Content pushing method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a content pushing method and device, equipment and a storage medium. The method comprises the steps of creating a content recommendation task for a target user based on interaction between the target user and a virtual object; obtaining a group of reference contents based on reference information associated with the target user; generating a plurality of texts corresponding to the plurality of content items based on the set of reference contents; generating voice contents corresponding to the plurality of content items based on the plurality of texts; and generating push content for the content recommendation task based on the multiple texts and the voice content, and providing the push content to the target user by the virtual object. In this way, the content pushing efficiency can be improved through the embodiment of the invention.

Description

Content pushing method, device, apparatus and storage medium TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a content pushing method, device, apparatus and computer readable storage medium. BACKGROUND

[0002] In recent years, with the development of the Internet, more and more users will conduct network activities in application platforms. For example, users will have a conversation with virtual objects in network platforms, etc. However, in the existing interaction scenarios with virtual objects, it is difficult to efficiently provide push content for users.

[0003] SUMMARY

[0004] In a first aspect of the present disclosure, a content pushing method is provided. The method comprises: creating a content recommendation task for a target user based on an interaction of the target user with a virtual object; obtaining a set of reference contents based on reference information associated with the target user; generating a plurality of texts corresponding to a plurality of content items based on the set of reference contents; generating voice contents corresponding to the plurality of content items based on the plurality of texts; and generating push contents for the content recommendation task based on the plurality of texts and the voice contents, to be provided to the target user by the virtual object.

[0005] In a second aspect of the present disclosure, a device for content pushing is provided. The device comprises: a creating module configured to create a content recommendation task for a target user based on an interaction of the target user with a virtual object; an obtaining module configured to obtain a set of reference contents based on reference information associated with the target user; a first generating module configured to generate a plurality of texts corresponding to a plurality of content items based on the set of reference contents; a second generating module configured to generate voice contents corresponding to the plurality of content items based on the plurality of texts; and a third generating module configured to generate push contents for the content recommendation task based on the plurality of texts and the voice contents, to be provided to the target user by the virtual object.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device comprises 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. The instructions, when executed by the at least one processing unit, cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The computer readable storage medium has stored thereon a computer program, which is executable by a processor to implement the method of the first aspect.

[0008] It is to be understood that the particulars shown herein are by way of example and for purposes of illustrative discussion of the embodiments of the present disclosure only and are not intended to limit the scope of the present disclosure to the particular embodiments illustrated. Other features, aspects, and advantages of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above-mentioned and other features and advantages of various embodiments of this disclosure will become more apparent from the following description referring to the accompanying drawings. In the drawings, like or similar elements are referred to by like or similar reference numbers, in which:

[0010] FIG. 1 shows a schematic diagram of an example environment in which some embodiments of the present disclosure can be implemented in real-time;

[0011] FIG. 2 shows a schematic block diagram of an example system for content push, according to some embodiments of the present disclosure;

[0012] FIG. 3A shows a flowchart of an overall example process for content push, according to some embodiments of the present disclosure;

[0013] FIG. 3B shows a flowchart of a detailed example process for content push, according to some embodiments of the present disclosure;

[0014] FIG. 4 shows a flowchart of an example process for content push, according to some embodiments of the present disclosure;

[0015] FIG. 5 shows a schematic block diagram of an example apparatus for content push, according to some embodiments of the present disclosure; and

[0016] FIG. 6 shows a block diagram of an electronic device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail with reference to the drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather should be construed to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the present disclosure.

[0018] It is noted that the headings provided herein are not limitations of the various embodiments of the present disclosure. The various embodiments are described throughout this document, and any type of embodiment can be included under any heading. Additionally, embodiments described in any heading can be combined with any other embodiment described in the same heading and / or a different heading in any manner.

[0019] In the description of the embodiments of the present disclosure, the term "comprising" and similar terms thereof are to be understood as open-ended, i.e., "including but not limited to". The term "based on" is to be understood as "based at least in part on". The term "one embodiment" or "the embodiment" is to be understood as "at least one embodiment". The term "some embodiments" is to be understood as "at least some embodiments". Other explicit or implicit definitions can also be included below. The terms "first", "second", etc. can refer to different or same objects. Other explicit or implicit definitions can also be included below.

[0020] In the embodiments of the present disclosure, data of users, acquisition and / or use of data, etc. can be involved. These aspects all comply with corresponding laws and regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are performed on the premise that the user is aware of and confirms. Accordingly, in the implementation of the embodiments of the present disclosure, the type of data or information that can be involved, the use range, the use scenario, etc. should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations. The specific informing and / or authorization manner can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this aspect.

[0021] In the present specification and embodiments, if the scheme involves processing of personal information, it will be processed on the premise of having a legal basis (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the prescribed or agreed range. The user refuses to process personal information other than the necessary information required for the basic function, which does not affect the user's use of the basic function.

[0022] As briefly mentioned above, in recent years, with the development of the Internet, more and more users will carry out network activities in application platforms. For example, users will have a dialogue with virtual objects in network platforms, etc. However, in the existing interaction scenarios with virtual objects, it is difficult to conveniently and efficiently provide content for users.

[0023] The embodiments of the present disclosure propose a scheme for content pushing. According to the scheme, a content recommendation task for a target user can be created based on the interaction of the target user with a virtual object; a set of reference contents can be acquired based on reference information associated with the target user; a plurality of texts corresponding to a plurality of content items can be generated based on the set of reference contents; a plurality of voice contents corresponding to the plurality of content items can be generated based on the plurality of texts; and a pushing content for the content recommendation task can be generated based on the plurality of texts and the plurality of voice contents, to be provided to the target user by the virtual object.

[0024] In this way, embodiments of the present disclosure can provide push content including text and voice for a user based on reference information associated with the user during the interaction of the user with the virtual object. In this way, the user can be conveniently and efficiently pushed content during the interaction of the user with the virtual object, and the quality of the push content can be improved.

[0025] Various example implementations of the solution are described in further detail below in conjunction with the accompanying drawings.

[0026] Example Environment

[0027] FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG. 1, the example environment 100 can include an electronic device 110.

[0028] In this example environment 100, the electronic device 110 can run an application 120 that supports interface interaction. The application 120 can be any suitable type of application for interface interaction, examples of which can include, but are not limited to, a news application, a virtual application, a social application, or other suitable application. A user 140 can interact with the application 120 via the electronic device 110 and / or its attached devices.

[0029] In the environment 100 of FIG. 1, the electronic device 110 can present an interface 150 for supporting interface interaction through the application 120 if the application 120 is in an active state.

[0030] In some embodiments, the electronic device 110 communicates with a server 130 to implement the provisioning of services of the application 120. The electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a palmtop computer, a portable gaming terminal, a VR / AR device, a Personal Communication System (PCS) device, a personal navigation device, a Personal Digital Assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including an apparatus and peripherals or peripherals thereof, or any combination thereof. In some embodiments, the electronic device 110 can also support any type of interface for the user (such as "wearable" circuitry, etc.).

[0031] The server 130 can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system, and can also be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks, and basic cloud computing services such as big data and artificial intelligence platforms. The server 130 may, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. The server 130 can provide background services for the application 120 in the electronic device 110 that supports a virtual scene.

[0032] A communication connection can be established between the server 130 and the electronic device 110. The communication connection can be established by wired or wireless means. The communication connection can include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, and the like, and embodiments of the present disclosure are not limited in this regard. In embodiments of the present disclosure, the server 130 and the electronic device 110 can achieve signaling interaction through the communication connection therebetween.

[0033] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure.

[0034] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0035] Information content pushing

[0036] FIG. 2 shows a schematic structural block diagram of an example system 200 for content pushing, according to some embodiments of the present disclosure. The system 200 can be implemented as or included in an electronic device. Various modules / components in the system 200 can be implemented by hardware, software, firmware, or any combination thereof.

[0037] In some embodiments, as shown in FIG. 2, the system 200 includes a task creation module 210 configured to create a content recommendation task, a speech processing module 220 configured to generate speech content in the content pushing content, a content service module 230 configured to generate the pushing content, a content preparation module 240 configured to provide a set of reference content, and a task scheduling module 250 configured to perform scheduling processing for multiple tasks including the content recommendation task. The specific processing content of each module in the system 200 can refer to the subsequent description of the process 300A, the process 300B, and the process 400, which will not be described here again.

[0038] The following will describe embodiments according to the present disclosure taking the pushing of information content as an example. It should be understood that the solutions of the present disclosure are also applicable to other types of content pushing tasks.

[0039] FIG. 3A shows a flowchart of an overall example process 300A of content pushing according to some embodiments of the present disclosure. FIG. 3B shows a flowchart of a detailed example process 300B of content pushing according to some embodiments of the present disclosure. The processes 300A and 300B can be implemented in the system 200. The process 300A is described below with reference to FIGS. 1, 3A and 3B.

[0040] In some embodiments, as shown in FIG. 3A, the client 301 can receive an interaction of a target user with a virtual object. Further, the client 301 can create an information recommendation task for the target user based on the interaction of the target user with the virtual object. As an example, the virtual object can be a robot assistant with a conversation function and feedback based on information. As an example, the virtual object can be implemented based on the bot service 303.

[0041] In some embodiments, with continued reference to FIG. 3A, in block 310, the client 301 can receive a first message sent by the target user to the virtual object. As an example, the client 310 can provide a conversation interface with the virtual object to the target user, and can receive the first message via the conversation interface.

[0042] In some embodiments, as shown in FIG. 3B, the client 301 can also receive a first message created by the target user containing an information recommendation task with a target pushing time.

[0043] In some embodiments, with continued reference to FIG. 3A, the client 301 can send the first message to the server 302, so that the server 302 can invoke the bot service 303 to process the first message.

[0044] In some embodiments, with continued reference to FIG. 3B, the client 301 can send the first message to the server 302, so that the server 302 can invoke the language model to process the first message. As an example, the bot service 303 can support processing the first message with the language model.

[0045] In some embodiments, with continued reference to FIG. 3A, the bot service 303 can determine whether the first message is associated with an information acquisition intent. Further, the bot service 303 can request the information service 304 to create an information recommendation task for the target user in response to the first message being associated with the information acquisition intent.

[0046] In some embodiments, referring to FIG. 3B, the server 302 can invoke the workflow 307 to request the information service 304 to create an information recommendation task for the target user. As an example, the server 302 can also invoke the workflow 307 to request the information service 304 to create an information recommendation task for the target user based on the bot service 303.

[0047] In some embodiments, referring to FIG. 3A, the client 301 can control the virtual object to send an information push message to the target user. Further, the client 301 can request the information service 304 to create an information recommendation task for the target user in response to a preset operation of the target user on the information push message. As an example, the information push message can include a prompt component or prompt information for creating an information push task. Further, the client 301 can request the information service 304 to create an information recommendation task for the target user based on a trigger of the target user on the prompt component or a preset operation associated with the prompt information (e.g., a click operation or a swipe operation on the prompt information, etc.).

[0048] In some embodiments, referring to FIG. 3A, the information service 304 can create an information recommendation task for the target user. Further, the information service 304 can also store the completion of the information recommendation task and feed back a task id and / or a message of the completion of the task creation to the client 301.

[0049] In some embodiments, referring to FIG. 3B, the information service 304 can create an information recommendation task (e.g., a timing task) for the target user based on the information recommendation task containing a target push time.

[0050] In some embodiments, referring to FIG. 3A, in block 320, the information service 304 can request the recommendation service 305 to prepare a set of reference information contents (e.g., news) in response to a trigger of the information recommendation task (e.g., receiving a trigger request or reaching a predetermined target push time).

[0051] In some embodiments, referring to FIG. 3A, the recommendation service 305 can obtain a set of reference information contents based on reference information associated with the target user.

[0052] In some embodiments, referring to FIG. 3B, the information service 304 can obtain reference information associated with the target user. Further, the information service 304 can determine at least one theme of a set of reference information contents based on the reference information. As an example, the reference information includes information associated with finance, and at least one theme of a set of reference information contents is finance.

[0053] In some embodiments, with continued reference to FIG. 3B, the information service 304 can obtain a set of reference information content associated with the at least one topic.

[0054] In some embodiments, with continued reference to FIG. 3B, the client 301 can provide a plurality of preference setting options in response to receiving the preference setting request of the target user. As an example, the plurality of preference setting options correspond to a plurality of topics.

[0055] In some embodiments, with continued reference to FIG. 3B, the client 301 can receive at least one target preference option selected by the target user from the plurality of preference setting options. Further, the server 302 can invoke a language model to process the at least one target preference option (e.g., based on the bot service 303) to determine the reference information associated with the target user.

[0056] In some embodiments, with continued reference to FIG. 3B, the information service 304 can further query the reference information of the user based on the storage 308. In some embodiments, the information service 304 can determine the reference information associated with the target user based on the interaction content of the target user with the virtual object and / or other virtual objects stored in the storage 308. As an example, the interaction content can include conversation information (also referred to as dialogue information, such as current dialogue information and / or historical dialogue information) and / or interaction actions (e.g., the operation of the target user clicking the information content).

[0057] In some embodiments, with continued reference to FIG. 3B, the information service 304 can store the updated reference information (e.g., preference) into the storage 308, so that the information service 304 can retrieve the reference information from the storage 308.

[0058] In some embodiments, with continued reference to FIG. 3A, the recommendation service 305 can obtain a set of candidate information content associated with the information recommendation task (e.g., a process of recalling news, a process of recalling a set of news content). Further, the recommendation service 305 can determine the relevance of the set of candidate information content to the reference information. The recommendation service 305 can determine a set of reference information content from the set of candidate information content, which has a relevance to the reference information higher than a threshold (e.g., ranking the news based on the relevance). As an example, the recommendation service 305 can determine the relevance of the set of candidate information content to the reference information based on a preset language model or a related text processing algorithm, which is not limited in the present disclosure.

[0059] In some embodiments, with continued reference to FIG. 3A, the recommendation service 305 can send a completion notification to the information service 304 in response to the completion of obtaining the set of reference information content. Further, the information service 304 can obtain the set of reference information content from the recommendation service.

[0060] In some embodiments, with continued reference to FIG. 3A, the information service 304 can generate the information push content based on the set of reference information content.

[0061] In some embodiments, with continued reference to FIG. 3A, the information service 304 can generate, based on the set of reference information content, a plurality of information texts corresponding to the plurality of information items. In some embodiments, the plurality of information texts can include information summaries and / or title texts. As an example, the information service 304 can generate, based on a plurality of keywords determined for the plurality of information items, title texts for the plurality of information texts based on the plurality of keywords.

[0062] In some embodiments, with continued reference to FIG. 3A, the plurality of information texts can include information summaries, and the information service 304 can determine, from the set of reference information content, a plurality of reference information content associated with a target topic. Further, the information service 304 can generate, based on the plurality of reference information content, a target information text corresponding to a target information item associated with the target topic. As an example, the target topic can be determined based on reference information of the target user. As an example, the information service 304 can generate, using a language model, a plurality of reference information summaries for the plurality of reference information content, and generate the target information text based on the plurality of reference information summaries.

[0063] In some embodiments, with continued reference to FIG. 3A, the information service 304 can further generate, based on the plurality of information texts, speech content corresponding to the plurality of information items.

[0064] In some embodiments, with continued reference to FIG. 3A, the information service 304 can further generate, based on the plurality of information texts, target texts associated with the plurality of information texts (e.g., generate speech announcement scripts using a language model). Further, the information service 304 can generate, using a speech model, speech content corresponding to the target texts. The speech content can be in a preset first voice (e.g., an existing voice in a voice library) or a second voice configured by the target user (e.g., a voice generated based on a speech file uploaded by the target user). The disclosure does not limit the specific content of the speech model, and any model that can generate speech content based on texts and voice will be included.

[0065] In some embodiments, with continued reference to FIG. 3A, the information service 304 can generate, based on the plurality of information texts and the speech content, information push content (e.g., a news card) for an information recommendation task. As an example, the information push content can further include image content associated with the plurality of information texts.

[0066] In some embodiments, continuing to refer to FIG. 3A, in block 330, the information service 304 can push the related data of the information push content to the server 302. The server 302 can send the related data of the information push content to the client 301. Further, the client 301 can render and generate the information push content based on the related data of the information push content, and present the information push content in the display interface of the client.

[0067] In some embodiments, continuing to refer to FIG. 3B, the information service 304 can also push the related data of the information push content to the workflow 307. The workflow 307 can invoke the plug-in in the applet 306 to create a message associated with the information push content, and send the message associated with the information push content to the server 302 based on the applet 306.

[0068] In some embodiments, the applet 306 can send the consumption status (e.g., consumed or not consumed) of the information push content by the client 301 to the information service 304 as a record.

[0069] In some embodiments, the client 301 can control the virtual object to provide the information push content to the target user.

[0070] In some embodiments, continuing to refer to FIG. 3A, the client 301 can also receive a second message of the target user for the information push content. Further, the client 301 can send the second message to the server 302. Further, the server 302 can invoke the bot service 303 to process the second message. The bot service 303 can generate a reply content for the second message based on a plurality of information texts, voice contents, or a set of reference information contents. Further, the bot service 303 can send the reply content to the target user by the client 301 using the virtual object.

[0071] Based on the above-described processes, embodiments of the present disclosure can generate information push content containing information texts and voice contents for a target user based on the configuration information of the target user. The target user can be provided with tailor-made information push content quickly and efficiently, the generation efficiency of the information push content can be improved, and the satisfaction of the target user for the information push content can be improved, thereby facilitating the target user to consume the information push content.

[0072] Example process

[0073] FIG. 4 shows a flowchart of an example process 400 of a conversation presentation, according to some embodiments of the present disclosure. The process 400 can be implemented at the electronic device 110. The process 400 is described below with reference to FIG. 1.

[0074] As shown in the figure, at block 410, the electronic device 110 can create a content recommendation task for the target user based on the interaction of the target user with the virtual object.

[0075] At block 420, the electronic device 110 can obtain a set of reference contents based on the reference information associated with the target user.

[0076] At block 430, the electronic device 110 can generate a plurality of texts corresponding to the plurality of content items based on the set of reference contents.

[0077] At block 440, the electronic device 110 can generate a speech content corresponding to the plurality of content items based on the plurality of texts.

[0078] At block 450, the electronic device 110 can generate a push content for the content recommendation task based on the plurality of texts and the speech content, to be provided to the target user by the virtual object.

[0079] In some embodiments, creating the content recommendation task for the target user based on the interaction of the target user with the virtual object comprises: creating the content recommendation task for the target user based on a trigger preset operation of the target user on a content push message sent by the virtual object to the target user.

[0080] In some embodiments, creating the content recommendation task for the target user based on the interaction of the target user with the virtual object comprises: determining whether a first message sent by the target user to the virtual object is associated with a content acquisition intention based on the first message; and creating the content recommendation task for the target user in response to the first message being associated with the content acquisition intention.

[0081] In some embodiments, obtaining the set of reference contents based on the reference information associated with the target user comprises: obtaining the reference information associated with the target user; determining at least one theme of the set of reference contents based on the reference information; and obtaining the set of reference contents associated with the at least one theme.

[0082] In some embodiments, obtaining the reference information associated with the target user comprises: providing a plurality of preference options corresponding to a plurality of themes in response to receiving a preference setting request of the target user; receiving at least one target preference option selected by the target user from the plurality of preference options; and determining the reference information associated with the target user based on the at least one target preference option.

[0083] In some embodiments, obtaining the reference information associated with the target user comprises: determining the reference information associated with the target user based on interaction content of the target user with the virtual object and / or other virtual objects, the interaction content comprising conversation information and / or interaction actions.

[0084] In some embodiments, the obtaining the set of reference contents based on the reference information associated with the target user comprises: obtaining a set of candidate contents associated with the content recommendation task; determining a relevance degree of the set of candidate contents to the reference information; and determining the set of reference contents from the set of candidate contents, the relevance degree of which to the reference information is higher than a threshold.

[0085] In some embodiments, the text comprises an abstract, and the generating the plurality of texts corresponding to the plurality of content items based on the set of reference contents comprises: determining a plurality of reference contents associated with the target topic from the set of reference contents; and generating a target text corresponding to a target content item associated with the target topic based on the plurality of reference contents.

[0086] In some embodiments, the target text comprises a title text and / or an abstract.

[0087] In some embodiments, the content recommendation task is a news recommendation task, and the push content is a news push content, the news push content comprising a news title and / or a news abstract.

[0088] In some embodiments, the generating the voice content corresponding to the plurality of content items based on the plurality of texts comprises: generating a target text associated with the plurality of texts based on the plurality of texts; and generating the voice content corresponding to the target text, wherein a tone of the voice content is a preset first tone or a second tone configured by the target user.

[0089] In some embodiments, the content recommendation task corresponds to a target push time, and the method further comprises: controlling the virtual object to provide the push content according to the target push time.

[0090] In some embodiments, the method 400 further comprises: receiving a second message of the user for the push content; and generating a reply content for the second message based on the plurality of texts, the voice content, or the set of reference contents.

[0091] Example apparatus and device

[0092] Embodiments of the present disclosure also provide a corresponding apparatus for implementing the above method or process. FIG. 5 shows a schematic structural block diagram of an example apparatus 500 for content push according to certain embodiments of the present disclosure. The apparatus 500 can be implemented as or included in an electronic device. Various modules / components in the apparatus 500 can be implemented by hardware, software, firmware, or any combination thereof.

[0093] As shown in FIG. 5, the apparatus 500 includes a creating module 510 configured to create, based on an interaction between a target user and a virtual object, a content recommendation task for the target user; an obtaining module 520 configured to obtain, based on reference information associated with the target user, a set of reference contents; a first generating module 530 configured to generate, based on the set of reference contents, a plurality of texts corresponding to a plurality of content items; a second generating module 540 configured to generate, based on the plurality of texts, voice contents corresponding to the plurality of content items; and a third generating module 550 configured to generate, based on the plurality of texts and the voice contents, push contents for the content recommendation task to be provided to the target user by the virtual object.

[0094] In some embodiments, the creating module 510 is further configured to create, based on the interaction between the target user and the virtual object, the content recommendation task for the target user includes: creating, based on a trigger preset operation of the target user on a content push message, the content recommendation task for the target user, the content push message being sent to the target user by the virtual object.

[0095] In some embodiments, the creating module 510 is further configured to create, based on the interaction between the target user and the virtual object, the content recommendation task for the target user includes: determining, based on a first message sent by the target user to the virtual object, whether the first message is associated with a content obtaining intention; and in response to the first message being associated with the content obtaining intention, creating the content recommendation task for the target user.

[0096] In some embodiments, the obtaining module 520 is further configured to obtain, based on the reference information associated with the target user, the set of reference contents includes: obtaining the reference information associated with the target user; determining, based on the reference information, at least one theme of the set of reference contents; and obtaining a set of reference contents associated with the at least one theme.

[0097] In some embodiments, the obtaining module 520 is further configured to obtain the reference information associated with the target user includes: in response to receiving a preference setting request of the target user, providing a plurality of preference options, the plurality of preference options corresponding to a plurality of themes; receiving at least one target preference option selected by the target user from the plurality of preference options; and determining the reference information associated with the target user based on the at least one target preference option.

[0098] In some embodiments, the obtaining module 520 is further configured to obtain the reference information associated with the target user includes: determining, based on interaction content between the target user and the virtual object and / or other virtual objects, the reference information associated with the target user, the interaction content including conversation information and / or interaction actions.

[0099] In some embodiments, the obtaining module 520 is further configured to: based on the reference information associated with the target user, obtaining the set of reference content comprises: obtaining a set of candidate content associated with the content recommendation task; determining an association degree of the set of candidate content with the reference information; and determining, from the set of candidate content, a set of reference content with an association degree higher than a threshold with the reference information.

[0100] In some embodiments, the first generating module 530 is further configured to: the text comprises an abstract, wherein the generating, based on the set of reference content, a plurality of texts corresponding to the plurality of content items comprises: determining, from the set of reference content, a plurality of reference content associated with the target topic; and generating, based on the plurality of reference content, a target text corresponding to a target content item, the target content item being associated with the target topic.

[0101] In some embodiments, the first generating module 530 is further configured to: the target text comprises a title text and / or an abstract.

[0102] In some embodiments, the creating module 510 is further configured to: the content recommendation task is a news recommendation task, the third generating module 540 is further configured to: the push content is a news push content, the news push content comprises a news title and / or a news abstract.

[0103] In some embodiments, the second generating module 540 is further configured to: the generating, based on the plurality of texts, a voice content corresponding to the plurality of content items comprises: generating, based on the plurality of texts, a target text associated with the plurality of texts; and generating a voice content corresponding to the target text, wherein a tone of the voice content is a preset first tone or a second tone configured by the target user.

[0104] In some embodiments, the creating module 510 is further configured to: the content recommendation task corresponds to a target push time. The third generating module 550 is further configured to: control the virtual object to provide the push content according to the target push time.

[0105] In some embodiments, the apparatus 500 further comprises a reply module configured to: receive a second message of the user for the push content; and generate, based on the plurality of texts, the voice content or the set of reference content, a reply content for the second message.

[0106] FIG. 6 shows a block diagram of an electronic device 600 in which one or more embodiments of the disclosure can be implemented. It should be understood that the electronic device 600 shown in FIG. 6 is merely an example and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 600 shown in FIG. 6 can be used for an electronic device.

[0107] As shown in FIG. 6, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 can include, but are not limited to, one or more processors or processing units 610, memory 620, storage 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processing unit(s) 610 can be actual or virtual processors and capable of executing various processing in accordance with programs stored in memory 620. In a multi-processing system, multiple processing units execute computer-executable instructions in parallel to improve the processing power of electronic device 600.

[0108] Electronic device 600 typically includes a plurality of computer storage media. Such media can be removable and / or non-removable, and can include volatile and / or nonvolatile media. Memory 620 can be volatile (such as, for example, registers, cache, random access memory (RAM)), non-volatile (such as, for example, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage 630 can be removable or non-removable and can include machine-readable media, such as, for example, flash drives, disks, or any other media capable of storing information and / or data and accessible by electronic device 600.

[0109] Electronic device 600 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 6, a disk drive or other computer-readable media drive can be provided for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "hard drive"), and a disk drive or other computer-readable media drive can be provided for reading from or writing to a removable, non-volatile optical disk (such as a CD-ROM or other optical medium). In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. Storage 630 can include a computer-program product 625 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0110] Communication unit(s) 640 enable communication with other electronic devices via communication media. Additionally, functionality of components of electronic device 600 can be implemented in a single computing cluster or a plurality of computer machines capable of communication through a communication connection. Accordingly, electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes.

[0111] The input device 650 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 660 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 can also communicate with one or more external devices (not shown), such as a storage device, a display device, etc., one or more devices that enable a user to interact with the electronic device 600, or any devices (e.g., a network card, a modem, etc.) that enable the electronic device 600 to communicate with one or more other electronic devices, as needed, via the communication unit 640. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0112] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0113] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0114] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0115] The computer readable program instructions can also 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 apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0116] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (media) having instances of the software embodied thereon, such as computer software, firmware, wireless application protocol (WAP), middleware or microcode. For example, a computer program product can be a floppy disk, a CD-ROM, a DVD, a Blu-ray Disc™, a flash drive, a memory stick, a magnetic tape, or a hard disk drive. The machine-readable medium can be a single medium, or multiple media, of the same or different type. The computer program product can be one or more computer program components embodied in medium and / or transmission signals. The computer program product can have one or more computer readable and / or computer executable components embodied in medium and / or transmission signals. The computer program product can be one or more computer readable and / or computer executable components embodied in medium and / or transmission signals.

[0117] The implementations of the disclosure have been described above with the intent to be illustrative rather than limiting. Although the implementations of the disclosure have been described with regard to one or more implementations, it will be recognized that various modifications and changes can be made by those skilled in the art that will achieve the desirable results of the implementations, such as comparable technical effects. Accordingly, the disclosure is not to be limited by what has been presented in the description above, but instead can be defined by the appended claims and their equivalents.

Claims

1. A content pushing method, comprising: creating a content recommendation task for a target user based on an interaction between the target user and a virtual object; acquiring a set of reference contents based on reference information associated with the target user; generating a plurality of texts corresponding to a plurality of content items based on the set of reference contents; generating a plurality of voice contents corresponding to the plurality of content items based on the plurality of texts; and generating a pushing content for the content recommendation task based on the plurality of texts and the plurality of voice contents, to be provided to the target user by the virtual object. 2.The method of claim 1, wherein the creating a content recommendation task for a target user based on an interaction between the target user and a virtual object comprises: creating a content recommendation task for the target user based on a trigger preset operation of the target user on a content pushing message sent by the virtual object to the target user. 3.The method of claim 1, wherein the creating a content recommendation task for a target user based on an interaction between the target user and a virtual object comprises: determining whether a first message sent by the target user to the virtual object is associated with a content acquisition intention based on the first message; and creating the content recommendation task for the target user in response to the first message being associated with the content acquisition intention. 4.The method of claim 1, wherein the acquiring a set of reference contents based on reference information associated with the target user comprises: acquiring the reference information associated with the target user; determining at least one theme of the set of reference contents based on the reference information; and acquiring the set of reference contents associated with the at least one theme. 5.The method of claim 4, wherein the acquiring reference information associated with the target user comprises: providing a plurality of preference options corresponding to a plurality of themes in response to receiving a preference setting request of the target user; receiving at least one target preference option selected by the target user from the plurality of preference options; and determining the reference information associated with the target user based on the at least one target preference option. 6.The method of claim 4, wherein the acquiring reference information associated with the target user comprises: determining the reference information associated with the target user based on interaction content between the target user and the virtual object and / or other virtual objects, the interaction content comprising conversation information and / or interaction actions. 7.The method of claim 1, wherein the acquiring a set of reference contents based on reference information associated with the target user comprises: acquiring a set of candidate contents associated with the content recommendation task; determining a degree of association between the set of candidate contents and the reference information; and determining the set of reference contents from the set of candidate contents having a degree of association higher than a threshold value with the reference information. 8.The method of claim 1, wherein the texts comprise summaries, and wherein the generating a plurality of texts corresponding to a plurality of content items based on the set of reference contents comprises: ​ ​ ​ ​ ​ From the set of reference content, identify multiple reference contents that are associated with the target topic; as well as Based on the multiple reference contents, target text corresponding to the target content item is generated, wherein the target content item is associated with the target topic.

9. The method of claim 8, wherein the target text includes title text and / or summary.

10. The method according to claim 1, wherein the content recommendation task is an information recommendation task, the pushed content is information push content, and the information push content includes an information title and / or an information summary.

11. The method according to claim 1, wherein generating speech content corresponding to the plurality of content items based on the plurality of texts comprises: Based on the multiple texts, generate target text that is associated with the multiple texts; as well as Generate the speech content corresponding to the target text, wherein the timbre of the speech content is a preset first timbre or a second timbre configured by the target user.

12. The method according to claim 1, wherein the content recommendation task corresponds to a target push time, and the method further includes: The virtual object is controlled to provide the push content according to the target push time.

13. The method according to claim 1, further comprising: Receive a second message from the target user regarding the pushed content; as well as Based on the multiple texts, the voice content, or the set of reference content, a response is generated for the second message.

14. An apparatus for content delivery, comprising: The creation module is configured to create recommendation tasks for the target user based on the interaction between the target user and the virtual object. The acquisition module is configured to acquire a set of reference content based on reference information associated with the target user; The first generation module is configured to generate multiple texts corresponding to multiple content items based on the set of reference content; The second generation module is configured to generate audio content corresponding to the multiple content items based on the multiple texts; as well as The third generation module is configured to generate push content for the content recommendation task based on the multiple texts and the voice content, so that the virtual object can provide it to the target user.

15. 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, according to the claim. Find the method described in any one of 1 to 13.

16. 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 13.

Images