Data processing method and electronic equipment

Abstract

The invention discloses a data processing method and electronic equipment, and the method comprises the steps: obtaining input content which is used for generating data; outputting at least one recommendation attribute according to the input content; the recommendation attribute represents the type of the generated data on the corresponding recommendation dimension; the recommendation attribute corresponds to at least one attribute option, and the recommendation attribute and the attribute option corresponding to the recommendation attribute are both related to the input content; and in response to a selection operation for a target option in the recommendation attribute, generating target data according to the input content and the target option.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method and electronic equipment. Background Art

[0002] With the development of artificial intelligence technology, users can provide prompt words to artificial intelligence models, so that they can interact with the artificial intelligence models through natural language, and the artificial intelligence models will generate text or images.

[0003] However, since users lack experience in how to construct effective prompt words, the generated text or image often has a large gap with the user's expectations and has poor accuracy. Summary of the invention

[0004] In view of this, the present application provides a data processing method and an electronic device as follows:

[0005] A data processing method, comprising:

[0006] Obtaining input content, wherein the input content is used to generate data;

[0007] Output at least one recommended attribute according to the input content; the recommended attribute represents the type of the generated data on the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content;

[0008] In response to a selection operation on a target option in the recommended attributes, target data is generated according to the input content and the target option.

[0009] The above method, preferably, further comprises:

[0010] Output at least one preview data; one preview data corresponds to an option group, and the option group contains the preview option selected in each recommended attribute.

[0011] The above method, preferably, further comprises:

[0012] Outputting a target text corresponding to the input content, the target text comprising at least one filler position, the filler position corresponding to an option menu, the option menu comprising at least one keyword;

[0013] The recommended attribute and the attribute option corresponding to the recommended attribute are determined based on a keyword selected in at least one of the filling positions.

[0014] In the above method, preferably, the target text, the recommended attributes and the target data are presented on a first interactive interface, and the first interactive interface also presents an input area;

[0015] Wherein, the method further comprises:

[0016] Obtaining an interactive operation for the first interactive interface, the interactive operation comprising at least one of the following: an operation of modifying the target text; an operation of inputting content in the input area; an operation of modifying an attribute option in the recommended attribute;

[0017] In response to the interactive operation, new data is presented on the first interactive interface, where the new data is at least related to the adjusted attribute option.

[0018] In the above method, preferably, the first interactive interface includes a first area, a second area and a third area;

[0019] The first area is used to present the target data, the second area is used to present the target text and the recommended attributes, and the third area is the input area.

[0020] The above method, preferably, further comprises:

[0021] Outputting a second interactive interface, wherein at least one data sample is presented in the second interactive interface, and a text sample corresponding to the data sample is presented in an area where the data sample is located;

[0022] A selection operation for one of the data samples is received, where the selection operation is used to output the first interactive interface.

[0023] In the above method, preferably, the second interactive interface also presents a target control;

[0024] Wherein, the method further comprises:

[0025] In response to a trigger operation on the target control, a third interactive interface is output, wherein the third interactive interface presents an input area and a plurality of prompt items, wherein the prompt items are used to prompt the user to input corresponding description content, and each of the prompt items has a different type of description content;

[0026] In response to the input content received in the input area, the first interactive interface is output.

[0027] In the above method, preferably, the attribute options corresponding to the recommended attributes are determined based on historical data;

[0028] The historical data includes at least one of the following: device historical data corresponding to the electronic device, and user historical data of the user logged in by the electronic device.

[0029] In the above method, preferably, the input content includes at least one or any multiple of text, voice, and image.

[0030] A data processing device, comprising:

[0031] An input obtaining unit, used for obtaining input content, wherein the input content is used for generating data;

[0032] an attribute output unit, configured to output at least one recommended attribute according to the input content; the recommended attribute represents the type of the generated data in the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content;

[0033] The data generating unit is used to generate target data according to the input content and the target option in response to a selection operation on a target option in the recommended attribute.

[0034] An electronic device, comprising:

[0035] A memory, used to store a computer program and data generated by the execution of the computer program;

[0036] A processor is used to execute the computer program to achieve: obtaining input content, the input content is used to generate data; outputting at least one recommended attribute based on the input content; the recommended attribute characterizes the type of the generated data on the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content; in response to a selection operation for a target option in the recommended attribute, generating target data based on the input content and the target option.

[0037] A computer storage medium having a computer program / instruction stored thereon, wherein the computer program / instruction, when executed by a processor, implements any of the data processing methods described above.

[0038] A computer program product comprises a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the data processing method described in any one of the preceding claims is implemented.

[0039] It can be seen from the above technical solution that in a data processing method and electronic device disclosed in the present application, after obtaining the input content for generating data, at least one recommended attribute related to the input content is output according to the input content, and the recommended attribute represents the type of the generated data on the corresponding recommended dimension, and the recommended attribute corresponds to at least one attribute option related to the input content that can be provided to the user for selection. Based on this, in response to the selection operation for the target option in the recommended attribute, the target data can be generated according to the input content and the target option. It can be seen that in the present application, at least one attribute option related to the input content can be provided to the user on the recommended attribute related to the input content according to the input content, and the user can select options from these attribute options, thereby enriching the input content. In this way, even if the user lacks experience in editing prompt words, the user's input content can be enriched through the attribute options selected by the user in this embodiment, so that the generated data is more in line with the user's actual intention, thereby improving the accuracy of the generated data. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0042] Figure 2 This is an example diagram of obtaining input content in an embodiment of the present application;

[0043] Figure 3 This is an example diagram of outputting recommended attributes for input content in an embodiment of the present application;

[0044] Figure 4 Another flow chart of a data processing method provided in an embodiment of the present application;

[0045] Figure 5 This is an example diagram of outputting preview data in an embodiment of the present application;

[0046] Figure 6 Another flow chart of a data processing method provided in an embodiment of the present application;

[0047] Figure 7 This is an example diagram of outputting the target text in the embodiment of the present application;

[0048] Figure 8 This is an example diagram showing corresponding changes in the recommended attributes of the keywords in the filler position in the embodiment of the present application;

[0049] Fig. 9 This is an example diagram of the first interactive interface in the embodiment of the present application;

[0050] Fig.10 This is an example diagram of the second interactive interface in the embodiment of the present application;

[0051] Fig.11 This is an example diagram of the third interactive interface in the embodiment of the present application;

[0052] Fig.12 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0053] Fig.13 A result schematic diagram of an electronic device provided by an embodiment of the present application;

[0054] Fig.14 An example diagram constructed for visualization in a scenario where this application is applicable to a Vincent diagram;

[0055] Fig.15 This is an example image of the preview output in the scenario where this application is applicable to Wensheng images;

[0056] Fig.16 Provides an example diagram of a step-by-step guidance process for scenarios where this application is applicable to Wensheng diagrams;

[0057] Fig.17 This is an example of a recommended image provided to users in the scenario where this application is applicable to Wensheng images;

[0058] Fig.18 This is an example diagram of a user selecting a recommended image to enter an interactive interface in a scenario where this application is applicable to Wensheng images;

[0059] Fig.19 This is an example diagram of a user clicking on a fill area in a scenario where this application is applicable to a Wensheng diagram;

[0060] Fig. 20 This is an example image of outputting a preview style image for a user in a scenario where this application is applicable to Wensheng images. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] refer to Figure 1As shown, it is a flowchart of a data processing method provided in an embodiment of the present application, which can be applied to electronic devices capable of data processing, such as mobile phones, tablet devices, notebooks or servers, etc. The technical solution in this embodiment is mainly used to improve the security of data generation.

[0063] Specifically, the method in this embodiment may include the following steps:

[0064] Step 101: Obtain input content.

[0065] Among them, the input content is used to generate data.

[0066] Specifically, in this embodiment, the user's input content can be obtained by providing an interactive interface for the user. Figure 2 As shown in , the user can enter content data in the input box of the interactive interface, so that the user's input content can be obtained in this embodiment.

[0067] The input content may include at least one or any multiple of text, voice, and image to achieve data generation based on multimodal input.

[0068] Step 102: Output at least one recommended attribute according to the input content.

[0069] The recommended attributes represent the type of the generated data on the corresponding recommended dimension. For example, the recommended dimensions of images can include image styles such as minimalist style or retro style, image tones such as dark tones or bright tones, and the recommended dimensions of texts can include text styles such as positive emotions or negative emotions. Each recommended attribute corresponds to at least one attribute option. For example, the recommended attributes of image style include: minimalist style and retro style, etc.; the recommended attributes of image tones include: dark tones and bright tones, etc.; the recommended attributes of text style include: positive emotions and negative emotions, etc.

[0070] It should be noted that the recommended attributes and the attribute options corresponding to the recommended attributes are related to the input content. In other words, the output recommended attributes are determined based on the input content, and the attribute options corresponding to each recommended attribute are also determined based on the input content. If the content type or the content itself of the input content changes, the output recommended attributes and / or the attribute options corresponding to the recommended attributes will also change accordingly.

[0071] For example, Figure 3As shown in , according to the input content "a cute girl wearing a glowing skirt", the recommended attributes of the image perspective and the recommended attributes of the image style are output in the interactive interface. The image perspective can have two attribute options: top-down perspective and bottom-up perspective, and the image style can have two attribute options: reality and fantasy. The user can select the attribute option of top-down perspective or bottom-up perspective in the recommended attributes of the image perspective, and select the attribute option of reality or fantasy in the recommended attributes of the image style.

[0072] Step 103: In response to the selection operation for the target option in the recommended attributes, target data is generated according to the input content and the target option.

[0073] For example, Figure 3 As shown in , the user selects the attribute options of the bottom-up perspective on the recommended attributes of the image perspective, and selects the realistic attribute options on the recommended attributes of the image style. The attribute options of the bottom-up perspective and the realistic attribute options are the target options.

[0074] Specifically, in this embodiment, a large language model or a text-based graph model may be used to process input content and target options to generate target data.

[0075] For example, in this embodiment, the Wensheng graph model is used to generate a target image for the input content "a cute girl wearing a glowing skirt" and the two target options of "bottom-up perspective" and "reality". The target image contains a cute girl wearing a glowing skirt, and the target image is a bottom-up perspective and the image style is a realistic style.

[0076] It should be noted that each recommended attribute has a default or initial attribute option. If the user does not modify the recommended attribute, the default or initial attribute option in the recommended attribute is used as the target option. Based on this, target data is generated according to the input content and the default attribute option in each recommended attribute or the attribute option selected by the user.

[0077] It can be seen from the above technical solution that in a data processing method provided by an embodiment of the present application, after obtaining the input content for generating data, at least one recommended attribute related to the input content is output according to the input content, and the recommended attribute represents the type of the generated data on the corresponding recommended dimension, and the recommended attribute corresponds to at least one attribute option related to the input content that can be provided to the user for selection. Based on this, in response to the selection operation for the target option in the recommended attribute, the target data can be generated according to the input content and the target option. It can be seen that in this embodiment, at least one attribute option related to the input content can be provided to the user on the recommended attribute related to the input content according to the input content, and the user can select options from these attribute options, thereby enriching the input content. In this way, even if the user lacks experience in editing prompt words, the user's input content can be enriched through the attribute options selected by the user in this embodiment, so that the generated data is more in line with the user's actual intention, thereby improving the accuracy of the generated data.

[0078] In one implementation, in this embodiment, the following processing may be performed after step 102 and before step 103: Figure 4 As shown in:

[0079] Step 104: Output at least one preview data.

[0080] Among them, one preview data corresponds to one option group, and the option group includes the preview option selected in each recommended attribute. The preview option refers to the attribute option that is selected by default or initially in the recommended attribute.

[0081] Specifically, one of the attribute options is selected as the preview option in each recommended attribute, and these preview options form an option group, and at least one preview option is different between any two option groups. Corresponding preview data is generated based on each preview option in the option group and the input content. In other words, the attribute option corresponding to the recommended attribute can be output in the form of preview data combined with the option description.

[0082] For example, the input content has two recommended attributes, image style and image lens. The recommended attributes of image style have four preview options: Pixar cartoon style, movie style, ink painting style, and abstract painting style. The recommended attributes of image lens have two attribute options: fisheye lens and tilt lens. Select one of the attribute options in the recommended attributes of image style and image lens as the preview option. The preview options form option groups. At least one preview option is different between any two option groups. Generate corresponding preview data based on each preview option in the option group and the input content.

[0083] like Figure 5As shown in , after the fisheye lens in the image lens is selected as the preview option, each attribute option in the image style forms an option group with the fisheye lens. Based on the preview options in the option combination and the input content "a cute big-headed furry dog ​​with a vibrant park background, green grass, blooming flowers, bright sunshine and a cheerful atmosphere", four preview images are output, namely: a dog head image with fisheye lens and Pixar cartoon style, a dog head image with fisheye lens and movie style, a dog head image with fisheye lens and ink painting style, and a dog head image with fisheye lens and abstract painting style.

[0084] It should be noted that, in addition to being determined based on the input content, the attribute options corresponding to each recommended attribute can also be determined based on historical data. Specifically, the preview options can be determined based on historical data, and the corresponding preview data is related to the historical data. The historical data here includes at least one of the following: device historical data corresponding to the electronic device, and user historical data of the user logged in by the electronic device.

[0085] For example, when users historically generate images, they often select the Pixar cartoon style, so the attribute options of the Pixar cartoon style are output in the recommended attributes of the image style; when users historically generate images, they often select the fisheye lens, so the attribute options of the fisheye lens are output in the recommended attributes of the image lens.

[0086] Thus, the user can refer to the output preview data, select the attribute options in the recommended attributes, and then generate target data according to the selected target options and input data, so that the generated target data is more in line with the user's actual intention, thereby improving the accuracy of the generated data.

[0087] In one implementation, in this embodiment, the following processing may be performed after step 102 and before step 103: Figure 6 As shown in:

[0088] Step 105: Output the target text corresponding to the input content.

[0089] The target text includes at least one filling position, the filling position corresponds to an option menu, and the option menu includes at least one keyword. The recommended attribute and the attribute option corresponding to the recommended attribute are determined based on the keyword selected in the at least one filling position.

[0090] Specifically, in this embodiment, the name, adjective or verb in the target text can be set as a fill-in place, and the keyword selected by default in the option menu corresponding to the fill-in place is the keyword in the input content, and the other keywords in the option menu corresponding to the fill-in place are words that have an associated relationship with the keyword selected by default, such as synonyms, antonyms, words representing the same type of content, words representing different types of content, etc.

[0091] For example, Figure 7 As shown in , the target text corresponding to the input content can be: "A cute girl wearing a glowing skirt", where the text positions corresponding to "cute", "girl", "glowing" and "skirt" are filler positions. Among them, "cute" is the default selected keyword in the filler position corresponding to "cute", and there are two other keywords "depressed" and "crying" to be selected in the option menu; "girl" is the default selected keyword in the filler position corresponding to "girl", and there is also a keyword "boy" to be selected in the option menu; "skirt" is the default selected keyword in the filler position corresponding to "skirt", and there are two other keywords "school uniform" and "trousers" to be selected in the option menu.

[0092] Based on this, if the selected keyword in the filler position in the target text changes, the recommended attributes and / or the attribute options corresponding to the recommended attributes will also change. For example, for the "girl" in the target text, there is a recommended attribute "skin color", and correspondingly there are three attribute options: "yellow", "white" and "black"; if "girl" is changed to "dog head", then the recommended attribute of "skin color" is adjusted to the recommended attribute of "breed", and correspondingly there are multiple attribute options such as "Chinese rural dog" and "shepherd dog", such as Figure 8 as shown in .

[0093] In one implementation, the target text, recommended attributes, and target data are presented on a first interactive interface, and the first interactive interface also presents an input area.

[0094] Based on this, in this embodiment, interactive operations for the first interactive interface can also be obtained, and the interactive operations include at least one of the following: modification operations on the target text; content input operations in the input area; modification operations on attribute options in the recommended attributes; thereafter, in response to the interactive operation, new data is presented on the first interactive interface, and the new data is at least related to the modified attribute options.

[0095] For example, the user modifies the keywords in any one or more fill-in positions in the target text in the first interactive interface, and accordingly, the recommended attributes and / or attribute options with recommended attributes are adjusted accordingly. Based on this, the default or initial attribute options in the recommended attributes are also adjusted accordingly. Based on this, the new data presented in the first interactive interface is generated based on the modified target text and the adjusted attribute options.

[0096] For another example, a user inputs new content in the input area presented on the first interactive interface, and accordingly, recommended attributes corresponding to the new content are output on the first interactive interface. The recommended attributes include attribute selections corresponding to the new content. After the user selects an attribute option, new data is generated based on the new content and the reselected or default attribute options.

[0097] For another example, the user modifies an attribute option in the recommended attributes presented in the first interactive interface, so that new data is generated based on the input content and the adjusted attribute option.

[0098] Specifically, Fig. 9 As shown in , the first interactive interface includes a first area, a second area and a third area, wherein the first area is used to present target data, the second area is used to present target text and recommended attributes, and the third area is an input area. Based on this, the user can view the generated target text or target image in the first area, the user can modify the target text in the second area and can also modify the attribute options in the recommended attributes in the second area, and the user can input content in the third area.

[0099] Based on the above implementation, in this embodiment, a second interactive interface can also be output. In which, at least one data sample is presented in the second interactive interface. The text sample corresponding to the data sample is presented in the area where the data sample is located. Based on this, in this embodiment, a selection operation for one of the data samples can be received, and the selection operation is used to output the first interactive interface.

[0100] For example, Fig.10 As shown in , at least one fourth area is presented in the second interactive interface, and each fourth area presents a data sample, such as a sample image or text. The text sample corresponding to the data sample can be presented on the surface of the data sample in the fourth area. For example, taking the sample image as an example, the text of the sample image is presented on the sample image in the form of a floating window. The user can select one of the data samples in these fourth areas, and then output the first interactive interface, such as Fig. 9 As shown, at this time, the target data presented in the first area of ​​the first interactive interface is the data sample, and the target text presented in the second area is the text sample corresponding to the data sample.

[0101] It should be noted that the data samples presented in the second interactive interface can be determined based on historical data, and the historical data here may include: historical data of the electronic device where the second interactive interface is located, and / or historical data of the user logged in to the second interactive interface. In other words, the data samples presented in the second interactive interface can be historical data that the user has generated through operations, or can be data samples that meet similar conditions as historical data.

[0102] The similarity condition here may include at least one of the following:

[0103] Relevant to the content itself; relevant to the type of content; relevant to the tone; relevant to the style.

[0104] For example, a user has used a Wensheng graph model to generate an image of a dog head. Based on this, the second interactive interface presented in this embodiment presents the dog head image that was generated as a data sample, and also presents cat images or hamster images related to the dog head image.

[0105] Furthermore, a target control is also presented in the second interactive interface. Fig.10 .

[0106] Based on this, in this embodiment, a third interactive interface can also be output in response to a trigger operation on a target control. The third interactive interface at least presents an input area and multiple prompt items, and these prompt items are used to prompt the input of corresponding description content. The type of description content between each prompt item is different; based on this, the user can input content in the input area according to the prompt item. Therefore, in this embodiment, the first interactive interface can be output in response to the input content received in the input area.

[0107] For example, a prompt item may prompt the user to input the subject, predicate, object, etc., or a prompt item may prompt the user to input the image content, or a prompt item may prompt the user to input detailed information, or a prompt item may prompt the user to input the image style, and so on.

[0108] For example, Fig.11 As shown in , the user clicks Fig.10 After clicking "New" as shown, an input area and three prompt items, such as "Content", "Style" and "Details", are output on the third interactive interface. The user enters content in the input area according to the prompt items. After the input is completed, in response to the input content received in the input area, an output Fig. 9 The first interactive interface shown, Fig. 9 In the first interactive interface, the target data presented in the first area is the target data generated according to the input content and the selected (default or user-selected) attribute options in each recommended attribute in the second area.

[0109] refer to Fig.12 , is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application, which can be configured in an electronic device capable of data processing, such as a mobile phone, a tablet device, a notebook or a server, etc. The technical solution in this embodiment is mainly used to improve the security of data generation.

[0110] Specifically, the device in this embodiment may include the following units:

[0111] An input obtaining unit 1201 is used to obtain input content, where the input content is used to generate data;

[0112] The attribute output unit 1202 is used to output at least one recommended attribute according to the input content; the recommended attribute represents the type of the generated data in the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content;

[0113] The data generating unit 1203 is configured to generate target data according to the input content and the target option in response to a selection operation on the target option in the recommended attribute.

[0114] It can be seen from the above technical solution that in a data processing device provided by an embodiment of the present application, after obtaining the input content for generating data, at least one recommended attribute related to the input content is output according to the input content, and the recommended attribute represents the type of the generated data on the corresponding recommended dimension, and the recommended attribute corresponds to at least one attribute option related to the input content that can be provided to the user for selection. Based on this, in response to the selection operation for the target option in the recommended attribute, the target data can be generated according to the input content and the target option. It can be seen that in the present application, at least one attribute option related to the input content can be provided to the user on the recommended attribute related to the input content according to the input content, and the user can select options from these attribute options, thereby enriching the input content. In this way, even if the user lacks experience in editing prompt words, the user's input content can be enriched through the attribute options selected by the user in this embodiment, so that the generated data is more in line with the user's actual intention, thereby improving the accuracy of the generated data.

[0115] In one implementation, the attribute output unit 1202 is further configured to: output at least one preview data; one preview data corresponds to one option group, and the option group includes a preview option selected in each of the recommended attributes.

[0116] In one implementation, the attribute output unit 1202 is also used to: output a target text corresponding to the input content, the target text includes at least one fill-in position, the fill-in position corresponds to an option menu, and the option menu includes at least one keyword; wherein the recommended attribute and the attribute option corresponding to the recommended attribute are determined based on a keyword selected in at least one of the fill-in positions.

[0117] The target text, the recommended attributes and the target data are presented on a first interactive interface, and the first interactive interface also presents an input area;

[0118] The input obtaining unit 1201 is further used to obtain an interactive operation for the first interactive interface, wherein the interactive operation includes at least one of the following: a modification operation on the target text; a content input operation in the input area; a modification operation on an attribute option in the recommended attribute;

[0119] The attribute output unit 1202 is further used to: in response to the interactive operation, present new data on the first interactive interface, the new data being at least related to the adjusted attribute option. The first interactive interface includes a first area, a second area, and a third area;

[0120] The first area is used to present the target data, the second area is used to present the target text and the recommended attributes, and the third area is the input area.

[0121] In one implementation, the attribute output unit 1202 is also used to: output a second interactive interface, in which at least one data sample is presented, and a text sample corresponding to the data sample is presented in an area where the data sample is located; receive a selection operation for one of the data samples, and the selection operation is used to output the first interactive interface.

[0122] Wherein, the second interactive interface also presents a target control;

[0123] Among them, the attribute output unit 1202 is also used to: output a third interactive interface in response to a trigger operation on the target control, the third interactive interface presenting an input area and multiple prompt items, the prompt items are used to prompt the input of corresponding description content, and the type of the description content between each prompt item is different; in response to the input content received in the input area, output the first interactive interface.

[0124] In one implementation, the attribute options corresponding to the recommended attributes are determined based on historical data; wherein the historical data includes at least one of the following: device historical data corresponding to the electronic device, and user historical data of a user logged in to the electronic device.

[0125] The input content includes at least one or any multiple of text, voice, and image.

[0126] It should be noted that the specific implementation method of each unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0127] refer to Fig.13 , is a result schematic diagram of an electronic device provided in an embodiment of the present application, and the electronic device may include the following structure:

[0128] Memory 1301, used to store computer programs and data generated by the execution of computer programs;

[0129] Processor 1302 is used to execute a computer program to achieve: obtaining input content, the input content is used to generate data; outputting at least one recommended attribute based on the input content; the recommended attribute characterizes the type of the generated data on the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content; in response to a selection operation for a target option in the recommended attribute, generating target data based on the input content and the target option.

[0130] It can be seen from the above technical solution that in an electronic device provided by an embodiment of the present application, after obtaining input content for generating data, at least one recommended attribute related to the input content is output according to the input content, and the recommended attribute represents the type of the generated data on the corresponding recommended dimension, and the recommended attribute corresponds to at least one attribute option related to the input content that can be provided to the user for selection. Based on this, in response to the selection operation for the target option in the recommended attribute, the target data can be generated according to the input content and the target option. It can be seen that in this embodiment, at least one attribute option related to the input content can be provided to the user on the recommended attribute related to the input content according to the input content, and the user can select options from these attribute options, thereby enriching the input content. In this way, even if the user lacks experience in editing prompt words, the user's input content can be enriched through the attribute options selected by the user in this embodiment, so that the generated data is more in line with the user's actual intention, thereby improving the accuracy of the generated data.

[0131] Taking the scene of Wenshengtu as an example, the technical solution of this application is illustrated as follows:

[0132] With the development of artificial intelligence (AI) technology, users can interact with AI models through natural language to generate text or image content. However, since most users lack experience in how to construct effective prompts, the generated results often differ greatly from user expectations. This "expectations do not match results" problem seriously affects the user experience and makes users feel frustrated when using AI model generation tools.

[0133] Therefore, there is an urgent need for an innovative interaction design that can guide users to gradually construct effective prompt words to achieve the goal of generating results that better meet user needs.

[0134] In view of this, this application aims to solve the problem that when users use AI models to generate images or texts, the generated results are far from what they expected due to their lack of understanding and ability to construct natural language prompts. To this end, this application guides users to gradually express their generation needs in a structured way, so that the content generated by the AI ​​model is more in line with the user's expectations and improves the user's overall experience.

[0135] First of all, this application has the following key implementations:

[0136] 1. Visual construction:

[0137] This application provides an intuitive interactive interface and provides content selection operations. Users can select and generate content based on visualization modules (including but not limited to "main content", "style" and "image details") by clicking and dragging, and can quickly build prompt words with high relevance to generate expected results, such as Fig.14 This visual construction method enables users to understand and select prompt words more intuitively, simplifying the construction process of prompt words.

[0138] 2. Situational filling:

[0139] This application provides smart filling options (i.e. filling positions) to automatically generate templates for prompt words in relevant situations. Users can directly fill in relevant content in the template, and after selecting the main elements corresponding to each filling position, this application can pop up relevant style suggestions (i.e. the recommended attributes mentioned above) and provide sample images (i.e. the preview data mentioned above) for preview. Fig.15 As shown in , this application provides a fill-in-the-blank template, and users can directly fill in the required content in the template. This application will also recommend relevant contextual content based on the user's choice, and combine it with a visual picture preview to help users understand and describe complex language needs. This contextual filling not only helps users better construct prompt words, but also improves the relevance of generated results through dynamic prompts.

[0140] 3. Distribution guidance:

[0141] For novice users, this application can provide a step-by-step guidance process, each step is accompanied by guidance instructions and sample pictures to help users gradually master the construction method of prompt words, such as Fig.16 In addition, the present application also makes personalized recommendations based on the user's past behavior, which may require settings or adjustments, so that the construction of prompt words is more in line with the user's usage habits, further improving the accuracy and relevance of the generated results.

[0142] For example, Fig.17As shown in , for users using the Wenshengtu application, this application can provide users with recommended images (i.e., the sample images in the previous text). When the user clicks on a recommended image, the prompt of the image will be preset in the input area, such as Fig.18 As shown in;

[0143] Based on the above implementation, Fig.19 As shown in , users can enter content by clicking on the fill-in-the-blank area;

[0144] In addition, if Fig. 20 As shown in , the user can click on the drop-down option to select the recommended style and angle, etc., where the style content will generate a preview style picture selection based on the content input by the user.

[0145] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0146] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0147] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0148] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, comprising: Obtaining input content, wherein the input content is used to generate data; Outputting at least one recommended attribute according to the input content; The recommended attribute represents the type of the generated data on the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content; In response to a selection operation on a target option in the recommended attributes, target data is generated according to the input content and the target option.

2. The method according to claim 1, further comprising: outputting at least one preview data; One preview data corresponds to one option group, and the option group includes the preview option selected in each recommended attribute.

3. The method according to claim 1, further comprising: Outputting a target text corresponding to the input content, the target text comprising at least one filler position, the filler position corresponding to an option menu, the option menu comprising at least one keyword; The recommended attribute and the attribute option corresponding to the recommended attribute are determined based on a keyword selected in at least one of the filling positions.

4. The method according to claim 3, wherein the target text, the recommended attributes and the target data are presented on a first interactive interface, and the first interactive interface also presents an input area; in, The method further comprises: Obtaining an interactive operation for the first interactive interface, the interactive operation comprising at least one of the following: an operation of modifying the target text; an operation of inputting content in the input area; an operation of modifying an attribute option in the recommended attribute; In response to the interactive operation, new data is presented on the first interactive interface, where the new data is at least related to the adjusted attribute option.

5. The method according to claim 4, wherein the first interactive interface comprises a first area, a second area and a third area; in, The first area is used to present the target data, the second area is used to present the target text and the recommended attributes, and the third area is the input area.

6. The method according to claim 4, further comprising: Outputting a second interactive interface, wherein at least one data sample is presented in the second interactive interface, and a text sample corresponding to the data sample is presented in an area where the data sample is located; A selection operation for one of the data samples is received, where the selection operation is used to output the first interactive interface.

7. The method according to claim 6, wherein the second interactive interface further presents a target control; in, The method further comprises: In response to a trigger operation on the target control, a third interactive interface is output, wherein the third interactive interface presents an input area and a plurality of prompt items, wherein the prompt items are used to prompt the user to input corresponding description content, and each of the prompt items has a different type of description content; In response to the input content received in the input area, the first interactive interface is output.

8. The method according to claim 1, wherein the attribute options corresponding to the recommended attributes are determined based on historical data; in, The historical data includes at least one of the following: device historical data corresponding to the electronic device, and user historical data of a user logged in by the electronic device.

9. The method according to claim 1, wherein the input content comprises at least one or any multiple of text, voice, and image.

10. An electronic device comprising: A memory, used to store a computer program and data generated by the execution of the computer program; A processor is used to execute the computer program to achieve: obtaining input content, the input content is used to generate data; outputting at least one recommended attribute according to the input content; the recommended attribute represents the type of the generated data in the corresponding recommended dimension; the recommended attribute corresponds to at least one attribute option, and the recommended attribute and the attribute option corresponding to the recommended attribute are both related to the input content; In response to a selection operation on a target option in the recommended attributes, target data is generated according to the input content and the target option.

Images