Display method and electronic equipment

By using the target model in an electronic device to generate associated second target objects based on user input, the dynamic display effect is achieved, and the problem of monotonous display of pictures or videos in the album is solved, and the display richness and user experience is increased without specific shooting. model.

CN119065561APending Publication Date: 2024-12-03LENOVO (BEIJING) LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411203720.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When browsing albums, the display method of pictures or videos is relatively monotonous, and a specific shooting mode is required to enable long pressing to display dynamic pictures. Otherwise, the dynamic picture effect cannot be achieved, and the monotonous display method of pictures or videos in the album cannot be effectively solved. The problem.

Method used

By providing a display method in an electronic device, the target model is used to generate a second target object associated with the original object based on user input, displaying different display effects, including amplification, transitional object and dynamically changing prompt words, to achieve dynamic display effects , no specific shooting mode is required.

Benefits of technology

It effectively solves the problem of monotonous display of pictures or videos in the album, increases the richness of the display and user experience, is simple to operate, reduces the use of the central processor and memory space of electronic devices, and is not affected by the network communication rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065561A_ABST
    Figure CN119065561A_ABST
Patent Text Reader

Abstract

The invention discloses a display method and electronic equipment, and the display method comprises the steps: obtaining a first target object which comprises any one of a picture or a video; displaying and outputting the first target object; obtaining a target input; in response to the target input, displaying and outputting a second target object, the second target object being a target object generated by the target model for the first target object; the second target object is associated with the first target object when being generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of electronic device display, and in particular to a display method and electronic device. Background Art

[0002] Usually, when browsing pictures or videos in an album using an electronic device, multiple photo thumbnails are directly displayed on the display screen. When the user clicks on a picture or video that he wants to display, the picture or video is enlarged and displayed. This display method is relatively monotonous.

[0003] Currently, there is a display method that displays dynamic images by long pressing, but this display method requires that a specific shooting mode be used when shooting, that is, the video during shooting is recorded in a specific shooting mode, in order to achieve the effect of long pressing to display dynamic images. Once the specific shooting mode is not used or the electronic device does not support the specific shooting mode, the effect of long pressing to display dynamic images cannot be achieved, so the problem of monotonous display of pictures or videos in the album cannot be effectively solved. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a display method and an electronic device.

[0005] In a first aspect, an embodiment of the present application provides a display method, including:

[0006] Obtaining a first target object, where the first target object includes any one of the following: a picture or a video;

[0007] Display and output the first target object;

[0008] Get target input;

[0009] In response to the target input, a second target object is displayed and output, wherein the second target object is a target object generated by the target model for the first target object; and the second target object is associated with the first target object when generated.

[0010] In a possible implementation manner, in response to the target input, displaying and outputting the second target object includes:

[0011] In response to the input operation, the target display area of ​​the first target object is refreshed based on the second target object to display and output the second target object, the second target object has the same body as the first target object, the body of the second target object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the target display area; the display effect of the second target object is different from that of the first target object.

[0012] In a possible implementation manner, in response to the target input, displaying and outputting the second target object includes:

[0013] In response to the input operation, continuously refreshing the target display area of ​​the first target object based on a plurality of transition objects and the second target object to display and output the second target object;

[0014] The multiple transition objects are target objects generated by the target model for the first target object, the multiple transition objects are associated with the first target object when generated, and the multiple transition objects are located between the first target object and the second target object;

[0015] The second target object has the same body as the first target object, and the body of the second target object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the target display area; the display effects of the second target object and the first target object are different.

[0016] In a possible implementation manner, before displaying and outputting the second target object, the method further includes:

[0017] Analyze the first target object to obtain a type parameter of the first target object;

[0018] Based on the type parameter, obtaining a group of prompt words matching the type parameter from a target database;

[0019] Based on the first target object and the set of prompt words, the target model generates the second target object that matches the description of the prompt words, and the second target object includes the same subject as the first target object.

[0020] In a possible implementation, the display method further includes:

[0021] Updating characters of a target prompt word in the target database, wherein the target prompt word has a dynamic change attribute;

[0022] The characters of the target prompt word in the target database are updated to include at least one of the following:

[0023] Obtaining sensing parameters through a target sensor, converting the sensing parameters into target characters, and using the target characters to update characters of target prompt words in the target database;

[0024] The target parameters are obtained through the network communication device, and the target parameters are converted into target characters, and the target characters are used to update the characters of the target prompt words in the target database.

[0025] In a possible implementation manner, before displaying and outputting the second target object, the method further includes:

[0026] Processing the first target object based on the first model to obtain a set of prompt words, wherein the prompt words are used by the target model to generate the second target object matching the description of the prompt words based on the first target object;

[0027] Based on the first target object and the set of prompt words, the target model generates the second target object matching the description of the prompt words, wherein the second target object includes the same subject as the first target object;

[0028] The step of processing the first target object based on the first model to obtain a set of prompt words includes:

[0029] Converting a first target object into a vector feature;

[0030] The vector features are operated with a vector feature library to generate a set of prompt words.

[0031] In a possible implementation, the group of prompt words includes a target prompt word, and the target prompt word has a dynamic change attribute;

[0032] The display method further includes at least one of the following:

[0033] Obtaining sensing parameters through a target sensor, converting the sensing parameters into target characters, and using the target characters as characters of a target prompt word, or;

[0034] The target parameters are obtained through a network communication device, and the target parameters are converted into target characters, and the target characters are used as characters of the target prompt word.

[0035] In a possible implementation, based on the first target object and the set of prompt words, the target model generates the second target object that matches the description of the prompt words, including:

[0036] Based on the first target object and the set of prompt words, the target model generates the plurality of transition objects matched by the description of the prompt words and the second target object matched by the description of the prompt words;

[0037] The set of prompt words includes hierarchical parameters for configuring the target model.

[0038] In a second aspect, an embodiment of the present application further provides an electronic device, comprising a display screen and a processor connected to each other;

[0039] The processor is used to obtain a first target object, where the first target object includes any one of the following: a picture or a video;

[0040] Controlling the display screen to display and output the first target object;

[0041] Get target input;

[0042] In response to the target input, the display screen is controlled to display and output a second target object, wherein the second target object is a target object generated by the target model for the first target object; and the second target object is associated with the first target object when generated.

[0043] In a possible implementation, the electronic device further includes:

[0044] The image acquisition device stores the acquired objects into an album, wherein the objects include any one of the following: pictures or videos, and the objects in the album can be determined as the first target objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 A flow chart of a display method provided by the present application is shown;

[0047] Figure 2 A schematic diagram showing the output photo album displayed in the display area of ​​the display screen provided by the present application is shown;

[0048] Figure 3 It shows that 8 first target objects and 1 second target object are displayed in the display area of ​​the display screen provided by the present application;

[0049] Figure 4 A schematic diagram showing that each sub-display area in the display area of ​​the display screen provided by the present application displays and outputs a second target object;

[0050] Figure 5 A schematic diagram showing a first target object provided by the present application is shown;

[0051] Figure 6 A schematic diagram showing a second target object provided by the present application is shown;

[0052] Figure 7A schematic diagram of a transition object provided by the present application is shown;

[0053] Figure 8 A flow chart of a method for generating a second target object in a display method provided by the present application is shown;

[0054] Fig. 9 A flowchart showing another display method provided by the present application is shown;

[0055] Fig.10 A flowchart showing another display method provided by the present application is shown;

[0056] Fig.11 A schematic structural diagram of an electronic device provided by the present application is shown. DETAILED DESCRIPTION

[0057] Various aspects and features of the present application are described herein with reference to the accompanying drawings.

[0058] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.

[0059] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.

[0060] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.

[0061] It should also be understood that, although the present application has been described with reference to some specific examples, those skilled in the art will be able to realize many other equivalent forms of the present application that have the features described in the claims and are therefore within the scope of protection defined thereby.

[0062] The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.

[0063] Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it should be understood that the embodiments applied for are merely examples of the present application, which may be implemented in a variety of ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that obscure the present application. Therefore, the specific structural and functional details applied for herein are not intended to be limiting, but merely serve as a basis and representative basis for the claims to teach those skilled in the art to use the present application in a variety of ways with substantially any suitable detailed structure.

[0064] This specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," all of which may refer to one or more of the same or different embodiments according to the present application.

[0065] To facilitate understanding of the present application, a display method provided by the present application is first introduced in detail. Here, the display method of the embodiment of the present application is applied to browsing an album using a display screen of an electronic device. It is applied to a processor of an electronic device. The display method can effectively solve the problem of monotonous display of pictures or videos in the album, and the second target object corresponding to the first target object can be obtained through the target model without a specific shooting mode, and the operation is simple.

[0066] As an example, Figure 1 A flow chart of a display method provided in an embodiment of the present application is shown, wherein specific steps include S101-S104.

[0067] S101, obtaining a first target object, where the first target object includes any one of the following: a picture or a video.

[0068] In a specific implementation, the album includes multiple objects, each of which can be a picture or a video. The objects in the album, i.e., the pictures or videos, can be collected by a collection device of an electronic device, transmitted to the electronic device by other devices, or downloaded from the Internet, etc.

[0069] Furthermore, the first target object is obtained from the album. As can be seen from the above, the first target object includes any one of the following: a picture or a video.

[0070] Optionally, the first target object is determined based on a user's touch action, gesture or voice. Figure 2 shows a schematic diagram of displaying an output album in a display area of ​​a display screen, Figure 2 Each object in the album is displayed as a thumbnail, that is, a preset number of objects can be displayed simultaneously in the display area of ​​the display screen. If the user touches one of the objects, the touched object is determined as the first target object.

[0071] S102: Display and output the first target object.

[0072] After obtaining the first target object, the display screen of the electronic device is controlled to display and output the first target object. Optionally, before displaying and outputting the first target object, the thumbnail of the first target object is adjusted, specifically, a first size of a display area of ​​the display screen is determined, and then a second size of the first target object is adjusted according to the first size until the second size is the same as the first size, and then the display area is controlled to display and output the first target object.

[0073] The adjusting of the second size of the first target object includes any one or more of the following: enlarging, restoring, and changing pixel values.

[0074] S103, obtaining target input.

[0075] In a specific implementation, the user can perform a preset operation on the first target object so that the processor obtains the input corresponding to the preset operation, and different preset operations, that is, different inputs, correspond to different display effects. Optionally, the preset operation can include multiple operations, such as tap, long press, move, etc.

[0076] In actual applications, the target input is obtained based on the target operation performed by the user, wherein the target operation can be set to a long press time of greater than or equal to 3 seconds for a first target object, or can be set to move a first target object to a target position and retain it for greater than or equal to 5 seconds, etc.

[0077] S104, in response to the target input, display and output a second target object, wherein the second target object is a target object generated by the target model for the first target object; and the second target object is associated with the first target object when generated.

[0078] Optionally, after obtaining the target input, the second target object may be generated for the first target object through the target model in response to the target input; or before obtaining the target input, the second target object may be generated for the first target object through the target model. For example, when the occupancy rate of the central processing unit of the electronic device is low or the unoccupied memory space in the electronic device is large, the second target object may be generated for the first target object through the target model.

[0079] As another example, considering that the electronic device needs to occupy the processing resources and memory space of the central processor of the electronic device to store and run the target model, based on this, the target model can also be set in the cloud, that is, when generating the second target object for the first target object, the first target object is transmitted to the cloud, so that the target model set in the cloud processes the first target object to generate the first target object, and then returns the second target object to the electronic device. Therefore, compared with setting the target model on the electronic device, setting the target model in the cloud can reduce the target model's occupation of the processing resources and memory space of the central processor of the electronic device; on the contrary, compared with setting the target model in the cloud, setting the target model on the electronic device can ensure that the speed of displaying and outputting the second target object is not affected by the network communication rate.

[0080] The target model of the embodiment of the present application can be set in the electronic device or in the cloud that can communicate with the electronic device according to actual needs.

[0081] After obtaining the target input, in response to the target input, the second target object is displayed and output, and the second target object may be one or more. Of course, when displaying and outputting the second target object, one of the second target objects may be displayed according to the display condition, or all the second target objects may be displayed in sequence.

[0082] The second target object is associated with the first target object when it is generated, for example, the second target object has the same main structure as the first target object. After the second target object is generated, the second target object can be stored in a newly created group in the album to distinguish between objects generated by the target model and objects not generated by the target model in the album; the second target object and the first target object can also be stored in the same group to clearly identify the associated second target object and the first target object.

[0083] Optionally, each object in the album can be used as the first target object. For example, each object in the album can be determined as the first target object without any determination conditions (such as user's touch actions, gestures, and voice, etc.); since generating a target object for the first target object requires occupying the processing resources and memory space of the central processing unit of the electronic device, based on this, without any determination conditions, some objects in the album can be determined as the first target object based on the processing resources and memory space of the central processing unit, for example, the object captured by the image acquisition device of the electronic device is determined as the first target object, etc.

[0084] As described above, when the thumbnails of multiple objects are displayed and output in the display area of ​​the display screen, a target input may be obtained to display and output the second target object in response to the target input, or the second target object may be directly displayed and output.

[0085] Continue to refer to Figure 2 In the example shown, the thumbnails of 9 objects are displayed and outputted simultaneously in the display area. In the scenario where the 9 objects are all first target objects, the user can perform a preset operation to instruct the display and output of a second target object corresponding to a first target object. For example, the user performs a double-click operation on one of the first target objects. On the basis of displaying the output thumbnail, in response to the double-click operation, the second target object corresponding to the first target object is displayed and outputted. At the same time, the other first target objects still keep displaying themselves. In actual applications, the first target object and the second target object are displayed and outputted alternately. Based on this, at some moments after responding to a double-click operation on a first target object, 8 first target objects and 1 second target object are displayed simultaneously in the display area. That is, Figure 3 The schematic diagram of the display output shown in the display area is shown in FIG. Figure 3 It can be seen that the eight first target objects and one second target object are also thumbnails.

[0086] It is worth noting that if there are 4 first target objects among the 9 objects displayed in the display area, at this time, the first target objects and non-first target objects can be displayed and output separately, such as setting the first target object to carry a visual label, and setting the non-first target object to not carry a label. In this way, the user can perform operations such as double-clicking on the first target object to indicate the display output of the second target object, avoiding the problem of performing operations on non-first target objects but failing to display the second target object, resulting in a poor experience.

[0087] In another example, in a scenario where thumbnails of nine objects are displayed and outputted simultaneously in a display area, and the nine objects are all first target objects, the second target object corresponding to each first target object can be directly displayed and outputted without any operation, that is, in the sub-display area where the thumbnail of each first target object is located, the first target object and the second target object are displayed and outputted alternately. In this process, at a certain moment, all the sub-display areas in the display area display the second target object. Figure 4 A schematic diagram is shown in which each sub-display area displays and outputs a second target object. Similarly, each second target object is also a thumbnail. Of course, this method is also applicable to the scene where some of the first target objects are displayed and output in the display area. This method can greatly increase the richness of the album display.

[0088] In an embodiment of the present application, after obtaining a target input for a first target object, a second target object generated by an output target model for the first target object is displayed in response to the target input. Without the need for a specific shooting mode, the second target object corresponding to the first target object can be obtained through the target model, and the second target object can be displayed based on the target input, which effectively solves the problem of monotonous display of pictures or videos in an album and is simple to operate.

[0089] As one example, when the second target object is displayed and output in response to a target input, specifically, in response to the input operation, the display size of the first target object in the target display area is determined, and the size of the second target object is adjusted according to the display size of the first target object, specifically, the size of the second target object is adjusted to the display size of the first target object, and then, the target display area of ​​the first target object is refreshed based on the second target object, so that the target display area displays and outputs the second target object.

[0090] Among them, the size of the adjusted second target object is the same as the display size of the first target object. Based on this, the main body of the second target object relative to the outline of the target display area is consistent with the outline of the first target object relative to the outline of the target display area. For example, the main bodies of the first target object and the second target object include a vehicle. When the target display area displays and outputs the first target object, the outline of the vehicle and the target display area is in a first relative position relationship. When the target display area displays and outputs the second target object, the outline of the vehicle and the target display area is in a second relative position relationship. The first relative position relationship is the same as the second relative position relationship or the error is within a certain range.

[0091] Of course, when the second target object is output in response to the target input display, the target display area of ​​the first target object on the display screen can also be determined, and the size of the target display area can be obtained, and the size of the second target object can be adjusted according to the size of the target display area, etc. The embodiments of the present application do not make specific limitations on this.

[0092] In a specific implementation, the second target object and the first target object have the same subject, and the display effects of the second target object and the first target object are different. Figure 5 shows a schematic diagram of a first target object, Figure 6 A schematic diagram of the second target object is shown. The main bodies of the first target object and the second target object are both asphalt roads and trees on both sides of the road. The display effect of the first target object is the asphalt road and trees on both sides of the road in summer, and the display effect of the second target object is the asphalt road and trees on both sides of the road in winter.

[0093] In another example, the target model can generate multiple transition objects while generating the second target object for the first target object, that is, the multiple transition objects are the target objects generated by the target model for the first target object. As above, the multiple transition objects are also associated with the first target object when they are generated, and the transition objects and the second target objects can be stored in the same group. In addition, the multiple transition objects are located between the first target object and the second target object. For example, the first target object, the transition object and the second target object each correspond to a time tag, and the time tag corresponding to the transition object represents a transition time point, the time tag corresponding to the first target object represents the first time point, and the time tag corresponding to the second target object represents the second time point, and the transition time point is between the first time point and the second time point.

[0094] Based on this, when the second target object is displayed and output in response to the target input, the target display area of ​​the first target object is continuously refreshed based on multiple transition objects and the second target objects in response to the input operation to display and output the second target object, that is, multiple transition objects and second target objects are continuously and sequentially displayed in the target display area.

[0095] For example, Figure 7 A schematic diagram of a transition object is shown, and the display effect of the transition object is an asphalt road in autumn and trees on both sides of the road. When the second target object is displayed and output in response to the target input, the Figure 7 as well as Figure 6 The target display area of ​​the first target object is continuously refreshed.

[0096] Of course, the second target object has the same body as the first target object, the body of the second target object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the outline of the target display area, and the body of the transition object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the outline of the target display area; the display effects of the second target object, the first target object and the transition object are all different.

[0097] From the above, the second target object can be displayed and output by responding to the target input, and the second target object can be used to refresh the target display area of ​​the first target object to display and output the second target object. The target display area of ​​the first target object can also be continuously refreshed by using multiple transition objects and the second target object to display and output the second target object. This greatly improves the richness of the object display in the album, thereby improving the user experience. In addition, there is no need to set special requirements for the functions of the electronic device and the mode of obtaining the objects in the album, and the implementation cost is low.

[0098] It is worth noting that each object in the album can be used as the first target object. Without any determining conditions (such as the user's touch action, gesture, and voice, etc.), each object in the album is determined as the first target object. At this time, the second target object or multiple transition objects and second target objects can be generated in advance for the first target object, and the generated second target object or multiple transition objects and second target objects are associated with the first target object and stored. When the target input is received, the second target object or multiple transition objects and second target objects can be directly displayed and output, and the display output efficiency is high.

[0099] Optionally, before displaying and outputting the second target object, it is necessary to first generate the second target object using the target model. As an example, Figure 8 A flow chart of a method for generating a second target object is shown, wherein the specific steps include S801-S803.

[0100] S801: Analyze a first target object to obtain a type parameter of the first target object.

[0101] S802: Based on the type parameter, a group of prompt words matching the type parameter is obtained from a target database.

[0102] S803: Based on the first target object and a group of prompt words, the target model generates a second target object that matches the description of the prompt words, and the second target object includes the same subject as the first target object.

[0103] When generating the second target object for the first target object, the first target object is first analyzed to obtain the type parameter of the first target object. Optionally, the first target object is identified and analyzed by a pre-trained recognition model to obtain the type parameter of the first target object. Here, the recognition model can use a TensorFlow Lite model, a VGG model, an Inception series, a ResNet series, etc.

[0104] Among them, the type parameter of the first target object can characterize the type to which the first target object belongs. For example, the type parameter of the first target object includes the element name, the area ratio of each element in the first target object, etc. The types to which the first target object belongs include scenery, building, sky, and person, etc.

[0105] Further, after obtaining the type parameter of the first target object, a group of prompt words matching the type parameter is obtained from the target database based on the type parameter. The target database pre-stores a mapping relationship between the type parameter and the prompt word, and one type parameter may correspond to multiple prompt words, that is, one type parameter may correspond to one prompt word or a group of prompt words.

[0106] After obtaining a set of prompt words that match the type parameters of the first target object, based on the first target object and the set of prompt words, a second target object that matches the description of the prompt words is generated using the target model. For example, the type parameter of the first target object indicates that the type of the first target object is "landscape", and the corresponding prompt words obtained from the target database are "do not change the photographic subject structure" and "generate pictures of the four seasons". Based on this, the target model is used to generate the second target object with the subject structure of the first target object and elements such as the four seasons. Of course, the generated second target object includes the same subject as the first target object and meets the description of any season of the four seasons.

[0107] In a specific implementation, in order to meet the user's display needs, after displaying the second target object, user feedback on the display effect of the second target object is obtained. Based on the feedback information, the target database is updated so that the generated second target object can better meet the user's display needs.

[0108] In another example, the target database has a dynamically changing attribute. Specifically, there are prompt words with dynamically changing attributes in the prompt words of the target database, for example, prompt words related to location, weather and other related content. Such prompt words with dynamically changing attributes need to be determined in real time. Based on this, after obtaining a group of prompt words matching the type parameter and before generating a second target object matching the description of the prompt word, the characters of the target prompt word in the target database are updated first, and the target prompt word is a prompt word with dynamically changing attributes.

[0109] Optionally, when updating the characters of the target prompt word, it is necessary to obtain the target character, which is used to update the characters of the target prompt word in the target database. Based on this, before updating the characters of the target prompt word in the target database, the target character is obtained by at least one of the following methods: obtaining a sensing parameter through a target sensor and converting the sensing parameter into a target character, or obtaining a target parameter through a network communication device and converting the target parameter into a target character.

[0110] Specifically, the method of obtaining the target character is determined according to the target prompt word. For example, if the target prompt word involves a location, a sensing parameter is obtained through at least one of a positioning sensor such as a gyroscope, a GPS positioning sensor, and an inertial navigation sensor, and the sensing parameter characterizes the current location of the electronic device, and the sensing parameter is converted into a target character, so as to update the character of the target prompt word in the target database using the target character. If the target prompt word involves weather, a target parameter is obtained through at least one of a network communication device such as an antenna, a network card, and a cable, and the target parameter characterizes the current weather conditions, and the target parameter is converted into a target character, so as to update the character of the target prompt word in the target database using the target character.

[0111] Thereby, the accuracy of the prompt word matching the type parameter is ensured, and the second target object generated based on the prompt word can better meet the display requirements of the user.

[0112] It should be noted that the update condition of the target prompt word may be a change in the sensing parameter obtained by the target sensor or a change in the target parameter obtained by the network communication device, or a change in the target input.

[0113] As another example, the first model is set to obtain prompt words that match the type parameters of the first target object. Specifically, before displaying and outputting the second target object, the first target object is processed based on the first model to obtain a group of prompt words, and the prompt words are used for the target model to generate a second target object that matches the description of the prompt words based on the first target object. Among them, the first model can perform processing such as identification, extraction, matching, and generation, such as identifying the first target object to determine the type to which the first target object belongs, and then matching the corresponding prompt words according to the type to which the first target object belongs, thereby obtaining a group of prompt words. Of course, a generation rule can also be pre-set in the first model, and the generation rule is used to generate a group of prompt words according to elements. At this time, the first model can extract the elements in the first target object, and then, according to the generation rule, a group of prompt words is generated according to all elements. The parameters and processing steps in the first model can be set according to actual needs, as long as the prompt words corresponding to the first target object can be obtained, and the embodiments of the present application do not specifically limit this.

[0114] In the embodiment of the present application, when the first target object is processed based on the first model to obtain a set of prompt words, the first target object is specifically converted into a vector feature, and the vector feature is operated with the vector feature library using the first model to generate a set of prompt words. The vector feature library represents the relationship between the first target object and the prompt words.

[0115] After obtaining a set of prompt words corresponding to the first target object, the set of prompt words is transmitted to the target model, so that the target model generates a second target object that matches the description of the prompt words based on the first target object and the set of prompt words. The steps of generating the second target object that matches the description of the prompt words based on the first target object and the set of prompt words are the same as above, and will not be described in detail here.

[0116] Similarly, a group of prompt words obtained by processing the first target object based on the first model also includes target prompt words with dynamically changing attributes. When a group of prompt words is generated through the first model, sensing parameters are obtained through the target sensor, and the sensing parameters are transmitted to the target model so that the target model converts the sensing parameters into target characters, and generates a group of prompt words based on the target characters, vector features, and vector feature library. Alternatively, when a group of prompt words is generated through the first model, target parameters are obtained through the network communication device, and the target parameters are transmitted to the target model so that the target model converts the target parameters into target characters, and generates a group of prompt words based on the target characters, vector features, and vector feature library. Among them, the target characters are the characters of the target prompt words.

[0117] Here, the target sensor, sensing parameters, network communication device and target parameters are as mentioned above and will not be elaborated here.

[0118] Compared to updating the target prompt word when the sensing parameters obtained by the target sensor change or the target parameters obtained by the network communication device change, updating the target prompt word in real time based on the first model after receiving the target input can avoid wasting resources caused by updating the target prompt word in advance but not using the updated target prompt word.

[0119] In a specific implementation, when the target model generates a second target object for a first target object and generates multiple transition objects at the same time, the target model generates multiple transition objects matching the description of the prompt words and a second target object matching the description of the prompt words based on the first target object and a set of prompt words. The set of prompt words includes a grading parameter for configuring the target model, and the grading parameter is used to indicate the number of generated transition objects.

[0120] For example, if the grading parameter of the target model is 11, and the first target object is a landscape picture of spring, then the target model generates 10 transition objects that match the description of the prompt words and a second target object that matches the description of the prompt words based on the first target object and a set of prompt words. Optionally, the first target object, the 10 transition objects, and the second target object correspond to landscape pictures of different months. When responding to input operations, the first target object, the transition object, and the second target object can continuously refresh the target display area of ​​the first target object in the order of their corresponding time points, thereby realizing the transition presentation of different months and seasons.

[0121] In another example, when the prompt word includes time and related vocabulary, a corresponding timeline virtual control key can be generated while generating multiple transition objects and second target objects. The timeline virtual control key is used to respond to user touch operations such as sliding, so as to control the transition object or the second target object to refresh the target display area, that is, to control the display progress of the transition object and the second target object, which has high flexibility.

[0122] As an example, Fig. 9 A flow chart of a display method is shown, referring to Fig. 9 , each object in the album in this scenario is determined as the first target object, and the second target object is generated in advance for the first target object. Specifically, the first target object is transmitted to the recognition model, and the recognition model identifies and analyzes the first target object to obtain a type parameter that can characterize the type to which the first target object belongs. After obtaining the type parameter of the first target object, a set of prompt words matching the type parameter is obtained from the target database based on the type parameter, and the first target object and a set of prompt words matching its type parameter are transmitted to the target model, so that the target model generates a second target object matching the description of the prompt word based on the first target object and a set of prompt words. After the target model generates the second target object, the second target object is transmitted to the album and stored in the same group as the first target object. When the user generates a target input based on an interactive device such as a touch screen, the second target object is displayed and output in response to the target input.

[0123] As an example, Fig.10 A flowchart showing another display method is shown, referring to Fig.10, in this scenario, a transition object and a second target object are generated in real time based on the user's target input. Specifically, when the user generates a target input based on an interactive device such as a touch screen, in response to the target input, the first target object is transmitted to the recognition model, and the recognition model recognizes and analyzes the first target object to obtain a type parameter that can characterize the type to which the first target object belongs. At the same time, the current target parameter is obtained through a network communication device, a group of prompt words are determined based on the type parameter and the target parameter, and the first target object and a group of prompt words that match it are transmitted to the target model. In this example, the target model is provided with a hierarchical parameter, based on which, the target model generates multiple transition objects and a second target object based on the first target object, a group of prompt words and the hierarchical parameter. Afterwards, the multiple transition objects and the second target objects are transmitted to the album, and stored in the same group with the first target object, and the multiple transition objects and the second target objects are displayed and output, specifically, the target display area of ​​the first target object is continuously refreshed using the multiple transition objects and the second target objects, so that the multiple transition objects and the second target objects are continuously displayed to the user. In addition, a corresponding timeline virtual control key is also set in this example. The timeline virtual control key is displayed, and the user performs a touch operation on the timeline virtual control key. Based on the control operation, the transition object or the second target object corresponding to the control operation is displayed and output, that is, the target display area is refreshed using the transition object or the second target object corresponding to the control operation.

[0124] Optionally, after displaying and outputting the second target object, a satisfaction questionnaire can be generated for the second target object and displayed, and the user provides feedback on the satisfaction questionnaire. After obtaining the satisfaction information from the user's feedback, the target model is optimized based on the satisfaction information so that the second target object generated by the target model improves user satisfaction.

[0125] The second aspect of the present application also provides an electronic device corresponding to the display method. Since the principle of solving the problem by the electronic device in the present application is similar to the above-mentioned display method of the present application, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0126] Fig.11 A schematic diagram of an electronic device provided in an embodiment of the present application is shown, referring to Fig.11 It can be seen that the electronic device includes a display screen and a processor connected to each other;

[0127] The processor is used to obtain a first target object, where the first target object includes any one of the following: a picture or a video;

[0128] Controlling the display screen to display and output the first target object;

[0129] Get target input;

[0130] In response to the target input, the display screen is controlled to display and output a second target object, wherein the second target object is a target object generated by the target model for the first target object; and the second target object is associated with the first target object when generated.

[0131] Continue to refer to Fig.11 , the electronic equipment also includes:

[0132] The image acquisition device stores the acquired objects into an album, wherein the objects include any one of the following: pictures or videos, and the objects in the album can be determined as the first target objects.

[0133] Optionally, in this embodiment, the above-mentioned storage medium may include, but is not limited to, various media that can store program codes, such as a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk. Optionally, in this embodiment, the processor executes the method steps recorded in the above-mentioned embodiment according to the program code stored in the storage medium. Optionally, the specific examples in this embodiment can refer to the examples described in the above-mentioned embodiment and the optional implementation mode, and this embodiment is not repeated here. Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented with a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. Optionally, they can be implemented with executable program codes of computing devices, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from here, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps in them can be made into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.

[0134] In addition, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present application with equivalent elements, modifications, omissions, combinations (e.g., various embodiments intersecting schemes), adaptations or changes. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the implementation of the application, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, and the true scope and spirit are indicated by the following claims and the full scope of their equivalents.

[0135] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, those of ordinary skill in the art can use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features can be grouped together to simplify the application. This should not be interpreted as an intention that a disclosed feature that does not require protection is necessary for any claim. On the contrary, the subject matter of the present application may be less than all the features of a specific disclosed embodiment. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently used as a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present application should be determined with reference to the attached claims and the full scope of equivalent forms granted by these claims.

[0136] Multiple embodiments of the present application are described in detail above, but the present application is not limited to these specific embodiments. Those skilled in the art can make various variations and modifications to the embodiments based on the concept of the present application, and these variations and modifications should all fall within the scope of protection required by the present application.

Claims

1. A display method, include: Obtaining a first target object, where the first target object includes any one of the following: a picture or a video; Display and output the first target object; Get target input; In response to the target input, a second target object is displayed and output, wherein the second target object is a target object generated by the target model for the first target object; and the second target object is associated with the first target object when generated.

2. The display method according to claim 1, wherein in response to the target input, a second target object is displayed and outputted; include: In response to the input operation, the target display area of ​​the first target object is refreshed based on the second target object to display and output the second target object, the second target object has the same body as the first target object, the body of the second target object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the target display area; the display effect of the second target object is different from that of the first target object.

3. The display method according to claim 1, wherein in response to the target input, a second target object is displayed and outputted. include: In response to the input operation, continuously refreshing the target display area of ​​the first target object based on a plurality of transition objects and the second target object to display and output the second target object; The multiple transition objects are target objects generated by the target model for the first target object, the multiple transition objects are associated with the first target object when generated, and the multiple transition objects are located between the first target object and the second target object; The second target object has the same body as the first target object, and the body of the second target object relative to the outline of the target display area is consistent with the outline of the body of the first target object relative to the target display area; the display effects of the second target object and the first target object are different.

4. The display method according to any one of claims 1 to 3, before displaying and outputting the second target object, further comprising: include: Analyze the first target object to obtain a type parameter of the first target object; Based on the type parameter, a group of prompt words matching the type parameter is obtained from a target database; Based on the first target object and the set of prompt words, the target model generates the second target object that matches the description of the prompt words, and the second target object includes the same subject as the first target object.

5. The display method according to claim 4, further comprising: include: Updating characters of a target prompt word in the target database, wherein the target prompt word has a dynamic change attribute; The characters of the target prompt word in the target database are updated to include at least one of the following: Obtaining sensing parameters through a target sensor, converting the sensing parameters into target characters, and using the target characters to update characters of target prompt words in the target database; The target parameters are obtained through the network communication device, and the target parameters are converted into target characters, and the target characters are used to update the characters of the target prompt words in the target database.

6. The display method according to any one of claims 1 to 3, before displaying and outputting the second target object, further comprising: include: Processing the first target object based on the first model to obtain a set of prompt words, wherein the prompt words are used by the target model to generate the second target object matching the description of the prompt words based on the first target object; Based on the first target object and the set of prompt words, the target model generates the second target object matching the description of the prompt words, wherein the second target object includes the same subject as the first target object; The step of processing the first target object based on the first model to obtain a set of prompt words includes: Converting a first target object into a vector feature; The vector features are operated with a vector feature library to generate a set of prompt words.

7. The display method according to claim 6, wherein the group of prompt words includes a target prompt word, and the target prompt word has a dynamic change attribute; The display method further includes at least one of the following: Obtaining sensing parameters through a target sensor, converting the sensing parameters into target characters, and using the target characters as characters of a target prompt word, or; The target parameters are obtained through a network communication device, and the target parameters are converted into target characters, and the target characters are used as characters of the target prompt word.

8. The display method according to claim 4 or 6, wherein based on the first target object and the set of prompt words, the target model generates the second target object matching the description of the prompt words, include: Based on the first target object and the set of prompt words, the target model generates the plurality of transition objects matched by the description of the prompt words and the second target object matched by the description of the prompt words; The set of prompt words includes hierarchical parameters for configuring the target model.

9. An electronic device comprising a display screen and a processor connected to each other; The processor is used to obtain a first target object, where the first target object includes any one of the following: a picture or a video; Controlling the display screen to display and output the first target object; Get target input; In response to the target input, controlling the display screen to display and output a second target object, in, The second target object is a target object generated by the target model for the first target object; when the second target object is generated, it is associated with the first target object.

10. The electronic device according to claim 9, further comprising: include: The image acquisition device stores the acquired objects into an album, wherein the objects include any one of the following: pictures or videos, and the objects in the album can be determined as the first target objects.