Method for generating electronic greeting card, computer equipment and storage medium

Abstract

The invention discloses a method for generating an electronic greeting card, computer equipment and a storage medium, and belongs to the technical field of computers. Comprising the steps of generating a target image according to a target blessing; according to the target image, an initial greeting card interface is displayed, and the initial greeting card interface comprises an audio adding control; in response to a click operation on the audio adding control, displaying an audio information configuration interface; in response to a configuration operation of a user on the audio information configuration interface, generating a target audio; and generating the electronic greeting card according to the target blessing, the target image and the target audio. Thus, the character elements, the image elements and the audio elements are fused in the generated electronic greeting card, and full-link personalized electronic greeting card generation from text to vision and hearing is realized, so that the production level of a gift greeting card is improved, digitized blessing experience with rich ceremony is brought to a user, and the user experience can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for generating an electronic greeting card, a computer device, and a storage medium. Background Art

[0002] With the development of technology, it has become possible to generate e-cards online, replacing traditional paper cards. Due to the diversity and convenience of e-card generation, this method has become widely used, improving the efficiency of gift giving and adding a sense of formality to receiving gifts.

[0003] In related technologies, when generating an electronic greeting card online, users can edit the blessings to be sent on the electronic greeting card generation interface and can choose to upload corresponding pictures. After that, the blessings on the electronic greeting card can be determined based on the blessings edited by the user, and the pictures uploaded by the user can be displayed on the electronic greeting card, thereby generating an electronic greeting card.

[0004] However, the content displayed by the electronic greeting cards in the above-mentioned manner is essentially the same as that of paper greeting cards, which are both a combination of text and pictures. From the perspective of user needs, they cannot bring users a new blessing experience. Summary of the Invention

[0005] This application provides a method, apparatus, computer device, storage medium, and product for generating electronic greeting cards. These cards can be generated based on text, images, and audio. The generated electronic greeting cards incorporate text, image, and audio elements, achieving full-link personalized electronic greeting card generation from text to visual and auditory elements. This improves the production of gift cards and provides users with a digital blessing experience rich in ritual, thereby enhancing the user experience. The technical solution includes the following.

[0006] In a first aspect, a method for generating an electronic greeting card is provided, the method comprising:

[0007] Generate a target image according to the target blessing words;

[0008] Displaying an initial greeting card interface according to the target image, wherein the initial greeting card interface includes an audio adding control;

[0009] In response to a click operation on the audio adding control, displaying an audio information configuration interface;

[0010] generating target audio in response to a configuration operation of the user on the audio information configuration interface;

[0011] An electronic greeting card is generated according to the target blessing words, the target image and the target audio.

[0012] In this application, a target image is first generated based on the target blessing words, and then an initial greeting card interface is displayed based on the target image. The initial greeting card interface includes an audio adding control for adding the audio of the electronic greeting card. When adding the audio of the electronic greeting card, you can click the audio adding control to display an audio information configuration interface so that the user can perform configuration operations on this audio information configuration interface, and then generate the target audio according to the configured content. Finally, an electronic greeting card is generated based on the target blessing words, target image and target audio. In this way, the generated electronic greeting card integrates text elements, image elements and audio elements, realizing the full-link personalized electronic greeting card generation from text to vision and hearing, thereby improving the production level of gift greeting cards, and then bringing users a digital blessing experience with a rich sense of ritual, which can enhance the user experience.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes:

[0014] Get the target blessing.

[0015] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, obtaining the target blessing includes:

[0016] After generating a target order, obtaining product information of the products in the target order;

[0017] The target blessing is generated according to the commodity information.

[0018] In the above method, by generating target blessings based on the product information of the goods in the target order, the blessings of the electronic greeting card can be determined based on the product information, so that blessings that match the purchased goods can be automatically generated, making the generation of target blessings more intelligent.

[0019] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, obtaining the target blessing includes:

[0020] Obtain product information of a target product, where the target product is the product that the user is browsing;

[0021] The target blessing is generated according to the commodity information of the target commodity.

[0022] In the above method, by displaying an electronic greeting card interface while the user is browsing products, the user can send an electronic greeting card without purchasing the products, which can improve the user experience. In addition, target blessings are generated based on the product information of the target product, so that the generated target blessings can be close to the user's wishes, thereby making the process of generating electronic greeting cards more intelligent and improving the user experience.

[0023] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the method further includes:

[0024] Determining a display mode of the target image according to the target audio, wherein the display mode includes static display and dynamic display;

[0025] Furthermore, generating an electronic greeting card according to the target blessing words, the target image, and the target audio includes:

[0026] In the case where the target image is displayed in a dynamic display mode, a dynamically displayed electronic greeting card is generated according to the target blessing words, the target image and the target audio;

[0027] In the case where the target image is displayed in a static manner, a statically displayed electronic greeting card is generated according to the target greeting words, the target image and the target audio.

[0028] Through the above implementation method, electronic greeting cards with dynamic or static display are generated according to the display mode of the target image, so that electronic greeting cards in different forms can be generated. Compared with electronic greeting cards that only generate static display, the visual effect of the electronic greeting card can be enhanced, thereby improving the user experience.

[0029] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, generating a dynamically displayed electronic greeting card based on the target greeting, the target image, and the target audio includes:

[0030] determining at least one target element from the target image;

[0031] generating the dynamically displayed electronic greeting card according to the target blessing words, the target image, the target audio, and the at least one target element;

[0032] And, the method further comprises:

[0033] The target greeting card interface of the electronic greeting card is displayed, and the target greeting card interface includes the at least one target element displayed dynamically.

[0034] In the above implementation method, the dynamically displayed electronic greeting card generated based on the target blessing words, target image, target audio and at least one target element is an electronic greeting card in which at least one target element is in a dynamic display state and displays the target blessing words, target image and plays the target audio. In this way, the generated electronic greeting card can provide users with excellent visual effects, thereby providing users with a richer blessing experience.

[0035] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the method further includes:

[0036] Acquiring the melody and / or rhythm of the target audio;

[0037] The at least one target element is dynamically displayed according to the melody and / or rhythm of the target audio.

[0038] In the above implementation, at least one target element is dynamically displayed according to the melody and / or rhythm of the target audio, so that at least one target element can be displayed in combination with the melody / rhythm of the target audio, thereby enhancing the association between the display of the target image and the rhythm of the target audio, thereby providing users with richer visual effects.

[0039] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, the target greeting card interface includes an audio playback control, and the audio playback control is displayed on the target greeting card interface in a rotating manner, or the audio playback control is displayed on the target greeting card interface in a manner of jumping notes.

[0040] In the above implementation, by setting the audio playback controls to be displayed in a rotating manner or in a jumping musical note manner, the user's visual effect can be enhanced, thereby bringing a better experience to the user.

[0041] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, generating a target image according to the target blessing includes:

[0042] The target blessing words are input into a Wensheng graph model, and the target blessing words are used as constraints of the Wensheng graph model. The Wensheng graph model is controlled by the constraints to generate the target image.

[0043] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the audio information configuration interface includes a music description configuration control, and generating the target audio in response to a user's configuration operation on the audio information configuration interface includes:

[0044] In response to a configuration operation on the music description configuration control on the audio information configuration interface, obtaining the music description information configured by the configuration operation;

[0045] The target audio is generated by a Vincent music model according to the music description information.

[0046] In combination with the first aspect and the above implementation manner, in some implementation manners of the first aspect, the audio information configuration interface further includes multiple reference description information, and the method further includes:

[0047] In response to a selection operation on the audio information configuration interface of target description information among the multiple reference description information, the target description information is determined to be the music description information.

[0048] In the above implementation, the user can directly select a desired reference description from the multiple reference descriptions provided in the audio information configuration interface, and the selected reference description is subsequently determined as the music description information. In this process, the user does not need to edit the music description information independently, which provides convenience and improves the user experience.

[0049] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, the audio information configuration interface includes at least one of a lyrics configuration control, a music style configuration control, a music atmosphere configuration control, and a singing voice configuration control, and generating target audio in response to a user's configuration operation on the audio information configuration interface includes:

[0050] In response to a configuration operation on at least one of the lyrics configuration control, the music style configuration control, the music atmosphere configuration control, and the singing voice configuration control on the audio information configuration interface, obtaining target audio information configured by the configuration operation;

[0051] The target audio is generated through the Vincent music model according to the target audio information configured by the configuration operation.

[0052] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, the target greeting card interface of the electronic greeting card includes an information customization control, and the method further includes:

[0053] In response to a selection operation on the information customization control, displaying an information customization interface;

[0054] In response to a configuration operation on the information customization interface, determining target customization information, wherein the target customization information is used to describe the attributes of a recipient of the electronic greeting card and / or the preferences of the recipient;

[0055] The electronic greeting card is updated according to the target blessing words, the target image, the target audio, and the target customized information.

[0056] In the above implementation method, by configuring the attributes and / or preferences of the receiving object in the information customization interface, the electronic greeting card can be updated subsequently according to the attributes and / or preferences of the receiving object, so that the generated electronic greeting card is more in line with the preferences of the receiving object, so that the generated electronic greeting card can provide users with a unique and ritualistic digital blessing experience, thereby enhancing the customization of the electronic greeting card.

[0057] In combination with the first aspect and the above implementations, in certain implementations of the first aspect, updating the electronic greeting card according to the target greeting message, the target image, the target audio, and the target customized information includes:

[0058] Adjusting the color tone and / or image elements of the target image according to the target customization information to obtain a new target image;

[0059] adjusting the music style and / or melody of the target audio according to the target customization information to obtain a new target audio;

[0060] The electronic greeting card is updated according to the target blessing words, the new target image, and the new target audio.

[0061] In combination with the first aspect and the above implementations, in some implementations of the first aspect, the method further includes:

[0062] generating a target video according to the target image and the music description information;

[0063] The step of generating an electronic greeting card according to the target blessing words, the target image, and the target audio includes:

[0064] The electronic greeting card is generated according to the target blessing words, the target video and the target audio.

[0065] In the above implementation method, since the music description information can indicate the content expressed by the target audio or the scene described by the target audio, the scene described by the target audio can be restored by combining the music description information, so that the generated target video and target audio are closely related, so that electronic greeting cards with similar scenes described by various types of elements can be generated subsequently, thereby improving the user's visual to auditory unity.

[0066] In combination with the first aspect and the above implementations, in some implementations of the first aspect, generating a target video based on the target image and the music description information includes:

[0067] The target image is input into a graph-generated video model, and the music description information is used as a constraint condition of the graph-generated video model. The generation process of the graph-generated video model is controlled by the constraint condition to obtain the target video.

[0068] In a second aspect, a device for generating an electronic greeting card is provided, the device comprising:

[0069] An image generation module is used to generate a target image according to the target blessing words;

[0070] A first display module is configured to display an initial greeting card interface according to the target image, wherein the initial greeting card interface includes an audio adding control;

[0071] A second display module is configured to display an audio information configuration interface in response to a click operation on the audio adding control;

[0072] An audio generation module, configured to generate target audio in response to a configuration operation of a user on the audio information configuration interface;

[0073] The electronic greeting card generation module is used to generate an electronic greeting card according to the target blessing words, the target image and the target audio.

[0074] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the above-mentioned method for generating an electronic greeting card when executed by the processor.

[0075] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating an electronic greeting card is implemented.

[0076] In a fifth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the steps of the above-mentioned method for generating an electronic greeting card.

[0077] It can be understood that the beneficial effects of the second, third, fourth and fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.

[0079] Figure 1 This is a schematic diagram of a scenario of generating a greeting card through a first application provided by an embodiment of the present application;

[0080] Figure 2 This is a schematic diagram of a scenario of generating a greeting card through a second application provided by an embodiment of the present application;

[0081] Figure 3 This is a schematic diagram of a scenario in which a greeting card is generated by a third application, provided in an embodiment of the present application;

[0082] Figure 4 This is a schematic diagram of a scenario of generating a greeting card through a fourth application provided by an embodiment of the present application;

[0083] Figure 5 This is a schematic diagram of a process of using the electronic greeting card function when a user places an order, provided by an embodiment of the present application;

[0084] Figure 6 This is a flow chart of a method for generating an electronic greeting card provided by an embodiment of the present application;

[0085] Figure 7 This is a schematic diagram of a process for generating an electronic greeting card provided in an embodiment of the present application;

[0086] Figure 8 This is a schematic diagram of a scenario for generating an electronic greeting card provided by an embodiment of the present application;

[0087] Figure 9 This is a schematic diagram of an information customization interface provided in an embodiment of the present application;

[0088] Figure 10 This is a schematic diagram of an audio information configuration interface provided in an embodiment of the present application;

[0089] Figure 11 This is a schematic structural diagram of a device for generating an electronic greeting card provided in an embodiment of the present application;

[0090] Figure 12 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0091] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0092] It should be understood that the “multiple” mentioned in this application refers to two or more. In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate the clear description of the technical solution of this application, words such as “first” and “second” are used to distinguish between identical or similar items with basically the same functions and effects. Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not necessarily limit them to be different.

[0093] The application scenarios of the embodiments of the present application are first described.

[0094] For ease of understanding, the following example will take the case where a user sends an electronic greeting card through a mobile phone on the first application, the second application, the third application, or the fourth application. Figure 1-Figure 4 This is a schematic diagram of a scenario for generating an electronic greeting card provided in an embodiment of the present application. Figure 1-Figure 4 Give a detailed explanation.

[0095] Figure 1 This is a scenario where a greeting card is generated by a first application (application A).

[0096] For example, Figure 1 (a) in the figure shows an order submission interface 101 for purchasing gifts in the first application (application A). The order submission interface 101 can display information such as the delivery address, delivery time, contact number, greetings, order price, etc.

[0097] like Figure 1 As shown in (a), when the user clicks the greeting function 10 on the order submission interface 101, the mobile phone may display the following in response to the user's click: Figure 1 The greeting card editing interface 102 shown in (b) of FIG. The greeting card editing interface 102 may include a contact information editing area 20, a greeting message editing area 30, and an image editing area 40. In the greeting card editing interface 102, the user can edit the recipient's nickname and contact information, edit the greeting message, and upload a corresponding image.

[0098] The user can edit the contact information of the recipient in the contact information editing area 20 of the recipient. In one possible way, the user can directly enter the contact information of the recipient in the contact information editing area 20. In another possible way, the contact information editing area 20 can display an address book control. Figure 1As shown in (b), the user can click on the address book control. In response to the user's click, the mobile phone can display a contact list. The user can view the contacts by sliding up and down. Then the user can select the corresponding contact from the contact list. In response to the user's click on the contact, the mobile phone can display the mobile phone number of the clicked contact in the contact editing area 20.

[0099] The user can edit the blessing words to be sent to the recipient in the blessing words editing area 30. In one possible way, the user can directly input the words he wants to say in the blessing words editing area 30. In another possible way, the blessing words editing area 30 can display at least one prompt blessing words, such as Figure 1 As shown in (b), the user can click on a prompt blessing. In response to the user's click, the mobile phone can obtain the text selected by the user and display the text selected by the user in the blessing editing area 30.

[0100] The user can also upload the pictures he wants to send in the picture editing area 40, such as Figure 1 As shown in (b) in FIG. 4 , the picture editing area 40 may include a picture upload control through which a user can upload a picture that he or she wants to send.

[0101] The greeting card editing interface 102 may also include a confirmation button 50. After the user has finished editing the above information, the user may click the confirmation button 50. In response to the user's click, the mobile phone may display the following Figure 1 The greeting card display interface 103 shown in (c) is used to display the generated greeting card to the user, so that the user can intuitively see the content displayed in the sent greeting card. Figure 1 As shown in (c) in FIG. 1 , the greeting card displayed in the greeting card display interface 103 includes a picture uploaded by the user, a blessing message written by the user, and the nickname of the recipient.

[0102] Figure 2 This is a scenario where a greeting card is generated by a second application (application B).

[0103] For example, Figure 2 (a) shows the order display interface 201 after purchasing goods in the second application (application B). The order display interface 201 can display the product introduction, product price, as well as the recipient information, order price, service guarantee information, etc. of the purchased goods.

[0104] The order display interface 201 may also include a greeting card control 60. The user can click on the greeting card control 60. In response to the user's click, the mobile phone can automatically generate a greeting card and display the following information: Figure 2The greeting card editing interface 202 shown in (b) of FIG. The greeting card editing interface 202 can display the automatically generated greeting card, and the user can edit the generated greeting card in the greeting card editing interface 202.

[0105] The greeting card editing interface 202 may include a greeting card editing control 70, such as Figure 2 As shown in (b) in FIG. 1 , the user can click on the greeting card editing control 70. In response to the user's click, the mobile phone can display the following Figure 2 The greeting card customization interface 203 shown in (c) of the figure is shown. In this interface 203, the user can edit the nickname of the recipient, modify the text of the greeting, and so on. After confirming the edited nickname and text of the greeting, the user can click the Confirm Customization button, or click the Exit Edit control and then click the Confirm Customization button to enable the second application to generate the greeting card. It should be understood that the interface finally edited by the user in this interface 203 is the interface of the final greeting card.

[0106] Figure 3 This is a scenario where a greeting card is generated by a third application (application C).

[0107] For example, Figure 3 (a) in the figure shows a pattern selection interface 301 for creating a gift card in a third application (application C). This pattern selection interface 301 can display patterns for gift cards and vouchers. Pattern selection interface 301 can display gift card and voucher patterns by category, such as "All Patterns," "Valentine's Day," "Birthday," "Thanks," "Colleague," "Friend," "Praise," "Apology," and "Caring."

[0108] For example, Figure 3 As shown in (a) of FIG, when the user clicks on any pattern in the pattern selection interface 301, the mobile phone may display the following in response to the user's click: Figure 3 The gift card purchase interface 302 shown in (b) of FIG. 3 may display the pattern of the selected gift card, and display multiple gift cards, commodities, etc. to the user.

[0109] like Figure 3 As shown in (b) in the figure, when the user clicks on any gift card / product in the gift card purchase interface 302, the mobile phone may display the following information in response to the user's click: Figure 3 The order submission interface 303 shown in (c) of FIG. The order submission interface 303 can display the generated greeting card 20 and the gifting method, the product information of the gifted product, etc. Figure 3 As shown in (c), the pattern in the greeting card 20 is Figure 3The pattern selected in (a).

[0110] For example, Figure 3 As shown in (c) in the figure, in the order submission interface 303, multiple prompt greetings can also be displayed, such as "Happy Valentine's Day", "Love you so much", "Wish all your troubles are gone", etc. Figure 3 As shown in (c) of FIG, when a user clicks on any of the prompt greetings, the mobile phone can replace the greeting displayed on the greeting card 80 in the order submission interface with the prompt greeting clicked by the user. In addition, the order submission interface 303 can also include a greeting edit control 90. When the user clicks on the greeting edit control 90, the user can re-edit the greeting displayed on the greeting card 80, thereby implementing customization of the greeting card 80 by the third application.

[0111] Figure 4 This is a scene in which a greeting card is generated by the fourth application (application D).

[0112] For example, Figure 4 (a) in the figure shows a greeting card creation interface 401 of a fourth application (application D). The greeting card creation interface 401 can display an automatically generated greeting card. In addition, the user can edit the displayed greeting card on the greeting card creation interface 401. The greeting card creation interface 401 can include a greeting editing control 11 and an image update control 12.

[0113] For example, Figure 4 As shown in (a) of FIG, when the user clicks the greeting edit control 11, in response to the user's click, the mobile phone can set the greeting to editable mode, so that the user can subsequently modify the greeting displayed on the greeting card, thereby realizing the user's customized editing of the greeting. When the user clicks the picture update control 12, in response to the user's click, the mobile phone can redisplay the greeting as shown in FIG. Figure 4 The greeting card shown in (b) Figure 4 The picture shown in the greeting card shown in (b) is the same as Figure 4 The picture in the greeting card shown in (a) is different.

[0114] Combined with the above Figure 1-Figure 4 As can be seen from the greeting card generation process shown in the embodiment, when generating a greeting card through the first application (application A), the user edits the recipient's nickname, mobile phone number, greeting message, cover picture and other information, and then generates a greeting card based on the edited information. Figure 1As shown in (b) of the figure, when the first application generates a greeting card, the user needs to manually upload the cover image. This makes the card generation process inconvenient, and if the user does not upload the image, the generated card is simply a greeting text, resulting in a relatively simple card.

[0115] When generating a greeting card through the second application (Application B), a greeting card is automatically generated based on the purchased product, and the generated greeting card only contains a paragraph of blessing text. When generating a greeting card through the third application (Application C), a suitable pattern is selected from the provided greeting card patterns, and the generated greeting card also contains only blessing words and pictures. When generating a greeting card through the fourth application (Application D), although the picture displayed on the greeting card can be updated according to the user's instructions, the generated greeting card also contains only blessing words and pictures.

[0116] Combination of the above Figures 1 to 4 This article introduces the process of generating and sending electronic greeting cards through different applications. In this process, the generated greeting cards generally contain only greeting text or greeting text and pictures. Therefore, the elements contained in the generated greeting cards are relatively simple and cannot bring a rich greeting experience to users.

[0117] Furthermore, in the related art, when generating greeting cards, various aspects of the recipient's information are not obtained. As a result, the generated greeting cards are not highly consistent with the recipient. In other words, the generated greeting cards cannot be customized based on the recipient's information, which makes the generated greeting cards lack a sense of customization.

[0118] To this end, an embodiment of the present application provides a method for generating electronic greeting cards, which can generate electronic greeting cards based on text, images, and audio, realizing the full-link personalized electronic greeting card generation from text to vision and hearing, thereby improving the production level of gift greeting cards, and then bringing users a digital blessing experience with a rich sense of ritual, which can enhance the user experience.

[0119] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0120] In one possible approach, during the process of developing the target application, technicians can configure the function of generating electronic greeting cards as a preset function on the order submission interface after placing an order, so that when the target application submits an order, electronic greeting cards can be generated based on the method of generating electronic greeting cards.

[0121] Specifically, the method for generating an electronic greeting card can be configured in a target application with an ordering function, such as the first application mentioned above. When a user places an order through the first application, if the user has a need to generate an electronic greeting card, a corresponding electronic greeting card can be generated based on the method for generating an electronic greeting card provided in an embodiment of the present application.

[0122] It should be noted that the above-mentioned target application can be an application with an ordering function, such as the first application, the second application, and the third application shown above. For example, the first application can be Ele.me, the second application can be Douyin, and the third application can be Taobao and other applications. The embodiment of this application does not specifically limit the target application.

[0123] For example, Figure 5 This is a schematic diagram of the process of using the electronic greeting card function when a user places an order, as provided in an embodiment of the present application.

[0124] For example, Figure 5 (a) in the figure shows the main interface 501 of the first application (application A), which can also be called the "homepage of the first application." The main interface 501 of the first application can display multiple category menus, operable controls or buttons, images, and other interface content to meet the user's usage needs.

[0125] For example, Figure 5 As shown in (a) of FIG, the main interface 501 of the first application displays the current delivery address, a search box, and different category menus such as food delivery, supermarkets, fruits, medicine, desserts, flowers and gifts, as well as a merchant list. A user can click on a category menu to view the merchant list under that category menu. This embodiment of the application does not limit the display content, display area size, etc. on the main interface 501 of the first application.

[0126] like Figure 1 As shown in (a), the user clicks on the category menu of flowers and gifts. In response to the user's click operation, the mobile phone can display the following Figure 1 Flower gift interface 502 shown in (b) of FIG. Flower gift interface 502 may display a search box, a gift guide, a list of merchants selling flower gifts, or a list of products. Furthermore, it may display different flower gift categories such as "holiday bouquets," "fruit gift boxes," "snack gift boxes," and "trendy toys."

[0127] The user can view more business information or product information by sliding up and down. For example, when the user clicks on any position of the product display area 21 of gift A in the product list, in response to the user's click operation, the mobile phone can display the following information: Figure 5The product purchase interface 503 for Gift A shown in (c) of FIG. 5 shows product information related to Gift A. Furthermore, by swiping upward, the user can view product information for multiple products sold by the merchant to which Gift A belongs, such as the price, favorable rating, and quantity sold of each product.

[0128] For example, when the user clicks the buy now button 22 in the product purchase interface 503, the mobile phone may display the following information in response to the user's click: Figure 5 The order submission interface 504 shown in (d) can display information such as delivery address, delivery time, contact number, greetings, order price, etc.

[0129] In addition, if Figure 5 The order submission interface 504 shown in (d) can also be configured with a surprise card feature and display the prompt "Free trial after payment, sent online at a scheduled time." Furthermore, the order submission interface 504 can also be configured with a details view control 23. When the user clicks the details view control 23, the phone can display instructions for the surprise card in response to the user's click.

[0130] For example, after the user clicks the submit order button 24 and pays, an electronic greeting card can be automatically generated by using the surprise greeting card function.

[0131] In another possible manner, during the process of developing the target application, the technicians may directly configure the function of generating an electronic greeting card as a preset function of the target application.

[0132] For example, taking the target application as the first application, the main interface of the first application may also include a channel greeting card entrance. The user can automatically generate an e-card through the channel greeting card entrance using the method for generating an e-card. For example, after entering the channel greeting card entrance, the user's order list may be displayed first, and then the user may select an order from it. In response to the user's click, the mobile phone may generate an e-card for this order using the method for generating an e-card provided in the embodiment of the present application.

[0133] The above embodiment introduces the operation process of the user using the electronic greeting card function from the user interaction level. Figures 6 to 9 The specific implementation method of generating an electronic greeting card provided in the embodiment of the present application is described.

[0134] Before introducing the method for generating an electronic greeting card, the professional terms involved in the embodiments of the present application are first explained.

[0135] 1. Diffusion Model SD

[0136] The Diffusion Model (SD) is a generative model that can generate detailed images from text descriptions. It can also be used for tasks such as image inpainting, image rendering, text-to-image, image-to-image, text-to-music, and image-to-video. In other words, given a text description of a desired image, the Diffusion Model (SD) can generate realistic images that match the description, or music that matches the text description. Furthermore, the Diffusion Model (SD) can generate videos based on a provided image as a template and text prompts.

[0137] 2. U-Net

[0138] U-Net is the core of the diffusion model SD. It takes three inputs: (1) a noisy image; (2) a time tag; and (3) other conditional variables. After layer-by-layer operations, a noisy output is obtained. This noisy output can be used to denoise a noisy image.

[0139] The U-Net model combines an encoding and decoding structure, using convolutional and pooling layers for feature extraction and deconvolutional layers for image restoration. The encoding structure (encoder) is a compression channel used to extract image features layer by layer, while the decoding structure (decoder) is an expansion channel used to restore the image based on its features.

[0140] The following is a detailed explanation of the method for generating an electronic greeting card provided in an embodiment of the present application.

[0141] Figure 6 This is a flow chart of a method for generating an electronic greeting card provided in an embodiment of the present application. This method can be applied to a computer device, which can be a terminal device such as a mobile phone, tablet, or computer. The embodiment of the present application does not limit the form of the computer device.

[0142] It should be understood that this method is in the aforementioned Figure 5 The process described above is executed after the order has been submitted and the payment has been made. Figure 6 , the method includes the following steps.

[0143] Step 601: Generate a target image according to the target blessing.

[0144] The target blessing is the blessing that the user wants to send. In the embodiment of the present application, the target blessing can be obtained on the greeting card making interface.

[0145] The target image is an image that matches the target blessing. For example, if the target blessing is a blessing about Christmas, the target image can be an image about Christmas. Specifically, the scene of the generated target image can be the same image as the scene described by the target blessing.

[0146] In this case, by generating a target image based on the target blessing, instead of directly uploading an image as in the related art, the target image is generated according to the target blessing, so that the user can automatically generate the image of the electronic greeting card without uploading the image, thereby making the generation of the image in the electronic greeting card more convenient.

[0147] In an embodiment of the present application, the operation of generating a target image according to the target blessing can be achieved in the following two possible ways.

[0148] One possible approach is to obtain target image description information that matches the target blessing from an image description library; and to obtain an image corresponding to the target image description information from a standard image library and determine it as the target image.

[0149] The image description library may include multiple image descriptions, where each of the multiple image descriptions is a description of the style, scene, and other information reflected by a corresponding image in the multiple images. In other words, the multiple images conform to the multiple image descriptions.

[0150] The multiple images are multiple images stored in a standard image library. Optionally, the multiple images in the standard image library are pre-generated images that respectively conform to the multiple image description information. The multiple image description information in the image description library corresponds one-to-one with the multiple images in the standard image library. That is, for any image description information in the multiple image description information, a corresponding image can be obtained from the standard image library.

[0151] The target image description information is a text description having semantics similar to that reflected by the target blessing. That is, an image that conforms to the target image description information is also an image that conforms to the target blessing.

[0152] In this case, by pre-establishing an image description library and a standard image library, when generating a target image based on a target blessing, the target image description information that matches the target blessing is first directly obtained from the image description library, and then the image corresponding to the target image description information in the standard image library is determined as the target image. In this way, the target image can be directly determined based on the image description library and the standard image library, thereby improving the efficiency of generating the target image.

[0153] Another possible approach is to input the target blessing words into the text graph model, and use the target blessing words as constraints of the text graph model, thereby controlling the text graph model to generate the target image through the constraints.

[0154] A text-based graph model is a model that generates images from textual content. Alternatively, it can be a generative network model such as a diffusion model or a generative adversarial model. For example, a diffusion model can be fed a piece of text into it, causing it to output an image that matches the input text.

[0155] As an implementation method, the target blessing words may be input into the diffusion model, so that the diffusion model starts from random noise data and gradually generates the target image under the guidance of the target blessing words.

[0156] In an embodiment of the present application, the Wensheng graph model may be a codec structure, which includes a first encoder, a first noise prediction network, and a first decoder.

[0157] The first encoder is used to extract features, such as the features of the target greeting. The first noise prediction network is used to predict noise. In this embodiment of the present application, the first noise prediction network can be a U-Net. The first encoder is used to restore the image based on the image features.

[0158] Specifically, the target blessing is input into the Wensheng graph model, and the target blessing is used as a constraint condition of the Wensheng graph model. The operation of controlling the Wensheng graph model to generate a target image through the constraint condition can be: encoding the target blessing through the first encoder to obtain a blessing vector; predicting the noise of the Wensheng graph model at each time step based on the blessing vector through the first noise prediction network, and at each time step, combining the predicted noise of each time step, gradually denoising the random noise data; restoring the image features after denoising through the first decoder to obtain the target image.

[0159] The random noise data can be a randomly generated image with Gaussian noise added.

[0160] Generally, diffusion models operate through two main phases: a forward diffusion process and a backward diffusion process. During the forward diffusion process, the model gradually adds noise to the original image until the image becomes pure noise. This process can be thought of as a gradual destruction, or "diffusion," of the image information. The amount of noise added at each time step is determined according to a preset variance schedule, and this process follows the properties of a Markov chain, where the state at each time step depends only on the state at the previous time step.

[0161] Inverse diffusion is a process that starts with pure noise and gradually removes it to recover image information. During this stage, the diffusion model learns a reverse Markov chain to predict and remove noise at each time step. Using pure noise as a starting point, the model attempts to gradually restore a clear image using the denoising capabilities learned during training.

[0162] In the embodiment of the present application, since the original image is not input into the text-generated graph model and the image is generated directly based on the text, pure noise can be used as the starting point, that is, only the inverse diffusion process is involved.

[0163] Specifically, when the Wensheng graph model generates the target image, the target blessing is first input into the first encoder, where its features are extracted to obtain the target blessing's features (the blessing vector). A random noise data set is then generated using the RAND function. This random noise data is then input into the first noise prediction network and denoised in combination with the blessing vector.

[0164] Based on its unique U-shaped structure, U-Net gradually removes noise and restores the image through a series of convolutional layers, upsampling, and downsampling operations. At the same time, each step of the U-Net iterative denoising process can be constrained based on constraints (the blessing vector) to ensure that the generated image meets the requirements.

[0165] The first decoder decodes the denoised features to obtain an image, which is the target image.

[0166] It is worth noting that, before step 601, the target blessing words may be obtained first. The operation of obtaining the target blessing words may be implemented through the following three possible implementations.

[0167] In a first possible implementation, the target greeting message may be obtained on a greeting card making interface.

[0168] In some embodiments, basic information of the recipient of the electronic greeting card (such as nickname, contact information) can also be obtained on the greeting card making interface.

[0169] Figure 7 This is a schematic diagram of a process for generating an electronic greeting card provided by an embodiment of the present application. Figure 7 The implementation process of step 601 to step 604 is introduced.

[0170] For example, Figure 7 (a) shows a greeting card making interface 701, in which the user can configure the nickname and contact information of the recipient of the electronic greeting card, the nickname of the sender, and the greetings sent by the sender to the recipient.

[0171] For example, Figure 7As shown in (a) in the figure, the greeting card making interface 701 may include a first nickname editing control, a second nickname editing control, a contact information editing control, a greeting message editing control, etc. Among them, the user can edit the nickname of the recipient through the first nickname editing control and edit the nickname of the sender through the second nickname editing control. Of course, in some embodiments, the user can also edit the nickname of the sender through the first nickname editing control and edit the nickname of the recipient through the second nickname editing control. This embodiment of the present application is not limited to this. The user can edit the contact number of the recipient through the contact information editing control and edit the greeting message through the greeting message editing control.

[0172] For example, the greeting card making interface 701 may also include a "AI helps you write blessings" function, which means automatically generating greetings. Figure 7 As shown in (a) in the figure, the greeting card making interface 701 may also include multiple categorized greeting tags, such as "For Girlfriend", "For Boyfriend", "For Mom", "For Dad", "For Friend", "Christmas", "Happy Birthday", etc. As an example, when a user clicks on any of the greeting tags, the computer device may automatically generate a greeting in response to the user's click, and this greeting can be used as the target greeting. In this way, the greeting editing needs of some users with imperfect language organization skills can be met, so that the user does not need to enter text, and a greeting that meets the user's needs can be automatically generated for the user, which can improve the user experience.

[0173] For example, when a user enters "Baby A" in the first nickname edit control, in response to the user's input, the computer device can display "Baby A" in the first nickname edit control and determine that the recipient's nickname is "Baby A." When the user enters "138-XXXX-XXXX" in the contact information edit control, it can be determined that the recipient's contact number is "138-XXXX-XXXX." When the user enters "Good Boy B" in the second nickname edit control, it can be determined that the sender's nickname is "Good Boy B." When the user enters "There is no Santa Claus in the world, all gifts come from those who love you, Merry Christmas" in the greeting edit control, in response to the user's input, the computer device can obtain the target greeting as "There is no Santa Claus in the world, all gifts come from those who love you, Merry Christmas."

[0174] Furthermore, after the user has finished editing the above information, he can click the OK button on the greeting card making interface 701. In response to the user's click, the computer device can display the following information: Figure 7The cover generation interface 702 shown in (b) of FIG. The cover generation interface 702 can display the generation process of the electronic card cover image. It should be understood that the generation process of the electronic card cover image is also the process of generating the target image according to the target blessing message.

[0175] A second possible implementation method is to obtain product information of the products in the target order after generating the target order; and generate target greetings based on the product information of the products in the target order.

[0176] The product information may be product description information, product name, etc.

[0177] In the above method, once a new order is generated, the product information of the product in the generated order can be obtained, and the target blessing message can be generated based on the product information. That is, after the user purchases the product, the product information of the user's purchased product can be obtained and the target blessing message can be generated based on the product information.

[0178] In this case, by generating target blessings based on the product information of the goods in the target order, the blessings of the electronic greeting card can be determined based on the product information, so that blessings that match the purchased goods can be automatically generated, making the generation of target blessings more intelligent.

[0179] In one possible manner, the operation of generating the target greeting message according to the product information of the product in the target order may be: determining the product category from the product information; and generating the target greeting message according to the product category.

[0180] In some scenarios, different categories of products have different meanings. For example, on Valentine's Day, chocolates and bouquets can represent sweetness, while for users, they represent love. Therefore, by determining the product category from the product information and generating targeted greetings based on the product category, we can generate greetings that better suit the user's needs, thereby improving the user experience.

[0181] The operation of determining the commodity category from the commodity information may be: inputting the commodity information into a category recognition model, and processing the commodity information through the category recognition model to obtain the commodity category.

[0182] The category recognition model is used to identify the product category contained in the product information, thereby obtaining the product category of the product. Optionally, the category recognition model can be a recurrent neural network model, a convolutional neural network model, etc., which is not limited in the embodiment of the present application.

[0183] Specifically, the category recognition model can include convolutional layers, pooling layers, and fully connected layers. The convolutional layers extract features from product information to produce a feature vector. The pooling layers then pool the resulting feature vectors to reduce their dimensionality, thereby reducing the computational complexity of the category recognition model. The fully connected layers then classify the pooled feature vectors to determine the product category.

[0184] Optionally, the operation of generating a target blessing according to the commodity category in the above method may be: according to the commodity category, obtaining a corresponding reference blessing from a plurality of reference blessings to determine as the target blessing.

[0185] Multiple reference blessings can be blessings corresponding to multiple product categories. That is to say, blessings corresponding to multiple product categories can be established in advance. After determining the product category of the product in the target order, the corresponding blessings can be obtained from multiple reference blessings based on the product category and determined as the target blessings, that is, the blessings that match the product category are determined.

[0186] For example, when the product category of the target order is chocolate, the corresponding blessing that can be obtained from multiple reference blessings is "the wind blows gently, hands are held, and we are sweetly together, the sea passes, the wind and clouds change, and we will never be separated in this life."

[0187] Another possible way is to generate the target blessing according to the product information of the product in the target order by inputting the product information into the blessing generation model, processing the product information through the blessing generation model, and obtaining the target blessing.

[0188] The greeting generation model is used to automatically generate a greeting based on product information. Optionally, the greeting generation model can be a recurrent neural network model, a long short-term memory model, a generative adversarial network model, etc. A neural network model is trained using large-scale product description data and preset greetings. This neural network model can extract semantic features from the product description data and learn feature representations. By continuously adjusting model parameters to minimize the loss function between the predicted results and the preset greetings, the model learns the generation patterns between the product description data and the preset greetings. The trained neural network model is the greeting generation model.

[0189] In the above method, after the product information is input into the blessing generation model, the product information can be encoded by the blessing generation model, the semantic features of the product information can be extracted, and then the semantic features can be decoded to generate the target blessing.

[0190] For example, Figure 7The blessing message in the "AI helps you write blessings" function in (a) can be a blessing message automatically generated based on the product information of the product in the target order.

[0191] A third possible implementation method is to obtain product information of a target product; and generate a target blessing message based on the product information of the target product.

[0192] The target product is the product that the user is browsing.

[0193] In the above manner, while the user is browsing products, an electronic greeting card interface may be displayed, and the greeting message on the electronic greeting card interface may be generated based on the product information of the product currently being browsed.

[0194] In this case, by displaying an e-card interface while the user is browsing products, the user can send an e-card without purchasing the product, which can improve the user experience. In addition, target blessings are generated based on the product information of the target product, so that the generated target blessings can be close to the user's wishes, making the process of generating e-cards more intelligent and thus improving the user experience.

[0195] Figure 8 801 is a schematic diagram of a scenario for generating an e-card provided in an embodiment of the present application. For example, after entering the flower gift interface, a user can click on any product on the flower gift interface. For example, if a user clicks on a product, the computer device can respond by displaying a product purchase interface 801 for that product, through which the user can browse product information. While the user is browsing products, the computer device can display an e-card interface 802, which reminds the user that they can create and send e-cards to friends even if they have not purchased any products.

[0196] For example, the electronic greeting card interface 802 may display a Customize Now button 81 and a Cancel Customize button 82. When the user wants to make an electronic greeting card immediately, the user may click the Customize Now button 81. When the user does not need to make an electronic greeting card at present, the user may click the Cancel Customize button 82. For example, when the user clicks the Customize Now button 81, the computer device may display a window related to the user's click. Figure 7 The cover generation interface 803 is similar to (b) in the figure. The cover generation interface 803 displays a blessing and an image to be generated. The blessing is generated based on the product information of the product that the user is browsing, and the image to be generated is an image that the computer device is generating based on the blessing.

[0197] It is worth noting that, through the above step 601, a target blessing message can be automatically generated, and a target image matching the target blessing message scene can be generated according to the target blessing message. In this way, the automatic generation of the blessing message and the cover image in the electronic greeting card can be achieved, thereby making the generation of the electronic greeting card more intelligent.

[0198] Step 602: Display an initial greeting card interface according to the target image, where the initial greeting card interface includes an audio adding control.

[0199] The initial greeting card interface is a preliminarily generated electronic greeting card, which includes a target image and a target greeting message. That is, the electronic greeting card generated at this point is a greeting card that includes both image elements and text elements. From the perspective of providing users with a richer greeting experience in the embodiments of this application, the elements included in the initial greeting card interface are not rich enough. Therefore, to enhance the richness of the elements in the electronic greeting card, an audio add-in control is also provided on the initial greeting card interface.

[0200] The audio adding control is used to add target audio to the electronic greeting card, and provides the user with a way to add the target audio. Preferably, the audio adding control can be in the form of a button, and the user can trigger the audio adding control by clicking or long pressing.

[0201] In this way, by setting an audio adding control on the initial greeting card interface, the user can add an audio clip to the electronic greeting card, thereby generating an electronic greeting card containing pictures, text and music, thereby providing the user with a richer blessing experience.

[0202] For example, Figure 7 (c) in the figure shows an initial greeting card interface 703, which includes a target image, a target blessing message, and an audio add control 61. Through this initial greeting card interface 703, the user can see the graphic interface of the electronic greeting card, including the cover image of the electronic greeting card and the desired blessing message. In addition, an audio clip can be added using the audio add control 61.

[0203] For example, Figure 7 As shown in (c) of FIG. , the initial greeting card interface 703 may also include an information customization control 62. This information customization control 62 allows for obtaining additional information about the recipient, and thereby updating the target image based on the recipient's additional information. Optionally, this information customization control 62 may be in the form of a button, which the user may trigger by clicking or long-pressing it.

[0204] Furthermore, in response to a selection operation on the information customization control 62, an information customization interface may be displayed; in response to a configuration operation on the information customization interface, target customization information may be determined; and according to the target customization information, a target image may be updated.

[0205] The target customization information is used to describe the recipient's attributes and / or preferences. The recipient's attributes may include occupation, age, gender, etc., and the recipient's preferences may include the recipient's favorite colors, animals, patterns, shapes, etc. In some embodiments, the recipient's preferences may also include the recipient's favorite music genre or specific music, which is not specifically limited in this embodiment of the application.

[0206] Figure 9 703. This is a schematic diagram of an information customization interface provided by an embodiment of the present application. For example, when a user clicks on the information customization control 62 in the initial greeting card interface 703, in response to the user's click, the computer device may display the following information: Figure 9 The information customization interface 901 shown in FIG. 9 may include multiple configuration controls through which a user may configure the attributes and preferences of a receiving object.

[0207] For example, Figure 9 As shown, when the user configures the age of the receiving object as "26", the gender as "female", the occupation as "lawyer", and the receiving object's favorite colors are "red and blue", the favorite animal is "kitten", the favorite pattern shape is "triangle and star shape", and the favorite music is "Beethoven Symphony", the target customized information can be determined as the age of the receiving object is "26", the gender is "female", the occupation is "lawyer", and the receiving object's favorite colors are "red and blue", the favorite animal is "kitten", the favorite pattern shape is "triangle and star shape", and the favorite music is "Beethoven Symphony".

[0208] In this case, by customizing other information of the recipient in the information customization interface, the target image can be updated later according to the attributes and preferences of the recipient, so that the generated target image is more in line with the preferences of the recipient, thereby enhancing the customization of the electronic greeting card.

[0209] Among them, the operation of updating the target image according to the target customization information can be: adjusting the color tone and / or image elements of the target image according to the target customization information; or adjusting the filter and / or image elements of the target image according to the target customization information.

[0210] Hue refers to the overall color atmosphere of an image. For example, if the favorite color of the recipient in the target customization information is red, the hue of the target image can be adjusted to be warmer.

[0211] Image elements refer to the basic visual elements that make up the target image, including lines, shapes, textures, etc. For example, if the recipient's favorite shape pattern in the target customization information is a star, then a star-shaped element can be added to the target image.

[0212] Of course, the target image can also be updated by integrating various aspects of the target customization information. For example, if the target customization information indicates that the recipient is a female, 24 years old, a lawyer, and likes the color red and kittens, the filter of the target image can be adjusted to be brighter, and patterns of Libra and kittens can be added to the target image.

[0213] It should be understood that after updating the target image according to the target customization information, the target image displayed on the initial greeting card interface can also be updated, that is, the original target image displayed on the initial greeting card interface is replaced with the updated target image.

[0214] Step 603: In response to a click operation on the audio adding control, an audio information configuration interface is displayed.

[0215] The audio information configuration interface is used to configure the audio to be added. For example, when adding a piece of music, you can configure the style, atmosphere and other information of the music.

[0216] For example, when the user clicks Figure 7 When the audio add control 61 in (c) is selected, the computer device may display the following information in response to a user click: Figure 7 d) in the figure. As an example, the user can configure the lyrics, singing voice, singing style, and emotional atmosphere of the added music through the audio information configuration interface 704. As another example, the user can also configure only the music description information of the added music through the audio information configuration interface 704.

[0217] Optionally, the audio information configuration interface may include at least one of a lyrics configuration control, a music style configuration control, a music atmosphere configuration control, and a singing voice configuration control. Figure 7 As shown in (d) in the figure, the audio information configuration interface 704 includes lyrics configuration controls, music style configuration controls, music atmosphere configuration controls, and singing voice configuration controls. The lyrics configuration controls are used to configure the lyrics of the added music. For example, you can create your own lyrics, such as Figure 7As shown in (d) of FIG, the audio information configuration interface 704 may also include multiple categorized lyrics tags, through which a verse of lyrics can be automatically generated. For example, when a user clicks a verse tag for New Year's greetings, a verse expressing New Year's greetings can be automatically generated. This provides convenience for users with limited verbal expression skills, allowing them to automatically generate a verse even if they do not compose their own lyrics, thereby improving the user experience.

[0218] In addition, the music style configuration control is used to configure the singing style of the added music, such as pop style, piano style, folk style, children's style music, etc.; the music atmosphere configuration control is used to configure the emotional atmosphere expressed by the music, such as music that expresses cheerfulness, tranquility, sweetness, melancholy and other emotions; the singing voice configuration is used to configure the gender of the singer, such as female or male singing.

[0219] Figure 10 This is a schematic diagram of an audio information configuration interface provided by an embodiment of the present application. Figure 10 As shown, the audio information configuration interface 1001 may include a music description configuration control, which describes the content expressed by the music to be added. Optionally, the audio information configuration interface 1001 may also include multiple reference description information. The multiple reference description information refers to several music description information available for the user to select, and the multiple reference description information may be descriptions of the content expressed by different music.

[0220] Step 604: Generate target audio in response to the user's configuration operation on the audio information configuration interface.

[0221] In step 604, the user may configure the audio information in the audio information configuration interface, and then target audio meeting the conditions may be generated according to the audio information configured by the user.

[0222] For example, the user Figure 7 (d) or Figure 10 After configuring the audio information on the audio information configuration interface shown, you can click the OK button on the audio information configuration interface to complete the configuration of the audio information. The computer device can then generate the target audio based on the audio information configured by the user in response to the user's click of the OK button.

[0223] Optionally, the operation of step 604 may be implemented in the following two possible ways.

[0224] One possible approach is that, when the audio information configuration interface includes at least one of a lyrics configuration control, a music style configuration control, a music atmosphere configuration control, and a singing voice configuration control, the target audio information configured by the configuration operation can be obtained in response to a configuration operation on at least one of the lyrics configuration control, the music style configuration control, the music atmosphere configuration control, and the singing voice configuration control on the audio information configuration interface; and the target audio is generated through a Vincent music model based on the target audio information configured by the configuration operation.

[0225] For example, suppose the user is Figure 7 On the audio information configuration interface 704 shown in (d), "female voice", "popular" singing style, and "cheerful" emotional atmosphere are selected, and a lyric "There is no Santa Claus in the world, all the gifts are from people who love you" is entered. Then, the target audio information configured by the configuration operation can be obtained as "female voice", "popular" singing style, and "cheerful" emotional atmosphere, and a lyric "There is no Santa Claus in the world, all the gifts are from people who love you". After that, the target audio can be generated according to the target audio information through the Vincent music model.

[0226] A Vincent music model is a model that generates audio from textual content. Optionally, the Vincent music model can be a diffusion model, an OpenMusic model, an Audiocraft model, etc. For example, a text can be input into a diffusion model, causing the diffusion model to output audio that meets the requirements.

[0227] In an embodiment of the present application, the Vincent music model is similar to the Vincent graph model and can be set to a codec structure, which includes a second encoder, a second noise prediction network and a second decoder.

[0228] The second encoder is used to extract features, such as features of the target audio information. The second noise prediction network is used to predict noise. In the embodiment of the present application, the second noise prediction network can be a U-Net. The second encoder is used to restore the target audio.

[0229] Specifically, according to the target audio information configured by the configuration operation, the operation of generating the target audio through the Vincent music model can be: extracting features of the target audio information through the second encoder to obtain the first audio feature; inputting the spectral noise data into the second noise prediction network, predicting the noise at each time step according to the first audio feature through the second noise prediction network, and gradually denoising the spectral noise data to obtain an audio spectrum graph; restoring the audio spectrum graph obtained after denoising through the second encoder to obtain the target audio.

[0230] The spectrum noise data may be a spectrum graph with Gaussian noise added. Alternatively, the spectrum noise data may be randomly generated by a random function RAND.

[0231] It should be understood that the Vincent music model also generates music from pure noise as a starting point, and therefore, only involves an inverse diffusion process.

[0232] Specifically, when the Vincent music model generates target audio, the target audio information is first input into the second encoder, which performs feature extraction on the target audio information to obtain the first audio feature of the target audio information. The spectral noise data is then input into the second noise prediction network, and denoising is performed in combination with the first audio feature.

[0233] Based on its unique U-shaped structure, U-Net gradually removes noise and restores the spectrogram through a series of convolutional layers, upsampling, and downsampling operations. At the same time, each step of the U-Net iterative denoising process can be constrained based on the constraints (the first audio feature of the target audio information) to ensure that the generated audio spectrogram meets the requirements.

[0234] After the number of iterations is reached, the second decoder decodes the denoised audio spectrum to restore a segment of audio, which is the target audio.

[0235] It is worth noting that when the target audio is generated in the above manner, the generated target audio can be a song with lyrics, especially when the user inputs the lyrics and selects the singing voice type, a song with lyrics can be generated. In some embodiments, if the user does not input the lyrics, a piece of pure music can be automatically generated.

[0236] In addition, in the embodiment of the present application, the target audio can be a piece of music (song) that does not exist in reality, that is, AI automatically generates new music (song), or it can be a piece of music (song) that exists in reality. The embodiment of the present application is not limited to this.

[0237] Another possible way is that when the audio information configuration interface only includes a music description configuration control, the music description information configured by the configuration operation can be obtained in response to the configuration operation of the music description configuration control on the audio information configuration interface; and the target audio is generated through the Vincent music model based on the music description information.

[0238] Music description information is used to describe the emotional content expressed by the music, or to describe information such as the rhythm and music type of the music.

[0239] As an example, when a user Figure 10When a description is entered into the music description control of the audio information configuration interface, the computer device can respond to the user's input, obtain the user's input, and determine the user's input as the music description information. This allows for autonomous input of music description information, thereby reducing restrictions on music description information and making the generated target audio more suitable for user needs.

[0240] As another example, when a user Figure 10 When a reference description information is selected in the audio information configuration interface shown, the computer device can determine the target description information as music description information in response to the selection operation of the target description information on the audio information configuration interface.

[0241] In this case, the user can directly select a desired reference description from the multiple reference descriptions provided in the audio information configuration interface, and the selected reference description is subsequently determined as the music description information. In this process, the user does not need to edit the music description information independently, which provides convenience for the user and improves the user experience.

[0242] Among them, the operation of generating the target audio through the Vincent music model according to the music description information can be: extracting features of the music description information through the second encoder to obtain second audio features; inputting the spectral noise data into the second noise prediction network, predicting the noise at each time step according to the second audio features through the second noise prediction network, and gradually denoising the spectral noise data to obtain an audio spectrogram; restoring the audio spectrogram obtained after denoising through the second encoder to obtain the target audio.

[0243] Specifically, the above-mentioned specific operation of generating the target audio through the Vincent music model according to the music description information is similar to the operation of generating the target audio through the Vincent music model according to the target audio information configured by the configuration operation in the above-mentioned one possible method, and will not be repeated here.

[0244] It is worth noting that when generating the target audio through the other possible method described above, the generated target audio can be a piece of pure music without lyrics. In addition, in the embodiment of the present application, the target audio can be a piece of pure music that does not exist in reality, that is, AI automatically generates new pure music, or it can be a piece of pure music that exists in reality, and the embodiment of the present application does not limit this.

[0245] It is worth noting that when the user Figure 9When the attributes and preferences of the receiving object are configured in the information customization interface shown, the operation of the above step 604 can also be: in response to the user's configuration operation in the audio information configuration interface, generate the target audio according to the audio information and target customization information configured by the configuration operation.

[0246] Since the target customization information is mainly used to describe the attributes and preferences of the recipient of the electronic greeting card, the target audio that is more in line with the user's preferences can be determined by integrating the audio information configured by the user in the audio information configuration interface and the attributes and preferences of the recipient, so that the subsequently generated electronic greeting cards are more in line with the user's preferences, thereby improving the customization of the electronic greeting cards.

[0247] For example, suppose the user Figure 9 The information customization interface 901 shown is configured to have the recipient's favorite music as "Beethoven Symphony", and the emotional atmosphere is configured as "cheerful" in the audio information configuration interface. Then the generated target audio can be a relatively cheerful audio segment in Beethoven's Symphony.

[0248] Through the above steps 601-604, the blessing words (target blessing words) entered by the user on the greeting card making interface can be obtained, and then the target image is generated according to the target blessing words, and the target audio is generated according to the audio information configured by the user on the audio information configuration interface. That is, the three elements of target blessing words, target image and target audio can be determined, and then an electronic greeting card can be generated based on this, that is, continue to execute the following step 605.

[0249] Step 605: Generate an electronic greeting card based on the target blessing words, target image and target audio.

[0250] Step 605 is to generate an electronic greeting card through the three elements of text, image, and audio. In this way, the generated electronic greeting card integrates text elements, image elements, and audio elements, realizing the full-link personalized electronic greeting card generation from text to vision and hearing, thereby improving the production level of gift greeting cards, and then bringing users a digital blessing experience with a rich sense of ritual, which can enhance the user experience.

[0251] Specifically, the operation of step 605 can be: determining the target blessing as the element content of the blessing element of the electronic greeting card, determining the target image as the element content of the image element of the electronic greeting card, and determining the target audio as the element content of the background music element to obtain the electronic greeting card.

[0252] When developing an e-card, developers can configure the e-card to include greetings, images, and background music. These elements can be pre-configured, and the corresponding element types can also be configured. For example, the greeting element can be set to text, the image element to picture, and the background music element to audio.

[0253] In this case, when the content of the corresponding element type has been obtained, that is, when the target greeting, target image and target audio are obtained, an electronic greeting card can be obtained by directly writing the content of the corresponding element type into the corresponding element. This is a convenient way to generate an electronic greeting card.

[0254] Optionally, the target image may be displayed in the electronic greeting card in different display modes, wherein the display modes may include dynamic display and static display.

[0255] In an embodiment of the present application, the display mode of the target image can be determined according to the target audio.

[0256] As a possible approach, when the rhythmic intensity of the target audio is greater than or equal to a preset intensity threshold, the display mode of the target image is determined to be dynamic display; when the rhythmic intensity of the target audio is less than the preset intensity threshold, the display mode of the target image is determined to be static display.

[0257] The rhythm intensity of the target audio refers to the intensity or obviousness of the rhythm elements in the target audio that the user feels. Optionally, the rhythm intensity can be reflected by the beat frequency.

[0258] If the target audio's rhythmic intensity is greater than or equal to a preset intensity threshold, it indicates a strong rhythmic sense, meaning the user can clearly perceive the rhythm. In this case, displaying the target image in a dynamic manner can enhance the visual and auditory effects. If the target audio's rhythmic intensity is less than the preset intensity threshold, it indicates a weak rhythmic sense, meaning the target audio is relatively soothing. In this case, displaying the target image in a static manner can enhance the soothing and tranquil atmosphere.

[0259] As another possible approach, when the target audio is a song with lyrics, the target image is determined to be displayed in a dynamic manner; when the target audio is pure music without lyrics, the target image is determined to be displayed in a static manner.

[0260] When the target audio contains lyrics, the lyrics in the target audio can provide a dynamic basis for the dynamic display of the target image. Therefore, when the target audio is a song with lyrics, the display mode of the target image can be determined to be dynamic display.

[0261] When the target audio is pure music, since pure music has no lyrics, it cannot provide a basis for the dynamic display of the target image. In addition, pure music is generally soothing. In this case, determining the display mode of the target image to be static can further enhance the musical atmosphere.

[0262] In a first possible implementation, the operation of step 605 may be: when the display mode of the target image is dynamic display, a dynamically displayed electronic greeting card is generated based on the target blessing words, target image and target audio; when the display mode of the target image is static display, a statically displayed electronic greeting card is generated based on the target blessing words, target image and target audio.

[0263] In this case, by generating electronic greeting cards that are dynamically displayed or statically displayed, electronic greeting cards of different forms can be generated, which can enhance the visual effect of the electronic greeting cards and thus improve user experience.

[0264] Among them, the operation of generating a dynamically displayed electronic greeting card based on the target greeting words, target image and target audio can be: determining at least one target element from the target image; generating a dynamically displayed electronic greeting card based on the target greeting words, target image, target audio and at least one target element.

[0265] The at least one target element refers to an element that is dynamically displayed in the target image. For example, if the target image includes "a couple in love," "rain," "umbrella," "pedestrians," and "houses," some of these elements may be dynamically displayed when the target image is dynamically displayed.

[0266] In this case, the dynamically displayed electronic greeting card generated based on the target blessing words, target image, target audio and at least one target element is an electronic greeting card in which at least one target element is in a dynamically displayed state and displays the target blessing words, target image and plays the target audio. In this way, the generated electronic greeting card can provide users with excellent visual effects, thereby providing users with a richer blessing experience.

[0267] Among them, the operation of determining at least one target element from the target image can be: obtaining keywords from the music description information of the target audio; matching the keywords with the elements contained in the target image, and determining the elements matched with the keywords among the elements contained in the target image as at least one target element.

[0268] For example, the music description information of the target audio is "a rainy night for lovers, sweet and lingering music", and the keywords obtained from the music description information may be "people", "lover", and "rain", while the elements contained in the target image include "a pair of lovers", "rain", and "pedestrians". "A pair of lovers", "rain", and "pedestrians" are elements that match "people", "lover", and "rain", so "a pair of lovers", "rain", and "pedestrians" can be determined as at least one target element.

[0269] Optionally, the operation of determining at least one target element from the target image can also be: obtaining keywords from the target blessing; matching the keywords with the elements contained in the target image, and determining the elements contained in the target image that match the keywords as at least one target element.

[0270] The "match" here not only has the same meaning, but also means that the two belong to the same category, such as flames and candles both belong to the category of Christmas, or the two are in a hierarchical relationship, such as flames and Christmas are in a hierarchical relationship.

[0271] For example, the target greeting is "There is no Santa Claus in the world, all gifts come from people who love you, Merry Christmas." The keywords "Santa Claus," "Christmas," and "gift" can be obtained from the target greeting. The elements contained in the target image may include "Santa Claus," "flame," "little girl," "cat," and "Christmas tree." If the elements "Santa Claus," "flame," and "Christmas tree" contained in the target image match the keywords "Santa Claus" and "Christmas," "Santa Claus," "flame," and "Christmas tree" can be determined as at least one target element.

[0272] Furthermore, after the electronic greeting card is generated through the above-mentioned first possible implementation method, a target greeting card interface of the electronic greeting card may also be displayed.

[0273] The target greeting card interface is the final greeting card interface after the electronic greeting card is generated, that is, the greeting card interface presented to the recipient. Figure 7 (e) in the figure shows a target greeting card interface 705, which can display a target image, target greeting words, and play target audio.

[0274] In an embodiment of the present application, when a dynamically displayed electronic greeting card is generated, the target greeting card interface may include at least one dynamically displayed target element.

[0275] The specific operation of dynamically displaying at least one target element may be: obtaining the melody and / or rhythm of the target audio; and dynamically displaying at least one target element according to the melody and / or rhythm of the target audio.

[0276] In this case, by dynamically displaying at least one target element according to the melody and / or rhythm of the target audio, at least one target element can be displayed in combination with the melody / rhythm of the target audio, thereby enhancing the association between the display of the target image and the rhythm of the target audio, thereby providing users with richer visual effects.

[0277] Optionally, the method of dynamically displaying the at least one target element may be: flashing the at least one target element, translating the at least one target element, rotating the at least one target element, or zooming the at least one target element.

[0278] Optionally, the target greeting card interface may further include an audio playback control.

[0279] The audio playback control is used to control the playback state of the target audio. It should be understood that the playback state of the target audio may include a playing state and a paused playback state.

[0280] For example, Figure 7 The target greeting card interface 705 shown in (e) may also include an audio playback control 63, which is used to control the playback state of the target audio. For example, when the target audio is playing on the target greeting card interface 705, if the user clicks the audio playback control 63, the computer device can pause the playback of the target audio in response to the user's click, placing the target audio in a paused playback state. If the user clicks the audio playback control 63 again, the computer device can continue to play the target audio in response to the user's click, placing the target audio in a playing state.

[0281] Optionally, the audio playback control may be displayed in any of the following ways.

[0282] First, the audio playback control can be displayed in a rotating manner on the target greeting card interface.

[0283] Specifically, when the target audio is in a playing state, the audio playback control can be displayed in a clockwise or counterclockwise rotation manner on the target greeting card interface.

[0284] When the target audio is in a paused playback state, the audio playback control may stop rotating and be displayed in a static manner.

[0285] Second, the audio playback control can be displayed in the form of jumping musical notes on the target greeting card interface.

[0286] Specifically, when the target audio is in a playing state, the audio playback control can be displayed in the target greeting card interface in the form of musical notes jumping up and down.

[0287] When the target audio is in a paused playback state, the notes of the audio playback control may stop jumping up and down and be displayed in a static manner, that is, displayed as static notes.

[0288] In this case, displaying the audio playback control in any of the above methods can enhance the user's visual effect and bring a better experience to the user.

[0289] A second possible implementation method may also first obtain music description information or target audio information of the target audio; generate a target video based on the target image and music description information; or generate a target video based on the target image and target audio information.

[0290] In the embodiment of the present application, the target video only includes visual effects and does not include auditory effects, that is, the target video refers to a video that does not include sound content. As an example, the target video can be a moving picture composed of multiple frames of images.

[0291] Since the music description information and the target audio information can indicate the content expressed by the target audio or the scene described by the target audio, the scene described by the target audio can be restored by combining the target audio information or the music description information, so that the generated target video and the target audio are closely related, thereby improving the user's visual to auditory unity.

[0292] Among them, the operation of generating the target video according to the target image and music description information can be: inputting the target image into the image-generated video model, and using the music description information as the constraint condition of the image-generated video model, and controlling the generation process of the image-generated video model through the constraint condition to obtain the target video.

[0293] An image-generated video model is a model that generates videos from images. That is, an image-generated video model receives an image as input and then outputs a video. Optionally, the image-generated video model can be a diffusion model.

[0294] In an embodiment of the present application, the image-generated video model may include a third encoder, a third noise prediction network and a third decoder.

[0295] The third encoder is used to extract image features of the target image and features of the music description information (text description vector). The third noise prediction network is used to predict noise. In the embodiment of the present application, the third noise prediction network can be a U-Net. The third decoder is used to restore the video frame sequence to obtain the target video.

[0296] In addition, since the image-generated video model receives a target image and generates a target video from the target image as a starting point, the image-generated video model includes a forward diffusion process to gradually destroy the image information, and includes a reverse diffusion process to gradually restore the video frame sequence starting from pure noise.

[0297] Specifically, during the forward diffusion process, the graph-generated video model gradually adds noise to the image features of the target image, generating noisy video frame sequence features until a set of completely noisy video frame sequence features is obtained. The amount of noise added at each time step is determined according to a preset variance schedule, and this process follows the characteristics of a Markov chain, where the state at each time step depends only on the state of the previous time step.

[0298] In the reverse diffusion process, starting with the fully noisy video frame sequence features obtained by forward diffusion, the text description vector is used as a constraint to control the third noise prediction network to gradually predict the noise at each time step and gradually remove the noise. In this stage, the third noise prediction network learns a reverse Markov chain to predict and remove the noise at each time step.

[0299] The third decoder can restore the features of the video frame sequence after noise removal to recover the video frame sequence.

[0300] Among them, the operation of generating the target video according to the target image and target audio information can be: inputting the target image into the image-generated video model, and using the target audio information as the constraint condition of the image-generated video model, and controlling the generation process of the image-generated video model through the constraint condition to obtain the target video.

[0301] Specifically, the specific operation of generating the target video according to the target image and target audio information is similar to the specific operation of generating the target video according to the target image and music description information, and will not be repeated here.

[0302] In this case, the operation of step 605 may be: generating an electronic greeting card according to the target blessing words, target video and target audio.

[0303] In this way, the generated electronic greeting card can include text elements, video elements and audio elements, so that the generated electronic greeting card can provide the user with a richer blessing experience and can fully impact the user's vision and hearing.

[0304] In this case, when developing the e-card function, the developer can set the e-card to include a greeting message element, a video element, and a background music element. The greeting message element, video element, and background music element can be pre-set by the developer, and the element types corresponding to these elements can also be set. For example, the element type of the greeting message element can be set to text type, the element type of the video element can be set to video type, and the element type of the background music element can be set to audio type.

[0305] Specifically, based on the target blessings, target video and target audio, the operation of generating an electronic greeting card can be: determining the target blessings as the element content of the blessing element of the electronic greeting card, determining the target video as the element content of the video element of the electronic greeting card, and determining the target audio as the element content of the background music element to obtain the electronic greeting card.

[0306] like Figure 7 As shown in (e) in FIG. 7 , the target greeting card interface 705 may also include an information customization control 62 , which is the same as the information customization control 62 in the initial greeting card interface 703 . The information customization control 62 may be used to configure other information of the recipient.

[0307] For example, when the user is not in Figure 7 The initial greeting card interface 703 shown in (c) uses the information customization function, that is, when other information of the recipient is not configured, the user can also use the information customization function in the target greeting card interface 705 to generate a more customized electronic greeting card by configuring other information of the recipient.

[0308] Specifically, when the user selects the information customization control 62 on the target greeting card interface 705, the computer device can display the information customization interface in response to the user's selection operation of the information customization control 62; determine the target customization information in response to the configuration operation on the information customization interface; and then update the electronic greeting card according to the target greeting, target image, target audio and target customization information.

[0309] The information customization interface can be as follows Figure 9 The information customization interface 901 shown can configure the attributes and / or preferences of the receiving object.

[0310] In this case, by configuring the attributes and / or preferences of the recipient in the information customization interface, the electronic greeting card can be updated later based on the attributes and / or preferences of the recipient, so that the generated electronic greeting card is more in line with the preferences of the recipient, thereby enhancing the customization of the electronic greeting card.

[0311] Among them, according to the target blessing, target image, target audio and target customized information, the operation of updating the electronic greeting card can be: adjusting the color tone and / or image elements of the target image according to the target customized information to obtain a new target image; adjusting the music style and / or melody of the target audio according to the target customized information to obtain a new target audio; updating the electronic greeting card according to the target blessing, the new target image and the new target audio.

[0312] In the above method, the target image's tone and / or image elements are essentially adjusted first through target customization information, and then the target audio's music style and / or melody is adjusted. After that, the original target image in the electronic greeting card is replaced with the adjusted target image, and the original target audio is replaced with the adjusted target audio, so that the information electronic greeting card can be updated.

[0313] The adjustment of the color tone and / or content of image elements of the target image according to the target customization information is described in the specific operation of updating the target image according to the target customization information in step 602 above, and will not be repeated here.

[0314] For example, Figure 9 As shown, the target customization information indicates that the recipient's age is "26," gender is "female," occupation is "lawyer," and the recipient's favorite colors are "red and blue," favorite animals are "kittens," favorite patterns are "triangles and stars," and favorite music is "Beethoven symphonies." It can be seen that the above target customization information indicates that the recipient is a female, 24 years old, a lawyer, and likes the color red and kittens. Therefore, the hue of the target image can be adjusted to be warmer, and pattern elements of Libra and kittens can be added to the target image. In addition, the melody of the target audio can be adjusted to be more cheerful to increase the liveliness. The original target image in the e-card can then be replaced with the adjusted target image, and the original target audio can be replaced with the adjusted target audio, thereby updating the e-card.

[0315] It is worth noting that in the embodiments of this application, by providing an information customization function in the e-card, by incorporating the user's input content, preference information, and specific occasion requirements, a customized visual and auditory artwork can be automatically generated, so that the generated e-card can provide users with a unique and ritualistic digital blessing experience. In addition, in the embodiments of this application, simple text can be used to generate scene-specific images and music, which can enhance the scalability and adaptability of the e-card.

[0316] Furthermore, after the electronic greeting card is generated and displayed through the above steps 601 to 605, the electronic greeting card may be sent to a recipient.

[0317] For example, Figure 7 As shown in (e) of FIG. 7 , the target greeting card interface 705 may also include an OK button. If the user determines that the generated e-card meets expectations, the user may click the OK button to complete the creation of the e-card. When the user clicks the OK button on the target greeting card interface 705, the computer device may complete the creation of the e-card in response to the user's click and simultaneously display a greeting card sending interface for determining whether to send the greeting card. If the user clicks OK to send the greeting card, the generated e-card may be sent to the recipient.

[0318] Furthermore, the push of electronic greeting cards can be achieved in the following two situations.

[0319] In the first case, when the recipient has registered an account in the target application, the electronic greeting card can be pushed through the target application.

[0320] The first case mentioned above is that when the account information of the recipient is found in the server to which the target application belongs and it is determined that the recipient has registered an account in the target application, the electronic greeting card can be pushed through the target application.

[0321] As an implementation mode, when the recipient opens the target application, the push interface of the electronic greeting card can be directly displayed, and the user can view the received electronic greeting card on the push interface of the electronic greeting card.

[0322] In the second case, if the recipient has not registered an account in the target application, a greeting card message can be sent to the recipient via a mobile phone text message.

[0323] The greeting card information is used to indicate that an electronic greeting card has been received.

[0324] The second situation mentioned above is that when the account information of the recipient is not found in the server to which the target application belongs, it is determined that the recipient has not registered an account in the target application. In this case, the e-card cannot be pushed through the target application. In this case, the greeting card information can be sent to the recipient via mobile phone text message, so that the recipient is informed of the receipt of the e-card.

[0325] In some embodiments, the greeting card information is also used to instruct the recipient to download and register a target application, so that the recipient can view the received electronic greeting card through the target application.

[0326] It is worth noting that through the above-mentioned electronic greeting card push method, a relationship between the gift giver and the gift recipient can be established, guiding the gift recipient to download and register the target application, allowing the participants to form positive fission and expand the scale of self-propagation.

[0327] In an embodiment of the present application, a computer device first generates a target image based on the target blessing words, and then displays an initial greeting card interface based on the target image. The initial greeting card interface includes an audio adding control for adding the audio of the electronic greeting card. When adding the audio of the electronic greeting card, you can click the audio adding control to display an audio information configuration interface so that the user can perform configuration operations on this audio information configuration interface, and then generate the target audio according to the configured content. Finally, an electronic greeting card is generated based on the target blessing words, target image and target audio. In this way, the generated electronic greeting card integrates text elements, image elements and audio elements, and realizes the full-link personalized electronic greeting card generation from text to vision and hearing, thereby improving the production level of gift greeting cards, and then bringing users a digital blessing experience with a rich sense of ritual, which can enhance the user experience.

[0328] Figure 11 This is a schematic diagram of the structure of a device for generating electronic greeting cards provided by an embodiment of the present application. The device for generating electronic greeting cards can be implemented as part or all of a computer device by software, hardware, or a combination of both. The computer device can be as follows Figure 12 Computer equipment shown. Figure 11 The device includes: an image generation module 1101, a first display module 1102, a second display module 1103, an audio generation module 1104 and an electronic greeting card generation module 1105.

[0329] The image generation module 1101 is used to generate a target image according to the target blessing message;

[0330] A first display module 1102 is configured to display an initial greeting card interface according to the target image, wherein the initial greeting card interface includes an audio adding control;

[0331] The second display module 1103 is configured to display an audio information configuration interface in response to a click operation on the audio adding control;

[0332] The audio generation module 1104 is configured to generate target audio in response to a configuration operation of the user on the audio information configuration interface;

[0333] The electronic greeting card generating module 1105 is used to generate an electronic greeting card according to target greeting words, target images and target audio.

[0334] In a possible implementation, the device for generating an electronic greeting card further includes: a first acquisition module, configured to acquire target greeting words.

[0335] In a possible implementation, the first acquisition module is specifically configured to: after generating a target order, acquire product information of the products in the target order; and generate a target greeting message based on the product information.

[0336] In a possible implementation, the first acquisition module is specifically configured to: acquire product information of a target product, where the target product is the product currently being browsed by the user; and generate a target blessing message based on the product information of the target product.

[0337] In one possible implementation, the device for generating an electronic greeting card also includes a first determination module, which is used to determine the display mode of the target image based on the target audio, and the display mode includes static display and dynamic display; and the electronic greeting card generation module 1105 is specifically used to: when the display mode of the target image is dynamic display, generate a dynamically displayed electronic greeting card based on the target blessing words, target image and target audio; when the display mode of the target image is static display, generate a statically displayed electronic greeting card based on the target blessing words, target image and target audio.

[0338] In one possible implementation, the electronic greeting card generation module 1105 is specifically used to: determine at least one target element from a target image; generate a dynamically displayed electronic greeting card based on the target greeting, target image, target audio and at least one target element; and the device for generating an electronic greeting card also includes a third display module for displaying the target greeting card interface of the electronic greeting card, which includes at least one dynamically displayed target element.

[0339] In one possible implementation, the device for generating an electronic greeting card also includes a second acquisition module for acquiring the melody and / or rhythm of the target audio; and a fourth display module for dynamically displaying at least one target element according to the melody and / or rhythm of the target audio.

[0340] In one possible implementation, the target greeting card interface includes an audio playback control, which is displayed in a rotating manner on the target greeting card interface, or the audio playback control is displayed in a jumping musical note manner on the target greeting card interface.

[0341] In a possible implementation, the image generation module 1101 is specifically configured to input the target blessing into the Wensheng graph model, and use the target blessing as a constraint of the Wensheng graph model, thereby controlling the Wensheng graph model to generate the target image through the constraint.

[0342] In one possible implementation, the audio information configuration interface includes a music description configuration control, and the audio generation module 1104 is specifically used to respond to the configuration operation of the music description configuration control on the audio information configuration interface, obtain the music description information configured by the configuration operation; and generate the target audio through the Vincent music model based on the music description information.

[0343] In one possible implementation, the audio information configuration interface also includes multiple reference description information, and the device for generating an electronic greeting card also includes a second determination module for determining the target description information as music description information in response to a selection operation of the target description information among the multiple reference description information on the audio information configuration interface.

[0344] In one possible implementation, the audio information configuration interface includes at least one of a lyrics configuration control, a music style configuration control, a music atmosphere configuration control, and a singing voice configuration control. The audio generation module 1104 is specifically used to respond to a configuration operation on at least one of the lyrics configuration control, the music style configuration control, the music atmosphere configuration control, and the singing voice configuration control on the audio information configuration interface, and obtain the target audio information configured by the configuration operation; based on the target audio information configured by the configuration operation, generate the target audio through the Vincent music model.

[0345] In one possible implementation, the target greeting card interface of the electronic greeting card includes an information customization control, and the device for generating an electronic greeting card also includes a fifth display module, which displays the information customization interface in response to a selection operation of the information customization control; and a third determination module, which is used to determine the target customization information in response to a configuration operation on the information customization interface, and the target customization information is used to describe the attributes of the recipient of the electronic greeting card and / or the preferences of the recipient; and an update module, which is used to update the electronic greeting card according to the target blessing, target image, target audio and target customization information.

[0346] In one possible implementation, the update module is specifically used to adjust the color tone and / or image elements of the target image according to the target customization information to obtain a new target image; adjust the music style and / or melody of the target audio according to the target customization information to obtain a new target audio; and update the electronic greeting card according to the target blessing, the new target image, and the new target audio.

[0347] In one possible implementation, the device for generating an electronic greeting card also includes a video generation module for generating a target video based on the target image and music description information; and the electronic greeting card generation module 1105 is specifically used to generate an electronic greeting card based on the target blessing words, target video and target audio.

[0348] In one possible implementation, the video generation module is specifically used to input the target image into the image-generated video model, and use the music description information as the constraint condition of the image-generated video model, and control the generation process of the image-generated video model through the constraint condition to obtain the target video.

[0349] In an embodiment of the present application, a target image is first generated based on the target blessing words, and then an initial greeting card interface is displayed based on the target image. The initial greeting card interface includes an audio adding control for adding the audio of the electronic greeting card. When adding the audio of the electronic greeting card, you can click the audio adding control to display an audio information configuration interface so that the user can perform configuration operations on this audio information configuration interface, and then generate the target audio according to the configured content. Finally, an electronic greeting card is generated based on the target blessing words, target image and target audio. In this way, the generated electronic greeting card integrates text elements, image elements and audio elements, and realizes the full-link personalized electronic greeting card generation from text to vision and hearing, thereby improving the production level of gift greeting cards, and then bringing users a digital blessing experience with a rich sense of ritual, which can enhance the user experience.

[0350] It should be noted that the device for generating electronic greeting cards provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when generating electronic greeting cards. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0351] The functional units and modules in the above embodiments may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The above integrated units may be implemented in the form of hardware or software functional units. In addition, the specific names of the functional units and modules are only for the purpose of distinguishing them from each other and are not intended to limit the scope of protection of the embodiments of this application.

[0352] The device for generating an electronic greeting card provided in the above embodiment and the method for generating an electronic greeting card are of the same concept. The specific working process and technical effects of the units and modules in the above embodiment can be found in the method embodiment part and will not be repeated here.

[0353] Figure 12 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. Figure 12 As shown, the computer device 1200 includes: a processor 120, a memory 121, and a computer program 122 stored in the memory 121 and executable on the processor 120. When the processor 120 executes the computer program 122, the steps of the method for generating an electronic greeting card in the above embodiment are implemented.

[0354] The computer device 1200 may be a general-purpose computer device or a dedicated computer device. In a specific implementation, the computer device 1200 may be a desktop computer, a portable computer, a handheld computer, a mobile phone, or a tablet computer. The embodiment of the present application does not limit the type of the computer device 1200. Those skilled in the art will understand that Figure 12 This is merely an example of the computer device 1200 and does not constitute a limitation on the computer device 1200 . The computer device 1200 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 1200 may also include input and output devices, network access devices, etc.

[0355] The processor 120 may be a central processing unit (CPU), or may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0356] In some embodiments, the memory 121 may be an internal storage unit of the computer device 1200, such as a hard disk or memory of the computer device 1200. In other embodiments, the memory 121 may also be an external storage device of the computer device 1200, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 1200. Furthermore, the memory 121 may also include both an internal storage unit of the computer device 1200 and an external storage device. The memory 121 is used to store an operating system, application programs, a boot loader, data, and other programs. The memory 121 may also be used to temporarily store data that has been output or is about to be output.

[0357] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0358] An embodiment of the present application provides a computer program product, which, when executed on a computer, enables the computer to execute the steps in the above-mentioned various method embodiments.

[0359] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above-mentioned method embodiments by using a computer program to instruct the relevant hardware. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the camera / terminal device, recording medium, computer memory, ROM (Read-Only Memory), RAM (Random Access Memory), CD-ROM (Compact Disc Read-Only Memory), magnetic tape, floppy disk, and optical data storage device. The computer-readable storage medium mentioned in the present application can be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0360] It should be understood that all or part of the steps for implementing the above embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the steps may be implemented in the form of a computer program product. The computer program product may include one or more computer instructions. The computer instructions may be stored in the above-mentioned computer-readable storage medium.

[0361] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0362] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0363] In the embodiments provided in this application, it should be understood that the disclosed apparatus / computer equipment and methods can be implemented in other ways. For example, the apparatus / computer equipment embodiments described above are merely schematic. For example, the division of modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of the apparatus or unit, which can be electrical, mechanical or other forms.

[0364] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0365] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for generating an electronic greeting card, characterized in that: The method comprises: Generate a target image according to the target blessing words; Displaying an initial greeting card interface according to the target image, wherein the initial greeting card interface includes an audio adding control; In response to a click operation on the audio adding control, displaying an audio information configuration interface; generating target audio in response to a configuration operation of the user on the audio information configuration interface; An electronic greeting card is generated according to the target blessing words, the target image and the target audio.

2. The method according to claim 1, wherein The method further comprises: Get the target blessing.

3. The method according to claim 2, wherein The obtaining of the target blessing includes: Obtain product information of a target product, where the target product is the product that the user is browsing; The target blessing is generated according to the commodity information of the target commodity.

4. The method according to claim 1, wherein The method further comprises: Determining a display mode of the target image according to the target audio, wherein the display mode includes static display and dynamic display; Furthermore, generating an electronic greeting card according to the target blessing words, the target image, and the target audio includes: In the case where the target image is displayed in a dynamic display mode, a dynamically displayed electronic greeting card is generated according to the target blessing words, the target image and the target audio; In the case where the target image is displayed in a static manner, a statically displayed electronic greeting card is generated according to the target greeting words, the target image and the target audio.

5. The method according to claim 4, wherein The method of generating a dynamically displayed electronic greeting card according to the target blessing words, the target image, and the target audio comprises: determining at least one target element from the target image; generating the dynamically displayed electronic greeting card according to the target blessing words, the target image, the target audio, and the at least one target element; And, the method further comprises: The target greeting card interface of the electronic greeting card is displayed, and the target greeting card interface includes the at least one target element displayed dynamically.

6. The method according to claim 5, wherein The method further comprises: Acquiring the melody and / or rhythm of the target audio; The at least one target element is dynamically displayed according to the melody and / or rhythm of the target audio.

7. The method according to claim 1, wherein The audio information configuration interface includes at least one of a lyrics configuration control, a music style configuration control, a music atmosphere configuration control, and a singing voice configuration control, and generating target audio in response to a user's configuration operation on the audio information configuration interface includes: In response to a configuration operation on at least one of the lyrics configuration control, the music style configuration control, the music atmosphere configuration control, and the singing voice configuration control on the audio information configuration interface, obtaining target audio information configured by the configuration operation; The target audio is generated through the Vincent music model according to the target audio information configured by the configuration operation.

8. The method according to claim 1, wherein The target greeting card interface of the electronic greeting card includes an information customization control, and the method further includes: In response to a selection operation on the information customization control, displaying an information customization interface; In response to a configuration operation on the information customization interface, determining target customization information, wherein the target customization information is used to describe the attributes of a recipient of the electronic greeting card and / or the preferences of the recipient; The electronic greeting card is updated according to the target blessing words, the target image, the target audio, and the target customized information.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method according to any one of claims 1 to 8 when executed by the processor.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images