Content generation method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a content generation method and device, equipment and a storage medium. The method comprises the steps of obtaining reference information associated with a target user based on interaction between the target user and a virtual object; acquiring a group of reference contents matched with the reference information; providing a group of reference contents for the first model to obtain a plurality of title contents generated by the first model and a plurality of corresponding abstract contents; and generating a plurality of content items for provision to the target user via the virtual object, each content item having corresponding header content and summary content. In this way, according to the embodiment of the invention, the efficiency of providing the adaptive content for the user can be improved.

Description

A method, apparatus, device, and storage medium for generating content. Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to a method, apparatus, device, and computer-readable storage medium for generating content. Background Technology

[0002] In recent years, with the development of the internet, more and more users are engaging in online activities on application platforms. For example, users may interact with virtual entities on these platforms. However, existing scenarios involving conversations with virtual entities cannot conveniently and efficiently provide users with content tailored to their individual needs.

[0003] Summary of the Invention

[0004] In a first aspect of this disclosure, a method for generating content is provided. The method includes: acquiring reference information associated with the target user based on interaction between the target user and a virtual object; acquiring a set of reference content matching the reference information; providing the set of reference content to a first model to acquire multiple title contents and corresponding multiple summary contents generated by the first model; and generating multiple content items to be provided to the target user via the virtual object, each content item having corresponding title contents and summary contents.

[0005] In a second aspect of this disclosure, an apparatus for generating content is provided. The apparatus includes: a first acquisition module configured to acquire reference information associated with a target user based on interaction between a target user and a virtual object; a second acquisition module configured to acquire a set of reference content matching the reference information; a providing module configured to provide the set of reference content to a first model to acquire multiple title contents and corresponding multiple summary contents generated by the first model; and a generation module configured to generate multiple content items to be provided to the target user via the virtual object, each content item having corresponding title content and summary content.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes computer-executable instructions that, when executed by a processor, implement the method according to a first aspect of this disclosure.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] 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. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment capable of real-time implementation of some embodiments of this disclosure;

[0012] Figures 2A to 2C illustrate flowcharts of detailed example processes according to some embodiments of the present disclosure;

[0013] Figure 3 illustrates a flowchart of an example process for generating content according to some embodiments of the present disclosure;

[0014] Figure 4 shows a schematic structural block diagram of an example apparatus for generating content according to some embodiments of the present disclosure; and

[0015] Figure 5 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0016] 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.

[0017] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0018] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0019] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0020] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0021] As briefly mentioned above, in recent years, with the development of the internet, more and more users are engaging in online activities on application platforms. For example, users may converse with virtual entities on online platforms. However, in existing scenarios involving conversations with virtual entities, it is not convenient and efficient to provide users with content tailored to their individual needs.

[0022] Embodiments of this disclosure propose a scheme for generating content. According to this scheme, reference information associated with the target user can be obtained based on the interaction between the target user and a virtual object; a set of reference content matching the reference information can be obtained; the set of reference content can be provided to a first model to obtain multiple title contents and corresponding multiple summary contents generated by the first model; and multiple content items can be generated to be provided to the target user via the virtual object, each content item having corresponding title contents and summary contents.

[0023] In this way, embodiments of this disclosure can provide users with multiple content items, including titles and summaries, based on the user's reference information in interaction scenarios between users and virtual objects. Thus, during user interaction with virtual objects, content tailored to the user can be provided conveniently and efficiently, improving content delivery efficiency and quality, and further enhancing the user experience.

[0024] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0025] Example Environment

[0026] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0027] In this example environment 100, electronic device 110 can run an application 120 that supports user interface interaction. Application 120 can be any suitable type of application for user interface interaction, examples of which may include, but are not limited to, news applications, social applications, or other suitable applications. User 140 can interact with application 120 via electronic device 110 and / or its attached devices.

[0028] In environment 100 of Figure 1, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting interface interaction.

[0029] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0030] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support virtual scenarios in electronic devices 110.

[0031] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0032] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0033] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0034] Content generation

[0035] Figures 2A to 2C illustrate flowcharts of detailed example processes 200A to 200C according to some embodiments of the present disclosure. Processes 200A to 200C will now be described with reference to Figure 1.

[0036] The following description uses the generation of information content as an example to illustrate embodiments according to this disclosure. It should be understood that the solutions of this disclosure are also applicable to generating other types of content.

[0037] In some embodiments, as shown in FIG2A, service module 201 can receive interactions between a target user and a virtual object. Further, service module 201 can obtain reference information associated with the target user based on the interactions between the target user and the virtual object. As an example, the virtual object can be a robot assistant with dialogue capabilities and the ability to provide feedback based on information. As an example, the virtual object can be implemented based on a bot service.

[0038] In some embodiments, continuing to refer to FIG2A, the reference information associated with the target user obtained by the service module 201 can be stored in the storage module 204.

[0039] In some embodiments, continuing to refer to FIG2A, service module 201 may provide multiple configuration items to a target user in response to a request from the target user to set reference information. Each configuration item may be associated with a preset topic. As an example, the multiple configuration items may include financial configuration items, political configuration items, military configuration items, entertainment configuration items, etc.

[0040] In some embodiments, continuing to refer to FIG2A, service module 201 can determine reference information based on at least one configuration item set by the target user. As an example, at least one configuration item set by the target user may include a financial configuration item, in which case service module 201 can determine that the reference information associated with the target user is associated with financial content.

[0041] In some embodiments, continuing to refer to FIG2A, service module 201 can determine reference information based on the interaction content between the target user and the virtual object obtained from storage module 204. The interaction content may include historical session information and / or historical interaction operations associated with the virtual object. For example, if the historical session information between the target user and the virtual object includes phrases like "I like finance," then service module 201 can determine that the reference information associated with the target user is related to financial content. Similarly, if the historical interaction operations between the target user and the virtual object include interactions with financial content (e.g., clicks, swipes, etc.), then service module 201 can determine that the reference information associated with the target user is related to financial content.

[0042] In some embodiments, the reference information associated with the target user may include one or more of the following: user preferences (e.g., configuration items set by the target user), short-term reference information (e.g., the current interaction content between the target user and the virtual object), long-term reference information (e.g., the historical interaction content between the target user and the virtual object, which is different from the current interaction content), and general reference information (e.g., various interaction operations of the target user recorded by the service module 201).

[0043] In some embodiments, continuing to refer to FIG2A, service module 201 may initiate a data preparation request to recommendation service 202 to prepare content to be provided to the target user. As an example, the data preparation request may include the amount of data to be prepared (e.g., 5-100 items).

[0044] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may, in response to receiving a data preparation request, store the data preparation request in a message queue. Furthermore, the recommendation service 202 may also, in response to receiving a data preparation request, return a notification of successful delivery to the service module.

[0045] In some embodiments, continuing to refer to Figure 2A, the recommendation service 202 can obtain a list of reference content that matches the reference information. As an example, a set of reference content can be obtained from a data source based on this list. Therefore, obtaining a list of reference content can be considered as obtaining a set of reference content. Thus, in the following text, the recommendation service 202 obtaining a set of reference content can be understood as obtaining a list of reference content.

[0046] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may consume the preparation data request in message queue 203 in response to receiving message data from message queue 203. Further, the recommendation service 202 may determine whether the preparation data request is a hot request. For example, if the preparation data request contains information associated with requested hot content, then the preparation data request is a hot request; otherwise, it is a non-hot request. For example, if the preparation data request contains content such as "pushing hot news," then the data preparation request is a hot request.

[0047] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may, in response to a data preparation request for a hot topic request, obtain at least one hot topic (or hot topic category). As an example, multiple hot topics may include, for example, military topics, financial topics, etc.

[0048] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may, in response to a preparation data request being a non-hot topic request, determine at least one hot topic based on reference information associated with the user obtained from the storage module 204.

[0049] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may obtain a set of candidate content (e.g., news content) associated with at least one hot topic from the data source 206. Further, the recommendation service 202 may determine a set of reference content from the set of candidate content.

[0050] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may blend a set of candidate content according to at least one topic (or category). Further, the recommendation service 202 may sort the blended set of candidate content based on reference information. Further, the recommendation service 202 may determine a set of reference content from the sorted set of candidate content.

[0051] In some embodiments, continuing to refer to FIG2A, recommendation service 202 can determine the relevance of a set of candidate content to reference information. Recommendation service 202 can rank the mixed set of candidate content based on the relevance to reference information. As an example, recommendation service 202 can determine a set of reference content from a set of candidate content based on a relevance to reference information that is higher than a threshold.

[0052] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 can use a language model to determine the relevance to the reference information based on the topic, time, and other relevant information of a set of candidate content. As an example, the more topic, time, and other relevant information related to the reference information contained in the first content of a set of candidate content, the higher the relevance between the first content and the reference information.

[0053] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 can also deduplicate a set of candidate content based on predetermined attributes. As an example, predetermined attributes may include event attributes, time attributes, etc. As an example, deduplicated content based on event attributes can be implemented by removing multiple pieces of content with high repetition rates from a set of candidate content based on a target event, and retaining a predetermined number of items (e.g., one item) of content associated with the target event.

[0054] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may also select a predetermined number (e.g., 50) of candidate content from a set of candidate content as a second set of candidate content (e.g., a news list containing the first 50 items). Further, the recommendation service 202 may sort the second set of candidate content by invoking a language model based on the prompting module 205.

[0055] In some embodiments, the prompting module 205 may invoke the language model to receive relevant information (e.g., article source and / or article content) of the second set of candidate content. Further, the language model may rank the second set of candidate content based on content characteristics. Example content characteristics may include facts and opinions. As an example, the language model may rank the second set of candidate content in the order of facts first, followed by opinions.

[0056] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may also, based on the prompting module 205, invoke a language model to rank a set of candidate content (e.g., a second set of candidate content) based on general reference information. As an example, the language model may obtain a ranked set of candidate content based on general reference information and a set of candidate content (e.g., a summary obtained by the language model based on the set of candidate content). As an example, the general reference information may be obtained, for example, based on various interactive operations (e.g., browsing content, liking content, etc.) recorded by the service module 201 on the target user.

[0057] In some embodiments, continuing to refer to FIG2A, the recommendation service 202 may push a notification of readiness completion to the message queue 203 based on the completion of the acquisition of a set of reference content.

[0058] In some embodiments, as shown in FIG2B, content service 208 may, in response to receiving a notification that a set of reference content has been retrieved based on message queue 203, retrieve a set of reference content from data source 206 based on a list of reference content (e.g., a list of recommended news) provided by recommendation service 202. As an example, content service 208 may filter a set of reference content based on a preset word count condition to obtain a filtered set of reference content.

[0059] In some embodiments, continuing to refer to FIG2B, content service 208 may provide a set of reference content to bot service 209. Further, bot service 209 may utilize a first model to generate multiple title contents and corresponding multiple summary contents based on the set of reference content. As an example, the first model may be a language model with text processing capabilities; this disclosure does not limit the specific content of the first model.

[0060] In some embodiments, continuing to refer to FIG2B, content service 208 may invoke bot service 209 to generate multiple content items (e.g., multiple news items) based on multiple title contents and multiple summary contents. Each content item has corresponding title contents and summary contents.

[0061] In some embodiments, continuing to refer to FIG2B, multiple content items can be provided to a target user via a virtual object. As an example, the virtual object can send multiple content items to a session interface with the target user in the form of a session.

[0062] In some embodiments, multiple content items are multiple information items, and these multiple information items can form a news card. As an example, a news card may include multiple cover image contents corresponding to multiple information items. As an example, the multiple cover image contents may be obtained or generated by the content service 208 calling the bot service 209 based on a set of reference content.

[0063] In some embodiments, continuing to refer to FIG2B, content service 208 may provide bot service 209 with multiple summary content corresponding to multiple content items. Further, bot service 209 may utilize a second model to generate voice broadcast text corresponding to multiple content items based on the multiple summary content. As an example, the second model is a language model.

[0064] In some embodiments, referring again to FIG2B, content service 208 may request service module 201 to generate voice content for multiple content items.

[0065] In some embodiments, as shown in FIG2C, service module 201 may provide voice-broadcast text corresponding to multiple content items to voice service 210. Further, voice service 210 may utilize a third model to generate voice-broadcast content corresponding to multiple content items based on the voice-broadcast text. As an example, the third model is a voice model. Any voice model capable of generating voice content based on text will be included within this disclosure, and this disclosure does not limit the specific content of the voice module.

[0066] In some embodiments, continuing to refer to FIG2C, service module 201 may provide timbre indication information to voice service 210 so that the voice broadcast content generated by voice service 210 matches the target timbre indicated by the timbre indication information. In some embodiments, the target timbre is a preset first timbre obtained by service module 201 from bot service 209 or a second timbre configured by target user using bot service 209. As an example, service module 201 may select a preset first timbre from multiple preset timbres in the preset timbre library of bot service 209. As an example, target user may upload an audio file to bot service 209, and bot service 209 may generate a second timbre associated with target user based on the audio file uploaded by target user.

[0067] In some embodiments, referring to FIG2C, the service module 201 may store the voice broadcast content into the storage module 204.

[0068] In some embodiments, service module 201 can also trigger the playback of voice broadcast content to the target user based on the target user's voice broadcast request. As an example, service module 201 can play voice broadcast content to the target user in response to the triggering of a control associated with the voice playback content.

[0069] In some embodiments, service module 201 can also obtain push requests from the target user associated with a target push time. Further, service module 201 can control the virtual object to provide multiple content items based on the target push time. As an example, in response to obtaining a push request associated with a target push time in a session message sent by the target user to the virtual object, service module 201 can control the virtual object to send the aforementioned multiple content items to the target user based on the target push time.

[0070] Based on the process described above, embodiments of this disclosure can provide users with multiple content items, including titles, summaries, and audio content, based on the user's reference information in interaction scenarios between users and virtual objects. In this way, during the interaction process between users and virtual objects, content tailored to the user can be provided conveniently and efficiently, improving content delivery efficiency and quality, and further enhancing the user experience.

[0071] Example process

[0072] Figure 3 illustrates a flowchart of an example process 300 for generating content according to some embodiments of the present disclosure. Process 300 may be implemented at electronic device 110. Process 300 will now be described with reference to Figure 1.

[0073] As shown in the figure, in box 310, electronic device 110 can obtain reference information associated with the target user based on the interaction between the target user and the virtual object.

[0074] In box 320, electronic device 110 can acquire a set of reference content that matches the reference information.

[0075] In box 330, electronic device 110 can provide a set of reference content to the first model to obtain multiple heading contents and corresponding multiple summary contents generated by the first model.

[0076] In box 340, electronic device 110 can generate multiple content items to be provided to a target user via virtual objects, each content item having a corresponding title and summary content.

[0077] In some embodiments, obtaining reference information associated with a target user based on the interaction between the target user and the virtual object includes: determining the reference information based on at least one configuration item set by the target user, wherein the at least one configuration item is associated with at least one preset topic; and / or determining the reference information based on the interaction content between the target user and the virtual object, wherein the interaction content includes historical session information and / or historical interaction operations associated with the virtual object.

[0078] In some embodiments, obtaining a set of reference content that matches the reference information includes: determining at least one topic based on the reference information; and obtaining a set of reference content associated with at least one topic.

[0079] In some embodiments, obtaining a set of reference content associated with at least one topic includes: obtaining a set of candidate content associated with at least one topic; determining the degree of relevance between the set of candidate content and reference information; and determining a set of reference content from the set of candidate content based on the degree of relevance to reference information.

[0080] In some embodiments, method 300 further includes: providing a second model with multiple summary contents corresponding to multiple content items to obtain speech broadcast text generated by the second model; and providing a third model with speech broadcast text to obtain speech broadcast content generated by the third model.

[0081] In some embodiments, method 300 further includes: providing timbre indication information to a third model such that the voice broadcast content matches the target timbre indicated by the timbre indication information, wherein the target timbre includes a preset first timbre or a second timbre configured by the target user.

[0082] In some embodiments, method 300 further includes: obtaining a push request from a target user associated with a target push time; and controlling a virtual object to provide multiple content items according to the target push time.

[0083] In some embodiments, method 300 further includes: triggering the playback of voice broadcast content to the target user based on the target user's voice broadcast request.

[0084] Example devices and equipment

[0085] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 4 shows a schematic structural block diagram of an example apparatus 400 for generating content according to certain embodiments of this disclosure. Apparatus 400 may be implemented as or included in an electronic device. The various modules / components in apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0086] As shown in Figure 4, the device 400 includes a first acquisition module 410 configured to acquire reference information associated with the target user based on the interaction between the target user and the virtual object; a second acquisition module 420 configured to acquire a set of reference content matching the reference information; a providing module 430 configured to provide a set of reference content to a first model to acquire multiple title contents and corresponding multiple summary contents generated by the first model; and a generation module 440 configured to generate multiple content items to be provided to the target user via the virtual object, each content item having corresponding title content and summary content.

[0087] In some embodiments, the first acquisition module 410 is further configured to: acquire reference information associated with the target user based on the interaction between the target user and the virtual object, including: determining reference information based on at least one configuration item set by the target user, wherein the at least one configuration item is associated with at least one preset topic; and / or determining reference information based on the interaction content between the target user and the virtual object, wherein the interaction content includes historical session information and / or historical interaction operations associated with the virtual object.

[0088] In some embodiments, the second acquisition module 420 is further configured to: acquire a set of reference content matching the reference information, including: determining at least one topic based on the reference information; and acquiring a set of reference content associated with at least one topic.

[0089] In some embodiments, the second acquisition module 420 is further configured to: acquire a set of reference content associated with at least one topic, including: acquiring a set of candidate content associated with at least one topic; determining the degree of association between the set of candidate content and reference information; and determining a set of reference content from the set of candidate content based on the degree of association with reference information.

[0090] In some embodiments, the providing module 430 is further configured to: provide a second model with multiple summary contents corresponding to multiple content items to obtain the voice broadcast text generated by the second model; and provide a third model with the voice broadcast text to obtain the voice broadcast content generated by the third model.

[0091] In some embodiments, the providing module 430 is further configured to provide timbre indication information to the third model so that the voice broadcast content matches the target timbre indicated by the timbre indication information, wherein the target timbre includes a preset first timbre or a second timbre configured by the target user.

[0092] In some embodiments, the first acquisition module 410 is further configured to: acquire a push request from a target user associated with a target push time; the generation module 440 is further configured to: control a virtual object to provide multiple content items according to the target push time.

[0093] In some embodiments, the device 400 further includes a playback module configured to trigger the playback of voice broadcast content to the target user based on the target user's voice broadcast request.

[0094] Figure 5 illustrates a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 500 shown in Figure 5 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 500 shown in Figure 5 can be used in electronic devices.

[0095] As shown in Figure 5, the electronic device 500 is in the form of a general-purpose electronic device. Components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, memory 520, storage devices 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be a physical or virtual processor and is capable of performing various processes according to programs stored in the memory 520. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0096] Electronic device 500 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 520 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 530 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 500.

[0097] Electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 520 may include computer program product 525 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0098] Communication unit 540 enables communication with other electronic devices via a communication medium. Additionally, the functionality of components of electronic device 500 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, electronic device 500 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0099] Input device 550 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 560 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 500 can also communicate with one or more external devices (not shown) via communication unit 540 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 500, or with any device that enables electronic device 500 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0100] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0101] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0102] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0103] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0104] 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 an instruction, which contains one or more executable instructions for implementing the specified logical function. 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 consecutive 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, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0105] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating content, comprising: Based on the interaction between the target user and the virtual object, obtain reference information associated with the target user; Obtain a set of reference content that matches the reference information; The first model is provided with the set of reference content to obtain multiple title contents and corresponding multiple summary contents generated by the first model; and Multiple content items are generated to be provided to the target user via the virtual object, each content item having a corresponding title and summary content.

2. The method according to claim 1, wherein obtaining reference information associated with the target user based on the interaction between the target user and the virtual object includes: The reference information is determined based on at least one configuration item set by the target user, wherein the at least one configuration item is associated with at least one preset topic; and / or The reference information is determined based on the interaction content between the target user and the virtual object, wherein the interaction content includes historical session information and / or historical interaction operations associated with the virtual object.

3. The method according to claim 1, wherein obtaining a set of reference content matching the reference information includes: Based on the reference information, at least one topic is identified; as well as Obtain the set of reference content associated with the at least one topic.

4. The method of claim 3, wherein obtaining the set of reference content associated with the at least one topic comprises: Obtain a set of candidate content related to the at least one topic; Determine the degree of correlation between the set of candidate contents and the reference information; as well as Based on the degree of relevance with the reference information, the set of reference content is determined from the set of candidate content.

5. The method according to claim 1, further comprising: Provide the second model with the summaries corresponding to the multiple content items, so as to... Obtain the voice broadcast text generated by the second model; as well as The voice broadcast text is provided to the third model to obtain the voice broadcast content generated by the third model.

6. The method according to claim 5, further comprising: The third model is provided with timbre indication information so that the voice broadcast content matches the target timbre indicated by the timbre indication information, wherein the target timbre includes a preset first timbre or a second timbre configured by the target user.

7. The method according to claim 1, further comprising: Obtain the push request associated with the target user and the target push time; as well as The virtual object is controlled to provide the multiple content items according to the target push time.

8. The method according to claim 5, further comprising: Based on the target user's voice broadcast request, the voice broadcast content is triggered to be played to the target user.

9. An apparatus for generating content, comprising: The first acquisition module is configured to acquire reference information associated with the target user based on the interaction between the target user and the virtual object. The second acquisition module is configured to acquire a set of reference content that matches the reference information; A module is configured to provide the set of reference content to a first model in order to obtain multiple title contents and corresponding multiple summary contents generated by the first model. as well as The generation module is configured to generate multiple content items to be provided to the target user via the virtual object, each content item having a corresponding title and summary content.

10. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.

12. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 8.

Images