Font emotional rendering method and device and medium

Abstract

The invention discloses a font emotional rendering method, font emotional rendering equipment and a medium, and relates to the technical field of mobile equipment display. The method comprises the steps of obtaining multi-dimensional data in a current scene, inputting ambient light intensity data and biological rhythm data into a font emotion response model, and obtaining font rendering parameters which are output by the font emotion response model and correspond to the current scene; and comparing the font rendering parameter with a preset rendering parameter interval, and executing a font rendering instruction corresponding to the font rendering parameter under the condition that the font rendering parameter is located in the preset rendering parameter interval so as to realize emotional expression of the font. In this way, emotional expression of the fonts can be achieved, then visual fatigue can be relieved, and the suitability of the fonts and the user state is enhanced.

Description

Technical Field

[0001] This application relates to the field of mobile device display technology, and in particular to a method, device and medium for font emotional rendering. Background Technology

[0002] Current mobile device font rendering technologies mostly focus on readability and static aesthetics, failing to dynamically adjust to changes in ambient light and user circadian rhythms (such as sleep schedules and activity levels). Most devices have fixed font styles or require manual switching, making it difficult to convey emotions appropriate to the user's current state under different lighting conditions (such as strong light and weak light) and time of day (such as morning and late at night). This leads to visual fatigue during prolonged use and a lack of emotionally resonant interactive adaptation. Summary of the Invention

[0003] This application provides a font emotional rendering method, device, and medium to solve the following technical problem: how to realize the emotional expression of fonts to reduce visual fatigue and improve the adaptability of fonts to user states.

[0004] In a first aspect, embodiments of this application provide a method for emotional font rendering. The method includes: acquiring multi-dimensional data of a current scene, wherein the multi-dimensional data further includes ambient light intensity data and circadian rhythm data; inputting the ambient light intensity data and the circadian rhythm data into a font emotional response model to obtain font rendering parameters output by the font emotional response model corresponding to the current scene, wherein the font emotional response model is used to generate corresponding font rendering parameters based on the ambient light intensity data and the circadian rhythm data; comparing the font rendering parameters with a preset rendering parameter range, wherein the preset rendering parameter range is the rendering parameters of the scene corresponding to the current scene in the preset rendering adjustment rules; and, if the font rendering parameters are within the preset rendering parameter range, executing a font rendering instruction corresponding to the font rendering parameters to achieve emotional expression of the font.

[0005] Secondly, embodiments of this application also provide a font emotional rendering method apparatus, the apparatus comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a font emotional rendering method as described in the first aspect above.

[0006] Thirdly, embodiments of this application also provide a computer storage medium storing computer-executable instructions, which, when executed, implement a font emotional rendering method as described in the first aspect above.

[0007] The font emotional rendering method, device, and medium provided in this application have the following beneficial effects: In this embodiment, multidimensional data of the current scene can be obtained, and then the ambient light intensity data and biological rhythm data in the multidimensional data can be input into the font emotion response model to obtain the font rendering parameters corresponding to the current scene. Subsequently, if the font rendering parameters are within the preset rendering parameter range, the corresponding font rendering instruction is executed. The emotional expression of the font can be realized in the above way, which can reduce the user's manual adjustment of the font, reduce visual fatigue, enhance the adaptability of the font to the user's state, and improve the emotional interaction experience. Attached Figure Description

[0008] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a font emotion rendering method provided in this application embodiment; Figure 2 This is a schematic diagram of the internal structure of a font emotion rendering device provided in an embodiment of this application. Detailed Implementation

[0009] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0010] This application provides a scheme for the emotional expression of fonts. The technical solution proposed in this application will be described in detail below with reference to the accompanying drawings.

[0011] Figure 1 This is a flowchart illustrating a font emotion rendering method provided in an embodiment of this application. Figure 1 As shown in the figure, the font emotional rendering method provided in this application embodiment specifically includes the following steps: Step 101: Obtain multidimensional data for the current scenario.

[0012] The multidimensional data also includes ambient light intensity data and biological rhythm data.

[0013] In this embodiment, multidimensional data of the current scene can be acquired, specifically, ambient light intensity data (strong light or weak light) and user's circadian rhythm data (e.g., sleep schedule). This lays the data foundation for subsequent emotional font rendering.

[0014] In practical applications, data can be acquired in real time, for example, when users use mobile devices (such as smartphones, tablets, e-book readers, etc.) to obtain multidimensional data in real time, which facilitates better service to users. Data can also be acquired periodically, such as once every 5 minutes, to save resources.

[0015] Step 102: Input the ambient light intensity data and the biological rhythm data into the font emotion response model to obtain the font rendering parameters output by the font emotion response model corresponding to the current scene.

[0016] The font emotion response model is used to generate corresponding font rendering parameters based on the ambient light intensity data and the biological rhythm data.

[0017] In practical applications, ambient light intensity is a crucial factor influencing visual perception. Users have varying needs regarding font readability and visual comfort under different light intensities. For example, in bright light, a thicker font weight and larger letter spacing may be easier to read; while in low light, a thinner font weight and tighter letter spacing may be more suitable. Biorhythm data can reflect a user's physiological and psychological state at different times. For instance, a user's visual sensitivity and attention levels differ at different times, and activity levels can also reflect a user's current mental state to some extent. This data can provide font sentiment response models with information about the user's current state, allowing for better adjustment of font parameters to meet user needs, and can serve as input to the model. Font rendering parameters, such as font weight, letter spacing, and font style, directly affect the font's visual effect and readability. Font weight determines the thickness of the font, letter spacing affects the spacing between characters, and font style determines the overall style of the font. By adjusting these parameters, the visual presentation of the font in different scenarios can be altered, thus better adapting to user needs.

[0018] In this embodiment, a font emotion response model can be used to map ambient light intensity data and circadian rhythm data to corresponding font rendering parameters. This means the font emotion response model can provide personalized font parameter settings based on the user's ambient light and circadian rhythm state. Different users have different font needs in different scenarios. Compared to directly using some rendering adjustment rules, this personalized setting can improve user reading comfort and satisfaction, while also handling complex and changing scenarios and meeting users' emotional needs for fonts. Moreover, compared to traditional font setting methods based on experience or subjective judgment, the data-driven font emotion response model is more objective and accurate.

[0019] It should be noted that multidimensional data may be acquired in real time, but ambient light intensity data and biological rhythm data may not necessarily be input into the font emotion response model in real time. They can be input periodically, for example, once every 5 minutes. If the font rendering parameters are the same as the last time, the current font rendering can be maintained, or they can be input at key nodes. There are no specific restrictions.

[0020] Step 103: Compare the font rendering parameters with the preset rendering parameter range.

[0021] The preset rendering parameter range is the rendering parameter range of the scene corresponding to the current scene in the preset rendering adjustment rules.

[0022] In practical applications, font emotion response models may generate inaccurate results. To further improve rendering accuracy, in this embodiment, the font rendering parameters can be compared with the rendering parameters of the scene corresponding to the current scene in the preset rendering adjustment rules to determine the specific parameters of font rendering. This can improve the user experience.

[0023] It should be noted that the preset rendering parameter range is a general range, which can be based on the output of the font sentiment response model and combined with user feedback. It is not static and can be determined according to the actual situation. For example, when the user is elderly, the font size settings in the preset rendering adjustment rules may be generally larger, while the font size settings for younger users are generally smaller. If the font sentiment response model is subsequently optimized, the corresponding preset rendering parameter range can be regenerated. The specific methods for formulating and updating the preset rendering rules are not specifically limited.

[0024] For example, preset rendering adjustment rules may include the following aspects: Morning (e.g., 6:00-9:00) + strong light environment: The font is automatically adjusted to a sharp style, the font weight is increased by 10%-20%, and the letter spacing is reduced by 5%-10% to enhance visual penetration and match the user's active state in the morning; During the day (e.g., 9:00-18:00) + medium lighting: Use regular fonts, maintain a balance between font weight and letter spacing to ensure reading efficiency; Evening (e.g., 18:00-21:00) + low light transition: The font gradually changes to a softer style, the font weight is reduced by 5%-10%, and the letter spacing is increased by 5%, to suit the user's relaxed state; Late at night (e.g., 9:00 PM - 6:00 AM) + low-light environment: Automatically switch to low visual pressure fonts such as wide round fonts, reduce font weight by 15%-25%, increase letter spacing by 10%-15%, and reduce visual fatigue associated with blue light stimulation.

[0025] In practical applications, if the current scenario is special or rare, such as when the user is in a medical setting, a high-contrast but soft font (such as dark gray rather than pure black) may be needed to reduce visual stimulation. The font emotion response model can generate corresponding font rendering parameters, but there is no corresponding scenario or preset rendering parameter range in the preset rendering adjustment rules. In this case, the font rendering parameters can be used directly for font rendering, which can enhance the user's comfort.

[0026] Step 104: When the font rendering parameters are within the preset rendering parameter range, execute the font rendering instruction corresponding to the font rendering parameters to achieve the emotional expression of the font.

[0027] In this embodiment, when the font rendering parameters and the preset rendering parameter range are consistent, the font rendering parameters can be adjusted based on the aforementioned font rendering parameters. This automated rendering mechanism reduces the frequency of users manually adjusting the font, improving ease of use. Furthermore, it allows the font to adapt to the user's current state, reducing visual fatigue and conveying matching emotions (such as vitality or relaxation), thus enhancing interactive comfort.

[0028] In this embodiment, multidimensional data of the current scene can be obtained, and then the ambient light intensity data and biological rhythm data in the multidimensional data can be input into the font emotion response model to obtain the font rendering parameters corresponding to the current scene. Subsequently, if the font rendering parameters are within the preset rendering parameter range, the corresponding font rendering instruction is executed. The emotional expression of the font can be realized in the above way, which can reduce the user's manual adjustment of the font, reduce visual fatigue, enhance the adaptability of the font to the user's state, and improve the emotional interaction experience.

[0029] In one possible implementation, obtaining multidimensional data in the current scenario includes: Ambient light signals are obtained using an ambient light sensor; The ambient light signal is processed using a sensor signal conversion and analysis method to obtain ambient light intensity data; Call the mobile device health data interface to obtain the user's circadian rhythm data, wherein the circadian rhythm data includes at least one of the following: the user's sleep schedule and activity status.

[0030] In the above embodiments, when collecting ambient light intensity data, an ambient light sensor (such as a photodiode) can be used to collect ambient light signals in real time, capturing the dynamic changes from strong light to weak light. The data processing method refers to the sensor signal conversion and analysis method in ambient light adaptive technology. When collecting circadian rhythm data, the mobile device's health data interface can be called to obtain data such as the user's sleep-wake cycle (e.g., wake-up / sleep time, active periods) and activity status (e.g., alertness, activity frequency), which serve as the basis for determining the user's current time period and status. In this way, ambient light collection can reuse existing light sensor technology, and circadian rhythm data retrieval relies on a mature health interface, resulting in strong technical compatibility and ease of implementation in mobile devices.

[0031] In practical applications, multidimensional data can also be obtained through other methods, and there are no specific restrictions.

[0032] In one possible implementation, after executing the rendering instructions corresponding to the font rendering parameters, the method further includes: Obtain the user's feedback data on the rendering effect and interaction behavior data, wherein the rendering effect is the display effect on the user interface based on the font rendering command, and the interaction behavior data includes one of the following: font adjustment operation, reading time; Based on the feedback data and the interaction behavior data, the font emotion response model is optimized and adjusted.

[0033] In practical applications, font sentiment response models are not fixed and can be optimized. For example, user feedback data on rendering effects (e.g., feedback obtained from soliciting user opinions) and interaction behavior data (e.g., font adjustment operations, reading time) can be used to adjust corresponding parameters. If, within a certain period, user feedback on the font sentiment response model is consistently unsatisfactory, or if users consistently make adjustments after automatic rendering, the font sentiment response model can be rebuilt or retrained. This allows the font sentiment response model to more accurately capture the relationship between ambient light intensity data, biorhythm data, and font rendering parameters, improving the accuracy of generation and ultimately providing users with more personalized font rendering services.

[0034] In one possible implementation, after comparing the font rendering parameters with a preset rendering parameter range, the method further includes: If the font rendering parameters are not within the preset rendering parameter range, the font rendering parameters are adjusted based on the preset rendering adjustment rules. Based on the adjusted font rendering parameters, execute the font rendering instruction corresponding to the font rendering parameters.

[0035] In the above embodiments, if the font rendering parameters are not within the preset rendering parameter range, it may be due to an error in the font emotion response model. The font rendering parameters output by the model can be adjusted based on preset rendering adjustment rules. For example, if the font rendering parameters exceed the preset range, the parameters can be reduced or regenerated. Then, based on the adjusted font rendering parameters, the corresponding font rendering instructions can be executed. This allows the font to better adapt to the user's state, reducing visual fatigue and enhancing interaction comfort.

[0036] In practical applications, the structure of the font sentiment response model is not specifically limited. For example, a traditional model structure can be adopted, where the input layer receives ambient light intensity data and circadian rhythm data, and the feature fusion layer fuses different types of input data to uncover their potential relationships and generate a more comprehensive feature representation. The hidden layer is the core of the font sentiment response model, used for deep learning and nonlinear transformation of the fused features to extract higher-level, abstract features. The output layer maps the features learned by the hidden layer to specific font parameters, providing users with font rendering parameters adapted to the current scene. The above model has a clear structure and modular design that facilitates optimization. However, the model may generate unreasonable fonts in scenes not covered in the training set (such as strokes that are too thick, causing text overlap), and direct splicing may lead to feature imbalance. Weighted fusion requires manual parameter tuning, has poor generalization, and may cause information loss. The training process of this model is consistent with that of conventional models. During training, the model can be trained by iteratively optimizing the algorithm based on a large amount of sample data (user comfort feedback under different lighting-rhythm combinations), thereby determining the optimal solution for font parameters in different scenarios (such as character weight threshold, character spacing range, and font style correspondence).

[0037] In one possible implementation, the font emotion response model may include: an environment-aware encoder, a biological rhythm encoder, a cross-modal interaction module, and a font parameter decoder; The environmental perception encoder is used to generate an environmental feature vector based on the ambient light intensity data. The circadian rhythm encoder is used to generate a circadian rhythm feature vector based on the circadian rhythm data; The cross-modal interaction module is used to generate a fused feature vector based on the environmental feature vector and the biological rhythm feature vector; The font parameter decoder is used to generate the font rendering parameters based on the fused feature vector.

[0038] In the above embodiments, the font sentiment response model can use a dual-path feature fusion mechanism to encode ambient light intensity data and circadian rhythm data separately and then perform cross-modal interaction, ultimately mapping them to an interpretable font parameter space. The input to the environmental perception encoder is ambient light intensity data. The temporal processing layer of this encoder can use LSTM or GRU networks to capture temporal changes in environmental data, while the spatial processing layer can use 1D convolution to extract local environmental features. Thus, the output of the environmental perception encoder is an environmental feature vector (containing temporal-spatial joint encoding). The input to the circadian rhythm encoder is circadian rhythm data. Fourier transform or periodic convolution can be used to capture 24-hour circadian rhythms, and then the weights of different rhythm indicators are adjusted according to the current time, thereby outputting a circadian rhythm feature vector (containing periodic-dynamic weight joint encoding). In this way, dynamic weighting avoids information loss. In the cross-modal interaction module, a multi-head attention mechanism can be used to achieve deep interaction between environmental and circadian rhythm features, while dynamically adjusting the contribution ratio of environmental and circadian rhythm features (e.g., suppressing the influence of sleep rhythm during high light) to output a fused feature vector (containing environmental-physiological synergistic information). The input to the font parameter decoder is the aforementioned fused feature vector, and random noise can be added to the font parameter decoder to increase diversity. In the font parameter decoder, a fully connected network can be used to map the fused features to an interpretable font parameter space (e.g., character height ratio, stroke thickness, tilt angle), while introducing physical constraints (e.g., minimum stroke width ≥ 0.5pt) to ensure font readability, and finally outputting font rendering parameters (e.g., {character height ratio: 1.2, stroke thickness: 3pt, tilt angle: 5°}). In this way, the font sentiment response model can automatically adjust the weights of circadian rhythm data according to the current time and environmental state (e.g., day / night) to achieve "morning / evening font differences". Furthermore, it can directly output interpretable font parameters. At the same time, the credibility of the model can be enhanced by comparing the synergistic effect of environmental data and biological rhythm data (such as generating more relaxed fonts under high light and low sleep pressure).

[0039] In the training process of the aforementioned font sentiment response model, the environmental awareness encoder and the biorhythm encoder can be pre-trained. Then, based on a large amount of sample data (user comfort feedback under different lighting-rhythm combinations), the cross-modal interaction module can be trained, enabling it to learn to select appropriate biorhythm feature weights in specific environments. Subsequently, the font parameter decoder can be trained, introducing physical constraints (such as stroke width not being negative) and aesthetic constraints (such as the golden ratio and character height ratio), while simultaneously calculating the loss function. For example, the constraint violation penalty term and user preference loss can be calculated. Other training methods can also be used, and there are no specific restrictions.

[0040] In one possible implementation, the multidimensional data further includes: document structure and reading pattern; After obtaining the font rendering parameters corresponding to the current scene output by the font emotion response model, the method further includes: The font rendering parameters, the document structure, and the reading mode are input into the academic reading model to obtain the academic font rendering parameters output by the academic reading model. The academic reading model is used to adjust the font rendering parameters based on the document structure and the reading mode to generate the academic font rendering parameters. Execute the font rendering command corresponding to the academic font rendering parameters.

[0041] In practical applications, users may engage in academic reading on mobile devices, such as reading academic papers. However, academic papers typically contain numerous mathematical formulas, references, figures, and footnotes. The layout needs to balance readability and standardization, while also reducing eye strain during extended reading sessions. Additional steps are required to improve user comfort.

[0042] In the above embodiments, document structure can be collected to identify various parts of the document (titles, paragraphs, formulas, references, etc.) and the current reading position. Reading mode detection can also be performed to determine whether the user is reading carefully, skimming, or searching for references.

[0043] After obtaining the font rendering parameters output by the font sentiment response model, these parameters can be adjusted based on the academic reading model. This academic reading model can adjust the generated font rendering parameters according to document structure and reading mode. For example, it can generate new font rendering parameters based on document structure and reading mode, then merge them with the original parameters to generate academic font rendering parameters. Alternatively, it can directly add to the font rendering parameters based on document structure and reading mode. For instance, the original font rendering parameters might include letter weight, letter spacing, and font style. When reading formulas, letter spacing can be increased to improve readability; when reading references, line spacing can be adjusted for easier skimming. Simultaneously, font size and line spacing can be adjusted according to reading position (e.g., body text or footnotes) and reading mode. It can also automatically adjust the font size, weight, and spacing of multi-level headings to create a clear visual hierarchy. In this way, adaptive rendering technology can provide optimal font rendering effects in academic paper reading scenarios, significantly improving user reading efficiency and comfort. The structure and training method of the aforementioned academic reading model are not specifically limited.

[0044] In one possible implementation, the multidimensional data further includes: biometric data and reading behavior data; After obtaining the font rendering parameters corresponding to the current scene output by the font emotion response model, the method further includes: The font rendering parameters, the biometric data, and the reading behavior data are input into the focused reading model to obtain the focused font rendering parameters output by the focused reading model. The focused reading model is used to adjust the font rendering parameters based on the emotional state and the reading cognitive state to generate focused font rendering parameters. Execute the font rendering instructions corresponding to the specified font rendering parameters.

[0045] In practical applications, users may be students who need to study on mobile devices, such as reading textbooks or learning materials. In this case, when rendering fonts, in addition to considering ambient light intensity data and circadian rhythm data, it is also necessary to consider the learner's emotional state (such as focus, interest, confusion, etc.) and reading cognitive state (such as reading speed). Dynamic font rendering is needed to adapt to the learner's emotional state and cognitive needs to improve the efficiency and comfort of reading and learning.

[0046] In the above embodiments, the multidimensional data also includes the user's biometric data (such as heart rate, skin conductance response, etc.) and reading behavior data (such as reading speed, pauses, etc.). At this point, ambient light intensity data and circadian rhythm data can be input into the font emotion response model to obtain preliminary font rendering parameters. Then, the font rendering parameters, biometric data, and reading behavior data can be input into the focused reading model. This allows the focused reading model to infer the learner's emotional state and cognitive load from the collected data, and then adjust the initial font rendering parameters based on the emotional and cognitive states to generate focused font rendering parameters, thereby adjusting the font rendering parameters in real time. The structure and training method of the above focused reading model are not specifically limited. The font rendering parameters obtained previously might include font weight, letter spacing, and font style. When learning to read, in addition to these, focusing on font rendering parameters can also include: font weight (adjusting stroke thickness, which may affect attention and visual comfort); font width (adjusting font width, which may affect reading speed and recognition difficulty); line height (adjusting line spacing, which may affect reading speed and eye strain); contrast (adjusting the contrast between text and background, which may affect visual clarity and fatigue); and color (adjusting text color, which may affect mood and attention). Adjusting font rendering in these ways can prevent information overload for users, promote comprehension, and help users maintain focus, reduce distractions, and sustain attention.

[0047] In one possible implementation, the method further includes: If the ambient light intensity data or the circadian rhythm data exceeds a corresponding preset threshold, the font rendering parameters are adjusted; and / or, Predict user behavior over a preset time period and obtain prediction results; Based on the prediction results, the font rendering parameters are adjusted.

[0048] In the above embodiments, real-time intervention can be performed based on certain rules. For example, if the ambient light is <100 lux and the time is >20:00, multi-dimensional data can be automatically input into the font emotion response model to adjust the font rendering parameters. This can avoid the problem of poor user experience caused by only acquiring multiple data but not starting dynamic font rendering, and at the same time, it can save resources.

[0049] In practical applications, adjustments can also be made based on other data. For example, if the device battery is less than 20%, dynamic rendering (such as font weight changes) can be turned off, and only basic eye protection functions can be retained. If the sitting posture tilt angle is greater than 15 degrees (detected by IMU), a "Please maintain the correct sitting posture" prompt can be displayed to the user and rendering adjustments can be paused.

[0050] In the above embodiments, adjustments can also be proactively made based on predictions of user behavior. For example, if it is predicted that "the probability of needing eye protection mode in the next hour is >80%" (e.g., the user habitually starts reading before bed at 9 PM), the screen brightness can be gradually reduced 10 minutes in advance (from 300 nits to 150 nits). If it is predicted that "the user may lose interest in the current content," the current font can be enlarged or the font style adjusted to a sharper font to attract the user's interest. The specific timing of these adjustments is not limited.

[0051] To make the above technical solutions clearer, the following will explain the methods in detail with specific font rendering examples.

[0052] Case 1: In the morning scene, the ambient light sensor detected a light intensity of >5000 lux (strong light), and the circadian rhythm data showed that the user was in the first hour after waking up (morning active state). The font emotion response model output the parameters "sharp font + font weight 700 + letter spacing - 8", and the font presented a clear and sharp visual effect. Case 2: In a late-night scene with light intensity <50 lux (low light), the circadian rhythm data shows that the user is in the normal sleep period (low activity level). The font sentiment response model outputs the parameters "fat round font + font weight 300 + letter spacing + 10", making the font round and loose, reducing visual stimulation.

[0053] The above are embodiments of the method proposed in this application. For example, based on the above method, a font emotion rendering system can also be provided. The system includes four core modules that work together to achieve dynamic rendering: The data acquisition module integrates the ambient light sensor and health data interface, responsible for real-time acquisition and preprocessing of illumination and circadian rhythm data; the model analysis module loads the font emotion response model, parses the acquired data, and outputs font rendering parameters; the font rendering module receives parameters, adjusts the font weight, spacing, style, etc. in real time, and executes rendering instructions; the feedback optimization module collects user feedback on the rendering effect (such as manual fine-tuning) for continuous optimization of model parameters.

[0054] The above system workflow is as follows: the data acquisition module transmits lighting and rhythm data to the model analysis module in real time → the model outputs the optimal rendering parameters → the font rendering module performs adjustments → the feedback optimization module collects user operations and iterates the model.

[0055] Based on the same inventive concept, this application also provides a font emotion rendering device, the structure of which is as follows: Figure 2 As shown.

[0056] Figure 2This is a schematic diagram of the internal structure of a font emotion rendering device provided in an embodiment of this application. Figure 2 As shown, the device includes: At least one processor 201; And a memory 202 that is communicatively connected to at least one processor; The memory 202 stores instructions that can be executed by at least one processor. The instructions are executed by at least one processor 201 to enable at least one processor 201 to: execute the font emotional rendering method described above.

[0057] In one possible implementation, the aforementioned processor is configured to: acquire multidimensional data of the current scene, wherein the multidimensional data includes ambient light intensity data and circadian rhythm data; input the ambient light intensity data and the circadian rhythm data into a font emotion response model to obtain font rendering parameters output by the font emotion response model corresponding to the current scene, wherein the font emotion response model is configured to generate corresponding font rendering parameters based on the ambient light intensity data and the circadian rhythm data; compare the font rendering parameters with a preset rendering parameter range, wherein the preset rendering parameter range is the rendering parameters of the scene corresponding to the current scene in the preset rendering adjustment rules; and, if the font rendering parameters are within the preset rendering parameter range, execute the font rendering instruction corresponding to the font rendering parameters to achieve emotional expression of the font.

[0058] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium stores computer-executable instructions, which are configured to execute the above-described font emotional rendering method.

[0059] In one or more possible implementations of the embodiments of this application, the aforementioned computer-executable instructions are configured to be executable to acquire multidimensional data in the current scene, wherein the multidimensional data includes ambient light intensity data and circadian rhythm data; input the ambient light intensity data and the circadian rhythm data into a font emotion response model to obtain font rendering parameters output by the font emotion response model corresponding to the current scene, wherein the font emotion response model is used to generate corresponding font rendering parameters based on the ambient light intensity data and the circadian rhythm data; compare the font rendering parameters with a preset rendering parameter range, wherein the preset rendering parameter range is the rendering parameters of the scene corresponding to the current scene in the preset rendering adjustment rules; if the font rendering parameters are within the preset rendering parameter range, execute the font rendering instructions corresponding to the font rendering parameters to achieve the emotional expression of the font.

[0060] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0061] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0068] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0070] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for rendering fonts with emotional expression, characterized in that, include: Acquire multidimensional data of the current scene, wherein the multidimensional data also includes ambient light intensity data and biological rhythm data; The ambient light intensity data and the biological rhythm data are input into the font emotion response model to obtain the font rendering parameters output by the font emotion response model corresponding to the current scene. The font emotion response model is used to generate the corresponding font rendering parameters based on the ambient light intensity data and the biological rhythm data. The font rendering parameters are compared with the preset rendering parameter range, wherein the preset rendering parameter range is the rendering parameters of the scene corresponding to the current scene in the preset rendering adjustment rules; When the font rendering parameters are within the preset rendering parameter range, the font rendering instruction corresponding to the font rendering parameters is executed to achieve the emotional expression of the font.

2. The method according to claim 1, characterized in that, The acquisition of multidimensional data in the current scenario includes: Ambient light signals are obtained using an ambient light sensor; The ambient light signal is processed using a sensor signal conversion method to obtain ambient light intensity data; Call the mobile device health data interface to obtain the user's circadian rhythm data, wherein the circadian rhythm data includes at least one of the following: the user's sleep schedule and activity status.

3. The method according to claim 1, characterized in that, After executing the rendering instructions corresponding to the font rendering parameters, the method further includes: Obtain the user's feedback data on the rendering effect and interaction behavior data, wherein the rendering effect is the display effect on the user interface based on the font rendering command, and the interaction behavior data includes one of the following: font adjustment operation, reading time; Based on the feedback data and the interaction behavior data, the font emotion response model is optimized and adjusted.

4. The method according to claim 1, characterized in that, After comparing the font rendering parameters with the preset rendering parameter range, the method further includes: If the font rendering parameters are not within the preset rendering parameter range, the font rendering parameters are adjusted based on the preset rendering adjustment rules. Based on the adjusted font rendering parameters, execute the font rendering instruction corresponding to the font rendering parameters.

5. The method according to claim 1, characterized in that, The font emotion response model includes: an environment-aware encoder, a biological rhythm encoder, a cross-modal interaction module, and a font parameter decoder; The environmental perception encoder is used to generate an environmental feature vector based on the ambient light intensity data. The circadian rhythm encoder is used to generate a circadian rhythm feature vector based on the circadian rhythm data; The cross-modal interaction module is used to generate a fused feature vector based on the environmental feature vector and the biological rhythm feature vector; The font parameter decoder is used to generate font rendering parameters based on the fused feature vector.

6. The method according to claim 1, characterized in that, The multidimensional data also includes: document structure and reading patterns; After obtaining the font rendering parameters corresponding to the current scene output by the font emotion response model, the method further includes: The font rendering parameters, the document structure, and the reading mode are input into the academic reading model to obtain the academic font rendering parameters output by the academic reading model. The academic reading model is used to adjust the font rendering parameters based on the document structure and the reading mode to generate the academic font rendering parameters. Execute the font rendering command corresponding to the academic font rendering parameters.

7. The method according to claim 1, characterized in that, The multidimensional data also includes: biometric data and reading behavior data; After obtaining the font rendering parameters corresponding to the current scene output by the font emotion response model, the method further includes: The font rendering parameters, the biometric data, and the reading behavior data are input into the focused reading model to obtain the focused font rendering parameters output by the focused reading model. The focused reading model is used to adjust the font rendering parameters based on the emotional state and the reading cognitive state to generate focused font rendering parameters. Execute the font rendering instructions corresponding to the specified font rendering parameters.

8. The method according to claim 1, characterized in that, The method further includes: If the ambient light intensity data or the circadian rhythm data exceeds a corresponding preset threshold, the font rendering parameters are adjusted; and / or, Predict user behavior over a preset time period and obtain prediction results; Based on the prediction results, the font rendering parameters are adjusted.

9. A font emotion rendering device, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform a font emotional rendering method as described in any one of claims 1-8.

10. A computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, a font emotional rendering method as described in any one of claims 1-8 is implemented.

Images