Picture generation method and device based on electronic wall calendar and computer equipment

Abstract

The invention provides a picture generation method and device based on an electronic wall calendar and computer equipment, and belongs to the field of computers. According to the method, based on parameter information capable of reflecting a use scene of the electronic wall calendar, a target prompt word group used for indicating a picture generation requirement is obtained, then the target prompt word group is processed based on a picture generation model, a picture used as a background of the electronic wall calendar is obtained, and the electronic wall calendar displays the picture as the background. Compared with the mode that the electronic wall calendar displays the picture in the preset picture library or displays the downloaded picture, the picture generated based on the target prompt word group is higher in flexibility and higher in matching degree with the use scene of the electronic wall calendar, and the display requirement of a user for the electronic wall calendar can be better met.

Description

Image generation method, apparatus, and computer equipment based on electronic calendars Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, and computer device for generating images based on an electronic calendar. Background Technology

[0002] With the development of digital technology, electronic calendars, with their ability to display diverse information and dynamically update, have gradually replaced paper calendars and become an important tool for people to obtain daily information such as time.

[0003] Currently, electronic calendars can display not only date, time, and weather information, but also images to enrich their content. For example, electronic calendars come with a preset image library from which users can select one or more images they like, and the calendar will then rotate through these selected images. Another example is that electronic calendars can connect to computers or mobile phones, allowing users to download their favorite images to their local device and then display the downloaded images.

[0004] The image generation methods described above based on electronic calendars, whether displaying images from a preset image library or images downloaded via a terminal, all display pre-prepared images. This does not necessarily match the usage scenario of an electronic calendar. In other words, the images displayed by the above methods lack flexibility and cannot meet the user's display needs for electronic calendars. Summary of the Invention

[0005] This application provides a method, apparatus, and computer device for generating images based on electronic calendars, which improves the flexibility of images to meet users' display needs for electronic calendars. The technical solution is as follows.

[0006] Firstly, a method for generating images based on an electronic calendar is provided. This method includes: obtaining at least one target prompt phrase based on parameter information of the electronic calendar, wherein the parameter information reflects the usage scenario of the electronic calendar, and the target prompt phrase is used to indicate the image generation requirements; each target prompt phrase includes multiple prompt words; processing each target prompt phrase based on an image generation model to obtain an image corresponding to each target prompt phrase; the image generation model is used to generate an image based on the prompt phrase, and the image is used as the background of the electronic calendar.

[0007] The image generation method based on electronic calendars provided in this application obtains target prompt phrases that indicate the image generation requirements based on parameter information that reflects the usage scenario of electronic calendars. Then, it processes the target prompt phrases based on an image generation model to obtain an image used as the background of the electronic calendar. The electronic calendar displays this image as the background. Compared with displaying images from a preset image library or downloaded images, the image generated based on the target prompt phrases is more flexible, more in line with the usage scenario of electronic calendars, and can better meet the user's display needs for electronic calendars.

[0008] Secondly, an image generation device based on an electronic calendar is provided. This device includes: a prompt phrase acquisition module, used to acquire at least one target prompt phrase based on parameter information of the electronic calendar, wherein the parameter information of the electronic calendar reflects the usage scenario of the electronic calendar, and the target prompt phrase is used to indicate the image generation requirements; each target prompt phrase includes multiple prompt words; and an image generation module, used to process each target prompt phrase based on an image generation model to obtain an image corresponding to each target prompt phrase, wherein the image generation model is used to generate an image based on the prompt phrase, and the image is used as the background of the electronic calendar.

[0009] Thirdly, a computer device is provided, the computer device including a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded and executed by the processor to perform the operations performed by the image generation method based on the electronic calendar provided in the first aspect or various alternative implementations of the first aspect.

[0010] Fourthly, a computer-readable storage medium is provided, wherein at least one computer program is stored therein, the at least one computer program being loaded and executed by a processor to perform the operations performed by the image generation method based on an electronic calendar provided in the first aspect or various alternative implementations of the first aspect.

[0011] Fifthly, a computer program product is provided, comprising a computer program executed by a processor to perform the operations of the image generation method based on an electronic calendar provided in the first aspect or various alternative implementations of the first aspect.

[0012] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 is a schematic diagram of the implementation environment of an image generation method based on an electronic calendar provided in an embodiment of this application; Figure 2 is a flowchart of an image generation method based on an electronic calendar provided in an embodiment of this application; Figure 3 is a flowchart of another image generation method based on an electronic calendar provided in an embodiment of this application; Figure 4 is a schematic diagram of multi-source parameter information acquisition provided in an embodiment of this application; Figure 5 is a flowchart of image generation provided in an embodiment of this application; Figure 6 is a flowchart of multi-target prompt phrase image generation provided in an embodiment of this application; Figure 7 is a flowchart of group schedule integration provided in an embodiment of this application; Figure 8 is a schematic diagram of component layout provided in an embodiment of this application; Figure 9 is a flowchart of UI component configuration data acquisition provided in an embodiment of this application; Figure 10 is a structural block diagram of an image generation device based on an electronic calendar provided in an embodiment of this application; Figure 11 is a structural schematic diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0016] In this application, the terms "first," "second," etc., are used to distinguish identical or similar items with essentially the same function. It should be understood that there is no logical or temporal dependency between "first," "second," and "nth," nor are there any restrictions on quantity or execution order.

[0017] In this application, the term "at least one" means one or more, and "multiple" means two or more.

[0018] It should be noted that all information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.), and signals involved in this application have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of related data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. For example, the parameter information, prompts, user information, and images involved in this application were all obtained with full authorization.

[0019] The image generation method based on electronic calendar provided in this application is applied to a computer device. Figure 1 is a schematic diagram of the implementation environment of the image generation method based on electronic calendar provided in this application. As shown in Figure 1, the implementation environment includes a computer device 101 and an electronic calendar 102. The computer device 101 and the electronic calendar 102 are directly or indirectly connected through a wired network or a wireless network. This application does not limit this connection.

[0020] The computer device 101 can be a terminal or a server. In some embodiments, the computer device 101 is a terminal, such as a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, smart voice interaction device, smart home appliance, or vehicle terminal, but it is not limited to these. In some embodiments, the computer device 101 is a server. For example, the computer device 101 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), big data, and artificial intelligence platforms. The computer device 101 has an application installed and running that supports the display of an electronic calendar. This application provides various functions, allowing users to configure the content displayed on the electronic calendar 102. For example, the computer device 101 can generate an image through the application and send the image to the electronic calendar 102, which will then display the image from the computer device 101 as the background. For example, computer device 101 can generate UI component configuration data through the application and send the generated UI component configuration data to electronic calendar 102. Electronic calendar 102 receives the UI component configuration data from computer device 101 and displays each UI component based on the layout and style indicated by the UI component configuration data.

[0021] For example, computer device 101 is a terminal or server used by a user. The application has functions such as registration and login, family group functionality, image library functionality, theme library functionality, and historical prompt word management. The registration and login function allows users to register and log in to their accounts through the application, enabling computer device 101 to manage the user's configuration of the electronic calendar based on their account. The family group function provides users with a group function, allowing them to create, join, and leave family groups to manage the display configuration of the electronic calendar. The image library function provides users with an image library, which can be an online art resource library from which users can select images as the background of the electronic calendar. Alternatively, the image library can be a local image library, allowing users to import local images from computer device 101 into the local image library and then select images from the local image library as the background of the electronic calendar. The theme library function provides users with a theme library, which can be a system UI (User Interface) library, a component UI library, or both. This embodiment of the application does not limit this. The system UI library includes various layouts and styles for the electronic calendar system UI, while the component UI library includes various layouts and styles for UI components that can be displayed on the electronic calendar. The aforementioned historical prompt word management function provides users with a personal database in an offline backend, storing the prompt words used by the user. This allows for subsequent image generation tasks or UI component configuration data generation tasks to be performed based on the prompt words in the personal database.

[0022] Furthermore, the various functions described above are all static functions. In this embodiment, the application running on the computer device 101 also has AI (artificial intelligence) functions. That is, the application provides users with an AI function entry point, through which users can call functions such as AI image generation, AI to-do list integration, and AI component configuration data generation.

[0023] It should be noted that the various functions of the above application are merely examples and do not limit the image generation method based on electronic calendars provided in this application embodiment. Indicatively, the above application may only have the above image generation function, or it may have any one or more other functions in addition to the above image generation function, or it may have various functions not mentioned above. This application embodiment does not limit these functions.

[0024] The aforementioned electronic calendar 102 can be a smart display terminal device such as a display screen (e.g., a drawing screen, an e-ink compatible screen, or other types of displays using low-power, high-brightness display technology), possessing functions such as calendar display and time display, and can be wall-mounted or placed on a table. The calendar display function includes at least one of the following: date display, day of the week display, lunar calendar display, solar term display, and holiday display. In some embodiments, the electronic calendar 102 also supports functions such as schedule management, information reminders, weather forecasts, music playback, and smart home interaction; this application embodiment does not limit these features. In this application embodiment, the electronic calendar 102 receives configuration information from the computer device 101 and displays corresponding backgrounds, components, and to-do items based on the configuration information.

[0025] The electronic calendar 102 can be applied to various scenarios such as education, office, commercial display, and life services. For example, in the education scenario, the electronic calendar 102 can leverage the eye-protecting characteristics of e-ink screens to build a growth companion system. Using the electronic calendar-based display method provided in this application embodiment, it can generate fun learning reminders and habit-forming plans, physically isolating entertainment access points to ensure user focus. In the office scenario, using the electronic calendar-based display method provided in this application embodiment, it can develop a team collaboration mode, realize panoramic visualization of team members' to-do lists, realize dynamic data dashboard display functions such as financial data, and generate and display knowledge graphs of hot events. In the commercial display scenario, the electronic calendar 102 can be equipped with a digital twin system for exhibits. Through cloud rendering, it can realize real-time binding of PPT (PowerPoint Presentation) templates and product parameters, and support the synchronous generation of AR (Augmented Reality) spatial annotations and narration. In the life service scenario, the electronic calendar 102 can provide multi-dimensional intelligent display services such as weather warnings, health index displays, and travel route displays.

[0026] In some embodiments, the above-mentioned electronic calendar does not have hardware devices such as microphones, cameras and speakers that may leak users' personal privacy information, thus ensuring the security of users' personal privacy information, ensuring privacy, and will not affect the user experience due to accidental touch or accidental wake-up, and can be applied in scenarios such as exhibition halls or conference rooms.

[0027] It should be noted that the various usage scenarios of the above-mentioned electronic calendar 102 are merely examples and do not limit the usage scenarios of the electronic calendar involved in the embodiments of this application.

[0028] Those skilled in the art will understand that the number of the aforementioned computer devices and electronic calendars can be more or less. For example, there may be only one computer device, or there may be dozens or hundreds of computer devices, or even more. This application does not limit the number or type of computer devices, or the number or type of electronic calendars.

[0029] In some embodiments, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can be any network, including but not limited to LAN (Local Area Network), MAN (Metropolitan Area Network), WAN (Wide Area Network), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including HTML (Hypertext Markup Language), XML (Extensible Markup Language), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as SSL (Secure Socket Layer), TLS (Transport Layer Security), VPN (Virtual Private Network), and IPsec (Internet Protocol Security) can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0030] The following describes the image generation method based on an electronic calendar provided in this application embodiment, in conjunction with the above implementation environment. Figure 2 is a flowchart of an image generation method based on an electronic calendar provided in this application embodiment. As shown in Figure 2, the method includes the following steps: 201. A computer device obtains at least one target prompt phrase based on the parameter information of the electronic calendar. The parameter information of the electronic calendar reflects the usage scenario of the electronic calendar, and the target prompt phrase is used to indicate the image generation requirements. Each target prompt phrase includes multiple prompt words.

[0031] The electronic calendar's parameters include at least one of the following: user-inputted text information, external environmental parameters, historical usage information, user's schedule data, time information, geographic location information, and network information. An application program runs on the computer device, which configures the content displayed on the electronic calendar. The user-inputted text information is the text entered by the user through the input box provided by the application program. External environmental parameters include at least one of temperature, humidity, light intensity, and weather. Historical usage information includes at least one of the user's historical image usage information and historical prompt usage information. Historical image usage information indicates images previously used by the user, i.e., images that were previously displayed as the background on the electronic calendar. Historical prompt usage information indicates prompts previously used by the user. User schedule data includes events to be performed by the user, and may also include at least one of the event's execution time and execution location; this embodiment does not limit this. Time information indicates the current date and time, geographic location information indicates the electronic calendar's geographic location, and network information indicates current events and hot topics. The target prompt phrase includes multiple prompts derived from parameter information. These prompts may include words like bright, warm, pleasant, youthful, joyful, and tense. Each prompt in the target prompt phrase indicates the image generation requirements; for example, if the prompt is "warm," then the prompt requires a warm-toned image. The usage scenarios for the electronic calendar include at least one of the following: the external environment of the electronic calendar, the user's (i.e., the user's) usage preferences, the user's mood, the current season, holiday, time of day, geographical location, and current events. The parameter information of the electronic calendar reflects its usage scenario. For example, if the parameter information indicates a high temperature, then the external environment is relatively warm; if the parameter information indicates that the user has many events to perform, then the user's mood is relatively tense; if the parameter information indicates that the current date is November 22nd, then the current season is winter.

[0032] In this embodiment of the application, the computer device obtains parameter information of the electronic calendar through at least one of sensors, databases and networks, and then obtains at least one target prompt phrase based on the parameter information of the electronic calendar.

[0033] 202. The computer device processes each target prompt phrase based on the image generation model to obtain the image corresponding to each target prompt phrase. The image generation model is used to generate images based on the prompt phrases, and the images are used as the background of the electronic calendar.

[0034] The image generation model is a pre-trained model that processes the input prompt phrases and outputs an image that matches the prompt phrases. This image is used as the background of the electronic calendar. Accordingly, the computer device sends the image to the electronic calendar, which receives and displays the image, and then displays other content on top of the image, such as the calendar, time, to-do list, and various components.

[0035] In this embodiment of the application, for each target prompt phrase, the computer device processes the target prompt phrase based on an image generation model to obtain the image corresponding to the target prompt phrase.

[0036] The image generation method based on electronic calendars provided in this application obtains target prompt phrases that indicate image generation requirements based on parameter information that reflects the usage scenario of electronic calendars. Then, the target prompt phrases are processed based on an image generation model to obtain an image used as the background of the electronic calendar. The electronic calendar displays this image as the background. Compared with displaying images from a preset image library or downloaded images, the image generated based on the target prompt phrases is more flexible, more in line with the usage scenario of electronic calendars, and can better meet the user's display needs for electronic calendars.

[0037] The above-described Figure 2 illustrates the main flow of the image generation method based on an electronic calendar provided in this application embodiment. The detailed flow of this method is described below. The image generation method based on an electronic calendar provided in this application embodiment has two scenarios: one is where there is only one target prompt phrase, and the computer device generates one or more images based on that single target prompt phrase; the other is where there are multiple target prompt phrases, and the computer device generates an image based on each target prompt phrase. These two scenarios are described below.

[0038] The detailed process of generating one or more images based on a target prompt word will be illustrated below with reference to Figure 3. Figure 3 is a flowchart of an image generation method based on an electronic calendar provided by an embodiment of this application. As shown in Figure 3, the method includes the following steps.

[0039] 301. Computer equipment acquires parameter information of electronic calendars, and the parameter information of electronic calendars reflects the usage scenarios of electronic calendars.

[0040] In this embodiment, the computer device obtains the parameter information of the electronic calendar through at least one of the following methods: the computer device obtains the parameter information of the electronic calendar from a database, the computer device obtains the parameter information of the electronic calendar through a network, and the electronic calendar sends parameter information to the computer device, and the computer device receives the parameter information from the electronic calendar. Schematively, as shown in Figure 4, the parameter information of the electronic calendar includes external environmental parameters, historical usage information, user schedule data, time information, geographical location information, and network information. The following describes each of the above parameter information items and the process of obtaining each parameter information item.

[0041] (1) External environmental parameters: External environmental parameters reflect the characteristics of the external environment in which the electronic calendar is located. For example, external environmental parameters include the temperature, humidity, light, and weather of the external environment in which the electronic calendar is located. Among them, temperature, humidity, and light are collected by sensors. For example, temperature is collected by a temperature sensor, humidity by a humidity sensor, and light by a light sensor. The sensor can be installed on the electronic calendar or on a computer device. When the sensor is installed on the electronic calendar, the electronic calendar sends the temperature, humidity, and light collected by the sensor to the computer device through the device network. For example, if a temperature sensor is installed on the electronic calendar, the electronic calendar will periodically send the temperature collected by the temperature sensor to the computer device. Alternatively, after receiving a temperature acquisition request from the computer device, the electronic calendar will send the temperature collected by the temperature sensor to the computer device. The same applies to humidity and light. This application embodiment does not limit this. The aforementioned weather data was obtained by computer devices via a network or weather software installed on the computer devices. Furthermore, the above description uses temperature, humidity, and light intensity as examples, obtained through sensor data collection. These parameters can also be obtained via a network or weather software installed on the computer devices; this application does not limit this aspect. It should be noted that the acquisition of the aforementioned external environmental parameters was done with the user's full authorization.

[0042] (2) Historical Usage Information: Historical usage information reflects the user's usage preferences. For example, historical usage information includes historical image usage information and historical prompt word usage information. Historical image usage information indicates images the user has used and their usage duration or frequency. Historical prompt word usage information indicates prompt words the user has used and their usage frequency or number of times they have been used. These previously used prompt words can be prompt words in the user-inputted text information; correspondingly, historical prompt word usage information indicates the number of times or frequency the user inputs the prompt word. Previously used prompt words can also be prompt words obtained based on the parameter information of the electronic calendar; correspondingly, historical prompt word usage information indicates the number of times or frequency the prompt word appears in the target prompt word group. This application embodiment does not limit this. In some embodiments, historical prompt word usage information also includes prompt words that the user has liked, etc. This application embodiment does not limit this. During the process of obtaining historical usage information, the computer device records images the user has used and records the usage duration or frequency of those images to obtain historical image usage information. The computer device records the prompt words that the user has previously used, and records the number of times or frequency of use of each prompt word, to obtain historical prompt word usage information. In some embodiments, the above-mentioned historical image usage information and historical prompt word usage information are stored in a database, and the computer device obtains the above information from the historical information database. This application embodiment does not limit this.

[0043] In some embodiments, during the process of obtaining historical image usage information, the computer device records the images used by the user within each period, and records the usage duration or frequency of the images within that period. Based on the usage duration or frequency of the images within that period, the computer device updates the historical image usage information. For example, the computer device replaces the old historical image usage information with the images used by the user within that period and the usage duration or frequency of those images within that period as new historical image usage information. Another example is that the computer device queries historical image usage information based on the images used by the user within that period. If the usage duration of the image exists in the historical image usage information, the computer device adds the usage duration of the image within that period to the total usage duration of the image in the historical image usage information. If the usage duration of the image does not exist in the historical image usage information, the computer device adds the image and the usage duration of the image within that period to the historical image usage information. This embodiment of the application does not limit this approach.

[0044] The above process is illustrated using the example of a computer device recording the usage duration or frequency of images to obtain historical image usage information. In some embodiments, the electronic calendar obtains and sends historical image usage information to the computer device. The electronic calendar can send historical image usage information to the computer device periodically, or it can send historical image usage information to the computer device after receiving a historical information acquisition request from the computer device. This application embodiment does not limit this. Taking recording image usage duration as an example, for each period, the electronic calendar records the usage duration of each image used within that period. The usage duration of each image is the duration the image is displayed when the electronic calendar is open. The electronic calendar periodically sends the usage duration of each image used within the above period (i.e., historical image usage information) to the computer device, and the computer device receives and stores the historical image usage information from the electronic calendar.

[0045] In some embodiments, during the process of obtaining historical prompt word usage information, the computer device records the prompt words used by the user within each period, and records the number of times or frequency of use of the prompt words within that period. Based on the number of times or frequency of use of the prompt words within that period, the computer device updates the historical prompt word usage information. For example, the computer device replaces the old historical prompt word usage information with the prompt words used by the user within that period and the number of times or frequency of use of those prompt words within that period as new historical prompt word usage information. Another example is that the computer device queries the historical prompt word usage information based on the prompt words used by the user within that period. If the historical prompt word usage information contains the number of times the prompt word is used, the computer device adds the number of times the prompt word is used within that period to the number of times the prompt word is used in the historical prompt word usage information. If the historical prompt word usage information does not contain the number of times the prompt word is used, the computer device adds the prompt word and the number of times the prompt word is used within that period to the historical prompt word usage information. This embodiment of the application does not limit this approach.

[0046] In some embodiments, during the process of obtaining historical prompt word usage information, for any prompt word, such as a prompt word in user-inputted text information, a prompt word liked by the user, or a prompt word previously used as a target prompt word group, the computer device queries the keyword database based on the prompt word. If the prompt word exists in the keyword database, the computer device performs statistics on the prompt word and records it in the historical prompt word usage information. If the prompt word does not exist in the keyword database, the computer device does not perform statistics on the prompt word, nor does it record it in the historical prompt word usage information. This avoids the scope of prompt words recorded in the historical prompt word usage information being too broad, and it also avoids recording sensitive words in the historical prompt word usage information by setting the words in the keyword database, thereby improving the security of electronic calendar usage. For example, if words such as "youth" and "family" exist in the keyword database, the computer device can perform statistics on these words and record them in the historical prompt word usage information. If words such as "handsome" and "beautiful" do not exist in the keyword database, the computer device will not perform statistics on these words and record them in the historical prompt word usage information.

[0047] The above process is illustrated using the example of a computer device recording every image and prompt word previously used by a user. In some embodiments, if the usage duration of an image is less than a preset usage duration, or if the usage frequency of an image is less than a first preset usage frequency, the computer device will not record the image in the historical image usage information. Similarly, if the number of times a prompt word is used is less than a preset number of times, or if the usage frequency of a prompt word is less than a second preset usage frequency, the computer device will not record the prompt word in the historical prompt word usage information, in order to save storage space on the computer device.

[0048] In some embodiments, when the application on the computer device has registration and login functions, each user corresponds to one account, and the computer device records the historical usage information corresponding to each account in order to provide personalized services for each user and optimize the user experience.

[0049] It should be noted that the aforementioned historical usage information was obtained with the user's full authorization.

[0050] (3) User's schedule data: User's schedule data reflects the user's time arrangement and psychological state. For example, if the user's schedule data indicates that the user has multiple meetings on a given day, it reflects that the user's schedule is relatively tight and the user's psychological state is relatively tense. If the user's schedule data indicates that the user only needs to do one outdoor activity on a given day, it reflects that the user's schedule is relatively loose and the user's psychological state is relatively relaxed and happy. This schedule data is obtained by the computer device from a schedule database. The schedule data in the schedule database can be collected from at least one of the user's input to-do items, the user's emails, text messages, memos, and reminders. This application embodiment does not limit this. It should be noted that the above schedule data is obtained with the user's full authorization.

[0051] (4) Time and Geographic Location Information: Time and geographic location information indicate the user's current geographic location and the time used at that location. The computer device locates the user's geographic location based on the user's IP (Internet Protocol) address, and then reads the time used at that location from the local system, or obtains the event used at that location via the network. This embodiment of the application does not limit this. It should be noted that the acquisition of the above-mentioned time and geographic location information is done with the user's full authorization.

[0052] (5) Online Information: Online information indicates current hot topics and events. Computer devices access various information platforms through the network to obtain these hot topics and events. It should be noted that the above-mentioned online information is obtained with the full authorization of the user.

[0053] It should be noted that the embodiments of this application use the example of parameter information including the above-mentioned multiple information to illustrate the concept. In some embodiments, the parameter information of the electronic calendar includes text information input by the user, or the parameter information of the electronic calendar includes one or more of the above-mentioned multiple information, or the parameter information of the electronic calendar includes text information input by the user and one or more of the above-mentioned multiple information. The embodiments of this application do not limit this.

[0054] 302. The computer device obtains multiple original prompt words based on the parameter information of the electronic calendar.

[0055] In this embodiment of the application, the computer device obtains multiple original prompt words based on the parameter information of the electronic calendar. When the parameter information includes multiple different types of information, the computer device obtains one or more original prompt words for each type of parameter information. The process of the computer device obtaining original prompt words based on different types of parameter information will be described below.

[0056] (1) The computer device obtains the original prompt words based on external environment parameters.

[0057] The external environmental parameters, such as temperature, humidity, light intensity, and weather, are expressed as numerical values. For example, the temperature is 25℃, the humidity is 40%, the light intensity is 10000 lx (lux), and the weather is a level 4 wind with rainfall less than 10 mm (millimeter). In the process of obtaining the original prompt words based on the external environmental parameters, the computer device converts the external environmental parameters into abstract textual expressions to obtain the original prompt words. Illustratively, the computer device converts the external environmental parameters into the original prompt words indicated by the environmental mapping conditions satisfied by the external environmental parameters in the parameter information. The environmental mapping conditions indicate the mapping relationship between the external environmental parameters and the original prompt words. For example, as shown in Table 1 below, the original prompt word corresponding to a temperature less than or equal to 5℃ is "cold," the original prompt word corresponding to a temperature between 6 and 15℃ is "cool," the original prompt word corresponding to a temperature between 16 and 25℃ is "comfortable," and the original prompt word corresponding to a temperature between 26 and 35℃ is "hot." As the examples above illustrate, the original prompts indicated by the environmental mapping conditions are set based on the characteristics of the corresponding external environment. Accordingly, the original prompts obtained based on the external environment parameters reflect the characteristics of the external environment. For example, if the external environment parameter indicates that the temperature is 3℃, which is too low, the corresponding original prompt would be "cold," accurately reflecting the characteristics of the external environment.

[0058] Table 1

[0059] The process of obtaining the original prompt words described above can improve the accuracy of image generation by converting the numerical values ​​of external environmental parameters into abstract textual expressions (i.e., original prompt words) when the image generation model has a poor understanding of numerical values ​​such as temperature, humidity, light, and weather. This allows the image generation model to generate images based on the prompt words.

[0060] (2) Computer devices obtain original prompt words based on historical usage information.

[0061] The historical usage information includes historical image usage information and historical prompt word usage information. For historical image usage information, the computer device obtains images that meet the image filtering criteria based on this information. For example, the computer device may obtain images whose usage duration is greater than or equal to the filtering duration, or images whose usage frequency is greater than or equal to a first usage frequency, or images with the longest usage duration (first number of images), or images with the highest usage frequency (second number of images). This embodiment does not limit the above image filtering criteria. When the filtered images correspond to prompt words, the computer device can directly use the prompt words corresponding to the filtered images as the original prompt words, or the computer device can process the filtered images based on a prompt word extraction model to obtain the original prompt words. This embodiment does not limit this approach. The prompt word extraction model is a pre-trained model used to identify prompt words from images. These prompt words can be at least one of the following: image brightness, hue, style, and elements within the image.

[0062] Regarding historical suggestion word usage information, the computer device obtains suggestion words that meet the suggestion word filtering criteria based on the historical suggestion word usage information. For example, the computer device obtains suggestion words whose usage frequency is greater than or equal to the number of filtering attempts; or, the computer device obtains suggestion words whose usage frequency is greater than or equal to the second usage frequency; or, the computer device obtains the third most frequently used suggestion words; or, the computer device obtains the fourth most frequently used suggestion words; or, the computer device obtains the fifth most liked suggestion words. This embodiment of the application does not limit the above suggestion word filtering criteria. The computer device uses the filtered suggestion words as the original suggestion words.

[0063] The original prompts extracted from the historical usage information in the parameter information reflect the historical usage of the electronic calendar and the user's usage preferences. The images generated subsequently based on these original prompts can well match the user's preferences and meet the user's display needs for the electronic calendar.

[0064] In some embodiments, the aforementioned historical usage information may include the user's personal information, such as the personal information entered by the user when registering an account. Before extracting the original prompt words, the computer device performs sensitive information filtering on the historical usage information to ensure the security of the user's personal information. Alternatively, after extracting the original prompt words from the historical usage information, the computer device performs sensitive information filtering on the extracted original prompt words to remove prompt words containing the user's personal information from the extracted original prompt words, thereby ensuring the security of the user's personal information. During the sensitive information filtering process, the computer device pre-sets characteristic rules for sensitive information, such as at least one of the following: keywords contained in the sensitive information, regular expressions for sensitive information, and pattern templates for sensitive information. The computer device uses these characteristic rules to perform string matching on the historical usage information to identify sensitive information in the historical usage information and delete the identified sensitive information from the historical usage information. Alternatively, the computer device uses the aforementioned characteristic rules to perform string matching on the extracted original prompt words to identify sensitive information in the extracted original prompt words and delete the sensitive information. The above-described sensitive information filtering process is merely an example. Computer devices can also perform sensitive information filtering in other ways. For example, the computer device can process historical usage information based on a pre-trained sensitive word recognition model to obtain sensitive information in the historical usage information, and then delete the sensitive information from the historical usage information. Alternatively, the computer device can process the extracted original prompt words based on the above-described sensitive word recognition model to obtain sensitive information in the original prompt words, and then delete the sensitive information from the original prompt words. This application embodiment does not limit the sensitive information filtering process.

[0065] (3) The computer device obtains the original prompt words based on the user's schedule data.

[0066] The schedule data includes events to be performed by the user. The computer device performs emotion recognition on the user's schedule data based on emotion mapping conditions to obtain the original prompt words. The emotion mapping conditions indicate the mapping relationship between keywords in the schedule data and the original prompt words. During emotion recognition, the computer device extracts at least one keyword from the user's schedule data. For each keyword, the computer device obtains the corresponding original prompt word based on the mapping key between the keyword indicated by the emotion mapping conditions and the original prompt words. For example, if the user's schedule data includes "eating hot pot tonight," the computer device extracts the keyword "hot pot" from this schedule data. Based on this keyword, it queries the emotion mapping conditions and obtains the original prompt word corresponding to "hot pot," which is "happy."

[0067] In some embodiments, during the process of extracting keywords from schedule data, the computer device performs word segmentation and deduplication on the schedule data to obtain multiple words. For each word, the computer device queries a schedule thesaurus based on that word. If the word exists in the schedule thesaurus, the computer device uses that word as a keyword extracted from the schedule data; if the word does not exist in the schedule thesaurus, the computer device discards the word and does not perform any further processing on it. The words contained in the aforementioned schedule thesaurus are words with clear meanings and are not related to sentiment, such as "fitness," "hot pot," "barbecue," and "badminton." The above process first filters the words extracted from the schedule data through the schedule thesaurus, and then obtains the original prompt words based on the filtered keywords. This avoids the keywords extracted from the schedule data having obvious sentimental biases, making the obtained original prompt words more objective and accurate. The above process of extracting keywords from schedule data is only an example. The computer device can also extract keywords from schedule data in other ways, such as processing the schedule data based on a keyword extraction model, etc. This application embodiment does not limit this.

[0068] In some embodiments, during the emotion recognition process of schedule data, each keyword has a priority. The computer device uses the original prompt words corresponding to the keywords that meet the priority conditions as the original prompt words obtained based on the schedule data. For example, the computer device uses the original prompt words corresponding to the keywords with the highest preset number of keywords as the original prompt words obtained based on the schedule data. Of course, the computer device can also filter keywords based on other priority conditions, which is not limited in this embodiment.

[0069] The above process is illustrated using the example of a pre-set priority for each keyword. In some embodiments, the computer device obtains the priority of a keyword based on the number of times it appears in the schedule data. Accordingly, the more times a keyword appears in the schedule data, the higher its priority; the fewer times a keyword appears in the schedule data, the lower its priority. In some embodiments, the computer device processes multiple keywords extracted from the schedule data based on a pre-trained priority determination model to obtain the priority corresponding to each of the multiple keywords. This application embodiment does not limit this approach.

[0070] The original prompts indicated by the aforementioned emotion mapping conditions are based on the general emotions of the public when facing corresponding events. Accordingly, the original prompts extracted from the user's schedule data reflect the emotions brought to the user by the schedule data. The images subsequently generated based on these original prompts match the user's emotions, which can optimize the user experience.

[0071] The above process is illustrated using the example of obtaining the original prompt words based on emotion mapping conditions. The computer device does not need to occupy additional storage space to run the emotion recognition model to obtain the original prompt words, thus saving storage space. Furthermore, it eliminates the need to transmit schedule data to the cloud, protecting the security of the user's schedule data. In some embodiments, the computer device can also process the aforementioned schedule data using a pre-trained emotion recognition model (such as the BERT model) to obtain the original prompt words reflecting the user's emotions; this application does not limit this approach.

[0072] (4) Computer devices obtain the original prompt words based on time information and geographical location information (also known as time and space features).

[0073] The computer device, based on the time and location information, obtains the user's current location and the time used at that location, and combines the location and time to filter for holidays, obtaining at least one of the seasonal information and holiday information, and uses the obtained information as the original prompt word. For example, if the computer device determines that the day is Chinese New Year based on the location and time, the computer device uses Chinese New Year as the original prompt word; or, if the computer device determines that the day is Christmas based on the location and time, the computer device uses Christmas as the original prompt word. This application embodiment does not limit this.

[0074] In some embodiments, before obtaining the original prompt word based on time and geographic location information, the computer device performs a device date synchronization check. That is, the computer device obtains the time used by the electronic calendar and checks whether the time used by the computer device and the electronic calendar are the same. If they are the same, the computer device obtains the original prompt word. If they are different, the computer device modifies the time used by the electronic calendar to the time used by the computer device so that the time used by the computer device and the electronic calendar are synchronized before obtaining the original prompt word.

[0075] (5) The computer device extracts the original prompt words from the network information.

[0076] In this process, the computer device performs information filtering and emotion recognition on the network information in the parameter information to obtain original prompt words. Schematic, the computer device performs word segmentation and deduplication on the network information to obtain multiple words extracted from the network information. The computer device then performs information filtering on these multiple words extracted from the network information in a manner similar to the aforementioned sensitive information filtering. Alternatively, the computer device may perform information filtering on the network information in a manner similar to the aforementioned sensitive information filtering, and then perform word segmentation and deduplication on the network information. This embodiment of the application does not limit this approach. Through the above filtering process, the computer device can filter out sensitive information and marketing information in the network information, thereby improving the effectiveness of the original prompt words subsequently obtained based on the network information. The computer device obtains multiple words through the above process. For each word, the computer device performs emotion recognition on the word using a pre-trained emotion recognition model, and selects one or more words with positive emotions from among the multiple words as original prompt words. Examples of these original prompt words include "first day of the college entrance examination," "tennis champion," and "manned space launch," etc. This embodiment of the application does not limit this approach.

[0077] The original prompt words obtained through the above process indicate network information. The images generated based on these original prompt words reflect current hot topics. Displaying these images through electronic calendars can improve the dissemination of hot topics and meet users' information acquisition needs.

[0078] In some embodiments, when the parameter information includes text information input by the user, the computer device obtains the original prompt word based on the text information input by the user in the parameter information. Indicatively, the computer device directly uses the text information as the original prompt word, or the computer device performs word segmentation and deduplication processing on the text information to obtain the original prompt word. This application embodiment does not limit this.

[0079] 303. The computer device obtains a target prompt phrase based on multiple original prompt words. The target prompt phrase is used to indicate the requirements for generating the image. Each target prompt phrase includes multiple prompt words.

[0080] In this embodiment, the computer device outputs intermediate prompt words as the original prompt words that match words in a preset word library from among multiple original prompt words. During this process, for each original prompt word, the computer device queries the preset word library. If the original prompt word exists in the preset word library, the computer device outputs it as an intermediate prompt word. The words in the preset word library are released after rigorous review. Filtering the original prompt words through this preset word library removes sensitive words and risky words that are unsuitable for image generation by the image generation model, ensuring the quality of the generated images. Furthermore, filtering the original prompt words through a controllable preset word library can prevent the computer device from malfunctioning due to "prompt word injection" attacks. After obtaining multiple intermediate prompt words, the computer device clusters these intermediate prompt words to obtain multiple candidate prompt word groups and the association value of each candidate prompt word group. Each candidate suggestion word group includes multiple intermediate suggestion words. The correlation value of each candidate suggestion word group indicates the degree of correlation between the intermediate suggestion words in the candidate suggestion word group. The higher the correlation value, the higher the degree of correlation between the intermediate suggestion words in the candidate suggestion word group; the lower the correlation value, the lower the degree of correlation between the intermediate suggestion words in the candidate suggestion word group. The computer device obtains the target suggestion word group based on the candidate suggestion word groups whose correlation values ​​meet the correlation requirements. For example, the computer device obtains the candidate suggestion word group with the highest correlation value as the target suggestion word group. This embodiment of the application does not limit this.

[0081] In some embodiments, during the clustering of multiple intermediate prompt words by the computer device, the computer device converts each intermediate prompt word into a vector. For each intermediate prompt word, the distance between the vector of the intermediate prompt word and the vectors of all other intermediate prompt words is obtained. This distance is, for example, cosine similarity, etc., which is not limited in this embodiment. The computer device adds the intermediate prompt word and other intermediate prompt words whose vectors are greater than or equal to a distance threshold to the candidate prompt word group corresponding to the intermediate prompt word, thus obtaining the candidate prompt word group corresponding to the intermediate prompt word. For each candidate prompt word group, the computer device sums or averages the distances corresponding to each intermediate prompt word in the candidate prompt word group to obtain the association value corresponding to the candidate prompt word group. For example, as shown in Table 2 below: Table 2

[0082] Referring to Table 2, the multiple intermediate prompt words are "cold", "youth", "meeting", "hot pot", "Christmas", and "bonfire party". The distances between the vector corresponding to "cold" and the vectors corresponding to "youth", "meeting", "hot pot", "Christmas", and "bonfire party" are 0.3, 0.2, 0.7, 0.8, and 0.5, respectively, with a distance threshold of 0.5. Correspondingly, the candidate prompt word group corresponding to "cold" includes "cold", "hot pot", "Christmas", and "bonfire party", and the association value of this candidate prompt word group is 2.

[0083] The above process is illustrated using the example of a computer device obtaining a target prompt word group based on association values. In some embodiments, the computer device counts the number of intermediate prompt words in each candidate prompt word group and obtains the candidate prompt word group with the most intermediate prompt words as the target prompt word group. This application embodiment does not limit this. This process does not require additional calculation of the association values ​​corresponding to the candidate prompt word groups, thus saving computing resources. When multiple candidate prompt word groups have the same number of intermediate prompt words, the computer device then obtains the association values ​​corresponding to each of the multiple candidate prompt word groups, and obtains the target prompt word group based on the association values ​​corresponding to each of the multiple candidate prompt word groups.

[0084] The above process obtains the target prompt word group by clustering multiple intermediate prompt words. This ensures that the prompt words in the target prompt word group are highly correlated, and that the images generated based on the target prompt word group are logically consistent and stylistically harmonious, resulting in high-quality images.

[0085] The above process is illustrated by directly using candidate suggestion phrases whose association values ​​meet the association requirements as target suggestion phrases. In some embodiments, the computer device expands the candidate suggestion phrases whose association values ​​meet the above association requirements based on a pre-trained text processing model to obtain the target suggestion phrases. The above process expands the candidate suggestion phrases through a text processing model, such as by standardizing and rewriting the candidate suggestion phrases to optimize them. This makes the requirements indicated by the candidate suggestion phrases more complete, highlights the key theme, and results in images generated based on the optimized candidate suggestion phrases that are more logical, more consistent, and more in line with the actual situation.

[0086] The above process is one possible implementation of a computer device obtaining at least one target prompt word group based on multiple original prompt words. This possible implementation is illustrated using obtaining one target prompt word group as an example. In the subsequent image generation process, the computer device generates one or more images based on this one target prompt word group. In some embodiments, the computer device obtains multiple target prompt word groups based on multiple original prompt words. That is, the computer device obtains the candidate prompt word group with the highest preset number of association values ​​as the target prompt word group, or the computer device obtains the candidate prompt word group with the largest preset number of intermediate prompt words as the target prompt word group. This application embodiment does not limit this. Subsequently, the computer device generates images based on each target prompt word group separately.

[0087] The above process is one possible implementation for obtaining at least one target prompt phrase based on the parameter information of the electronic calendar. This possible implementation provides a way for the computer device to automatically obtain prompt phrases when the user is unwilling to actively input them, enriching the usage modes of the electronic calendar. It enables the computer device to generate images and send them to the electronic calendar for display even without user input of prompt phrases, improving the convenience of the services provided by the electronic calendar. In addition, the personalized prompt phrase generation engine provided in this application collects various parameter information after de-identification, filters the prompt phrases through a preset thesaurus, and then clusters the prompt phrases to obtain safe and effective prompt phrases for use by AIGC (Artificial Intelligence Generated Content), which can improve the image generation effect of the image generation model.

[0088] 304. The computer device processes the target prompt phrase based on the image generation model to obtain at least one original image corresponding to the target prompt phrase. The image generation model is used to generate images based on the prompt phrase.

[0089] The image generation model described above is a pre-trained model. In this embodiment, the computer device processes the target prompt phrase based on the image generation model to obtain at least one original image corresponding to the target prompt phrase. Schematically, as shown in Figure 5, a user triggers an image generation request through the aforementioned application. The computer device obtains the target prompt phrase based on this request and uses the image generation model to generate multiple original images based on the prompt phrase included in the image generation request by calling the image generation API (Application Programming Interface). The computer device, through the aforementioned image generation model, introduces AIGC technology, enabling it to generate images with a high degree of freedom based on the target prompt phrase. This image generation model can be a diffusion model such as a poster generation algorithm; this embodiment does not limit it to this type of model.

[0090] In some embodiments, before processing the target prompt phrase based on the image generation model, the computer device normalizes and rewrites the target prompt phrase, and then processes the rewritten target prompt phrase based on the image generation model to optimize the image generation effect.

[0091] In some embodiments, as shown in FIG5, this application embodiment provides multiple generation methods. Illustratively, if the image generation request includes prompts input or selected by the user, the computer device directly calls the image generation API and uses the image generation model to generate multiple original images based on the prompts included in the image generation request. If the image generation request does not include prompts, the computer device obtains the target prompt phrase through the above process, and then calls the image generation API and uses the image generation model to generate multiple original images based on the target prompt phrase. Alternatively, the computer device calls the image generation API and uses the image generation model to generate original images based on default or random prompts. This application embodiment does not limit this approach. Of course, if the user chooses not to generate images, the computer device opens and displays a pre-set image library, from which the user selects an original image as the background for the electronic calendar. The image library can be a local image library, from which the user selects a local image. Alternatively, the image library can be a network image library, in which case the computer device provides a network preview function. The user can preview the images and select the original image from the network images to be used as the background of the electronic calendar. The computer device then downloads the image selected by the user to the local computer. Or, the computer device downloads the network images to the local computer, and the user then selects the original image from the downloaded images to be used as the background of the electronic calendar. This application embodiment does not limit this approach.

[0092] The above process integrates sensor data (such as temperature, humidity, and light intensity), time characteristics (such as schedule data and time information), and historical usage information. Based on a diffusion model, it performs three-dimensional correlation modeling to generate personalized images as the background for the electronic calendar, making the displayed content more personalized and optimizing the user experience. Furthermore, the computer device in this embodiment also supports dynamic image generation technologies such as particle effects and fluid simulation dynamic element rendering. Correspondingly, the electronic calendar supports dynamic display effects such as particle effects and fluid simulation, enriching the visual display experience.

[0093] In some embodiments, as shown in FIG5, after generating multiple original images, the computer device displays these original images, and the user can choose to keep or not keep the original images generated by the computer device. If the user chooses not to keep all the original images generated by the computer device, the computer device calls the image generation API to regenerate the original images, or the computer device stops generating images. If the user chooses to keep all or part of the original images generated by the computer device and the user chooses to perform a retouching operation on the kept original images, the computer device performs step 305 below based on the original images kept by the user to perform style rendering on the original images. In the case where the original images are images selected by the user from an image library, the computer device may also perform step 305 below on the original images if the user chooses to perform a retouching operation on the original images.

[0094] 305. For each original image, the computer equipment processes the original image based on the image style transfer model to obtain the image corresponding to the target prompt phrase. The image style transfer model is used to render the style of the image, and the processed image is used as the background of the electronic calendar.

[0095] The aforementioned image style transfer model is a pre-trained model, such as a model employing an image transfer algorithm. In this embodiment, for each original image, the computer device processes the original image based on the image style transfer model to perform style rendering, obtaining an image corresponding to the target prompt phrase. Schematively, as shown in Figure 5, the computer device calls the image style transfer API to process multiple original images using the image style transfer model, obtaining multiple images corresponding to the target prompt phrase. This process, by processing multiple original images based on the image style transfer model, enables the generation of multiple images with different parameters under the same theme, based on the target prompt phrase. These parameters include at least one of brightness, time, and weather. For example, based on the weather conditions, the computer device uses the aforementioned image generation method based on an electronic calendar to generate 24 images with the same style, each image corresponding to one hour of the 24-hour period, reflecting the weather within that time period. The electronic calendar changes its background every hour, providing users with a sense of novelty. For example, based on the user's usual settings, the computer device can generate ultra-low brightness images for power-saving or away-from-home modes, enabling the electronic calendar to display backgrounds with low power consumption and thus save energy. Furthermore, based on the aforementioned image style transfer model, the computer device can render images in different styles to suit different types of users (such as different age groups). For instance, in educational scenarios, the computer device can use the image style transfer model to render the original image as a cartoon style, avoiding an overly realistic style. Similarly, in commercial display scenarios, the computer device can use the image style transfer model to render the original image in a comic book style, etc., depending on the specific circumstances. This application does not limit the scope of these embodiments. Rendering the original image using the image style transfer model makes the rendered image more suitable for the electronic calendar's usage scenario, optimizing the user experience.

[0096] In some embodiments, as shown in Figure 5, after obtaining multiple images corresponding to the target prompt phrase, the computer device displays these images. The user can choose to retain or not retain the multiple images rendered by the computer device. If the user chooses not to retain the multiple images, the computer device stops generating images. If the user chooses to retain the multiple images, the computer device stores the multiple images in a background library so that the images in the background library can be used as the background of the electronic calendar and displayed on the electronic calendar in subsequent processes.

[0097] The above process is illustrated using the example of a user choosing to retouch the original image. In some embodiments, the user chooses not to retouch the original image, and the computer device stores the original image in a background library so that the image in the background library can be used as the background of the electronic calendar and displayed on the electronic calendar in subsequent processes.

[0098] The above process is one possible implementation method based on an image generation model, which processes each target prompt phrase to obtain the image corresponding to each target prompt phrase. This possible implementation method is illustrated using the generation of an image based on a single target prompt phrase as an example. In some embodiments, there are multiple target prompt phrases, and the computer device generates images based on each of these multiple target prompt phrases. The following content describes this process in detail with reference to Figure 6.

[0099] As shown in Figure 6, the computer device obtains multiple target prompt phrases based on a pre-set image generation mode. This image generation mode indicates the division method of the electronic calendar's parameter information. Correspondingly, based on this image generation mode, the computer device divides the electronic calendar's parameter information into multiple parts, and obtains a target prompt phrase based on each part of the parameter information. This acquisition process is similar to the related content mentioned above. For example, referring to Figure 6, the image generation mode can be a weather mode or a to-do mode. When the user selects the weather mode, the computer device connects to the network to obtain weather information based on the user's IP address, processes the weather information based on the weather information processing model, and obtains weather change information within 24 hours. This weather change information includes temperature changes and clothing recommendations, etc., which are not limited in this embodiment. The computer device divides the electronic calendar's parameter information according to the weather change period, obtaining the parameter information corresponding to each weather change period. Based on the parameter information corresponding to each weather change period, the computer device obtains the target prompt phrase corresponding to that weather change period. That is, the computer device generates prompts one by one according to the weather change period, and the obtained target prompt phrase is also called a weather change prompt phrase. When the user selects the to-do mode, the computer device obtains multiple to-do items (i.e., a to-do list) through step 306. Then, based on a time-segmentation model, it processes these multiple to-do items to identify several key to-do items with clearly defined time intervals. The computer device divides the parameter information of the electronic calendar based on the time period corresponding to each key to-do item, obtaining parameter information for each time period. Based on the parameter information for each time period, the computer device obtains the target prompt phrases corresponding to that time period. In other words, the computer device generates prompts one by one according to the key to-do items; the resulting target prompt phrases are also called dynamic to-do prompt phrases. After obtaining multiple target prompt phrases, for each target prompt phrase, the computer device processes it based on an image generation model to obtain at least one candidate image corresponding to that target prompt phrase. Then, based on the at least one candidate image corresponding to each of the multiple target prompt phrases, it obtains the image corresponding to each target prompt phrase.

[0100] In some embodiments, during the process of the computer device acquiring at least one candidate image corresponding to each target prompt phrase, for the first target prompt phrase, the computer device processes the first target prompt phrase based on an image generation model to obtain at least one candidate image corresponding to the first target prompt phrase. For the i-th target prompt phrase, the computer device processes the i-th target prompt phrase and the template image based on an image generation model to obtain at least one candidate image corresponding to the i-th target prompt phrase. The template image is a candidate image corresponding to the target prompt phrase preceding the i-th target prompt phrase (the template target prompt phrase). For example, the template image is one or more candidate images corresponding to the first target prompt phrase, or the template image is one or more candidate images corresponding to the (i-1)-th target prompt phrase. This embodiment does not limit this, and i is an integer greater than 1.

[0101] In some embodiments, when each target prompt phrase corresponds to one candidate image, the template image is the candidate image corresponding to the template target prompt phrase. When each target prompt phrase corresponds to multiple candidate images, each candidate image corresponding to the template target prompt phrase is a template image. The computer device processes each candidate image corresponding to the i-th target prompt phrase and the template target prompt phrase based on the image generation model to obtain multiple candidate images corresponding to the i-th target prompt phrase. The different candidate images corresponding to the i-th target prompt phrase are obtained based on the different candidate images corresponding to the template target prompt phrase.

[0102] For example, taking the weather pattern as an example, the computer device generates a candidate image based on the first target cue phrase. This candidate image is a template used to generate images based on the cue phrase. In this process, the computer device takes the following content or text generated based on the following content as input to the image generation model: "Change logic is: {weather / logic}; current information is: {first target cue phrase}; requirements include: {① Do not make too many literary descriptions, and focus on conciseness and accuracy in generating the target; ② Ensure that the description of the cue phrase itself has no logical conflicts; ③ This cue phrase will be directly used for image generation, so do not output any markdown or other formatted information...".

[0103] After obtaining the template image, the computer device generates candidate images corresponding to other target prompt phrases based on the idea of ​​One-Shot Learning. Illustratively, the computer device generates candidate images corresponding to the target prompt phrase based on the template image and the i-th target prompt phrase. During this process, the computer device uses the following content or text generated based on the following content as input to the image generation model: "Change logic is: {weather / logic}; Current information is: {i-th target prompt phrase}; Requirements include: {① Do not make too many literary descriptions; focus on conciseness and accuracy in target generation; ② Ensure that the description of the prompt phrase itself has no logical conflicts; ③ This prompt phrase will be directly used for image generation, so do not output any markdown or other formatted information; ④ Please maintain a high degree of consistency with the {template image}, only making distinctions in details…}.

[0104] By generating candidate images corresponding to multiple target cue phrases through the above process, a high degree of consistency can be achieved among the candidate images corresponding to multiple target cue phrases, thereby ensuring that the multiple backgrounds displayed on the electronic calendar maintain a consistent style and optimizing the display effect.

[0105] In some embodiments, during the process of obtaining the image corresponding to each target prompt word group based on the candidate images corresponding to each of the multiple target prompt word groups, the computer device arranges and combines at least one candidate image corresponding to each of the multiple target prompt word groups to obtain multiple image groups. Each image group includes one candidate image corresponding to each of the multiple target prompt word groups, and the multiple image groups do not overlap. For example, if there are two target prompt word groups, and each target prompt word group corresponds to two candidate images, namely T11, T12, T21, and T22, then the computer device can obtain four image groups, namely (T11, T21), (T11, T22), (T12, T21), and (T12, T22). For each image group in a plurality of image groups, the computer device processes multiple candidate images in the image group based on a pre-trained image recognition model to obtain the position of key elements (such as the coordinates of key elements) in each candidate image in the image group. Then, based on the position of key elements in each candidate image in the image group, the consistency degree among multiple candidate images in the image group is obtained. This consistency degree indicates the degree of consistency among multiple candidate images in the image group. The consistency degree among multiple candidate images in the image group can be realized as the sum of the distances between the position of a key element in any candidate image in the image group and the positions of key elements in every other candidate image in the image group, etc., and this embodiment of the application does not limit this. The computer device determines the candidate image corresponding to each target prompt phrase in the image group that meets the consistency requirement as the image corresponding to the target prompt phrase. For example, the computer device determines the candidate image in the image group with the highest consistency degree as the image corresponding to the target prompt phrase. The above process generates multiple candidate images for each target prompt phrase. Then, the candidate images corresponding to multiple target prompt phrases are combined into multiple selectable combinations. Using the idea of ​​cluster analysis, an object detection algorithm is introduced to select the position of key elements in the candidate images. Based on this position, multiple candidate images in the image group are matched with each other, and the image group with the highest consistency is selected. This achieves the goal of ensuring the consistency of elements among the images in the image group through consistency checks. This is used to ensure high consistency among multiple images used as backgrounds for electronic calendars, thereby optimizing the display effect.

[0106] The image generation process described above focuses on the consistency between images, such as thematic consistency or stylistic consistency, as well as the degree to which image prompts are followed, such as whether the images contain key elements and whether they are presented in chronological order. This process transforms weather change information or a list of events with a chronological relationship into a set of images with a visual expression of time sequence and priority. Through visual presentation, it helps users intuitively perceive weather changes or the importance and time distribution of events.

[0107] In some embodiments, the computer device performs reinforcement learning to fine-tune the image generation model, such as by deploying a camera with a fixed viewpoint and capturing changes in lighting or weather at the same location as the camera to construct a time-series change dataset. This dataset includes parameters such as real temperature and time, and the parameters in the dataset are labeled with keywords such as weather by humans. The computer device uses this dataset to fine-tune and train the image generation model to enhance the generation capability of the image generation model.

[0108] After receiving the image corresponding to the target prompt phrase, the computer device sends the image to the electronic calendar. Upon receiving the image from the computer device, the electronic calendar displays the image as its background. In some embodiments, when there are multiple target prompt phrases, as explained above, each target prompt phrase corresponds to a time period, such as a weather change period or a time period corresponding to a key to-do item. During the process of sending images corresponding to multiple target prompt phrases to the electronic calendar, the computer device sends the image corresponding to each target prompt phrase and the time period corresponding to that target prompt phrase. This allows the electronic calendar to display the image within the corresponding time period after receiving it from the computer device, switching the displayed image as the time period changes.

[0109] 306. The computer device processes the user's schedule data based on the schedule integration model to obtain multiple first to-do items that conform to a preset format. These multiple first to-do items are used to display on the electronic calendar in a preset manner.

[0110] The user's schedule data is data obtained by the computer device from a schedule database. The schedule data in the database is collected from at least one of the following: user-input to-do items, user emails, SMS messages, memos, and reminders. For example, the schedule data may be imported schedules or to-do items from the user's mobile phone, schedules or to-do items created by the user through the aforementioned application, or schedules or to-do items extracted from the user's SMS or email content. This application embodiment does not limit this. For example, a user's email may contain a meeting notification indicating that the user will attend a meeting at 3 PM today. Another example is a memo indicating that the user has an exam at 9 AM today. The aforementioned schedule integration model is a pre-trained model used to convert schedule data into to-do items in a preset format. For example, if the preset format is "Time-Location-Event-Person," and the schedule data includes "User xxx will attend a meeting at 3 PM on January 21st," then the to-do item obtained after processing by the schedule integration model would be "2026 / 01 / 21-15:00-Attend Meeting-User xxx".

[0111] In this embodiment, the computer device retrieves the user's schedule data within a preset time period from a schedule database, such as the user's schedule data for the current day, the user's schedule data for the week, or the user's schedule data for the past three days, etc. This embodiment does not limit the scope of the data. Based on a schedule integration model, the computer device processes the user's schedule data to obtain multiple first to-do items conforming to a preset format. The computer device sends these multiple first to-do items to the electronic calendar, and the electronic calendar displays these multiple first to-do items in a preset area. This process enables the electronic calendar to have a schedule reminder function, allowing it to not only display the calendar and time but also the user's to-do items, enriching the functionality of the electronic calendar and better meeting the user's display needs.

[0112] The above process is illustrated by taking the acquisition of to-do items in a preset format based on a schedule integration model as an example. In some embodiments, the user creates or inputs to-do items in a preset format through the above application, and the computer device directly obtains the to-do items input by the user. Alternatively, the computer device imports to-do items in a preset format from the user's memos or reminders. This simplifies the process of acquiring to-do items and eliminates the need to deploy an additional schedule integration model on the computer device, thereby saving computing resources.

[0113] In some embodiments, the computer device and the aforementioned electronic calendar also provide a family group to-do function. Users can create, join, leave, and delete groups using their corresponding accounts through the application, integrating schedules and displaying to-do items by group. These groups are also called family groups, and this embodiment does not limit the specific group. Schematically, as shown in Figure 7, after logging into their account through the application, users can choose whether to join an existing family group. If a user chooses to join an existing family group, they send a join request to the group's administrator through the application. After the administrator approves the request, the user joins the existing family group. If a user chooses not to join an existing family group, they can create a family group through the application to join another family group, and this embodiment does not limit the specific family group. When a user selects to integrate schedules and display to-do items by family group, the computer device obtains the to-do items of multiple members in the group through the aforementioned processes. For example, the computer device processes the schedule data of multiple members in the group based on a schedule integration model to obtain multiple second to-do items conforming to a preset format. In this process, the computer device can process the schedule data of each member sequentially to obtain that member's to-do items, or it can process the schedule data of multiple members as a whole to obtain the to-do items of multiple members. This application embodiment does not limit this approach. Another example is that the computer device obtains each member's to-do items from each member's memos or reminders in the group. Yet another example is that each member in the group creates or inputs to-do items through the aforementioned application, and the computer device obtains the to-do items created or input by each member. This application embodiment does not limit this approach either.

[0114] After receiving the to-do items from multiple members in the group, as shown in Figure 7, the group administrator proactively initiates the family group to-do item consolidation function, or the computer device periodically initiates this function. After initiating the consolidation, the computer device merges the to-do items from multiple members according to preset merging rules, such as time-priority merging, location-priority merging, task-priority merging, or personal task-priority merging. When the preset merging rule is time-priority, location-priority, or task-priority merging, the computer device obtains the family group's to-do items by merging multiple members' to-do items. The computer device then updates the family group's to-do items using the newly obtained to-do items and sends them to the electronic calendar to ensure the calendar displays the latest to-do items. When the preset merging rule is personal task-priority, the computer device obtains each member's individual to-do items by merging multiple members' to-do items. The computer device then updates each member's individual to-do items using their new personal to-do items and sends them to the electronic calendar to ensure the calendar displays the latest to-do items. The preset merging rules are rules set by the administrator, rules based on user preferences obtained from system statistics, or system default rules. This application embodiment does not limit these rules.

[0115] The merging methods are as follows: **Time-priority merging:** The computer device pre-sets multiple time periods, merging multiple to-do items whose execution time falls within the same time period into one category. The electronic calendar then displays these to-do items in different time periods. **Location-priority merging:** The computer device merges multiple to-do items whose execution location is the same into one category. The electronic calendar then displays these to-do items in different locations. **Event-priority merging:** The computer device merges multiple to-do items whose pending events are the same into one category. The electronic calendar then displays these to-do items with different pending events. **Personal event priority merging:** The computer device categorizes to-do items according to members within a group. The electronic calendar then displays these to-do items to be executed by different members of the group.

[0116] In some embodiments, as shown in Figure 7, after initiating the family group to-do integration function, the computer device checks whether each to-do item conforms to the preset format. If the to-do item does not conform to the preset format, the computer device extracts the to-do item based on the schedule integration model to obtain the to-do item that conforms to the preset format. If the to-do item conforms to the preset format, the computer is set to continue executing the subsequent family group to-do integration function.

[0117] In some embodiments, the above-mentioned preset format is obtained by the user configuring the above-mentioned schedule integration model through a computer device. For example, the computer device sets the role of the schedule integration model to "you are a family schedule intelligent aggregator, integrating scattered to-do items according to the timeline", sets the input of the schedule integration model to "the original to-do text provided by the user (supporting mixed Chinese and English)", and sets the processing rules of the schedule integration model as follows.

[0118] 1. Time deconstruction .

[0119] Absolute time (e.g., "July 20th, 2 PM"): Convert to ISO format; Relative time (e.g., "Next Monday"): Calculated based on the current date 2025-07-17; Fuzzy time (e.g., "Weekend"): Parsed as Saturday or Sunday; No time item: Classified as "unscheduled".

[0120] 2. Task aggregation .

[0121] Tasks with the same date are merged into an array; the original text is retained for tracing purposes.

[0122] The computing device's schedule integration model output requirement is to strictly return clean JSON, with the following structure: json{"timeline": [{"date": "2025-07-20", "display_date": "July 20th (Sunday)", "period": "All day / morning / afternoon / evening", "tasks": [{"task": "task summary", "raw_text": "raw input text", "time_ref": "specific time point (optional)"}]}], "unscheduled": [{"task": "task summary", "raw_text": "raw input text"}]} For example, if the schedule data is ["Pick up a package at 10 am on Saturday", "Repair the water pipe on Sunday afternoon", "Buy a birthday present as soon as possible"], the to-do list obtained after processing by the schedule integration model is as follows: {"timeline": [{"date": "2025-07-19", "d `isplay_date`: "July 19th (Saturday)", "period": "morning", "tasks": [{"task": "Pick up package", "raw_text": "Pick up package at 10:00 AM on Saturday", "time_ref": "10:00"}]}, {"date": "2025-07-20", "display_date": "July 20th (Sunday)", "period": "afternoon", "tasks": [{"task": "Fix water pipe", "raw_text": "Fix water pipe on Sunday afternoon"}]}], "unscheduled": [{"task": "Buy birthday present", "raw_text": "Buy birthday present as soon as possible"}]} The above content, by providing a family group to-do function, builds a family group network, intelligently coordinates the to-do items of each member in the family group, and provides visual reminders, enriching the functions of the electronic calendar and increasing its appeal to users. Furthermore, the acquisition and integration of the aforementioned to-do items rely on the large model extraction function. This large model extraction function can be applied not only to schedule data but also to functions such as promotional copy generation, dish descriptions, and daily menu generation. This application embodiment does not limit this aspect.

[0123] 307. The computer device obtains UI component configuration data based on the image corresponding to the target prompt phrase. The UI component configuration data indicates the layout and style of at least one UI component. The UI component configuration data is used to display the at least one UI component on the electronic calendar in the aforementioned layout and style.

[0124] UI components are used to divide display areas on the electronic calendar. Different UI components correspond to different display areas. By displaying different categories of content on different UI components, users can quickly distinguish between different categories of content. For example, Figure 8 below is a schematic diagram of a component layout provided by an embodiment of this application. As shown in Figure 8, the electronic calendar displays a calendar on one UI component and to-do items on another UI component. UI components are usually distinguished from the background by borders, background colors, and shadows, thereby highlighting the display content corresponding to the UI component. The layout of the UI component indicates the size of the UI component and its position on the electronic calendar (or an image used as the background of the electronic calendar). The style of the UI component includes at least one of the following: brightness, transparency, hue, color temperature, and pattern. The UI component configuration data can be implemented as a JSON file, for example, a computer device sends the JSON file to the electronic calendar, and the electronic calendar displays the UI components based on the layout and style indicated by the JSON file, and displays the content corresponding to the UI component on the UI component.

[0125] In this embodiment, the computer device and the electronic calendar provide intelligent rendering functionality for system theme components. As shown in Figure 9, after obtaining the image corresponding to the target prompt phrase in a manner similar to that in Figure 5, the computer device generates block information for each UI component in at least one UI component based on the image. The block information indicates the position, size, and style of the corresponding UI component. This block information can be implemented as a JSON file, etc., and this embodiment does not limit this. In this process, the computer device processes the image corresponding to the target prompt phrase and the display information of the electronic calendar based on a pre-trained block information generation model to obtain the block information for each UI component. The display information of the electronic calendar includes the content to be displayed on the electronic calendar, the position and size of each content item on the electronic calendar, etc. For example, the display information of the electronic calendar indicates that the calendar is displayed in a 16×16 area in the upper left corner of the electronic calendar. Then, referring to Figure 9, the computer device performs style rendering on at least one UI component one by one. During this process, the computer device processes the block information and target prompt phrases of each UI component based on the component rendering model to obtain the configuration data of each UI component. The computer device integrates the configuration data of each UI component to obtain the UI component configuration data.

[0126] In some embodiments, as shown in Figure 9, before obtaining the configuration data for each UI component, the computer device performs normalized rewriting of the target prompt phrases to optimize the generation effect of the configuration data for the UI components.

[0127] In some embodiments, as shown in Figure 9, after obtaining the configuration data of each UI component, the computer device checks the configuration data of the UI component through a compliance checker, such as checking whether the UI component exceeds the display range of an image or electronic calendar. If the configuration data of the UI component passes the check, the computer device retains the configuration data of the UI component. If the configuration data of the UI component fails the check, the computer device optimizes the target prompt phrase, and then processes the block information of the UI component and the optimized target prompt phrase based on the component rendering model to obtain the configuration data of the UI component.

[0128] In some embodiments, during the process of integrating the configuration data of multiple UI components, the computer device merges the configuration data of multiple UI components into one UI component configuration data, or the computer device processes the configuration data of multiple UI components and target prompt phrases based on a pre-trained configuration data generation model to obtain UI component configuration data (such as UI component Theme Configuration JSON). This application embodiment does not limit this.

[0129] In some embodiments, as shown in Figure 9, after obtaining the UI component configuration data, the computer device performs a global UI check on the UI component configuration data to check whether the UI component indicated by the UI component configuration data meets the visual harmony conditions. If the UI component indicated by the UI component configuration data does not meet the visual harmony conditions, that is, the UI component is determined to be visually conflicting, the computer device rewrites the target prompt words and regenerates the UI component configuration data. If the UI component indicated by the UI component configuration data meets the visual harmony conditions, the computer device sends the UI component configuration data to the electronic calendar so that the electronic device applies the UI component layout and style indicated by the UI component configuration data. The computer device can perform a global UI check on the UI component configuration data in various ways. For example, the computer device checks whether the difference between the hue of the UI component and the hue of the background is greater than or equal to a first preset difference. If the difference is greater than or equal to the first preset difference, the UI component does not meet the visual harmony conditions; if the difference is less than the first preset difference, the UI component meets the visual harmony conditions. For example, the computer device checks whether the difference between the hue of a UI component and the hue of adjacent UI components is greater than or equal to a second preset difference. If the difference is greater than or equal to the second preset difference, the UI component does not meet the visual harmony condition; if the difference is less than the second preset difference, the UI component meets the visual harmony condition. Of course, the computer device can also use other methods to perform global UI checks on UI component configuration data, which will not be elaborated on in this embodiment.

[0130] The above process is illustrated using the example of a computer device generating UI component configuration data. In some embodiments, as shown in Figure 9, the computer device pre-sets multiple UI styles and corresponding UI component configuration data. The user selects a UI style through the application. Based on the user's selection, the computer device uses the UI style specified by the selection and sends the corresponding UI component configuration data to the electronic calendar so that the electronic calendar displays the UI components according to the layout and style of the UI components indicated by the UI component configuration data.

[0131] In some embodiments, the computer device may implement the above functions through MCP (Model Context Protocol), and this application embodiment does not limit this.

[0132] The above-described rendering process for UI components implements an agent-driven adaptive interaction architecture. Based on the visual cognition of a large model agent, it dynamically adjusts the configuration data such as brightness, transparency, color temperature, and layout of UI components to dynamically match display performance, ambient lighting, and user visual habits, thereby optimizing the user experience.

[0133] 308. Computer equipment is set with reminder parameters. These parameters are used to enable the electronic calendar to display images or UI components that meet the reminder conditions in a preset display manner when the reminder conditions are met.

[0134] The preset display modes include at least one of the following: solid color gradient display, brightness change display, background color switching display, and flashing display.

[0135] In this embodiment, the computer device sets reminder parameters through the aforementioned application, such as setting reminder conditions that the electronic calendar must meet, setting the preset display method when the reminder conditions are met, and setting whether to display the entire image or the corresponding UI components in the preset display method, etc. This embodiment does not limit these settings. The computer device sends these reminder parameters to the electronic calendar so that the electronic calendar displays based on these parameters. For example, a user sets a to-do item for 9 PM through the computer device. By setting the reminder parameters, the computer device causes the electronic calendar to change the background color of the "calendar area" to a solid color gradient and increase the brightness to provide a visual "silent reminder."

[0136] The speakerless visual reminder mechanism described above achieves a silent, strong visual reminder by rotating the RGB (Red-Green-Blue) background color. In some embodiments, the electronic calendar can also simultaneously trigger multi-channel reminders from the mobile application, that is, trigger the computer device to remind users in the form of pop-ups or vibrations, thereby enhancing the reminder effect.

[0137] It should be noted that any of the steps 306 to 308 above are optional steps. The computer device may execute the step to enrich the functions of the electronic calendar, or it may not execute the step to save computing resources. This application embodiment does not limit this.

[0138] The image generation method based on electronic calendars provided in this application obtains target prompt phrases indicating image generation requirements based on parameter information reflecting the usage scenario of the electronic calendar. Then, it processes the target prompt phrases using an image generation model to obtain an image used as the background of the electronic calendar. Compared to displaying images from a preset image library or downloaded images, this image generation method based on target prompt phrases is more flexible, better suited to the usage scenario of the electronic calendar, and better meets users' display needs. This method integrates multimodal perception, AIGC generation, and agent (intelligent agent) decision-making capabilities. It is an intelligent interactive electronic calendar system and dynamic content generation method based on a large-model agent, applicable to smart homes, artificial intelligence technologies, and the Internet of Things. It solves problems such as insufficient visual interaction depth, limited scene adaptability, and weak proactive service capabilities in traditional intelligent assistant devices. It constructs physical carriers for different application scenarios and achieves closed-loop control of environment perception, content generation, and interface optimization by combining with a large-model agent system. This method also addresses the following issues present in existing devices: weak scene adaptability (i.e., existing devices cannot dynamically adjust display strategies based on user history and external environmental parameters), lack of dynamic content (i.e., existing devices only support static image display or manual subject switching, and cannot generate personalized content based on the environment and user history), limited interaction dimensions (i.e., existing devices rely on voice or touch to adjust display content, lacking visual interaction that combines AI-generated content), insufficient adaptation to large-screen scenarios (i.e., existing large-size screens are not optimized for home scenarios, resulting in high power consumption, poor eye protection, and fragmented functions), and weak intelligent linkage capabilities (i.e., the reminder function of existing devices is limited to local data and cannot integrate network information such as weather warnings with user behavior to generate proactive suggestions). Furthermore, the electronic calendar involved in this method fills a gap in the large-screen ecosystem, specifically by expanding the application of large-size smart screens in home scenarios. In summary, this method, coupled with a mobile control system, supports remote configuration of device parameters, content library management, and cross-screen interactive operation. Through multi-source data fusion and agent autonomous decision-making mechanism, it achieves a technological leap from static display to scenario-based intelligent services, forming a systematic innovation in energy efficiency control, eye-protection display, and personalized interaction. It is applicable to various scenarios such as home, education, office, and commercial display.

[0139] Figure 10 is a structural block diagram of an image generation device based on an electronic calendar according to an embodiment of this application. This device is used to execute the steps of the above-described image generation method based on an electronic calendar. Referring to Figure 10, the image generation device based on an electronic calendar includes: a prompt phrase acquisition module 1001, used to acquire at least one target prompt phrase based on the parameter information of the electronic calendar. The parameter information of the electronic calendar reflects the usage scenario of the electronic calendar, and the target prompt phrase is used to indicate the image generation requirements. Each target prompt phrase includes multiple prompt words. An image generation module 1002 is used to process each target prompt phrase based on an image generation model to obtain an image corresponding to each target prompt phrase. The image generation model is used to generate an image based on the prompt phrase, and the image is used as the background of the electronic calendar.

[0140] In some embodiments, the above-mentioned prompt word acquisition module 1001 includes: an original prompt word acquisition unit, used to acquire multiple original prompt words based on the parameter information of the electronic calendar; and a prompt word group acquisition unit, used to acquire at least one target prompt word group based on the multiple original prompt words.

[0141] In some embodiments, the original prompt word acquisition unit is configured to: acquire original prompt words based on text information input by the user in the parameter information; convert external environmental parameters into original prompt words indicated by environmental mapping conditions based on environmental mapping conditions satisfied by external environmental parameters in the parameter information, wherein the external environmental parameters include at least one of temperature, humidity, light intensity, and weather, and the environmental mapping conditions indicate the mapping relationship between the external environmental parameters and the original prompt words, and the original prompt words reflect the characteristics of the external environment; extract original prompt words from historical usage information in the parameter information, wherein the historical usage information includes at least one of the user's historical image usage information and historical prompt word usage information, and the original prompt words reflect the historical usage of the electronic calendar; perform emotion recognition on the user's schedule data in the parameter information based on emotion mapping conditions to obtain original prompt words, wherein the emotion mapping conditions indicate the mapping relationship between keywords in the schedule data and the original prompt words, and the original prompt words reflect the emotions brought to the user by the schedule data; acquire original prompt words based on time information and geographical location information in the parameter information, wherein the original prompt words indicate at least one of seasonal information and holiday information; and perform information filtering and emotion recognition on network information in the parameter information to obtain original prompt words, wherein the original prompt words indicate network information.

[0142] In some embodiments, the above-mentioned prompt word group acquisition unit includes: an intermediate prompt word acquisition subunit, configured to output the original prompt words that match words in a preset word library from a plurality of original prompt words as intermediate prompt words; a clustering subunit, configured to cluster the plurality of intermediate prompt words to obtain a plurality of candidate prompt word groups and an association value for each candidate prompt word group, wherein each candidate prompt word group includes some or all of the intermediate prompt words from the plurality of intermediate prompt words, and the association value of each candidate prompt word group indicates the degree of association between the intermediate prompt words in the candidate prompt word group; and a prompt word group acquisition subunit, configured to acquire a target prompt word group based on the candidate prompt word groups whose association values ​​meet the association requirements.

[0143] In some embodiments, the above-mentioned prompt word group acquisition subunit is used to: expand the candidate prompt word groups whose association values ​​meet the association requirements based on the text processing model to obtain the target prompt word group.

[0144] In some embodiments, the above-mentioned prompt phrase acquisition module 1001 is used to: divide the parameter information of the electronic calendar into multiple parts based on the image generation mode, wherein the image generation mode indicates the division method of the parameter information of the electronic calendar; and acquire a target prompt phrase based on each part of the parameter information of the electronic calendar.

[0145] In some embodiments, the image generation module 1002 is configured to: for each target prompt phrase, process the target prompt phrase based on an image generation model to obtain at least one original image corresponding to the target prompt phrase; for each original image, process the original image based on an image style transfer model to obtain an image corresponding to the target prompt phrase, wherein the image style transfer model is used to render the style of the image.

[0146] In some embodiments, there are multiple target prompt word groups, and different target prompt word groups are obtained based on parameter information corresponding to different time periods. The image generation module 1002 is used for: a candidate image acquisition unit, which processes the target prompt word group based on the image generation model for each target prompt word group to obtain at least one candidate image corresponding to the target prompt word group; and a target image acquisition unit, which acquires the image corresponding to each target prompt word group based on at least one candidate image corresponding to each of the multiple target prompt word groups.

[0147] In some embodiments, the candidate image acquisition unit is configured to: for the first target prompt phrase, process the first target prompt phrase based on an image generation model to obtain at least one candidate image corresponding to the first target prompt phrase; for the i-th target prompt phrase, process the i-th target prompt phrase and the template image based on an image generation model to obtain at least one candidate image corresponding to the i-th target prompt phrase, wherein the template image is the candidate image corresponding to the template target prompt phrase, and the template prompt phrase is the target prompt phrase preceding the i-th target prompt phrase, where i is an integer greater than 1.

[0148] In some embodiments, each target prompt phrase corresponds to multiple candidate images, and each candidate image corresponding to a template target prompt phrase is a template image. The candidate image acquisition unit is configured to: for the i-th target prompt phrase, process each candidate image corresponding to the i-th target prompt phrase and the template target prompt phrase based on an image generation model to obtain multiple candidate images corresponding to the i-th target prompt phrase, wherein the different candidate images corresponding to the i-th target prompt phrase are obtained based on the different candidate images corresponding to the template target prompt phrase.

[0149] In some embodiments, the target image acquisition unit is configured to: for each of a plurality of image groups, based on the position of key elements in each candidate image in the image group, acquire the consistency degree between multiple candidate images in the image group, wherein each image group includes one candidate image corresponding to each target prompt word group in a plurality of target prompt word groups, and the consistency degree indicates the degree of consistency between multiple candidate images in the image group; and determine the candidate image corresponding to each target prompt word group in the image group whose consistency degree meets the consistency requirement as the image corresponding to the target prompt word group.

[0150] In some embodiments, the above-described apparatus further includes: a schedule module, configured to process the user's schedule data based on a schedule integration model to obtain multiple first to-do items conforming to a preset format, the multiple first to-do items being displayed on an electronic calendar.

[0151] In some embodiments, the above-described apparatus further includes: a schedule module, configured to process the schedule data of multiple members in a group based on a schedule integration model to obtain multiple second to-do items conforming to a preset format, the multiple second to-do items being displayed on an electronic calendar in a preset manner.

[0152] In some embodiments, the apparatus further includes: a block information acquisition module, configured to generate block information for each user interface component in at least one user interface component based on an image corresponding to a target prompt phrase, wherein the block information indicates the position, size, and style of the corresponding user interface component; and a component rendering module, configured to process the block information of each user interface component based on a component rendering model to obtain user interface component configuration data, wherein the user interface component configuration data indicates the layout and style of each user interface component in at least one user interface component, and the user interface component configuration data is used to display at least one user interface component on an electronic calendar in the layout and style indicated by the user interface component configuration data.

[0153] In some embodiments, the above-described device further includes: a reminder setting module, used to set display reminder parameters, wherein the display reminder parameters are used to enable the electronic calendar to display images or user interface components that meet the reminder conditions in a preset display manner when the reminder conditions are met.

[0154] It should be noted that the device provided in the above embodiments is only illustrated by the division of the above functional modules when generating images. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0155] This application also provides a computer device, which includes a processor and a memory. The memory stores at least one computer program, which is loaded and executed by the processor to perform the operations performed in the additional information display method of the above embodiments.

[0156] Figure 11 shows a schematic diagram of the structure of a computer device 1100 provided in an exemplary embodiment of this application.

[0157] Computer device 1100 includes a processor 1101 and a memory 1102.

[0158] Processor 1101 may include one or more processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1101 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1101 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1101 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1101 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0159] The memory 1102 may include one or more computer-readable storage media, which may be non-transitory. The memory 1102 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1102 are used to store at least one computer program, which is used by the processor 1101 to implement the additional information display method provided in the method embodiments of this application.

[0160] In some embodiments, the computer device 1100 may also optionally include: a peripheral device interface 1103 and at least one peripheral device. The processor 1101, memory 1102, and peripheral device interface 1103 can be connected via a bus or signal line. Each peripheral device can be connected to the peripheral device interface 1103 via a bus, signal line, or circuit board. Optionally, the peripheral device includes at least one of: a radio frequency circuit 1104, a display screen 1105, a camera assembly 1106, an audio circuit 1107, and a power supply 1108.

[0161] Peripheral device interface 1103 can be used to connect at least one I / O (Input / Output) related peripheral device to processor 1101 and memory 1102. In some embodiments, processor 1101, memory 1102 and peripheral device interface 1103 are integrated on the same chip or circuit board; in some other embodiments, any one or two of processor 1101, memory 1102 and peripheral device interface 1103 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0162] The radio frequency (RF) circuit 1104 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The RF circuit 1104 communicates with communication networks and other communication devices via electromagnetic signals. The RF circuit 1104 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals back into electrical signals. Optionally, the RF circuit 1104 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The RF circuit 1104 can communicate with other devices via at least one wireless communication protocol. This wireless communication protocol includes, but is not limited to: metropolitan area networks (MANs), various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area networks (WLANs), and / or WiFi (Wireless Fidelity) networks. In some embodiments, the RF circuit 1104 may also include circuitry related to NFC (Near Field Communication), which is not limited in this application.

[0163] Display screen 1105 is used to display a UI (User Interface). This UI may include graphics, text, icons, videos, and any combination thereof. When display screen 1105 is a touch display screen, it also has the ability to collect touch signals on or above its surface. These touch signals can be input as control signals to processor 1101 for processing. In this case, display screen 1105 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there may be one display screen 1105, disposed on the front panel of computer device 1100; in other embodiments, there may be at least two display screens, disposed on different surfaces of computer device 1100 or in a folded design; in still other embodiments, display screen 1105 may be a flexible display screen, disposed on a curved or folded surface of computer device 1100. Furthermore, display screen 1105 may be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen 1105 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0164] The camera assembly 1106 is used to acquire images or videos. Optionally, the camera assembly 1106 includes a front-facing camera and a rear-facing camera. The front-facing camera is disposed on the front panel of the computer device 1100, and the rear-facing camera is disposed on the back of the computer device 1100. In some embodiments, there are at least two rear-facing cameras, which are any one of a main camera, a depth-sensing camera, a wide-angle camera, and a telephoto camera, to achieve background blurring by fusion of the main camera and the depth-sensing camera, panoramic shooting by fusion of the main camera and the wide-angle camera, VR (Virtual Reality) shooting, or other fusion shooting functions. In some embodiments, the camera assembly 1106 may also include a flash. The flash may be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cool light flash, which can be used for light compensation at different color temperatures.

[0165] The audio circuit 1107 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, converting the sound waves into electrical signals that are input to the processor 1101 for processing, or input to the radio frequency circuit 1104 for voice communication. For stereo sound acquisition or noise reduction purposes, multiple microphones may be used, each located in a different part of the computer device 1100. The microphone may also be an array microphone or an omnidirectional microphone. The speaker is used to convert electrical signals from the processor 1101 or the radio frequency circuit 1104 into sound waves. The speaker may be a conventional diaphragm speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can convert electrical signals not only into audible sound waves but also into inaudible sound waves for purposes such as distance measurement. In some embodiments, the audio circuit 1107 may also include a headphone jack.

[0166] Power supply 1108 is used to supply power to the various components in computer device 1100. Power supply 1108 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1108 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0167] In some embodiments, the computer device 1100 further includes one or more sensors 1109. The one or more sensors 1109 include, but are not limited to: an accelerometer 1110, a gyroscope 1111, a pressure sensor 1112, an optical sensor 1113, and a proximity sensor 1114.

[0168] Accelerometer 1110 can detect the magnitude of acceleration along the three coordinate axes of a coordinate system established by computer device 1100. For example, accelerometer 1110 can be used to detect the components of gravitational acceleration along the three coordinate axes. Processor 1101 can control display screen 1105 to display the user interface in either a landscape or portrait view based on the gravitational acceleration signal acquired by accelerometer 1110. Accelerometer 1110 can also be used for games or for acquiring user motion data.

[0169] The gyroscope sensor 1111 can detect the orientation and rotation angle of the computer device 1100. The gyroscope sensor 1111 can work in conjunction with the accelerometer sensor 1110 to collect the user's 3D movements on the computer device 1100. Based on the data collected by the gyroscope sensor 1111, the processor 1101 can perform the following functions: motion sensing (e.g., changing the UI based on the user's tilt), image stabilization during shooting, game control, and inertial navigation.

[0170] Pressure sensor 1112 can be disposed on the side bezel of computer device 1100 and / or on the lower layer of display screen 1105. When pressure sensor 1112 is disposed on the side bezel of computer device 1100, it can detect the user's grip signal on computer device 1100, and processor 1101 can perform left / right hand recognition or quick operation based on the grip signal collected by pressure sensor 1112. When pressure sensor 1112 is disposed on the lower layer of display screen 1105, processor 1101 can control operable controls on the UI interface based on the user's pressure operation on display screen 1105. Operable controls include at least one of button controls, scroll bar controls, icon controls, and menu controls.

[0171] An optical sensor 1113 is used to collect ambient light intensity. In one embodiment, the processor 1101 can control the display brightness of the display screen 1105 based on the ambient light intensity collected by the optical sensor 1113. Optionally, when the ambient light intensity is high, the display brightness of the display screen 1105 is increased; when the ambient light intensity is low, the display brightness of the display screen 1105 is decreased. In another embodiment, the processor 1101 can also dynamically adjust the shooting parameters of the camera assembly 1106 based on the ambient light intensity collected by the optical sensor 1113.

[0172] A proximity sensor 1114, also known as a distance sensor, is installed on the front panel of the computer device 1100. The proximity sensor 1114 is used to detect the distance between the user and the front of the computer device 1100. In one embodiment, when the proximity sensor 1114 detects that the distance between the user and the front of the computer device 1100 is gradually decreasing, the processor 1101 controls the display screen 1105 to switch from a screen-on state to a screen-off state; when the proximity sensor 1114 detects that the distance between the user and the front of the computer device 1100 is gradually increasing, the processor 1101 controls the display screen 1105 to switch from a screen-off state to a screen-on state.

[0173] Those skilled in the art will understand that the structure shown in FIG11 does not constitute a limitation on the computer device 1100, and may include more or fewer components than shown, or combine certain components, or employ different component arrangements.

[0174] This application also provides a computer-readable storage medium storing at least one computer program. This computer program is loaded and executed by a processor of a computer device to implement the operations performed by the computer device in the above-described electronic calendar-based image generation method. For example, the computer-readable storage medium may be ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage device, etc.

[0175] This application also provides a computer program product or computer program, which includes computer program code stored in a computer-readable storage medium. A processor of a computer device reads the computer program code from the computer-readable storage medium and executes the computer program code, causing the computer device to perform the image generation method based on an electronic calendar provided in the various optional implementations described above.

[0176] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0177] The above description is merely an optional embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for generating images based on an electronic calendar, characterized in that, The method includes: obtaining at least one target prompt phrase based on the parameter information of the electronic calendar, wherein the parameter information of the electronic calendar reflects the usage scenario of the electronic calendar, the target prompt phrase is used to indicate the image generation requirements, and each target prompt phrase includes multiple prompt words; processing each target prompt phrase based on an image generation model to obtain an image corresponding to each target prompt phrase, wherein the image generation model is used to generate an image based on the prompt phrase, and the image is used as the background of the electronic calendar.

2. The method according to claim 1, characterized in that, The step of obtaining at least one target prompt word group based on the parameter information of the electronic calendar includes: obtaining multiple original prompt words based on the parameter information of the electronic calendar; and obtaining the at least one target prompt word group based on the multiple original prompt words.

3. The method according to claim 2, characterized in that, The process of obtaining multiple original prompt words based on the parameter information of the electronic calendar includes at least one of the following: obtaining the original prompt words based on the text information input by the user in the parameter information; Based on the environmental mapping conditions satisfied by the external environmental parameters in the parameter information, the external environmental parameters are converted into original prompt words indicated by the environmental mapping conditions. The external environmental parameters include at least one of temperature, humidity, light intensity, and weather. The environmental mapping conditions indicate the mapping relationship between the external environmental parameters and the original prompt words. The original prompt words reflect the characteristics of the external environment. The original prompt words are extracted from the historical usage information in the parameter information. The historical usage information includes at least one of the user's historical image usage information and historical prompt word usage information. The original prompt words reflect the historical usage of the electronic calendar. Based on the emotion mapping condition, emotion recognition is performed on the user's schedule data in the parameter information to obtain the original prompt words. The emotion mapping condition indicates the mapping relationship between keywords in the schedule data and the original prompt words. The original prompt words reflect the emotions that the schedule data evokes in the user. Based on the time information and geographical location information in the parameter information, the original prompt word is obtained, and the original prompt word indicates at least one of seasonal information and holiday information; Information filtering and emotion recognition are performed on the network information in the parameter information to obtain the original prompt words, which indicate the network information.

4. The method according to claim 2, characterized in that, The step of obtaining the at least one target prompt word group based on the plurality of original prompt words includes: outputting the original prompt words that match words in a preset word library from the plurality of original prompt words as intermediate prompt words; clustering the plurality of intermediate prompt words to obtain a plurality of candidate prompt word groups and an association value for each candidate prompt word group, wherein each candidate prompt word group includes some or all of the intermediate prompt words from the plurality of intermediate prompt words, and the association value of each candidate prompt word group indicates the degree of association between the intermediate prompt words in the candidate prompt word group; and obtaining the target prompt word group based on the candidate prompt word groups whose association values ​​meet the association requirements.

5. The method according to claim 4, characterized in that, The process of obtaining the target prompt word group based on the candidate prompt word groups whose association values ​​meet the association requirements includes: expanding the candidate prompt word groups whose association values ​​meet the association requirements based on a text processing model to obtain the target prompt word group.

6. The method according to claim 1, characterized in that, The step of obtaining at least one target prompt phrase based on the parameter information of the electronic calendar includes: dividing the parameter information of the electronic calendar into multiple parts based on an image generation mode, wherein the image generation mode indicates the division method of the parameter information of the electronic calendar; and obtaining a target prompt phrase based on each part of the parameter information of the electronic calendar.

7. The method according to claim 1, characterized in that, The step of processing each target prompt phrase based on the image generation model to obtain an image corresponding to each target prompt phrase includes: for each target prompt phrase, processing the target prompt phrase based on the image generation model to obtain at least one original image corresponding to the target prompt phrase; for each original image, processing the original image based on an image style transfer model to obtain an image corresponding to the target prompt phrase, wherein the image style transfer model is used to render the style of the image.

8. The method according to claim 1, characterized in that, There are multiple target prompt phrases, and different target prompt phrases are obtained based on parameter information corresponding to different time periods. The step of processing each target prompt phrase based on the image generation model to obtain the image corresponding to each target prompt phrase includes: for each target prompt phrase, processing the target prompt phrase based on the image generation model to obtain at least one candidate image corresponding to the target prompt phrase; and obtaining the image corresponding to each target prompt phrase based on at least one candidate image corresponding to each of the multiple target prompt phrases.

9. The method according to claim 8, characterized in that, The step of processing each target prompt phrase based on the image generation model to obtain at least one candidate image corresponding to the target prompt phrase includes: for the first target prompt phrase, processing the first target prompt phrase based on the image generation model to obtain at least one candidate image corresponding to the first target prompt phrase; for the i-th target prompt phrase, processing the i-th target prompt phrase and the template image based on the image generation model to obtain at least one candidate image corresponding to the i-th target prompt phrase, wherein the template image is a candidate image corresponding to the template target prompt phrase, and the template prompt phrase is the target prompt phrase preceding the i-th target prompt phrase, where i is an integer greater than 1.

10. The method according to claim 9, characterized in that, Each target hint phrase corresponds to multiple candidate images, and each candidate image corresponding to the template target hint phrase is a template image. The process of processing the i-th target hint phrase and the template image based on the image generation model to obtain at least one candidate image corresponding to the i-th target hint phrase includes: for the i-th target hint phrase, processing each candidate image corresponding to the i-th target hint phrase and the template target hint phrase based on the image generation model to obtain multiple candidate images corresponding to the i-th target hint phrase, where the different candidate images corresponding to the i-th target hint phrase are obtained based on the different candidate images corresponding to the template target hint phrase.

11. The method according to claim 8, characterized in that, The step of obtaining the image corresponding to each of the multiple target prompt phrases based on at least one candidate image corresponding to each target prompt phrase includes: for each of the multiple image groups, obtaining the consistency degree between the multiple candidate images in the image group based on the position of key elements in each candidate image in the image group, wherein each image group includes one candidate image corresponding to each of the multiple target prompt phrases, and the consistency degree indicates the degree of consistency between the multiple candidate images in the image group; and determining the candidate image corresponding to each of the target prompt phrases in the image group whose consistency degree meets the consistency requirement as the image corresponding to the target prompt phrase.

12. The method according to claim 1, characterized in that, The method further includes: processing the user's schedule data based on a schedule integration model to obtain multiple first to-do items that conform to a preset format, the multiple first to-do items being displayed on the electronic calendar.

13. The method according to claim 1, characterized in that, The method further includes: processing the schedule data of multiple members in the group based on the schedule integration model to obtain multiple second to-do items that conform to the preset format, and the multiple second to-do items are used to display on the electronic calendar in a preset manner.

14. The method according to claim 1, characterized in that, The method further includes: generating block information for each of the at least one user interface components based on the image corresponding to the target prompt phrase, wherein the block information indicates the position, size, and style of the corresponding user interface component; processing the block information of each user interface component based on a component rendering model to obtain user interface component configuration data, wherein the user interface component configuration data indicates the layout and style of each of the at least one user interface components, and the user interface component configuration data is used to display the at least one user interface component on the electronic calendar in the layout and style indicated by the user interface component configuration data.

15. The method according to claim 1, characterized in that, The method further includes: setting display reminder parameters, wherein the display reminder parameters are used to enable the electronic calendar to display the image or a user interface component that meets the reminder conditions in a preset display mode when the reminder conditions are met.

16. A picture generation device based on an electronic calendar, characterized in that, The device includes: a prompt phrase acquisition module, used to acquire at least one target prompt phrase based on parameter information of the electronic calendar, wherein the parameter information of the electronic calendar reflects the usage scenario of the electronic calendar, and the target prompt phrase is used to indicate the image generation requirements, and each target prompt phrase includes multiple prompt words; and an image generation module, used to process each target prompt phrase based on an image generation model to obtain an image corresponding to each target prompt phrase, wherein the image generation model is used to generate an image based on the prompt phrase, and the image is used as the background of the electronic calendar.

17. A computer device, characterized in that, The computer device includes a processor and a memory, the memory being used to store at least one computer program, the at least one computer program being loaded by the processor and executing the method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store at least one computer program for performing the method according to any one of claims 1 to 15.

19. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method as claimed in any one of claims 1 to 15.

Images