Information processing method and apparatus, and electronic device, storage medium and program product

Abstract

Provided in the embodiments of the present disclosure are an information processing method and apparatus, and an electronic device, a storage medium and a program product. The information processing method comprises: in response to a prompt information setting operation, acquiring first prompt information, wherein the first prompt information includes description information for first content and / or effects expected to be presented in a live-streaming room; and in response to a live-streaming description generation request, displaying live-streaming prompt information corresponding to the first prompt information, wherein the live-streaming prompt information is used for prompting second content that can be presented in the live-streaming room and / or a target operation that can be executed in the live-streaming room. In the technical solutions of the embodiments of the present disclosure, live-streaming prompt information meeting actual requirements can be generated in a targeted manner on the basis of first prompt information, thereby solving the problems of unstable live-streaming quality and live-streaming effects of some live-streaming rooms. By means of displaying live-streaming prompt information, a live-streaming user can be assisted in enriching the display content of a live-streaming room, thereby improving the live-streaming effect.

Description

Information processing methods, apparatuses, electronic devices, storage media and program products

[0001] This application claims priority to Chinese Patent Application No. 202411035050.3, filed on July 30, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0002] This disclosure relates to an information processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0003] With the rapid development of internet technology, more and more users are inclined to obtain information through live streaming, which is favored for its intuitiveness and immediacy. The widespread adoption of smartphones and the development of mobile networks have significantly lowered the hardware requirements for live streaming, allowing users to watch or participate in live streams anytime, anywhere, laying the foundation for its widespread popularity.

[0004] In live streaming scenarios, the quality and effectiveness of the stream are closely related to the content. However, live streaming content often relies on human intervention, and the quality and effectiveness of different live streaming rooms often vary, with some rooms exhibiting inconsistent quality and performance. Therefore, how to present relatively coherent live streaming content within the live streaming room has become a pressing issue to address in order to improve live streaming quality and experience. Summary of the Invention

[0005] This disclosure provides an information processing method, apparatus, electronic device, storage medium, and program product to enrich live streaming content and improve live streaming effects.

[0006] In a first aspect, embodiments of this disclosure provide an information processing method, the method comprising:

[0007] In response to the first information setting operation, the first prompt information of the setting is obtained, wherein the first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room;

[0008] In response to the request to generate a live stream notification, a live stream notification corresponding to the first notification information is displayed, wherein the live stream notification information is used to indicate second content that can be presented in the live stream and / or a target operation that can be performed in the live stream.

[0009] Secondly, embodiments of this disclosure also provide an information processing apparatus, the apparatus comprising:

[0010] The prompt information setting module is used to respond to the first information setting operation and obtain the set first prompt information, wherein the first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room;

[0011] The live stream display generation module is used to respond to the live stream prompt generation request and display live stream prompt information corresponding to the first prompt information, wherein the live stream prompt information is used to prompt second content that can be presented in the live stream and / or target operations that can be performed in the live stream.

[0012] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0013] One or more processors;

[0014] Storage device for storing one or more programs.

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the information processing method as described in any of the embodiments of this disclosure.

[0016] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the information processing method as described in any of the embodiments of this disclosure.

[0017] Fifthly, embodiments of this disclosure also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the information processing method described in any embodiment of this disclosure. Attached Figure Description

[0018] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0019] Figure 1 is a flowchart illustrating an information processing method provided in an embodiment of this disclosure;

[0020] Figure 2 is a schematic flowchart of another information processing method provided in an embodiment of this disclosure;

[0021] Figure 3 is a schematic flowchart of a live broadcast prompt information generated using the information processing method of this disclosure according to an embodiment of the present disclosure.

[0022] Figure 4 is a schematic diagram of a process for generating special effects description information and / or application prompt information using the information processing method of this disclosure according to an embodiment of the present disclosure.

[0023] Figure 5 is a schematic diagram of the display effect of the special effects description information and application prompt information provided in the embodiments of this disclosure;

[0024] Figure 6 is a schematic diagram of the structure of an information processing device provided in an embodiment of this disclosure;

[0025] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0026] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0027] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0028] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0029] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0030] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0031] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0032] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0033] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0034] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0035] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0036] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0037] Figure 1 is a flowchart illustrating an information processing method provided in an embodiment of this disclosure. This embodiment is applicable to situations where corresponding live broadcast prompts are generated based on received prompts. The method can be executed by an information processing device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, such as a mobile terminal, a PC, or a server.

[0038] As shown in Figure 1, the method of this embodiment may specifically include:

[0039] S110. In response to the first information setting operation, obtain the first prompt information, wherein the first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room.

[0040] The first information setting operation can be understood as an operation used to set descriptive information for the content and / or effects expected to be presented in the live stream. The first prompt information can be used to describe the content and / or effects expected to be presented in the live stream. Optionally, the first prompt information includes descriptive information for the first content and / or effects expected to be presented in the live stream. The first content can be the live stream content expected to be presented in the live stream. For example, the first content can specifically be at least one of the following: the live stream theme, the objects presented in the live stream, the participants in the live stream, and the content of preset functions applied in the live stream (e.g., decorative elements in the live stream and / or special effects that can be applied in the live stream). The effect can be the live stream effect expected to be presented in the live stream. For example, the description of the live stream effect can be a description of the live stream atmosphere (e.g., warm, cheerful, or lively) and / or a description of the live stream style. The live stream style can include the decoration style of the live stream and / or the style of the host. The host style can include at least one of the following styles: intellectual, humorous, competitive, and educational. That is, the first prompt information can include information describing the live stream content and / or live stream effects expected to be presented in the live stream. The first prompt message can contain characters in one or more languages. The first prompt message can be in Chinese, English, or other languages.

[0041] In this embodiment, the first information setting operation can be any operation that supports setting live content description information, such as an information setting operation in response to an information setting item; or an information selection operation in response to candidate prompt information, etc. Furthermore, the form of the obtained first prompt information will also differ depending on the first information setting operation. Optionally, the first prompt information can be at least one sentence with complete meaning, which can consist of multiple characters connected by conjunctions to form a complete sentence; or it can be composed of multiple words, with no conjunctions between adjacent words; or it can be other forms of prompt information, etc.

[0042] Optionally, in response to a first information setting operation, obtaining first prompt information includes: displaying a prompt information setting interface, wherein the prompt information setting interface includes information editing items; and in response to an information setting operation input for the information editing items, obtaining the information input in the information editing items as the first prompt information.

[0043] The prompt message settings interface can be understood as a visual editing interface that supports setting prompt messages. The message editing item can be used to edit the initial prompt message. The message editing item can be understood as an entry point for editing the prompt message. The message editing item can be any form of editing item that supports message input. Optionally, the message editing item can be a text input box.

[0044] As an optional implementation of this embodiment, when a trigger operation on a preset information setting control is detected, a prompt information setting page can be displayed on the terminal device's display interface. This prompt information setting interface may include information editing items. Furthermore, prompt information can be entered for the information editing items. Then, when an information setting operation is detected for the information editing items, information corresponding to the information setting operation is determined in response to the operation. Furthermore, the information entered in the information editing items can be used as the first prompt information.

[0045] Optionally, in response to a first information setting operation, obtaining a first prompt information includes: displaying a prompt information setting interface, wherein the information setting interface includes at least one candidate prompt information; and in response to an information selection operation for at least one candidate prompt information, determining the first prompt information based on the selected at least one candidate prompt information.

[0046] In this context, candidate prompts can be understood as descriptive information about the content or effects to be presented in the expected live stream. There can be one or more candidate prompts.

[0047] As an optional implementation of this disclosure, the candidate prompt information may be one or more prompt information used to generate live prompt information within a preset time period, i.e., historical setting data of the first prompt information. Alternatively, the method for determining the candidate prompt information may include at least one of the following: historical setting data of the object initiating the information setting operation for the first prompt information; historical setting data of multiple objects for the first prompt information, etc. For example, historical application data of the object initiating the information setting operation in the application software can be obtained, and historical setting data of the object for the first prompt information can be determined based on the historical application data. Furthermore, at least one candidate prompt information can be determined based on the historical setting data.

[0048] As another optional implementation of this disclosure, the candidate prompt information can also be a plurality of pre-set prompt words. Specifically, these can be pre-set prompt words associated with the content and / or effects presented in the live stream. For ease of querying and operation, they can be categorized and displayed according to their corresponding types. For example, prompt words related to the live stream content can be categorized and displayed according to one or more pieces of information such as the target object, scene, theme, and location involved in the live stream content; and / or, prompt words can be categorized and displayed according to the category of the operation to be performed in the live stream. Prompt words associated with the live stream effects can be categorized and displayed according to the live stream atmosphere and / or the live stream style, etc.

[0049] As another optional implementation of this disclosure, when a trigger operation on a preset information setting control is detected, a prompt information setting page can be displayed on the terminal device's display interface. This prompt information setting page may include at least one candidate prompt information. Further, when an information selection operation on at least one candidate prompt information is detected, the selected candidate prompt information can be determined based on the information selection operation. Then, the prompt information composed of the selected candidate prompt information can be used as the first prompt information. The display method of the selected candidate prompt information on the interface can include various methods; optionally, it can be highlighted among at least one candidate prompt information; or, the selected candidate prompt information can be displayed in a pre-set text box, etc.

[0050] S120. In response to the live broadcast prompt generation request, display the live broadcast prompt information corresponding to the first prompt information, wherein the live broadcast prompt information is used to prompt the second content that can be presented in the live broadcast room and / or the target operation that can be performed in the live broadcast room.

[0051] The live stream prompt generation request can be understood as an instruction to request the execution of the operation of generating a live stream prompt. The live stream prompt generation request can include various generation methods. Optionally, a live stream prompt generation request can be generated when a trigger operation is detected for input to a preset live stream prompt generation control; or, a live stream prompt generation request can be generated when the received audio information includes a trigger word associated with generating a live stream prompt; or, a live stream prompt generation request can be generated when a user-inputted live stream prompt generation instruction is detected. Live stream prompt information can be understood as information that prompts the content and / or effects presented in the live stream room. In this embodiment of the disclosure, the live stream prompt information can be used to describe a second content that can be presented in the live stream room and / or a target operation that can be performed in the live stream room. The second content can be understood as prompting the live stream content presented in the live stream room.

[0052] It should be noted that the first content represents the content expected to be presented in the live stream, while the second content represents the content displayed in the live stream. Generally, the first content is a brief description of the content presented in the live stream. The second content is a detailed description of the content displayed in the live stream. The second content may include multiple pieces of information related to the live stream content and / or live stream effects presented in the live stream. Optionally, the second content includes at least one special effect identifier and / or application method. The special effect identifier included in the second content may be an effect identifier for at least one special effect that prompts the user to apply it in the live stream. Correspondingly, the application method can be understood as how the corresponding special effect is applied to the prompt information in the live stream. The application method can be determined based on at least one of the following: triggering method, application object, and application timing.

[0053] Optionally, the target operation performed in the live stream may include, but is not limited to, at least one of the following operations: interaction with a target interactive object in the live stream; information adjustment operation on the live stream information already presented in the live stream; effect editing operation on the target special effects used in the live stream, etc. The target interactive object may include at least one of the following: the viewer of the live stream, virtual objects presented in the live stream, and objects connected to the live stream. Information adjustment operation can be understood as at least one of the following operations: adding, deleting, and modifying live stream information. Effect editing operation can be understood as one or more of the following operations: element editing operation performed on at least some elements of the target special effect, operation to add, apply, or de-apply the target special effect, operation to set the target special effect's target object, and operation to set the target special effect's trigger information (including triggering method and / or triggering timing, etc.).

[0054] In this embodiment of the disclosure, upon detecting a live stream notification generation request, the system responds to the request. Then, based on the acquired first notification information, live stream notification information corresponding to the first notification information can be generated and displayed.

[0055] In this embodiment, the second content includes at least one special effect identifier. To facilitate a clearer and more intuitive understanding of the special effect style, content, and / or details included in the live stream notification information, after displaying the live stream notification information corresponding to the first notification information, the method further includes: in response to an identifier triggering operation on the special effect identifier in the live stream notification information, displaying the special effect description information corresponding to the special effect identifier. This technical solution supports interaction with the target special effect indicated in the live stream notification information to view more information about the target special effect, facilitating a deeper understanding of the target special effect and enabling a better determination of whether to apply the target special effect and how to apply it.

[0056] In this embodiment of the disclosure, when the live broadcast prompt information includes a special effect identifier, the included special effect identifier can be highlighted in the live broadcast prompt information and set to a selectable state when the live broadcast prompt information is displayed. Furthermore, if a selection trigger operation for the special effect identifier is detected, it can be determined that an identifier trigger operation for the special effect identifier in the live broadcast prompt information has been detected. The target special effect can be the special effect corresponding to the selected special effect identifier. The special effect description information can be pre-determined descriptive information used to provide a detailed description of the relevant information of the special effect. For example, the special effect description information can be used to describe at least one of the following: special effect content, special effect effect, and special effect application scenario. The information describing the special effect content can be information used to describe the content contained in the special effect. Specifically, the content contained in the special effect can include at least one of the following: special effect identifier, special effect elements used in the special effect, and the image processing method corresponding to the special effect. The information describing the special effect effect can specifically be used to describe the changes that occur after the special effect is applied to the target object relative to before the special effect application, and the direct or indirect effects produced by these changes. Information describing the application scenarios of special effects can specifically describe which scenario the special effect will be used in and how the special effect will be applied in that scenario.

[0057] It should be noted that the display method for special effects description information can include various options, such as displaying the description information based on a pop-up window or a display panel. For example, the special effects description information can be displayed as a floating window in the area adjacent to the display area of ​​the special effects icon.

[0058] As an optional implementation of this embodiment, multiple special effects can be predetermined, and special effect description information corresponding to each special effect can be determined respectively. Furthermore, the special effect identifier and the corresponding special effect description information can be associated and stored. Further, after displaying the live broadcast prompt information corresponding to the first prompt information, the special effect identifier included in the live broadcast prompt information is in a triggerable state. Furthermore, when an identifier triggering operation is detected for a special effect identifier, the selected special effect identifier can be determined based on the identifier triggering operation, and the special effect corresponding to the selected special effect identifier can be used as the target special effect. Further, the special effect description information corresponding to the target special effect can be determined from the pre-stored special effect description information based on the special effect identifier of the target special effect, and the determined special effect description information can be displayed in the adjacent area of ​​the display area of ​​the special effect identifier. The identifier triggering operation for the special effect identifier can be of various types, such as clicking the special effect identifier, or hovering the cursor over the special effect identifier, etc.

[0059] The technical solution of this disclosure provides a setting function for the first prompt information by responding to the first information setting operation and obtaining the first prompt information. This increases the information interaction method. Since the first prompt information contains descriptive information about the first content and / or effect expected to be presented in the live broadcast room, it can easily, directly, quickly and accurately obtain the main information expected to be presented in the live broadcast room, providing data basis for the generation of live broadcast prompt information. Then, by responding to the live broadcast prompt generation request, the live broadcast prompt information corresponding to the first prompt information is displayed. Since the live broadcast prompt information is used to prompt the second content that can be presented in the live broadcast room and / or the target operation to be performed in the live broadcast room, and the first prompt information corresponds to the live broadcast prompt information, it is possible to generate live broadcast prompt information that fits the actual needs in a targeted manner based on the first prompt information. This solves the problem of unstable live broadcast quality and live broadcast effect in some live broadcast rooms. By displaying the live broadcast prompt information, it can help live broadcast users enrich the display content of the live broadcast room and improve the live broadcast effect.

[0060] Figure 2 is a schematic flowchart of another information processing method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment, in response to a live broadcast prompt generation request, determines the target special effects information corresponding to the first prompt information, and generates live broadcast prompt information based on the first prompt information and the target special effects information. For detailed implementation methods, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here.

[0061] As shown in Figure 2, the method of this embodiment may specifically include:

[0062] S210. In response to the first information setting operation, obtain the first prompt information of the setting, wherein the first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room.

[0063] S220. In response to the live broadcast prompt generation request, determine the target special effect information corresponding to the first prompt information, and generate live broadcast prompt information based on the first prompt information and the target special effect information.

[0064] The target special effect information can be understood as the special effect association information of at least one special effect matched with the first prompt information. The target special effect information may include any information associated with the special effect. Optionally, the target special effect information may include at least one of special effect description information, special effect identifier, and special effect video. The special effect identifier may be information used to identify the special effect. The special effect identifier may be a special effect name, special effect code, and / or special effect thumbnail, etc. The special effect video may be video data used to demonstrate the effect of the special effect. The special effect video may be a pre-generated video including the process of applying the special effect to a preset template image. For example, a preset template image can be obtained, and any special effect can be applied to the preset template image to perform special effect processing on the preset template image based on the special effect. Further, a video demonstrating the effect of the special effect can be used as the special effect video.

[0065] In this embodiment of the disclosure, upon detecting a live stream prompt generation request, at least one special effect matching the first content and / or effect expected to be presented in the live stream, contained in the acquired first prompt information, can be determined, along with the corresponding special effect description information, special effect identifier, and / or special effect video. Furthermore, target special effect information corresponding to the first prompt information can be determined based on the determined special effect description information, special effect identifier, and / or special effect video. Further, live stream prompt information can be generated based on the first prompt information and the target special effect information.

[0066] It should be noted that, upon obtaining the first prompt information and determining the corresponding target effect information, a live-stream prompt message can be generated based on the description of the content and / or effects to be presented in the expected live-stream room contained in the first prompt information and the matching target effect information. This prompt message describes the application of the effects included in the target effect information under the condition of conforming to the first prompt information. The methods for generating the live-stream prompt message based on the first prompt information and the target effect information can include various approaches. Optionally, information analysis can be performed on the first prompt information and the target effect information, and the live-stream prompt message can be generated based on the analysis results; alternatively, new prompt information can be generated based on the first prompt information and the target effect information, and then processed according to a preset information processing method to obtain the live-stream prompt message, etc.

[0067] Optionally, generating live stream prompt information based on the first prompt information and the target special effects information includes: generating second prompt information based on the first prompt information, the target special effects information, and a preset prompt information template; and generating live stream prompt information based on the second prompt information. This technical solution combines the first prompt information and the target special effects information to achieve multi-dimensional information integration. Furthermore, the prompt information template makes the second prompt information more standardized, thereby generating more targeted and specific live stream prompt information.

[0068] The first prompt message template can be a pre-set blank prompt template used to generate live stream prompt messages. This blank prompt template can be a template with a preset fixed format. The second prompt message can be used to guide the generation of live stream prompt messages that match the first prompt message.

[0069] In this embodiment of the disclosure, the method of generating live broadcast prompt information based on the second prompt information can include a variety of methods. Optionally, the second prompt information can be analyzed and the live broadcast prompt information can be determined based on the analysis results; or, the second prompt information can be processed according to a pre-trained information processing model and the live broadcast prompt information can be output, etc.

[0070] As an optional implementation of this embodiment, the first prompt information and the target effect information can be filled into the corresponding positions in the prompt information template. Then, the filled prompt information template can be used as the second prompt information. Furthermore, the second prompt information can be input into a pre-trained information processing model to process the second prompt information based on the information processing model, and the model's output information can be used as the live broadcast prompt information corresponding to the first prompt information. The advantage of this setup is that it achieves the effect of processing the first prompt information and the target effect information through the prompt information template to generate live broadcast prompt information, thereby making the generated live broadcast prompt information more closely match the first prompt information and improving the user experience.

[0071] In this embodiment of the disclosure, upon obtaining the first prompt information, at least one target effect to be applied to the live stream can be determined based on the first prompt information, and the target effect description information and effect identifier corresponding to the target effect can be determined. Furthermore, the target effect information corresponding to the first prompt information can be determined based on the determined effect description information and effect identifier.

[0072] Optionally, determining the target effect information corresponding to the first prompt information includes: determining the target effect description information based on the first prompt information and the target database, and determining the effect identifier corresponding to the target effect description information. This technical solution, with the help of the target database, can more quickly and accurately match the effect description information and effect identifier corresponding to the first prompt information.

[0073] The target database stores descriptions and identifiers for multiple special effects, with each description and identifier stored correspondingly. The target effect description can be the description of a target effect that matches the first prompt.

[0074] As an optional implementation of this embodiment, multiple special effects can be predetermined, and special effect description information and special effect identifiers corresponding to each special effect can be determined respectively. Further, the special effect description information and special effect identifiers can be associated and stored in a target database. Further, when the first prompt information is obtained, the first prompt information can be matched with the special effect description information of multiple special effects in the target database. At least one target special effect matching the first prompt information is determined, and the special effect description information corresponding to the target special effect is used as the target special effect description information. Furthermore, the special effect identifier corresponding to the target special effect description information can be determined according to the pre-established association between the special effect identifier and the special effect description information. Furthermore, the target special effect information corresponding to the first prompt information can be determined based on the target special effect description information and the corresponding special effect identifier. The advantage of this setup is that it achieves the effect of determining the target special effect information matching the first prompt information based on pre-stored special effect information, thereby improving the efficiency of determining the target special effect information and, consequently, improving the efficiency of generating live prompt information.

[0075] In this embodiment, the target database also stores effect description vectors corresponding to the effect description information. The effect description vector can be an information vector generated based on the effect description information. The effect description vector can be used to capture semantic, syntactic, or other related information in the effect description information. The effect description vector can be obtained by converting words, phrases, or sentences in the effect description information into vectors of a preset length. It should be noted that, when the target database stores effect description vectors, in order to more accurately determine the target effect description information that matches the first prompt information, so that the final generated live broadcast prompt information is closer to the user's expected live broadcast effect, the target effect description information corresponding to the first prompt information can be determined based on vector matching.

[0076] Optionally, the target special effect description information is determined from the special effect description information of multiple special effects stored in the target database based on the first prompt information. This includes: determining the prompt feature vector corresponding to the first prompt information; determining the vector similarity between the prompt feature vector and the special effect description vector corresponding to each special effect description information stored in the target database; determining at least one target feature vector based on the vector similarity; and determining the special effect description information corresponding to the target feature vector as the target special effect description information. Using this technical solution, the special effect description information corresponding to the first prompt information can be easily, quickly, and accurately matched from multiple special effect description information in the target database, thereby improving the relevance between the special effects prompted in the generated live broadcast prompt information and the first prompt information.

[0077] The prompt feature vector can be a feature vector obtained by representing the first prompt information in numerical form. In this embodiment, the first prompt information can be processed by text vector conversion according to a preset vector representation method to convert the words, phrases, or sentences in the first prompt information into vectors of fixed length. Then, the converted vector can be used as the prompt feature vector corresponding to the first prompt information. Optionally, the vector representation method can include word embedding, text embedding, bag-of-words model, or language representation model, etc. Vector similarity can be a measure of the closeness between any two vectors in the vector space.

[0078] In the embodiments of this disclosure, determining at least one target feature vector based on vector similarity may include various implementation methods, and each implementation method will be described below.

[0079] Optionally, at least one target feature vector is determined based on vector similarity, including: determining at least one target vector similarity with a vector similarity greater than or equal to a preset similarity threshold; and using the prompt feature vector corresponding to the target vector similarity as the target feature vector.

[0080] The preset similarity threshold can be a standard value used to measure whether the vector similarity meets the similarity requirements. The preset similarity threshold can be any similarity, such as 0.7, 0.8, or 0.9.

[0081] As an optional implementation of this disclosure, for at least one vector similarity, the vector similarity is compared with a preset similarity threshold. If the vector similarity is determined to be greater than or equal to the preset similarity threshold, the vector similarity is taken as the target vector similarity. Further, the prompt feature vector corresponding to at least one target vector similarity can be taken as the target feature vector.

[0082] Optionally, determining at least one target feature vector based on vector similarity includes: sorting at least one prompt feature vector in descending order of their corresponding vector similarity, and determining a preset number of prompt feature vectors at the top of the sort as target feature vectors.

[0083] The preset quantity can be set according to actual needs and is not specifically limited here. Optionally, the preset quantity can be 1, 3, or 5, etc.

[0084] As another optional implementation of this disclosure, at least one prompt feature vector can be sorted in descending order of vector similarity. Further, a predetermined number of prompt feature vectors can be filtered out, starting with the first-ranked prompt feature vector. Then, the predetermined number of filtered prompt feature vectors can be used as target feature vectors.

[0085] As an optional implementation of this embodiment, the first prompt information can be processed using word embedding to obtain a prompt feature vector corresponding to the first prompt information. Further, the vector similarity between the prompt feature vector and the effect description vector corresponding to each effect description information stored in the target database can be determined according to a preset vector similarity determination method. Further, at least one prompt feature vector is sorted in descending order of its corresponding vector similarity, and a preset number of prompt feature vectors at the top of the sorting are determined as target feature vectors. Then, the effect description information corresponding to the target vector similarity can be used as the target effect description information. The vector similarity determination method can be any method capable of determining vector similarity. Optionally, the vector similarity determination method may include cosine similarity, Euclidean distance, Manhattan distance, or Pearson correlation coefficient, etc.

[0086] For example, Figure 3 is a flowchart illustrating a method for generating live stream prompt information using an embodiment of this disclosure. As shown in Figure 3, first prompt information input by the user is obtained. This first prompt information could be, "I want to create a forest-themed live stream room and use some special effects to enhance the visual effects. Can you give me some hints?". Further, the first prompt information is segmented and word-embedded to obtain a prompt feature vector. Then, the vector similarity between the prompt feature vector and the special effect description vector corresponding to each special effect description stored in the vector database is determined. Next, at least one target feature vector is determined based on the vector similarity, and the special effect description information corresponding to the target feature vector is determined as the target special effect description information. A special effect identifier corresponding to the target special effect description information is also determined. Finally, a second prompt information can be generated based on the first prompt information, the target special effect description information, the special effect identifier, and a preset prompt information template. Then, the second prompt information is input into a pre-trained information processing model to process the second prompt information based on the information processing model, and output a live prompt information corresponding to the first prompt information. The live prompt information may be "I have created a forest-style live room for you. You can first use effect A to decorate yourself, and then use effect B to change the style of your live room background..."

[0087] In this embodiment of the disclosure, before determining the target effect description information based on the first prompt information and the target database, multiple effects can be determined, and effect description information and effect identifiers corresponding to each effect can be determined respectively. Furthermore, the effect identifiers and effect description information can be associated and stored in the target database so that the target effect description information corresponding to the first prompt information can be obtained subsequently based on the target database.

[0088] Building upon the aforementioned technical solutions, the method further includes: acquiring the effect association information of the target effect, generating the effect description information of the target effect based on the effect association information, and storing the effect description information and the effect identifier of the target effect in the target database. Since it is impossible to predict which effects will be used in the live broadcast prompts, this technical solution allows for the pre-generation of the effect description information before its application. This allows for direct retrieval from the target database during application, avoiding the time consumption caused by real-time generation and the resource consumption caused by repeated generation during multiple applications. This improves the efficiency of subsequent processing of the effect description information and provides rich data support for the subsequent application of the target effect.

[0089] The target effect can be understood as the effect whose description information is to be generated. The target effect can be one or more existing effects. Optionally, the target effect can be an effect previously used by the target user in the live stream; or, the target effect can be an effect with a high frequency of use among the effects already used by the target user; or, the target effect can be an effect set by default in the application software, etc. The effect-related information can be any pre-generated information associated with the effect. Optionally, the effect-related information can include at least the effect video, effect image, and / or third-party prompting information. The third-party prompting information can be information used to prompt how to describe and introduce the effect. The effect description information is used to describe at least one of the following: effect content, effect effect, and application scenario.

[0090] In this embodiment of the disclosure, when the special effects association information includes special effects videos or special effects images, various acquisition methods can be included. Optionally, when a target special effects are determined, the target special effects can be rendered offline to render the target special effects into a preset template video or preset template image. Then, a special effects video or special effects image corresponding to the target special effects can be obtained. Alternatively, when a target special effects are determined, a special effects video or special effects image corresponding to the target special effects can be retrieved from pre-stored special effects videos or special effects images.

[0091] In this embodiment of the disclosure, when a target special effect is determined, special effect association information corresponding to the target special effect can be obtained. Furthermore, the information included in the special effect association information can be analyzed to generate special effect description information for the target special effect based on the information included in the special effect association information.

[0092] Optionally, the special effects association information includes at least the special effects video and third-party prompt information. Further, generating special effects description information for the target special effects based on the special effects association information includes: acquiring multiple target video frames from the special effects video, and generating special effects description information for the target special effects based on the multiple target video frames and the third-party prompt information. Using this technical solution, the special effects video of the target special effects can provide more analytical data for the special effects description information, and the third-party prompt information can accurately guide the content presented in the special effects description information, thereby making the generated special effects description information richer and more relevant to the needs.

[0093] The target video frame can be any video frame in the special effects video. It should be noted that multiple target video frames can be at least a subset of the video frames in the special effects video. That is, all video frames in the special effects video can be used as target video frames; alternatively, frames can be extracted from the special effects video, and the extracted frames can be used as target video frames.

[0094] In this embodiment of the disclosure, multiple target video frames and third-party prompt information can be processed according to a preset video processing method to obtain effect description information corresponding to the target effect. The video processing method can be any method; optionally, it can be performed based on a pre-trained video processing model. More specifically, the video processing model can be obtained by training a diffusion model.

[0095] As an optional implementation of this embodiment, after obtaining the effect association information corresponding to the target effect, frames can be extracted from the effect video in the effect association information, and the extracted video frames can be used as target video frames. Then, the multiple target video frames and the third prompt information included in the effect association information can be input into a pre-trained video processing model to process the multiple target video frames and the third prompt information based on the video processing model, and the information output by the model can be used as the effect description information corresponding to the target effect. The advantage of this setup is that it makes the final effect description information more closely match the target effect and the third prompt information, and it improves the generation efficiency and accuracy of the effect description information.

[0096] In this embodiment of the disclosure, for a predetermined target effect, in order to facilitate users' clearer and more intuitive understanding of the application method of the target effect, based on the above technical solutions, it further includes: in response to the second information setting operation for the target effect, displaying application prompt information corresponding to the set fourth prompt information. Using this technical solution, the application prompt information of the target effect can be obtained simply, quickly, and directly through the set fourth prompt information.

[0097] The fourth prompt message inquires about the application method of the target effect in the target scenario. The target scenario can be a user-defined scenario for the effect; alternatively, it can be a scenario set by the application software's default settings that matches the target effect, etc. The second information setting operation can be understood as the operation used to set the effect application prompt message. The application prompt message can be understood as information that prompts how the target effect should be applied in the target scenario.

[0098] As an optional implementation of this disclosure, when a target effect is determined, a second information setting operation can be performed for the target effect. Then, in response to the second information setting operation, the set fourth prompt information is obtained. Furthermore, the fourth prompt information and the effect video of the target effect can be processed according to a preset video processing method, thereby obtaining application prompt information corresponding to the fourth prompt information. The video processing method can be any processing method; optionally, it can be processed according to a pre-trained video processing model.

[0099] It should be noted that the generation timing of the effect description information and application prompt information corresponding to the special effect can be as follows: when multiple special effects are predetermined, effect description information and / or application prompt information corresponding to each special effect can be generated separately. Then, the generated effect description information and / or application prompt information can be associated and stored with the corresponding effect identifier. Furthermore, during the user application phase, when any special effect is determined, the effect description information and / or application prompt information corresponding to that special effect can be directly retrieved from the database. Alternatively, the generation timing of the effect description information and application prompt information can also be as follows: during the user application phase, when any special effect is determined, the effect description information and / or application prompt information corresponding to that special effect can be generated in real time. Therefore, based on the generated effect description information and / or application prompt information, the live broadcast prompt information corresponding to that special effect is determined. This embodiment of the disclosure does not specifically limit the generation timing of the effect description information and application prompt information.

[0100] For example, Figure 4 is a flowchart illustrating a method for generating special effects description information and / or application prompt information using an embodiment of this disclosure. As shown in Figure 4, assuming special effects C is the target special effects, offline rendering is performed on special effects C to obtain a special effects video corresponding to special effects C. Then, frames can be extracted from the special effects video according to a preset step size to obtain multiple target video frames. Next, the multiple target video frames and pre-acquired third prompt information can be input into a video processing model, and special effects description information corresponding to special effects C can be output. Furthermore, the special effects description information, the special effects identifier of special effects C, and the special effects video can be associated and stored in a database. Further, the special effects description information can be segmented and word-embedded to obtain a special effects description vector corresponding to the special effects description information. Furthermore, the special effects description information and the special effects description vector can be associated and stored in a vector database. Alternatively, multiple target video frames and pre-acquired fourth prompt information can be input into a video processing model to output application prompt information corresponding to special effects C.

[0101] For example, Figure 5 is a schematic diagram of the display effect of the special effect description information and application prompt information provided in the embodiments of this disclosure. Continuing with the example above, assuming that special effect C is a wearable rabbit ear-shaped hair clip, a special effect image corresponding to this special effect can be displayed. Specifically, the image of the special effect itself, such as the image of the wearable rabbit ear-shaped hair clip shown in Figure 5a, can also be a special effect image obtained by applying the rabbit ear effect to a template image, that is, an effect image of wearing the rabbit ear-shaped hair clip on the head of the target object in the template image. Then, the special effect image and the third prompt information can be input into the video processing model, and the text shown in Figure 5b can be output. This text can be used as the special effect description information corresponding to the rabbit ear effect. Inputting the special effect image and the fourth prompt information into the video processing model can output the text shown in Figure 5c. This text can be used as the application prompt information corresponding to the rabbit ear effect.

[0102] In practical applications, pre-defined special effects in application software are usually stored in a database associated with their corresponding effect identifiers. Therefore, when searching for special effects, the identifier of the desired effect is typically retrieved, and the search is performed based on that identifier to identify the target effect. However, this method of searching for special effects may have limitations, such as the user not knowing the identifier of the desired effect, or the entered identifier being incomplete, leading to inaccurate results in the search for the target effect.

[0103] To address the above situation, in this embodiment of the disclosure, the determined special effect description information is information that provides a detailed introduction to the target special effect. After determining the special effect description information corresponding to the target special effect and associating and storing the special effect description information with the special effect identifier, when performing a special effect search, special effect keywords associated with the special effect to be searched can be entered. The target special effect is then determined based on the special effect keywords and the special effect description information.

[0104] Optionally, after generating the effect description information of the target effect based on the effect association information, the method further includes: in response to the effect search operation, obtaining search keywords, determining the target effect based on the search keywords and the effect description information, and displaying the effect identifier of the target effect. By using this technical solution, the search scope for search keywords can be expanded through the effect description information, enabling the matching of more target effects for the search keywords and increasing the freedom of choice in selecting target effects. Compared to matching using effect identifiers, it supports fuzzy search for target effects, reduces search difficulty, and improves the search experience.

[0105] The special effects search operation can be used to search for special effects. Search keywords can be keywords entered that are related to the target special effect being searched for. Search keywords can be keywords extracted from a search query entered by the user; alternatively, they can be words entered by the user as search keywords, etc.

[0106] As an optional implementation of this embodiment, a special effects search interface can be displayed, which includes a search box and a search control. A special effects search query can be entered into the search box. Furthermore, upon detecting a trigger operation on the search control, it can be determined that a special effects search operation has been detected. Furthermore, in response to the special effects search operation, at least one search keyword is determined based on the special effects search query. Furthermore, a search can be performed on stored special effects description information based on the search keyword, and target special effects description information matching the search keyword can be determined. The special effects corresponding to the target special effects description information are then designated as the target special effects. Furthermore, the special effects identifier corresponding to the target special effects can be determined and displayed.

[0107] The technical solution of this disclosure embodiment obtains the set first prompt information in response to the first information setting operation. The first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room. Further, in response to the live broadcast prompt generation request, the target special effect information corresponding to the first prompt information is determined, and the live broadcast prompt information is generated according to the first prompt information and the target special effect information. This achieves the effect of generating live broadcast prompt information based on the first prompt information and its corresponding target special effect information, thereby improving the matching degree between the live broadcast prompt information and the first prompt information, and thus improving the live broadcast effect.

[0108] Figure 6 is a schematic diagram of the structure of an information processing device provided in an embodiment of the present disclosure. As shown in Figure 6, the device includes: a prompt information setting module 310 and a live broadcast display generation module 320.

[0109] The prompt information setting module 310 is used to obtain the set first prompt information in response to the first information setting operation, wherein the first prompt information includes descriptive information about the first content and / or effect expected to be presented in the live broadcast room; the live broadcast display generation module 320 is used to display the live broadcast prompt information corresponding to the first prompt information in response to the live broadcast prompt generation request, wherein the live broadcast prompt information is used to prompt the second content that can be presented in the live broadcast room and / or the target operation that can be performed in the live broadcast room.

[0110] The technical solution of this embodiment, through the prompt information setting module 310 responding to the first information setting operation, obtains the set first prompt information, providing a setting function for the first prompt information and increasing the information interaction method. Since the first prompt information contains descriptive information about the first content and / or effect expected to be presented in the live broadcast room, it can easily, directly, quickly and accurately obtain the main information expected to be presented in the live broadcast room, providing data basis for the generation of live broadcast prompt information. Then, through the live broadcast display generation module 320 responding to the live broadcast prompt generation request, it displays the live broadcast prompt information corresponding to the first prompt information. Since the live broadcast prompt information is used to describe the second content to be presented in the live broadcast room and / or the target operation to be performed in the live broadcast room, and the first prompt information corresponds to the live broadcast prompt information, it can generate live broadcast prompt information that fits the actual needs in a targeted manner based on the first prompt information, solving the problem of unstable live broadcast quality and effect in some live broadcast rooms. By displaying live broadcast prompt information, it can help live broadcast users enrich the display content of the live broadcast room and improve the live broadcast effect.

[0111] Based on the above-mentioned optional technical solutions, the second content may optionally include at least one special effect identifier and / or application method.

[0112] Based on the above-mentioned optional technical solutions, the device may optionally further include: a description information display module. The description information display module is configured to, after displaying the live broadcast notification information corresponding to the first notification information, respond to an identifier triggering operation for an effect identifier in the live broadcast notification information, display effect description information of the target effect corresponding to the effect identifier.

[0113] Based on the above-mentioned optional technical solutions, the live broadcast display generation module 320 optionally includes: a special effects information determination submodule. The special effects information determination submodule is used to determine target special effects information corresponding to the first prompt information, and generate live broadcast prompt information based on the first prompt information and the target special effects information; wherein the target special effects information includes at least one of special effects description information, special effects identifier, and special effects video.

[0114] Based on the above-mentioned optional technical solutions, optionally, the special effects information determination submodule includes: a second prompt information generation unit. The second prompt information generation unit is used to generate second prompt information based on the first prompt information, the target special effects information, and a preset prompt information template, and to generate live broadcast prompt information based on the second prompt information.

[0115] Based on the above-mentioned optional technical solutions, optionally, the special effects information determination submodule includes: a special effects identifier determination unit. The special effects identifier determination unit is used to determine target special effects description information based on the first prompt information and the target database, and to determine the special effects identifier corresponding to the target special effects description information. The target database stores special effects description information and special effects identifiers for multiple special effects, and the special effects description information and the special effects identifiers are stored correspondingly.

[0116] Based on the above-mentioned optional technical solutions, optionally, the target database further stores special effect description vectors corresponding to the special effect description information; the special effect identification unit includes: a prompt feature vector determination subunit and a special effect description information determination subunit. The prompt feature vector determination subunit is used to determine the prompt feature vector corresponding to the first prompt information, and to determine the vector similarity between the prompt feature vector and the special effect description vector corresponding to each piece of special effect description information stored in the target database; the special effect description information determination subunit is used to determine at least one target feature vector based on the vector similarity, and to determine the special effect description information corresponding to the target feature vector as the target special effect description information.

[0117] Optionally, based on the above-mentioned optional technical solutions, the device further includes: a special effects description information storage module. The special effects description information storage module is used to, before determining the target special effects description information based on the first prompt information and the target database, obtain special effects association information of the target special effects, generate special effects description information of the target special effects based on the special effects association information, and store the special effects description information and the special effects identifier of the target special effects in the target database; wherein the special effects description information is used to describe at least one of special effects content, special effects effect, and application scenario.

[0118] Based on the above-mentioned optional technical solutions, optionally, the special effects association information includes at least the special effects video and the third prompt information; the special effects description information storage module includes: a special effects description information generation unit. The special effects description information generation unit is used to acquire multiple target video frames from the special effects video, and generate special effects description information for the target special effects based on the multiple target video frames and the third prompt information.

[0119] Optionally, based on the above-mentioned optional technical solutions, the device further includes: a special effects search module. The special effects search module is configured to, in response to a special effects search operation, obtain search keywords after generating the special effects description information of the target special effects based on the special effects association information, determine the target special effects based on the search keywords and the special effects description information, and display the special effects identifier of the target special effects, in response to the special effects search operation.

[0120] Based on the above-mentioned optional technical solutions, the device may optionally further include: an application prompt information display module. The application prompt information display module is used to display application prompt information corresponding to the set fourth prompt information in response to a second information setting operation for the target effect, wherein the fourth prompt information is used to inquire about the application method of the target effect in the target scene.

[0121] The information processing apparatus provided in this disclosure can execute the information processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0122] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0123] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Referring to Figure 7 below, a schematic diagram of the structure of an electronic device (e.g., the terminal device or server in Figure 7) 500 suitable for implementing embodiments of this disclosure is shown. The terminal device in embodiments of this disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in Figure 7 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of this disclosure.

[0124] As shown in Figure 7, the electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An edit / output (I / O) interface 505 is also connected to the bus 504.

[0125] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 shows electronic device 500 with various devices, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0126] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0127] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0128] The electronic device provided in this embodiment and the information processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0129] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the information processing method provided in the above embodiments.

[0130] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0131] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0132] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0133] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to a first information setting operation, acquire first prompt information, wherein the first prompt information includes descriptive information about first content and / or effects expected to be presented in the live broadcast room; and in response to a live broadcast prompt generation request, display live broadcast prompt information corresponding to the first prompt information, wherein the live broadcast prompt information is used to prompt second content that can be presented in the live broadcast room and / or a target operation that can be performed in the live broadcast room.

[0134] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0136] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not necessarily limiting in certain circumstances; for example, the prompt information setting module can also be described as "a module for setting descriptive information about the first content and / or effect expected to be presented in the live broadcast room" or "a module for setting the first prompt information," etc.

[0137] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0138] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0139] One or more embodiments of this disclosure provide an information processing method, including: in response to a first information setting operation, acquiring first prompt information set, wherein the first prompt information includes descriptive information about first content and / or effects expected to be presented in a live broadcast room; in response to a live broadcast prompt generation request, displaying live broadcast prompt information corresponding to the first prompt information, wherein the live broadcast prompt information is used to prompt second content that can be presented in the live broadcast room and / or a target operation that can be performed in the live broadcast room.

[0140] The information processing method provided by one or more embodiments of this disclosure further includes, optionally, at least one special effects identifier and / or application method.

[0141] The information processing method provided in one or more embodiments of this disclosure further includes:

[0142] Optionally, after displaying the live notification information corresponding to the first notification information, the method further includes: in response to an identifier triggering operation for an effect identifier in the live notification information, displaying effect description information of the target effect corresponding to the effect identifier.

[0143] The information processing method provided in one or more embodiments of this disclosure further includes: optionally, displaying live notification information corresponding to the first notification information includes: determining target special effects information corresponding to the first notification information, and generating live notification information based on the first notification information and the target special effects information; wherein, the target special effects information includes at least one of special effects description information, special effects identifier, and special effects video.

[0144] The information processing method provided in one or more embodiments of this disclosure further includes: optionally, generating live broadcast prompt information based on the first prompt information and the target special effects information includes: generating second prompt information based on the first prompt information, the target special effects information and a preset prompt information template, and generating live broadcast prompt information based on the second prompt information.

[0145] The information processing method provided in one or more embodiments of this disclosure further includes: optionally, determining the target special effect information corresponding to the first prompt information includes: determining the target special effect description information according to the first prompt information and the target database, and determining the special effect identifier corresponding to the target special effect description information, wherein the target database stores the special effect description information and special effect identifiers of multiple special effects, and the special effect description information and the special effect identifiers are stored correspondingly.

[0146] The information processing method provided in one or more embodiments of this disclosure further includes: optionally, the target database further stores special effect description vectors corresponding to the special effect description information; the step of determining target special effect description information from the special effect description information of multiple special effects stored in the target database based on the first prompt information includes: determining a prompt feature vector corresponding to the first prompt information, determining the vector similarity between the prompt feature vector and the special effect description vector corresponding to each special effect description information stored in the target database; determining at least one target feature vector based on the vector similarity, and determining the special effect description information corresponding to the target feature vector as the target special effect description information.

[0147] The information processing method provided by one or more embodiments of this disclosure further includes: optionally, before determining the target special effect description information based on the first prompt information and the target database, the method further includes: obtaining special effect association information of the target special effect, generating special effect description information of the target special effect based on the special effect association information, and storing the special effect description information and the special effect identifier of the target special effect in the target database; wherein, the special effect description information is used to describe at least one of special effect content, special effect effect, and application scenario.

[0148] The information processing method provided by one or more embodiments of this disclosure further includes: optionally, the special effects association information includes at least a special effects video and third prompt information; the step of generating special effects description information of the target special effects based on the special effects association information includes: acquiring multiple target video frames in the special effects video, and generating special effects description information of the target special effects based on the multiple target video frames and the third prompt information.

[0149] The information processing method provided in one or more embodiments of this disclosure further includes: optionally, after generating the effect description information of the target effect based on the effect association information, it further includes: in response to an effect search operation, obtaining search keywords, determining the target effect based on the search keywords and the effect description information, and displaying the effect identifier of the target effect.

[0150] The information processing method provided in one or more embodiments of this disclosure further includes, optionally, displaying application prompt information corresponding to the set fourth prompt information in response to a second information setting operation for a target effect, wherein the fourth prompt information is used to inquire about the application method of the target effect in a target scene.

[0151] One or more embodiments of this disclosure provide an information processing apparatus, including: a prompt information setting module, configured to, in response to a first information setting operation, acquire set first prompt information, wherein the first prompt information includes descriptive information about a first content and / or effect expected to be presented in a live broadcast room; and a live broadcast display generation module, configured to, in response to a live broadcast prompt generation request, display live broadcast prompt information corresponding to the first prompt information, wherein the live broadcast prompt information is used to prompt a second content that can be presented in the live broadcast room and / or a target operation that can be performed in the live broadcast room.

[0152] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0153] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0154] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information processing method, comprising: obtaining set first prompt information in response to a first information setting operation, wherein the first prompt information contains description information of first content and / or effects expected to be presented in a live room; displaying live prompt information corresponding to the first prompt information in response to a live prompt generation request, wherein the live prompt information is used to prompt second content that can be presented in the live room and / or target operations performed in the live room.

2. The information processing method according to claim 1, wherein The live prompt information at least includes the special effect identifier and / or application method of at least one special effect.

3. The information processing method according to claim 2, wherein After displaying the live prompt information corresponding to the first prompt information, further comprising: in response to an identifier triggering operation for the special effect identifier in the live prompt information, displaying special effect description information of a target special effect corresponding to the special effect identifier.

4. The information processing method according to any one of claims 1 to 3, wherein The display of the live prompt information corresponding to the first prompt information comprises: determining target special effect information corresponding to the first prompt information, and generating live prompt information according to the first prompt information and the target special effect information; wherein the target special effect information includes at least one of special effect description information, special effect identifier and special effect effect video.

5. The information processing method according to claim 4, wherein The generation of live prompt information according to the first prompt information and the target special effect information comprises: generating second prompt information according to the first prompt information, the target special effect information and a preset prompt information template, and generating the live prompt information according to the second prompt information.

6. The information processing method according to claim 4 or 5, wherein The determination of the target special effect information corresponding to the first prompt information comprises: determining target special effect description information according to the first prompt information and a target database, and determining a special effect identifier corresponding to the target special effect description information, wherein the target database stores a plurality of special effect description information and special effect identifiers of special effects, and the special effect description information and the special effect identifier are stored correspondingly.

7. The information processing method according to claim 6, wherein The target database also stores special effect description vectors corresponding to the special effect description information; the determination of the target special effect description information from the plurality of special effect description information stored in the target database according to the first prompt information comprises: determining a prompt feature vector corresponding to the first prompt information, and respectively determining vector similarities between the prompt feature vector and special effect description vectors corresponding to each of the special effect description information stored in the target database; determining at least one target feature vector according to the vector similarities, and determining the special effect description information corresponding to the target feature vector as the target special effect description information.

8. The information processing method according to claim 6 or 7, wherein Before the determination of the target special effect description information according to the first prompt information and the target database, further comprising: obtaining special effect association information of a target special effect, generating special effect description information of the target special effect according to the special effect association information, and storing the special effect description information and a special effect identifier of the target special effect in the target database correspondingly; wherein the special effect description information is used to describe at least one of special effect content, special effect effect and application scenario.

9. The information processing method according to claim 8, wherein The special effect association information at least includes a special effect video and third prompt information; and The special effect description information of the target special effect is generated according to the special effect association information, including:

10. The information processing method according to claim 8 or 9, wherein A plurality of target video frames in the special effect video are acquired, and the special effect description information of the target special effect is generated according to the plurality of target video frames and the third prompt information. After the special effect description information of the target special effect is generated according to the special effect association information, the method further includes: In response to a special effect search operation, a search keyword is acquired, a target special effect is determined according to the search keyword and the special effect description information, and a special effect identifier of the target special effect is displayed.

11. The information processing method of any one of claims 1-10, further comprising: In response to a second information setting operation for a target special effect, application prompt information corresponding to the set fourth prompt information is displayed, wherein the fourth prompt information is used to inquire about an application mode of the target special effect in a target scene.

12. An information processing apparatus, comprising: A prompt information setting module configured to acquire set first prompt information in response to a first information setting operation, wherein the first prompt information contains description information of first content and / or effects expected to be presented in a live room; A live display generation module configured to display live prompt information corresponding to the first prompt information in response to a live prompt generation request, wherein the live prompt information is used to prompt second content that can be presented in the live room and / or a target operation that can be performed in the live room.

13. An electronic device, comprising: One or more processors; A storage device configured to store one or more programs, 14. A storage medium containing computer-executable instructions, wherein, When the one or more programs are executed by the one or more processors, the one or more processors implement the information processing method of any one of claims 1-11. The computer executable instructions, when executed by a computer processor, are used to perform the information processing method of any one of claims 1-11.

15. A computer program product comprising a computer program which, when executed by a processor, implements the information processing method according to any one of claims 1-11.

Images