Special-shaped character generation method and device

Abstract

The embodiment of the invention provides a special-shaped character generation method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of computers. The method comprises the steps of obtaining text content input by a target object; selecting a plurality of target symbols from a special-shaped character generation library according to the text content; wherein the special-shaped character generation library is configured with a plurality of selectable symbols, and at least part of the selectable symbols are obtained by decomposing a special-shaped character sample; and combining the plurality of target symbols to generate at least one target special-shaped character associated with the text content. According to the technical scheme provided by the embodiment of the invention, the special-shaped characters meeting the requirements of the user can be automatically generated according to the description of the user, so that the automation level and efficiency of the special-shaped character generation method are improved, and the personalized level of special-shaped character generation is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of computer technology, and in particular, to a method, apparatus, computer device, computer-readable storage medium, and computer program product for generating special-shaped characters. Background Art

[0002] With the development of social media, people increasingly use special-shaped characters for communication to increase the fun of communication. Special-shaped characters, also known as variant characters or artistic characters, are a special form of characters formed by deforming, distorting, or artistically processing traditional character forms. There are various categories of special-shaped characters. For example, emoticons are one category of special-shaped characters. Emoticons are formed by combining keyboard symbols. However, the creation of special-shaped characters such as emoticons often relies on manual design, with low levels of automation and intelligence, and it is difficult to meet the personalized needs of users.

[0003] It should be noted that the above content is not necessarily prior art and is not used to limit the patent protection scope of the present application. Summary of the Invention

[0004] Embodiments of the present application provide a method, apparatus, computer device, computer-readable storage medium, and computer program product for generating special-shaped characters to solve or alleviate one or more of the above-mentioned technical problems.

[0005] One aspect of embodiments of the present application provides a method for generating special-shaped characters, the method including:

[0006] Obtaining text content input by a target object;

[0007] According to the text content, selecting a plurality of target symbols from a special-shaped character generation library; wherein, the special-shaped character generation library is configured with a plurality of selectable symbols, and at least some of the selectable symbols are obtained by decomposing special-shaped character samples;

[0008] Combining the plurality of target symbols to generate at least one target special-shaped character associated with the text content.

[0009] Optionally, the target special-shaped character includes a target emoticon, and the target emoticon includes a plurality of component parts; according to the text content, selecting a plurality of target symbols from the special-shaped character generation library includes:

[0010] According to the text content, selecting a target symbol for each of the component parts respectively to obtain the plurality of target symbols.

[0011] Optionally, in the special-shaped character generation library, each of the component parts is associated with one or more selectable symbol sequences;

[0012] According to the text content, select a target symbol for each of the constituent parts to obtain the multiple target symbols, including:

[0013] Determine a target optional symbol sequence for each of the constituent parts;

[0014] According to the target optional symbol sequence of each of the constituent parts, select a target symbol for each of the constituent parts.

[0015] Optionally, a target constituent part among the multiple constituent parts is associated with multiple optional symbol sequences, and the multiple optional symbol sequences of the target constituent part respectively correspond to different attributes;

[0016] Determine a target optional symbol sequence for each of the constituent parts, including:

[0017] Select a target optional symbol sequence from the multiple optional symbol sequences of the target constituent part according to the target attribute of the text content; wherein, the selected target optional symbol sequence for the target constituent part corresponds to the target attribute.

[0018] Optionally, an optional symbol sequence is obtained through the following operations:

[0019] Obtain multiple variant character samples with the same attribute;

[0020] Through respectively identifying and decomposing the multiple variant character samples, obtain multiple sample symbols;

[0021] Aggregate the sample symbols corresponding to the same constituent part among the multiple sample symbols to construct the corresponding optional symbol sequence.

[0022] Optionally, combine the multiple target symbols to generate at least one target variant character associated with the text content, including:

[0023] Obtain the arrangement mode of the multiple constituent parts;

[0024] According to the arrangement mode, arrange the multiple target symbols to generate at least one of the target variant characters.

[0025] Optionally, the method further includes:

[0026] Generate multiple function interfaces, the function interfaces are connected to the variant character generation library, and each function interface corresponds to a keyword;

[0027] Wherein, the function interface is used to return at least one of the target variant characters associated with the keyword when being called.

[0028] Another aspect of the embodiments of the present application provides a device for generating special-shaped characters, the device comprising:

[0029] An acquisition module, which acquires the text content input by a target object;

[0030] A selection module, configured to select a plurality of target symbols from a special-shaped character generation library according to the text content; wherein, the special-shaped character generation library is configured with a plurality of selectable symbols, and at least some of the selectable symbols are obtained by decomposing special-shaped character samples;

[0031] A combination module, configured to combine the plurality of target symbols to generate at least one target special-shaped character associated with the text content.

[0032] Another aspect of the embodiments of the present application provides a computer device, comprising:

[0033] At least one processor; and

[0034] A memory communicatively connected to the at least one processor;

[0035] Wherein: the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method as described above.

[0036] Another aspect of the embodiments of the present application provides a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are executed by a processor, the method as described above is implemented.

[0037] Another aspect of the embodiments of the present application provides a computer program product, comprising a computer program, and when the computer program is executed by a processor, the method as described above is implemented.

[0038] The embodiments of the present application adopting the above technical solutions may include the following advantages: combining a plurality of symbols according to the text input by the user to generate target special-shaped characters. Thus, according to the user's description, special-shaped characters that meet the user's needs can be automatically generated, thereby improving the automation level and efficiency of the special-shaped character generation method, and enhancing the personalization level of the special-shaped character generation method. Description of the Drawings

[0039] The drawings exemplarily show embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments. The shown embodiments are only for illustrative purposes and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0040] Figure 1Schematically shows an operating environment diagram of a special-shaped text generation method according to Embodiment 1 of the present application;

[0041] Figure 2 Schematically shows a flowchart of a special-shaped text generation method according to Embodiment 1 of the present application;

[0042] Figure 3 Schematically shows a principle block diagram of a special-shaped text generation library;

[0043] Figure 4 Schematically shows an additional flowchart of a special-shaped text generation method according to Embodiment 1 of the present application;

[0044] Figure 5 Schematically shows another additional flowchart of a special-shaped text generation method according to Embodiment 1 of the present application;

[0045] Figure 6 Schematically shows Figure 2 a sub-step flowchart of step S204 in

[0046] Figure 7 Schematically shows an exemplary application process diagram of a special-shaped text generation method according to Embodiment 1 of the present application;

[0047] Figure 8 Schematically shows a block diagram of a special-shaped text generation device according to Embodiment 2 of the present application; and

[0048] Figure 9 Schematically shows a hardware architecture diagram of a computer device according to Embodiment 3 of the present application. Detailed implementation manners

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0050] It should be noted that in the embodiments of the present application, the descriptions involving "first", "second", etc. are only for descriptive purposes and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. Additionally, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0051] In the description of the present application, it should be understood that the numerical labels before the steps do not identify the order of execution of the steps, but are only used to facilitate the description of the present application and to distinguish each step. Therefore, it should not be construed as a limitation to the present application.

[0052] First, the following provides the term explanations involved in the present application:

[0053] Heteromorphic text: Also known as variant text or artistic text, it is a special form of text formed by deforming, distorting, or artistically processing the traditional text form.

[0054] Emoji: It is a graphical expression formed by combining keyboard symbols and is used in online chats, social media, and emails to intuitively convey emotions, attitudes, or moods. By arranging and combining punctuation marks, letters, and special characters, patterns similar to human faces, animals, or other images are created.

[0055] TypeScript: It is an open-source programming language, a superset of JavaScript, adding modern programming language features such as a static type system, classes, interfaces, modules, etc., while being compatible with existing JavaScript code.

[0056] Pattern recognition: It is a technology that automatically analyzes and recognizes the rules, features, and patterns in data through computer technology. By learning and analyzing a large amount of sample data, the key features in the data are extracted, and a model is established to describe the relationships between these features, thereby realizing the classification, recognition, and prediction of new data.

[0057] Support Vector Machine (SVM): It is a supervised learning algorithm used for classification and regression analysis. By finding an optimal hyperplane in the feature space to separate data points of different classes, while maximizing the margin between the hyperplane and the nearest data points (support vectors).

[0058] Decision Tree: A supervised learning algorithm based on a tree structure, used for classification and regression tasks. By recursively dividing the dataset into multiple subsets, tree-shaped decision rules are formed.

[0059] Random Forest: An ensemble learning algorithm that combines multiple decision tree models to improve the accuracy and stability of predictions.

[0060] Natural Language Processing (NLP) is an important branch in the fields of computer science and artificial intelligence, aiming to enable computers to understand, generate, and process human language. By combining linguistics, computer science, and machine learning techniques, it analyzes the syntactic, semantic, and pragmatic structures of language, thus achieving effective communication between humans and machines.

[0061] Word Embedding: A technique that maps words in text into low-dimensional, dense vector representations. By training neural networks or other models, it captures the semantic and contextual relationships between words, making words with similar semantics closer in the vector space.

[0062] Sequence-to-Sequence Model (Seq2Seq): A deep learning architecture used for tasks of generating and transforming sequence data.

[0063] Template Matching Algorithm: An algorithm based on image processing and pattern recognition, used to find the region in the target image that is most similar to the given template image.

[0064] Genetic Algorithm: An optimization algorithm that simulates the process of biological evolution. It solves complex problems through natural selection and genetic principles.

[0065] Simulated Annealing Algorithm (SA): A general probabilistic algorithm that randomly searches in the solution space and accepts worse solutions with a certain probability to avoid getting stuck in local optimal solutions, and finally gradually converges to the global optimal solution during the "cooling" process.

[0066] Secondly, to facilitate the understanding of the technical solutions provided in the embodiments of the present application by those skilled in the art, the related technologies are described below:

[0067] With the popularity of the Internet and social media, emoticons play an increasingly important role in people's daily communication, and their application scenarios are constantly expanding. However, traditional emoticon creation mainly relies on manual design, where creators express emotions and creativity through combinations of keyboard symbols. However, this method has obvious limitations. On the one hand, the efficiency of manual design is relatively low, making it difficult to generate a large number of emoticons in a short time and unable to meet the immediate needs of users for emoticons in fast-paced online communication. On the other hand, everyone's expression habits and emotional expression methods are different, and manually designed emoticons are difficult to be highly customized and cannot fully meet the personalized needs of users.

[0068] For this reason, the embodiments of this application provide a technical solution for generating special-shaped characters. In this technical solution, (1) special-shaped characters (such as emoticons) are automatically generated through programming, improving the automation level and efficiency of special-shaped character generation; (2) different categories of emoticons are generated according to user needs, improving the personalization level of special-shaped character generation; (3) an emoticon generation library is constructed, which is easy to add new emoticon categories and samples, improving the generality and scalability of special-shaped character generation. See the following for details.

[0069] Finally, for ease of understanding, an exemplary operating environment is provided below.

[0070] As Figure 1 shown, the operating environment diagram includes: a server 2, a network 4, and a client 6, where:

[0071] The server 2 can be composed of a single or multiple computing devices. The multiple computing devices can include virtualized computing instances. The virtualized computing instances can include virtual machines, such as emulations of computer systems, operating systems, servers, etc. The computing devices can load virtual machines based on virtual images and / or other data that define specific software (such as operating systems, dedicated applications, servers) for emulation. As the demand for different types of processing services changes, different virtual machines can be loaded and / or terminated on one or more computing devices. A hypervisor can be implemented to manage the use of different virtual machines on the same computing device.

[0072] The server 2 can be configured to communicate with the client 6, etc. through the network 4. The network 4 includes various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and / or the like. The network 4 can include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, and their combinations, etc., or wireless links, such as cellular links, satellite links, Wi-Fi links, etc.

[0073] The server 2 can provide services such as storage, reading, writing, querying, deleting, etc., such as providing a text content input service for the client.

[0074] The client 6 can be an electronic device running operating systems such as Windows, Android TM ), or iOS, such as a smart phone, a tablet device, a laptop computer, a virtual reality device, a gaming device, a set-top box, a vehicle-mounted terminal, or a smart TV. Based on the above operating systems, various application programs can be run, such as a cute emoticon display program.

[0075] The client 6 can provide / configure a user access page for manipulating the server 2 or uploading an object, etc.

[0076] It should be noted that the above devices are exemplary, and in different scenarios or according to different requirements, the number and types of devices can be adjusted.

[0077] The following takes the server 2 / client 6 as the execution subject, and introduces the technical solutions of the present application through multiple embodiments. It should be noted that these embodiments can be implemented in various different forms and should not be construed as being limited only to the embodiments described herein.

[0078] Embodiment 1

[0079] Figure 2 A flowchart of a method for generating special-shaped characters according to Embodiment 1 of the present application is schematically shown.

[0080] As Figure 2 shown, the method for generating special-shaped characters may include steps S200 to S204, where:

[0081] Step S200: Obtain the text content input by the target object.

[0082] Step S202: Select a plurality of target symbols from a special-shaped character generation library according to the text content; wherein, the special-shaped character generation library is configured with a plurality of optional symbols, and at least some of the optional symbols are obtained by decomposing special-shaped character samples.

[0083] Step S204: Combine the plurality of target symbols to generate at least one target special-shaped character associated with the text content.

[0084] The method for generating special-shaped characters provided in this embodiment combines a plurality of symbols according to the text input by the user to generate a target special-shaped character. Thus, according to the user's description, special-shaped characters that meet the user's needs can be automatically generated, thereby improving the automation level and efficiency of special-shaped character generation, and enhancing the personalization level of the special-shaped character generation method.

[0085] The following will Figure 2 be elaborated in detail on each step in steps S200 to S204 and other optional steps.

[0086] Step S200 , obtain the text content input by the target object.

[0087] In specific implementation, various components such as a text input box can be set. The user (i.e., the target object) can input text content through the input box. In some embodiments, the text input box can provide multiple suggested texts for the keywords input by the user for the user to select. The finally obtained text content can be the suggested text selected by the user.

[0088] The user can also input text content by means of voice or handwriting, etc. The user can also upload media files such as pictures, gifs or videos. At this time, the server 2 or the client 6 can convert the media files into text content through the corresponding modules or interfaces.

[0089] The text content can be one or more words, a complete sentence or a text description. For example, the text content can be "angry", "The weather is really nice today and it's suitable to go out and play." or "Recently, the work pressure is a bit high, feeling a bit tired and hoping to relax." etc. After obtaining the text content input by the user, the text can be cleaned to remove irrelevant characters, punctuation marks, spaces, etc., and the core text information can be extracted. It can also identify keywords, sentiment tendencies, semantic information, etc. in the text through natural language processing technology and other means.

[0090] Step S202 , select a plurality of target symbols from the special-shaped character generation library according to the text content; wherein, the special-shaped character generation library is configured with a plurality of optional symbols, and at least some of the optional symbols are obtained by decomposing special-shaped character samples.

[0091] For example, by decomposing the special-shaped character sample "╰(‵□′)╯", the following optional symbols can be obtained:

[0092] A pair of parentheses "( )", two commas "‵" and "′", a square symbol "□", and "╰" and "╯".

[0093] When the text content input by the user is "angry", the plurality of target symbols selected from the special-shaped character generation library can be "╰", "( ", "‵", "□", "′", ") " and "╯".

[0094] The collected special-shaped character samples can be emoticons expressing expressions, animals, items, etc. In some embodiments, the special-shaped character samples can be automatically collected from websites such as social media, forums, chat records, etc. through a web crawler program, or can be special-shaped characters actively submitted by users on public platforms or communities.

[0095] In some other embodiments, the special-shaped character samples can also be collected from various network resources through manual search and collation, or obtained through existing special-shaped character interface services, or sorted and classified by using existing public special-shaped character databases or resource libraries.

[0096] The optional symbols in the special-shaped character generation library can also be collected from open-source material websites, generated by intelligent models, or uploaded by users themselves. The special-shaped character generation library can contain symbols of different styles and themes, and at the same time support users to customize symbols, further enhancing the personalization degree of the generated special-shaped characters.

[0097] In some embodiments, as Figure 3 shown, the special-shaped character generation library can also be configured with a data collection module, a pattern recognition module, an algorithm design module, and a library implementation module. The data collection module is used to collect special-shaped character samples, the pattern recognition module is used to recognize the structural rules of special-shaped character samples, the algorithm design module is used to design special-shaped character generation algorithms according to the recognized structural rules of special-shaped characters, and the library implementation module is used to implement the special-shaped character generation library.

[0098] The special-shaped character generation library can also store multiple ready-made special-shaped characters and can return corresponding special-shaped characters according to the user's input content. When there is no corresponding ready-made special-shaped character for the content input by the user, it can also be selected from the default multiple special-shaped characters.

[0099] During the selection process of optional symbols, with the user's authorization, the selection weights and recommendation orders of symbols can also be dynamically adjusted according to the user's historical usage records and feedback information to improve the accuracy of symbol selection and user satisfaction.

[0100] In this embodiment, a special-shaped character generation library storing optional symbols is provided. Select a matching target symbol from the optional symbols of the special-shaped character generation library. Thus, the diversity of symbols and the high matching degree with the text content can be ensured, effectively improving the personalization and intelligence level of special-shaped character generation and meeting the personalized needs of different users.

[0101] In specific applications, there can be multiple types of target special-shaped characters, and different types of target special-shaped characters can correspond to different operation methods. The following provides an exemplary situation.

[0102] In an alternative embodiment, the target special-shaped character includes a target emoticon, and the target emoticon includes multiple constituent parts; step S204 includes:

[0103] According to the text content, select a target symbol for each of the constituent parts to obtain the multiple target symbols.

[0104] For example:

[0105] Multiple component parts may include eyes, mouth, eyebrows, arms, etc. For example, an emoticon “(╯‵□′)╯︵┻━┻” includes the following component parts:

[0106] Head: Surrounded by parentheses “()”.

[0107] Eyes: Represented by “‵” and “′” as angry eyes.

[0108] Mouth: Represented by a “□” as an angry mouth.

[0109] Arms: Represented by two “╯” as waving arms.

[0110] Action: Represented by “︵” as the action of flipping the table.

[0111] Object: Represented by “┻━┻” as a table.

[0112] In some embodiments, sentiment analysis can be performed on the text content through natural language processing technology to determine the sentiment tendency (such as anger, happiness, sadness, etc.) expressed by the text, so as to select corresponding symbols for the component parts of emoticons with different sentiment tendencies. In other embodiments, keywords can also be extracted from the text content. Based on the analysis or matching of these keywords, specific symbols can be selected. For example, if the text content contains the keyword “flame”, a symbol in the shape of a flame can be selected for the eye part of the target emoticon.

[0113] In this embodiment, the target emoticon is decomposed into multiple component parts, and target symbols are separately selected for each component part. Thus, emoticons with pertinence and differentiation can be accurately assembled, thereby improving the pertinence and diversity of the generation of special-shaped characters.

[0114] In the actual use process, target symbols can be selected through various methods. The following provides an exemplary method.

[0115] In an alternative embodiment, in the special-shaped character generation library, each of the component parts is associated with one or more optional symbol sequences. As Figure 4 shown, according to the text content, selecting a target symbol for each of the component parts includes:

[0116] S400, determining a target optional symbol sequence for each of the component parts.

[0117] S402, selecting a target symbol for each of the component parts according to the target optional symbol sequence of each of the component parts.

[0118] For example:

[0119] The optional symbol sequences associated with the head can be {"(", ")", "(", ")", "[", "]"};

[0120] The optional symbol sequences associated with the eyes can be { "ε"} and { "`", "□"}, etc.

[0121] During the generation process of the target ideogram:

[0122] When determining the target optional symbol sequence of the head, {"(", ")", "(", ")", "[", "]"} is selected;

[0123] When determining the target optional symbol sequence associated with the eyes, one is selected from { "ε"} and { "`", "□"}. In some embodiments, it can be randomly selected, or selected according to the text content or certain rules.

[0124] The target optional symbol sequence can be determined by performing semantic analysis on the input text content to extract information such as keywords, sentiment tendency, and theme. It can also be determined by analyzing the context information of the text content, including semantic associations and dialogue scenarios before and after. With the user's authorization, the personalized preferences of the target object can also be considered when determining the target optional symbol sequence, including historical usage records, favorite kawaii text styles, etc. According to the user's personalized preferences, a target optional symbol sequence that better suits the user's preferences can be determined for each component part.

[0125] Each optional symbol sequence is configured with multiple optional symbols. For example, after determining that the target optional symbol sequence associated with the eyes is { "ε"}, one can be selected from "ε" as the target symbol representing the eyes. When selecting this target symbol, it can be randomly selected, or weighted selection can be performed based on factors such as the analysis result of the text content, the usage frequency, or popularity of the symbol. It is also possible to obtain the user's feedback information in real time during the process of selecting the target symbol, such as the user's evaluation and modification suggestions for the generated kawaii text. According to the user's feedback information, the target optional symbol sequence can be dynamically updated and the target symbol can be reselected.

[0126] The optional symbols of each component part are grouped by using symbol sequences, and selection is made according to the grouping results. Thus, the target symbol can be selectively picked according to the user's needs, improving the matching degree between the target symbol and the user's needs as well as the speed of selecting the target symbol, thereby enhancing the efficiency of the ideogram generation method.

[0127] As can be seen from the above example, a component part may correspond to one optional symbol sequence, or there may be multiple optional symbol sequences. When there are multiple optional symbol sequences, a selection needs to be made, for example, randomly, or it can be selected in the following way.

[0128] In an optional embodiment, a target component part among the multiple component parts is associated with multiple optional symbol sequences, and the multiple optional symbol sequences of the target component part respectively correspond to different attributes. Step S400 includes:

[0129] Select a target optional symbol sequence from the multiple optional symbol sequences of the target component part according to the target attribute of the text content; wherein, the target optional symbol sequence selected for the target component part corresponds to the target attribute.

[0130] The attribute can be an emotional attribute, such as anger, happiness, sadness, etc., or a scene attribute, such as chatting, working, studying, etc. It can also be a user preference attribute, such as personal style, commonly used symbols, etc., and a time attribute, such as festivals, seasons, etc. Each attribute can be further refined. For example, anger can be refined into "slightly angry", "extremely angry", "briefly angry", etc.

[0131] For example, the mouth part corresponds to the following multiple optional symbol sequences:

[0132] {"^", "□", "︵"} corresponding to the attribute "anger";

[0133] {"︶", "▽", "ω"} corresponding to the attribute "happy";

[0134] {"︿", "△", "︶"} corresponding to the attribute "sad";

[0135] {"_", "ε", "3"} corresponding to the attribute "helpless".

[0136] When the text content input by the user is "So angry!", it can be determined that the target attribute of the text content is "anger". Then, for the target component part of "mouth", {"^", "□", "︵"} corresponding to the attribute "anger" can be selected as the target optional symbol sequence.

[0137] In some embodiments, the target attributes in the text content can be determined through analysis using natural language technology or the like. With the user's authorization, the historical text content input by the user and the corresponding target attributes can also be combined to summarize the user's preferences for different attributes, and the obtained preferences can be used to guide the analysis of the text content and the determination of the target attributes. After the generation of the ideographic characters, the methods or models used to analyze the text content and determine the target attributes can also be adjusted according to the user's feedback to improve the accuracy of the analysis.

[0138] Selecting a target optional symbol sequence with the same attributes as the text content can make the generated ideographic characters match the attributes of the text content, thereby improving the fit between the generated ideographic characters and the text content, helping to enhance the automation and personalization levels of the ideographic character generation method, and further enhancing the user's satisfaction.

[0139] The above describes how to select an optional symbol sequence for a specific component part and how to select a target symbol from the optional symbol sequence.

[0140] The optional symbol sequence can be constructed in various ways, and the following provides an exemplary construction method.

[0141] In an alternative embodiment, as Figure 5 shown, one of the optional symbol sequences is obtained through the following operations:

[0142] S500, obtain multiple ideographic character samples with the same attributes.

[0143] S502, through the recognition and decomposition of the multiple ideographic character samples respectively, obtain multiple sample symbols.

[0144] S504, aggregate the sample symbols corresponding to the same component part among the multiple sample symbols to construct the corresponding optional symbol sequence.

[0145] For example, obtain three ideographic character samples of “(╯‵□′)╯︵┻━┻” and “╰(‵□′)╯” with the same attribute of “anger”. Through the recognition and decomposition of these three ideographic character samples, the following sample symbols can be obtained:

[0146] Sample 1,

[0147] Head: two commas “,,”;

[0148] Eyes: two

[0149] Mouth: one “□”.

[0150] Sample 2, "(╯‵□′)╯︵┻━┻":

[0151] Head: parentheses "()";

[0152] Eyes: two "‵";

[0153] Mouth: one "□";

[0154] Arms: two "╯";

[0155] Actions and objects: symbols "︵" and "┻━┻".

[0156] Sample 3, "╰(‵□′)╯":

[0157] Head: parentheses "()";

[0158] Eyes: two "‵";

[0159] Mouth: one "□";

[0160] Arms: symbols "╰" and "╯".

[0161] Aggregating the obtained sample symbols, the following optional symbol sequences can be obtained:

[0162] Head: {“,,,,”, “()”, “()”};

[0163] Eyes: { “‵”, “‵”};

[0164] Mouth: {“^”, “□”, “□”};

[0165] Arms: {“╯”, “╰”};

[0166] Actions and objects: {“︵”, “┻━┻”}.

[0167] In some embodiments, pattern recognition techniques such as machine learning (such as support vector machine SVM, decision tree, random forest, etc.), deep learning (such as convolutional neural network CNN or recurrent neural network RNN, etc.), natural language processing (such as word embedding and sequence-to-sequence model), or template matching algorithm can be used to identify and decompose the special-shaped text samples.

[0168] During the recognition and decomposition process, the structural rules of the special-shaped text samples can also be analyzed and used to guide the generation of special-shaped text samples. For example, during the recognition and decomposition process of the above three special-shaped text samples, the following rules can be obtained:

[0169] (1) Head: Usually surrounded by parentheses or other symbols.

[0170] (2) Eyes: Specific symbols can be used (such as ‵, ) indicates angry eyes.

[0171] (3) Mouth: You can use specific symbols (such as ^, □) to represent an angry mouth.

[0172] (4) Arms: Symbols (such as ╯, ╰) can be used to indicate arm movements.

[0173] (5) Actions and objects: Specific symbols (such as ︵, ┻━┻) can be used to represent actions and objects.

[0174] In some embodiments, a dynamic optional symbol sequence update mechanism can be established for the constructed optional symbol sequence, and the optional symbol sequence can be adjusted and updated in real time according to user feedback and network popularity trends. For example, if a symbol is frequently used by users or becomes popular on the network within a period of time, the system can automatically add it to the corresponding optional symbol sequence to maintain the timeliness and attractiveness of the optional symbol sequence.

[0175] In this embodiment, by decomposing the special-shaped characters samples with the same attributes, the optional symbol sequences (with the same attributes) of each component part can be obtained. Thus, it can be ensured that each component part has rich and accurate optional symbols, thereby improving the diversity and personalization of the target special-shaped characters, and making the generated special-shaped characters more expressive and unique.

[0176] Step S204 , combining the multiple target symbols to generate at least one target variant character associated with the text content.

[0177] For example, if multiple target symbols selected at a time are “╰”, “(”, “‵”, “□”, “′”, “)” and “╯”, they can be combined into “╰(‵□′)╯” as a target variant character.

[0178] In some embodiments, the combination process can be controlled by introducing optimization algorithms such as genetic algorithms and simulated annealing algorithms to ensure the diversity and innovation of the combination results and avoid generating too many repeated or similar special-shaped characters. Special-shaped characters with high innovation can also be screened out by setting a certain innovation threshold.

[0179] There may be multiple target shaped characters generated each time. In some embodiments, after returning multiple target shaped characters to the user, the user's preference habits may be analyzed based on the user's selection results or feedback. Then, in the subsequent shaped character generation process, the analyzed user preference habits are used to guide the generation of the shaped characters.

[0180] In this embodiment, by combining the multiple target symbols, target special-shaped characters can be automatically and efficiently generated, improving the automation level, efficiency, and customizability of special-shaped character generation, and enhancing the user experience of using special-shaped characters.

[0181] There are various ways to combine the target symbols, and an exemplary way is provided below.

[0182] In an alternative embodiment, as Figure 6 shown, step S204 includes:

[0183] S600, obtaining the arrangement of the multiple component parts.

[0184] S602, arranging the multiple target symbols according to the arrangement to generate at least one target special-shaped character.

[0185] The target symbols can be combined in the default arrangement order, for example, combined in the order of "arm, head, eyes, mouth, eyes, head, arm". Multiple target symbols can also be input into a pre-trained symbol arrangement model to return a suitable arrangement by the symbol arrangement model. The arrangement of the target symbols can also be customized by the user.

[0186] In some embodiments, the arrangement can be automatically adjusted according to the characteristics of the display device used by the user, such as the screen size, resolution, aspect ratio, etc., to ensure that the generated special-shaped characters can achieve the best display effect on different devices.

[0187] In other embodiments, the mutual relationships between the target symbols, such as similarity, contrast, relevance, etc., can also be analyzed, and the positions and orders can be reasonably arranged to enhance the integrity and expressiveness of the special-shaped characters. Dynamic effects, such as gradual change, rotation, scaling, etc., can also be added to the arranged target special-shaped characters to make the target special-shaped characters have a dynamic visual effect.

[0188] The target symbols are combined in a suitable arrangement to obtain the target special-shaped characters. Thus, it can be ensured that the generated special-shaped characters comply with the design rules or requirements and are more in line with the text content, improving the success rate and expression accuracy of the special-shaped character generation method.

[0189] In an alternative embodiment, the method further includes:

[0190] Generating a plurality of function interfaces, the function interfaces connecting to the special-shaped character generation library, and each function interface corresponding to a keyword; wherein, the function interface is used to return at least one target special-shaped character associated with the keyword when called.

[0191] The generated function interface can be applied in chat software and input method software.

[0192] In some embodiments, the keyword list in the generation library can be scanned to automatically generate the corresponding function interface and fill in the specific logic. When the keywords or symbols in the special-shaped character generation library change, the function interface can be automatically updated.

[0193] In some embodiments, the function interface can support asynchronous call modes to avoid interface freezing problems caused by the time-consuming process of generating special-shaped characters. The function interface can support parameterized calls. For example, a parameter can be passed to specify attributes such as the style, color, and size of the generated special-shaped characters, or a parameter can be passed to limit the number of generated special-shaped characters.

[0194] In some embodiments, the function interface can also be a combined function interface. The combined function interface can generate a special-shaped character corresponding to multiple attributes according to multiple input keywords. For example, "mixed feelings of grief and joy" can correspond to two emotions, "sad" and "happy". After inputting into the combined function interface, the combined function interface can return a target special-shaped character corresponding to both "sad" and "happy", such as

[0195] Generating a function interface corresponding to the keyword can enable the special-shaped character generation library to be more easily integrated with other systems or platforms, improving the compatibility and versatility of the special-shaped character generation library. At the same time, it also enables users or developers to call the special-shaped character generation library more conveniently, reducing the usage difficulty of the special-shaped character generation method. In addition, the function interface is associated with the keyword, and users or developers can add new keywords according to needs, improving the personalization level of special-shaped character generation.

[0196] To make the present application easier to understand, the following is combined with Figure 7 An exemplary application is provided.

[0197] In this exemplary application, the special-shaped character generation library and related programs can be written in the TypeScript language. Among them:

[0198] S11, the user (i.e., the target object) inputs a keyword "so angry" (i.e., the text content);

[0199] S12, determine that the emotion expressed by the keyword (i.e., the target attribute) is "anger";

[0200] S13, from multiple optional symbol sequences for eyes in the special-shaped character generation library, select the target optional symbol sequence corresponding to "anger" as { "`", "`"}, and select as the target symbol;

[0201] S14. From the multiple optional symbol sequences for the mouth in the special-shaped character generation library, select the target optional symbol sequence corresponding to "angry" as {"^", "□", "︵"}, and select "^" as the target symbol from them;

[0202] S15. From the multiple optional symbol sequences for the head in the special-shaped character generation library, select the target optional symbol sequence corresponding to "angry" as {“,,,,”, "()", "()"}, and select "()" as the target symbol from them;

[0203] S16. From the multiple optional symbol sequences for the arm in the special-shaped character generation library, select the target optional symbol sequence corresponding to "angry" as {"╯", "╰"}, and select "╯" as the target symbol from them;

[0204] S17. From the multiple optional symbol sequences for actions and objects in the special-shaped character generation library, select the target optional symbol sequence corresponding to "angry" as {"︵┻━┻"}, and select "︵┻━┻" as the target symbol;

[0205] S18. Arrange the selected target symbols in the default order to obtain a target kaomoji (i.e., target special-shaped character) as " ╯︵┻━┻";

[0206] S19. Return " ╯︵┻━┻" to the user.

[0207] Embodiment 2

[0208] Figure 8 Schematically shows a block diagram of a special-shaped character generation device according to Embodiment 2 of the present application. The device can be divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the embodiments of the present application. The program modules referred to in the embodiments of the present application refer to a series of computer program instruction segments that can complete specific functions. The following description will specifically introduce the functions of each program module in this embodiment. As Figure 8 shown, the device 1000 may include: an acquisition module 1100, a selection module 1200, and a combination module 1300, where:

[0209] The acquisition module 1100 acquires the text content input by the target object;

[0210] The selection module 1200 is used to select a plurality of target symbols from the special-shaped character generation library according to the text content; wherein, the special-shaped character generation library is configured with a plurality of optional symbols, and at least some of the optional symbols are obtained by decomposing special-shaped character samples;

[0211] Combination module 1300 is used to combine the multiple target symbols to generate at least one target ideogram associated with the text content.

[0212] As an alternative embodiment, the target ideogram includes a target kaomoji, the target kaomoji includes multiple component parts, and the selection module 1200 is further used for:

[0213] According to the text content, select a target symbol for each of the component parts respectively to obtain the multiple target symbols.

[0214] As an alternative embodiment, in the ideogram generation library, one or more optional symbol sequences are associated with each of the component parts, and the device 1000 further includes a symbol sequence determination module for:

[0215] Determine a target optional symbol sequence for each of the component parts respectively;

[0216] According to the target optional symbol sequence of each of the component parts, select a target symbol for each of the component parts respectively.

[0217] As an alternative embodiment, a target component part among the multiple component parts is associated with multiple optional symbol sequences, and the multiple optional symbol sequences of the target component part respectively correspond to different attributes. The symbol sequence determination module is further used for:

[0218] According to the target attribute of the text content, select a target optional symbol sequence from the multiple optional symbol sequences of the target component part; wherein, the target optional symbol sequence selected for the target component part corresponds to the target attribute.

[0219] As an alternative embodiment, the device 1000 further includes a symbol sequence construction module for:

[0220] Obtain multiple ideogram samples with the same attribute;

[0221] By respectively identifying and decomposing the multiple ideogram samples, obtain multiple sample symbols;

[0222] Aggregate the sample symbols corresponding to the same component part among the multiple sample symbols to construct the corresponding optional symbol sequence.

[0223] As an alternative embodiment, the combination module 1300 is further used for:

[0224] Obtain the arrangement mode of the multiple component parts;

[0225] According to the arrangement mode, arrange the multiple target symbols to generate at least one of the target ideograms.

[0226] As an alternative embodiment, the apparatus 1000 further includes an interface generation module for:

[0227] generating a plurality of function interfaces, each of the function interfaces corresponding to a keyword;

[0228] wherein the function interface is configured to return at least one of the target ideographic characters associated with the keyword when being called.

[0229] Embodiment III

[0230] Figure 9 FIG. schematically shows a hardware architecture diagram of a computer device 10000 suitable for implementing the ideographic character generation method according to Embodiment III of the present application. In some embodiments, the computer device 10000 may be a terminal device such as a smart phone, a wearable device, a tablet computer, a personal computer, a vehicle-mounted terminal, a game console, a virtual device, a workbench, a digital assistant, a set-top box, a robot, etc. In other embodiments, the computer device 10000 may be a rack server, a blade server, a tower server, or a cabinet server (including an independent server or a server cluster composed of multiple servers). As Figure 9 shown, the computer device 10000 includes, but is not limited to: a memory 10010, a processor 10020, and a network interface 10030 that can communicate with each other through a system bus. Among them:

[0231] The memory 10010 includes at least one type of computer-readable storage medium. The readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 10010 may be an internal storage module of the computer device 10000, such as the hard disk or memory of the computer device 10000. In other embodiments, the memory 10010 may also be an external storage device of the computer device 10000, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 10000. Of course, the memory 10010 may also include both the internal storage module and the external storage device of the computer device 10000. In this embodiment, the memory 10010 is generally used to store the operating system and various application software installed on the computer device 10000, such as the program code of the special-shaped text generation method. In addition, the memory 10010 may also be used to temporarily store various data that have been output or will be output.

[0232] In some embodiments, the processor 10020 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other chips. The processor 10020 is generally used to control the overall operation of the computer device 10000, such as performing control and processing related to data interaction or communication with the computer device 10000. In this embodiment, the processor 10020 is used to run the program code stored in the memory 10010 or process data.

[0233] The network interface 10030 may include a wireless network interface or a wired network interface, which is generally used to establish a communication link between the computer device 10000 and other computer devices. For example, the network interface 10030 is used to connect the computer device 10000 to an external terminal through a network, and establish a data transmission channel and a communication link between the computer device 10000 and the external terminal. The network may be a wireless or wired network such as an enterprise intranet (Intranet), the Internet, the Global System of Mobile communication (GSM for short), Wideband Code Division Multiple Access (WCDMA for short), 4G network, 5G network, Bluetooth, Wi-Fi, etc.

[0234] It should be noted that Figure 9 Only the computer device with components 10010 - 10030 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0235] In this embodiment, the special-shaped character generation method stored in the memory 10010 can also be divided into one or more program modules and executed by one or more processors (such as the processor 10020) to complete the embodiments of the present application.

[0236] Embodiment 4

[0237] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the special-shaped character generation method in the embodiments are implemented.

[0238] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device. Of course, the computer-readable storage medium may also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is generally used to store the operating system and various application software installed on the computer device, such as the program code of the special-shaped text generation method in the embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various data that have been output or will be output.

[0239] Embodiment Five

[0240] The embodiment of the present application also provides a computer program product, including a computer program, which when executed by a processor implements the method in the above embodiment.

[0241] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the embodiments of the present application can be implemented by a general-purpose computer device. They can be concentrated on a single computer device or distributed on a network composed of multiple computer devices. Optionally, they can be implemented by program codes executable by the computer device. Thus, they can be stored in a storage device and executed by the computer device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to implement. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0242] It should be noted that the above are only the preferred embodiments of the present application, and do not limit the patent protection scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present application by the same token.

Claims

1. A method for generating special-shaped characters, characterized in that: The method comprises: Get the text content entered by the target object; According to the text content, multiple target symbols are selected from a heteromorphic character generation library; wherein the heteromorphic character generation library is configured with multiple optional symbols, and at least some of the optional symbols are obtained by decomposing heteromorphic character samples; The plurality of target symbols are combined to generate at least one target variant character associated with the text content.

2. The method according to claim 1, characterized in that The target special-shaped characters include target emoticons, and the target emoticons include multiple components; according to the text content, multiple target symbols are selected from the special-shaped character generation library, including: According to the text content, a target symbol is selected for each of the component parts to obtain the multiple target symbols.

3. The method according to claim 2, characterized in that In the heteromorphic character generation library, each of the component parts is associated with one or more optional symbol sequences; According to the text content, a target symbol is selected for each component part to obtain the multiple target symbols, including: Determine a target optional symbol sequence for each of the component parts; According to the target selectable symbol sequence of each component part, a target symbol is selected for each component part.

4. The method according to claim 3, characterized in that A target component part among the multiple component parts is associated with multiple optional symbol sequences, and the multiple optional symbol sequences of the target component part correspond to different attributes respectively; Determine a target optional symbol sequence for each of the component parts, including: According to the target attribute of the text content, a target optional symbol sequence is selected from a plurality of optional symbol sequences of the target component part; wherein the target optional symbol sequence selected for the target component part corresponds to the target attribute.

5. The method according to any one of claims 2 to 4, characterized in that: One of the optional symbol sequences is obtained by the following operations: Obtain multiple samples of special characters with the same attributes; Acquire multiple sample symbols by respectively identifying and decomposing the multiple special-shaped character samples; The sample symbols corresponding to the same component part among the multiple sample symbols are aggregated to construct a corresponding optional symbol sequence.

6. The method according to any one of claims 2 to 4, characterized in that: Combining the plurality of target symbols to generate at least one target variant character associated with the text content comprises: Obtaining an arrangement of the plurality of components; According to the arrangement method, the plurality of target symbols are arranged to generate at least one target variant character.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Generate a plurality of function interfaces, the function interfaces are connected to the special-shaped character generation library, and each of the function interfaces corresponds to a keyword; The function interface is used to return at least one target variant character associated with the keyword when called.

8. A device for generating special-shaped characters, characterized in that: The device comprises: Acquisition module, to obtain the text content input by the target object; A selection module is used to select a plurality of target symbols from a heteromorphic character generation library according to the text content; wherein the heteromorphic character generation library is configured with a plurality of optional symbols, at least some of which are obtained by decomposing heteromorphic character samples; The combination module is used to combine the multiple target symbols to generate at least one target variant character associated with the text content.

9. A computer device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images