explanatoryly, a character is a human-readable symbol, including but not limited to Chinese and English letters, numbers, punctuation marks, and Chinese characters. Different characters are usually represented by one or more bytes in a computer. A byte is the basic unit for storing and transmitting data in a computer. For example, in ASCII code, one English letter or number occupies one byte; in UTF-8 encoding, one English character occupies one byte, and one Chinese character occupies three bytes; in Unicode encoding, one English character occupies two bytes, and one Chinese character occupies two bytes.

[0049] According to the above description, based on the display environment including but not limited to the front-end device type, screen size, screen pixels, system platform, encoding scheme, and display characteristics including but not limited to age, gender, occupation, font size, font color, whether it is highlighted, whether it is bold, whether it is italic, determine the size of each character contained in the initial poster copy, and obtain the byte size corresponding to each character. Then, based on the display environment and the byte size, determine the display position of the character in the poster image, that is, the display coordinates. Finally, determine the factors affecting the display effect corresponding to the poster copy display, including but not limited to position, color, font, whether it is bold, and whether it is highlighted, and obtain the target poster copy.

[0050] Furthermore, determining the size of each character included in the initial poster text according to the display environment and the display characteristics, and obtaining the byte size corresponding to each character, includes:

[0051] Identifying character features corresponding to characters included in the initial poster copy;

[0052] Identifying style features corresponding to the initial poster copy included in the display features;

[0053] The size of each character is calculated according to the display environment, the character features, and the style features to obtain the byte size corresponding to each character.

[0054] Specifically, character features corresponding to the characters contained in the initial poster copy are identified, and character features include but are not limited to character types or character categories corresponding to Chinese and English letters, Chinese characters, numbers, special characters, and punctuation marks, and style features corresponding to the initial poster copy included in the display features are identified, and style features include but are not limited to font category, font size, font color, whether it is highlighted, whether it is bold, and whether it is italic. Then, based on the display environment, character features, and style features, different display factors are combined to specifically calculate the size of each character on the front-end device corresponding to the front-end user to obtain the byte size corresponding to each character. The determination of the byte size is personalized and tailored based on the display features and display features corresponding to the front-end user. As a result, the display of the target poster copy can be highly consistent with the user's own information features and the front-end device features, thereby improving the display effect of the poster copy, improving the quality of poster image generation, and improving the interactive effect of the online user-oriented interactive system, which is conducive to promoting business development.

[0055] The embodiment of the present invention determines the size of each character contained in the initial poster copy according to the display environment and display characteristics, obtains the byte size corresponding to each character, and then determines the display position of the character in the poster image according to the display environment and the byte size to obtain the target poster copy, thereby determining the target poster copy according to the display environment corresponding to the front-end device, and realizing adaptive display of the poster copy. On the basis of realizing the customization and personalized display of the poster copy for the front-end user, it solves the compatibility problem of the poster image in the platforms corresponding to different terminals, improves the cross-platform compatibility and adaptability of the poster image, thereby improving the generation quality of the poster image, and can improve the interactive effect of the online user-oriented interactive system, which is conducive to promoting the development of business.

[0056] See also Figure 3 , Figure 3 This is a flow chart of a method for generating a poster image in the back end provided by an embodiment of the present invention. Figure 3 As shown, the method is applied to the backend, and the method includes but is not limited to the following steps S31-S35:

[0057] S31. Receive a call instruction for a preset front-end to generate a poster image, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user.

[0058] Explanatoryally, in an online user-interactive system, the front-end device responds to a startup instruction for poster image generation and generates a call instruction for the corresponding back-end. The description of generating the call instruction is detailed in the description of the above-mentioned processing method embodiment for poster image generation applied to the front-end, which will not be repeated here. The call instruction is transmitted to the corresponding back-end, and the back-end receives the above-mentioned call instruction. The call instruction includes a preset front-end user identifier corresponding to the front-end user. The back-end can also be called a server side or a back-end. The back-end can be but not limited to an independent server, a server cluster, or a cloud platform.

[0059] For example, in the insurance field, after an insurance user purchases insurance through an online user-oriented insurance interactive system such as an APP or a web page at the front end, he responds to the startup instruction generated by the poster image, generates a call instruction for the insurance back end, and transmits the call instruction to the insurance back end. The insurance back end receives the call instruction, wherein the call instruction includes a preset insurance user identifier corresponding to the insurance user.

[0060] For example, in the banking field, after a bank user makes a bank transfer through an online user-oriented banking transaction interaction system such as an APP or a web page at the front end, he or she responds to the startup instruction generated by the poster image, generates a call instruction for the bank's back end, and transmits the call instruction to the bank's back end. The bank's back end receives the call instruction, where the call instruction includes the preset bank user identifier corresponding to the bank user.

[0061] For another example, in the field of medical health, after a physical examination user makes a physical examination appointment or checks the physical examination results through an online user-oriented physical examination interactive system such as an APP or a web page, he or she responds to the start instruction generated by the poster image, generates a call instruction for the back end of the physical examination service unit, and transmits the call instruction to the back end of the physical examination service unit. The back end of the physical examination service unit receives the call instruction, wherein the call instruction includes the preset physical examination user identifier corresponding to the physical examination user.

[0062] S32. Obtain user information data corresponding to the front-end user according to the preset front-end user identifier.

[0063] Explanatoryly, the backend obtains the user information of the front-end user corresponding to the preset front-end user identifier based on the calling instruction and the preset front-end user identifier. The user information is generally collected through the front-end user on the company's online channels such as the enterprise APP and web pages. The user information includes but is not limited to user profile information, user behavior information, user achievement information and other front-end user information content. User profile information is not limited to age, gender, occupation, and education level. User behavior information is not limited to browsing information and consultation information. User achievement information is not limited to purchase information, transaction information, and refueling service information.

[0064] For example, in the insurance field, based on the preset insurance user identifier corresponding to the insurance user, the user profile information corresponding to the insurance user, including but not limited to age, gender, occupation, and education level, as well as the insurance user behavior information corresponding to browsing insurance products and consulting insurance products, and the insurance user achievement information corresponding to purchasing insurance products and enjoying insurance rights and interests are obtained.

[0065] For example, in the banking field, based on the preset bank user identifier corresponding to the bank user, the user personal profile information corresponding to the bank user, including but not limited to age, gender, occupation, and education level, as well as the bank user behavior information corresponding to but not limited to browsing bank products and consulting bank products, and the bank user achievement information corresponding to but not limited to deposits, withdrawals, loans, and purchases of bank wealth management products are obtained.

[0066] For example, in the field of medical health, based on the preset physical examination user identifier corresponding to the physical examination user, the user personal profile information corresponding to the physical examination user, including but not limited to age, gender, occupation, and educational background, as well as the physical examination user behavior information corresponding to browsing physical examination service products and consulting physical examination service products, and the physical examination user achievement information corresponding to conducting physical examination activities and maintenance activities are obtained.

[0067] S33. Determine information keywords based on the user information data.

[0068] Explanatory, based on a number of user information data, an information keyword determination algorithm including but not limited to TF-IDF (Term Frequency-Inverse Document Frequency), TextRank algorithm, RNN (recurrent neural network), BERT model (Bidirectional Encoder Representations from Transformers), and co-occurring vocabulary is used to determine information keywords, thereby screening out and predicting the main and key information content corresponding to the front-end user, and then generating corresponding poster copy based on the information keywords. This not only enables customization of poster copy according to the front-end user, and realizes tailor-made and personalized poster copy, making the poster copy adaptive to the front-end user, but also improves the fit between the poster copy and the user information characteristics corresponding to the front-end user, and improves the generation quality of the poster image.

[0069] S34. Generate initial poster copy and display features based on the information keywords and a preset deep learning model.

[0070] Explanatory speaking, a pre-set deep learning model, i.e., a preset deep learning model, refers to a deep learning model that outputs corresponding poster copy and display features based on user information data. The preset deep learning model includes but is not limited to the Transformer model and the BERT model.

[0071] Based on the above ideas and settings, and according to information keywords, and based on the preset deep learning model, the initial poster copy and display features corresponding to the preset front-end user identification are customized and generated. The initial poster copy refers to the copy text that is not designed with display features, wherein the initial poster copy includes but is not limited to Chinese, English, numbers, special characters and other text content, and the display features represent the design features of the initial poster copy displayed on the generated poster image. The display features include but are not limited to the style features and user features of the copy. The style features include but are not limited to the combination of attributes corresponding to the font, size, color, and style of the copy. The style features include but are not limited to font category, font size, font color, whether it is highlighted, whether it is bold, whether it is italic, and the font category includes but is not limited to Kaiti, Songti, Heiti, and Fangsong. The user features represent but are not limited to the features corresponding to the personal portrait of the front-end user, such as the age, gender, and occupation of the front-end user.

[0072] For example, in the field of auto insurance, based on the auto insurance user information data corresponding to the auto insurance user, the corresponding initial poster copy can be "Come on hero, you are an expert in oil car lover!", and if the auto insurance user is a business man, the display features can be biased towards business style; if the auto insurance user is a young woman, the display features can be biased towards youthful and beautiful style, for example, the poster copy font uses pink.

[0073] S35. According to the calling instruction, the initial poster copy and the display features are returned to the preset front end, and then the preset front end customizes and generates the target poster image corresponding to the preset front end according to the initial poster copy and the display features.

[0074] Explanatoryally, after the backend customizes and generates the initial poster copy and display features based on the user information data corresponding to the front-end user, it returns the initial poster copy and display features to the preset front-end according to the calling instruction. Then, the preset front-end customizes and generates the target poster image corresponding to the preset front-end based on the initial poster copy and display features. For details, please refer to the description of the above-mentioned processing method embodiment for poster image generation applied to the front-end, which will not be repeated here.

[0075] In an embodiment of the present invention, a call instruction for generating a poster image is received by a preset front-end, the call instruction includes a preset front-end user identifier corresponding to a front-end user, and user information data corresponding to the front-end user is obtained based on the preset front-end user identifier. Information keywords are then determined based on the user information data, and initial poster text and display features are generated based on the information keywords and a preset deep learning model. Finally, according to the call instruction, the initial poster text and display features are returned to the preset front-end, and the preset front-end customizes and generates a target poster image corresponding to the preset front-end based on the initial poster text and display features. A poster text that is highly matched with the front-end user can be obtained based on existing user information, thereby achieving customization of the poster text according to the front-end user. The preset front-end customizes and generates the target poster image corresponding to the preset front-end based on the initial poster text and display features, thereby achieving customization of the poster text according to the front-end user and customization of the poster image according to the front-end device. This not only achieves customization and personalized display of the poster image for the front-end user, but also solves the compatibility problem of the poster image on the platforms corresponding to different terminals. Therefore, both the content of the poster text and the display of the poster image are highly consistent with the user's own information characteristics and the characteristics of the front-end device, thereby improving the generation quality of the poster image.

[0076] In one embodiment, determining information keywords based on the user information data includes:

[0077] Segmenting the user information data to obtain a number of vocabulary units;

[0078] Determining co-occurring words and their word weights based on the word units;

[0079] Constructing a co-occurrence vocabulary network graph based on the co-occurrence vocabulary and the vocabulary weights, wherein the co-occurrence vocabulary network graph includes graph nodes;

[0080] Calculating the node weights corresponding to the graph nodes;

[0081] Information keywords are determined according to the node weights.

[0082] Explanation-wise, the user information data is segmented using methods including but not limited to jieba segmentation, and stop words are removed to obtain several vocabulary units, which are tokens. In NLP, a token is the smallest semantic unit, that is, the smallest meaningful unit in a text.

[0083] Then, based on the vocabulary units, the co-occurring words and their lexical weights are determined. Among them, co-occurring words, also known as co-occurring words or lexical co-occurrence, are called co-occurrence in English. In Natural Language Processing (NLP), word co-occurrence refers to the situation where two or more words appear at the same time in a certain context. The lexical weight corresponding to the co-occurring words represents the proportion of the co-occurring words in all co-occurring words. Furthermore, based on the vocabulary units, different vocabulary units are grouped into independent semantic units with clear semantics and logic using methods including but not limited to preset templates, and the independent semantic units are used as co-occurring vocabulary. Thus, by constructing co-occurring vocabulary, co-occurring vocabulary can be determined and its vocabulary weight can be calculated. For example, a "purchase () ()" template is pre-set. If the vocabulary units include "refueling", "car insurance", "service", and "product", semantic units corresponding to the co-occurring vocabulary "purchase refueling service" and "purchase car insurance product" can be constructed. The constructed co-occurring vocabulary can represent but not limited to the user behavior, user achievements, user trajectory, and user needs of the front-end user, corresponding to a certain aspect of the user, and can more clearly express the information content of the front-end user, and calculate the vocabulary weight of the co-occurring vocabulary corresponding to "purchase refueling service" and "purchase car insurance product". The weight calculation method of "purchase refueling service" and "purchase car insurance product" is to count the proportion of "purchase refueling service" and "purchase car insurance product" in the above-mentioned user information data. The weight of "purchase refueling service" and "purchase car insurance product" in the above-mentioned user information data can be used as the weight of "purchase refueling service" and "purchase car insurance product" in the above-mentioned user information data according to the proportion of "refueling" and "car insurance" in the above-mentioned user information data.

[0084] According to the co-occurring words and word weights, the co-occurring words are analyzed using methods including but not limited to co-occurrence and clustering, and a co-occurring word network graph is constructed, wherein the co-occurring word network graph includes graph nodes. The co-occurring word network graph is also called a co-occurrence network, a word co-linear network graph, a co-word network graph or a semantic co-occurrence network graph. It is a knowledge network graph constructed based on the co-occurrence relationship of words in text data. This network graph uses words (or "knowledge units") as nodes and the co-occurrence relationship between words as edges, and displays the correlation and structural characteristics between words, as well as the degree of word co-occurrence in a visual way.

[0085] According to the co-occurring vocabulary network graph, and based on the weights of the graph node and its adjacent nodes, the node weight corresponding to the graph node is calculated, and then the information keyword is determined based on the node weight. Exemplarily, the co-occurring vocabulary is used as the graph node of the co-occurring vocabulary network graph, the vocabulary weight corresponding to the co-occurring vocabulary is used as the value of the graph node, and based on the values ​​of the graph node and its adjacent graph nodes, for example, the ratio of the value of the graph node to the sum of all values ​​corresponding to the graph node and its adjacent graph nodes is calculated to calculate the node weight corresponding to the graph node, and the ratio is used as the graph node weight. Then, based on the node weight, that is, the size of the node weight, several graph nodes are selected, and the co-occurring vocabulary corresponding to the graph nodes is used as the information keyword, thereby determining the information keyword.

[0086] Furthermore, determining information keywords based on the node weights includes:

[0087] Determine the graph node with the highest node weight and use it as the target graph node;

[0088] The co-occurring words corresponding to the target graph nodes are used as information keywords.

[0089] Specifically, the graph node with the highest node weight is determined and used as the target graph node, and the co-occurring words corresponding to the target graph node are used as information keywords, so as to screen out the information keywords with the highest degree of fit with the front-end users, and then generate corresponding poster copy based on the information keywords. The poster copy also has the highest degree of fit with the front-end users, so that the target poster copy is highly consistent with the user's own information characteristics, which can enhance the publicity effect of the poster copy, improve the quality of poster image generation, and improve the interactive effect of the online user-oriented interactive system, which is conducive to promoting business development.

[0090] In an embodiment of the present invention, user information data is segmented to obtain a number of vocabulary units, and then co-occurring vocabulary and its vocabulary weights are determined based on the vocabulary units, and then a co-occurring vocabulary network graph is constructed based on the co-occurring vocabulary and the vocabulary weights, wherein the co-occurring vocabulary network graph includes graph nodes, and the node weights corresponding to the graph nodes are calculated, and finally, information keywords are determined based on the node weights. By means of constructing co-occurring vocabulary and analyzing the co-occurring vocabulary with the help of the co-occurring vocabulary network graph, the accuracy of information keyword screening can be improved, and the customized poster copy can be further made to have the highest degree of fit with the front-end user, so that the target poster copy is highly consistent with the user's own information characteristics, which can improve the publicity effect of the poster copy, achieve an improvement in the quality of poster image generation, and improve the interactive effect of the online user-oriented interactive system.

[0091] In one embodiment, returning the initial poster text and the display features to the preset front end according to the calling instruction includes:

[0092] Convert the initial poster text into a JSON raw string to obtain an initial poster text string, and convert the display features into a JSON raw string to obtain a display feature string;

[0093] Perform JSON assembly on the initial poster text string and the display feature string to obtain an assembled string;

[0094] According to the calling instruction, the assembled character string is returned to the preset front end.

[0095] Explanatory, according to the calling instruction, when the initial poster copy and display features are returned to the preset front end, the JavaScript object corresponding to the initial poster copy is first converted into a JSON raw string to obtain the initial poster copy string, and the JavaScript object corresponding to the display features is converted into a JSON raw string to obtain the display feature string, wherein the JSON raw string refers to unparsed JSON data represented in string form. The raw value of the string usually has better performance than the string object, and JSON is easy to read, write and machine parse, which facilitates cross-platform data exchange.

[0096] Then the initial poster copy string and the display feature string are assembled into JSON. Tools including but not limited to arrays can be used to assemble the initial poster copy string and the display feature string into JSON, so that the initial poster copy string and the display feature string are organized into a whole according to certain rules to obtain an assembled string. Then, according to the calling instruction, the assembled string is returned to the preset front end, and then the preset front end parses the assembled string to obtain the initial poster copy and display features, and generates a poster image based on the initial poster copy and display features, thereby using the js original string. The preset front-end API can perform special processing on different character formats according to the display environment of the front end, and perform corresponding analysis and calculation for different character features, which can solve the compatibility problem of the API caused by the traditional technology that only measures the width of characters in a single platform range, and solves the compatibility problem of poster images on platforms corresponding to different terminals.

[0097] In an embodiment of the present invention, the initial poster copy is converted into a JSON raw string to obtain an initial poster copy string, and the display feature is converted into a JSON raw string to obtain a display feature string, and then the initial poster copy string and the display feature string are JSON assembled to obtain an assembled string, and then according to the calling instruction, the assembled string is returned to the preset front end, and then the preset front end customizes and generates a target poster image corresponding to the preset front end according to the preset front end according to the initial poster copy and the display feature, so that the preset front end can perform corresponding processing on different character formats according to the assembled string, and perform corresponding analysis and calculation for different character features, which can solve the compatibility problem of the API caused by the traditional technology of only measuring the width of characters within a single platform range, solve the compatibility problem of poster images in the platforms corresponding to different terminals, improve the cross-platform compatibility and adaptability of poster images, and improve the aesthetics and quality of generated poster images, thereby improving the generation quality of poster images.

[0098] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0099] In one embodiment, a processing device for generating poster images applied to a front end is provided. The processing device for generating poster images applied to a front end corresponds to the processing method for generating poster images applied to a front end in the above embodiment. Figure 4 , Figure 4 This is a schematic block diagram of a processing device for generating poster images for a front end according to an embodiment of the present invention. Figure 4As shown, the processing device 40 for generating a poster image for the front end includes a first generating module 41, a transmitting module 42, a first acquiring module 43, a first determining module 44 and a first display module 45. The above functional modules are described in detail as follows:

[0100] The first generating module 41 is configured to generate a preset backend calling instruction in response to the start instruction for poster image generation, wherein the calling instruction includes a preset front-end user identifier corresponding to the front-end user;

[0101] The transmission module 42 is configured to transmit the call instruction to the preset backend, and the preset backend customizes the initial poster copy and display features corresponding to the preset frontend user identifier according to the call instruction and the preset frontend user identifier, and returns the initial poster copy and the display features;

[0102] A first acquisition module 43 is configured to acquire the initial poster text and the display features, and determine the display environment corresponding to the front-end user;

[0103] A first determining module 44 is configured to determine a target poster copy based on the display environment, the initial poster copy, and the display characteristics;

[0104] The first display module 45 is used to determine a background image according to the preset front-end user identifier, and display the target poster text on the background image to obtain a target poster image.

[0105] In one embodiment, the first determining module 44 includes:

[0106] A first determining submodule is configured to determine the size of each character included in the initial poster text according to the display environment and the display characteristics, and obtain the byte size corresponding to each character;

[0107] The second determining submodule is used to determine the display position of the character in the poster image according to the display environment and the byte size, and obtain the target poster copy.

[0108] In one embodiment, the first determining submodule includes:

[0109] A first recognition submodule is used to recognize character features corresponding to characters included in the initial poster copy;

[0110] A second identification submodule is configured to identify style features corresponding to the initial poster copy included in the display features;

[0111] The first calculation submodule is used to calculate the size of each character according to the display environment, the character features, and the style features, and obtain the byte size corresponding to each character.

[0112] The embodiment of the present invention provides a processing device for generating poster images for the front end, which generates a call instruction of a preset back end by responding to a start instruction generated by the poster image, wherein the call instruction includes a preset front end user identifier corresponding to the front end user, transmits the call instruction to the preset back end, and the preset back end customizes the initial poster copy and display features corresponding to the preset front end user identifier according to the call instruction and the preset front end user identifier, and returns the initial poster copy and display features, and the front end obtains the initial poster copy and display features, and determines the display environment corresponding to the front end user, based on the display environment and according to the initial poster copy and display features, determines the target poster copy, and according to the preset The front-end user is identified, the background image is determined, and the target poster copy is displayed on the background image to obtain the target poster image. This not only realizes the customization of poster copy according to the front-end user, but also determines the target poster copy according to the display environment corresponding to the front-end device, and realizes the adaptive display of poster copy. It not only realizes the customization and personalized display of poster images for front-end users, but also solves the compatibility problem of poster images in the platforms corresponding to different terminals, and improves the cross-platform compatibility and adaptability of poster images. Therefore, whether it is from the content of the poster copy or the display of the poster image, it is highly consistent with the user's own information characteristics and the front-end device characteristics, thereby improving the generation quality of the poster image.

[0113] In one embodiment, a processing device for generating poster images in the back end is provided. The processing device for generating poster images in the back end corresponds to the processing method for generating poster images in the back end in the above embodiment. Figure 5 , Figure 5 This is a schematic block diagram of a processing device for generating poster images at the back end provided by an embodiment of the present invention. Figure 5 As shown, the processing device 50 for generating poster images at the back end includes a receiving module 51, a second obtaining module 52, a second determining module 53, a first generating module 54 and a returning module 55. The above functional modules are described in detail as follows:

[0114] The receiving module 51 is configured to receive a call instruction for generating a poster image from a preset front-end, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user;

[0115] The second acquisition module 52 is used to acquire user information data corresponding to the front-end user according to the preset front-end user identifier;

[0116] A second determining module 53 is configured to determine information keywords based on the user information data;

[0117] A first generation module 54 is configured to generate initial poster copy and display features based on the information keywords and a preset deep learning model;

[0118] The return module 55 is used to return the initial poster copy and the display features to the preset front end according to the calling instruction, and then the preset front end customizes and generates the target poster image corresponding to the preset front end according to the initial poster copy and the display features.

[0119] In one embodiment, the second determining module 53 includes:

[0120] A word segmentation submodule, configured to segment the user information data into words to obtain a plurality of vocabulary units;

[0121] A third determining submodule is used to determine co-occurring words and their word weights based on the word units;

[0122] A construction submodule, configured to construct a co-occurrence vocabulary network graph based on the co-occurrence vocabulary and the vocabulary weights, wherein the co-occurrence vocabulary network graph includes graph nodes;

[0123] A second calculation submodule is used to calculate the node weight corresponding to the graph node;

[0124] The fourth determining submodule is configured to determine information keywords according to the node weights.

[0125] In one embodiment, the fourth determining submodule includes:

[0126] A fifth determination submodule, configured to determine the graph node with the highest node weight and use it as the target graph node;

[0127] The sixth determination submodule is configured to use the co-occurring words corresponding to the target graph nodes as information keywords.

[0128] An embodiment of the present invention provides a processing device for generating a poster image for a back-end. The device receives a call instruction for generating a poster image from a preset front-end, the call instruction including a preset front-end user identifier corresponding to a front-end user, obtains user information data corresponding to the front-end user based on the preset front-end user identifier, determines information keywords based on the user information data, generates initial poster text and display features based on the information keywords, and finally returns the initial poster text and display features to the preset front-end. The preset front-end then customizes and generates a target poster image corresponding to the preset front-end based on the initial poster text and display features. The device can obtain a poster text that is highly matched with the front-end user based on the existing user information, thereby customizing the poster text according to the front-end user. The device then customizes and generates the target poster image corresponding to the preset front-end based on the initial poster text and display features, thereby customizing the poster text according to the front-end user and customizing and displaying the poster image according to the front-end device. This not only realizes tailor-made and personalized display of the poster image for the front-end user, but also solves the compatibility problem of the poster image on the platforms corresponding to different terminals. Therefore, both the content of the poster text and the display of the poster image are highly consistent with the user's own information features and the front-end device features, thereby improving the generation quality of the poster image.

[0129] Regarding the specific limitations of the above-mentioned processing device for generating poster images at the front end or the processing device for generating poster images at the back end, please refer to the limitations of the processing method for generating poster images at the front end or the processing method for generating poster images at the back end in the above text, which will not be repeated here. Each module in the above-mentioned processing device for generating poster images at the front end or the processing device for generating poster images at the back end can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0130] In one embodiment, a computer device is provided. The computer device may be a server, i.e., a backend, and its internal structure may be as shown in FIG. Figure 6 As shown, Figure 61 is a schematic diagram of the structure of a computer device in one embodiment of the present invention. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the server side of a processing method for generating a poster image.

[0131] In one embodiment, a computer device is provided. The computer device may be a client, i.e., a front end. The internal structure diagram thereof may be as follows: Figure 7 As shown, Figure 7 1 is another structural schematic diagram of a computer device according to one embodiment of the present invention. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When executed by the processor, the computer program implements the client-side functions or steps of a method for generating a poster image.

[0132] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the processing method for generating a poster image applied to the front end described in the above embodiment are implemented, or the steps of the processing method for generating a poster image applied to the back end described in the above embodiment are implemented.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the processing method for generating a poster image applied to the front end described in the above embodiment are implemented, or the steps of the processing method for generating a poster image applied to the back end described in the above embodiment are implemented.

[0134] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0135] Those skilled in the art will appreciate that all or part of the processes in the above-described embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described embodiments. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0136] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0137] The software tools or components not produced by our company that appear in the embodiments of the present invention are for illustrative purposes only and do not represent actual use.

[0138] The relevant data collection appearing in the embodiments of the present invention complies with the requirements of relevant laws and regulations, such as China's "Personal Information Protection Law", GDPR (EU General Data Protection Regulation) or information security standards of other countries and regions.

[0139] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for generating a poster image, applied to the front end, characterized in that: include: In response to the start instruction generated by the poster image, a call instruction for a preset backend is generated, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user; The calling instruction is transmitted to the preset backend, and the preset backend customizes the initial poster copy and display features corresponding to the preset front-end user identifier according to the calling instruction and the preset front-end user identifier, and returns the initial poster copy and the display features; Obtaining the initial poster text and the display features, and determining the display environment corresponding to the front-end user; Determining a target poster copy based on the display environment, the initial poster copy, and the display characteristics; According to the preset front-end user identifier, a background image is determined, and the target poster text is displayed on the background image to obtain a target poster image.

2. The method for generating a poster image according to claim 1, wherein: Determining a target poster copy based on the display environment, the initial poster copy, and the display characteristics includes: Determining the size of each character included in the initial poster text according to the display environment and the display characteristics, and obtaining the byte size corresponding to each character; According to the display environment and the byte size, the display position of the character in the poster image is determined to obtain the target poster copy.

3. The method for generating a poster image according to claim 2, wherein: Determining the size of each character included in the initial poster text according to the display environment and the display characteristics, and obtaining the byte size corresponding to each character, including: Identifying character features corresponding to characters included in the initial poster copy; Identifying style features corresponding to the initial poster copy included in the display features; The size of each character is calculated according to the display environment, the character features, and the style features to obtain the byte size corresponding to each character.

4. A method for processing poster image generation, applied to the back end, characterized in that: include: Receiving a call instruction for a preset front-end to generate a poster image, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user; According to the preset front-end user identifier, obtaining user information data corresponding to the front-end user; Determining information keywords based on the user information data; Generate initial poster copy and display features based on the information keywords and a preset deep learning model; According to the calling instruction, the initial poster copy and the display features are returned to the preset front end, and then the preset front end customizes and generates the target poster image corresponding to the preset front end according to the initial poster copy and the display features.

5. The method for generating a poster image according to claim 4, wherein: Determining information keywords based on the user information data includes: Segmenting the user information data to obtain a number of vocabulary units; Determining co-occurring words and their word weights based on the word units; Constructing a co-occurrence vocabulary network graph based on the co-occurrence vocabulary and the vocabulary weights, wherein the co-occurrence vocabulary network graph includes graph nodes; Calculating the node weights corresponding to the graph nodes; Information keywords are determined according to the node weights.

6. The method for generating a poster image according to claim 5, wherein: Determine information keywords based on the node weights, including: Determine the graph node with the highest node weight and use it as the target graph node; The co-occurring words corresponding to the target graph nodes are used as information keywords.

7. A poster image generation processing device, applied to the front end, characterized in that: include: A first generating module is configured to generate a preset backend calling instruction in response to a start instruction for generating a poster image, wherein the calling instruction includes a preset front-end user identifier corresponding to the front-end user; a transmission module, configured to transmit the call instruction to the preset backend, and then the preset backend customizes the initial poster copy and display features corresponding to the preset front-end user identifier according to the call instruction and the preset front-end user identifier, and returns the initial poster copy and the display features; A first acquisition module is used to acquire the initial poster text and the display features, and determine the display environment corresponding to the front-end user; A first determining module is configured to determine a target poster copy based on the display environment, the initial poster copy, and the display characteristics; The first display module is used to determine the background image according to the preset front-end user identifier, and display the target poster text on the background image to obtain the target poster image.

8. A poster image generation processing device, applied to the back end, characterized in that: include: A receiving module, configured to receive a call instruction for generating a poster image from a preset front-end, wherein the call instruction includes a preset front-end user identifier corresponding to the front-end user; A second acquisition module is used to acquire user information data corresponding to the front-end user according to the preset front-end user identifier; A second determining module, configured to determine information keywords based on the user information data; A first generation module is used to generate initial poster copy and display features according to the information keywords and based on a preset deep learning model; The return module is used to return the initial poster copy and the display features to the preset front end according to the calling instruction, and then the preset front end customizes and generates the target poster image corresponding to the preset front end according to the initial poster copy and the display features.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the steps of the processing method for generating the poster image applied to the front end as claimed in any one of claims 1 to 3, or implements the steps of the processing method for generating the poster image applied to the back end as claimed in any one of claims 4 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the processing method for generating the poster image applied to the front end as claimed in any one of claims 1 to 3 are implemented, or the steps of the processing method for generating the poster image applied to the back end as claimed in any one of claims 4 to 6 are implemented.

Images