Content publishing method and apparatus and computer-readable storage medium

Abstract

The present disclosure relates to the technical field of computers, and relates to a content publishing method and apparatus and a computer-readable storage medium. The content publishing method comprises: on the basis of acquired network information, generating multimedia content to be published by an agent, wherein the multimedia content comprises related content generated on the basis of the network information and key information in the network information; publishing the multimedia content; in response to a user initiating an interaction request for the multimedia content, displaying a human-computer interaction interface of the agent; and in the human-computer interaction interface, implementing interaction between the user and the agent on the basis of the multimedia content.

Description

Content publishing method, device and computer readable storage medium TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a content publishing method, a content publishing device, a computer readable storage medium, a computer program product and a computer program product. BACKGROUND

[0002] With the rapid development of the Internet, the number of network users is growing larger and larger, and users can browse various network information through the network. Therefore, network information can be published to achieve large-scale information push.

[0003] In the related art, network information can be pushed to users through various network dissemination methods such as websites, forums and social media.

[0004] SUMMARY

[0005] According to some embodiments of the present disclosure, a content publishing method is provided, including: generating, according to obtained network information, multimedia content to be published by an agent, the multimedia content including relevant content generated according to the network information and key information in the network information; publishing the multimedia content; in response to a user initiating an interaction request for the multimedia content, displaying a human-computer interaction interface of the agent; and in the human-computer interaction interface, implementing interaction between the user and the agent based on the multimedia content.

[0006] In some embodiments, the key information includes keywords and / or image information extracted from the network information, and the relevant content includes theme information generated according to the key information using a machine learning model.

[0007] In some embodiments, displaying the human-computer interaction interface of the agent includes: in response to a selection operation of the user on the multimedia content, displaying detailed information of the multimedia content; and in response to the user initiating an interaction operation on the detailed information, displaying the human-computer interaction interface.

[0008] In some embodiments, implementing the interaction between the user and the agent based on the multimedia content includes: in response to the user inputting question information related to the detailed information in the human-computer interaction interface, generating reply information according to the detailed information and the question information; and in the human-computer interaction interface, feeding back the reply information to the user.

[0009] In some embodiments, the human-computer interaction interface displays candidate question information for the user to select, the candidate question information being generated according to historical question information for the multimedia content and / or generated according to the key information using a machine learning model.

[0010] In some embodiments, the displaying the human-computer interaction interface comprises: displaying the human-computer interaction interface in a window manner in a detail page of the multimedia content; or jumping from the detail page of the multimedia content to an interaction page of the user and the intelligent agent, and displaying the human-computer interaction interface in the interaction page.

[0011] In some embodiments, the detailed information comprises summary information generated according to the network information by using a machine learning model.

[0012] In some embodiments, the detailed information comprises at least one of link information, image information, video information, and text information related to the network information.

[0013] In some embodiments, the displaying the detailed information of the multimedia content comprises: in response to the network information comprising video information, playing the video information in a detail page of the multimedia content.

[0014] In some embodiments, the publishing the multimedia content comprises: publishing the multimedia content as dynamic content recommended by the intelligent agent in a network community.

[0015] In some embodiments, the publishing the multimedia content comprises: adding the multimedia content into a push information stream comprising a plurality of multimedia contents from different publishers.

[0016] According to another embodiment of the present disclosure, a content publishing apparatus is provided, comprising: a generating unit configured to generate multimedia content to be published by an intelligent agent according to obtained network information, the multimedia content comprising relevant content generated according to the network information and key information in the network information; a publishing unit configured to publish the multimedia content; a displaying unit configured to display a human-computer interaction interface of the intelligent agent in response to a user initiating an interaction request for the multimedia content; and an interaction unit configured to implement interaction between the user and the intelligent agent based on the multimedia content in the human-computer interaction interface.

[0017] In some embodiments, the key information comprises keywords and / or image information extracted from the network information, and the relevant content comprises theme information generated according to the key information by using a machine learning model.

[0018] In some embodiments, the displaying unit displays detailed information of the multimedia content in response to a selection operation of the user on the multimedia content, and displays the human-computer interaction interface in response to the user initiating an interaction operation on the detailed information.

[0019] In some embodiments, the interaction unit generates reply information according to the detailed information and question information input by the user in the human-computer interaction interface, and feeds back the reply information to the user in the human-computer interaction interface.

[0020] In some embodiments, the candidate question information is displayed in the human-computer interaction interface for the user to select, and the candidate question information is generated according to historical question information for the multimedia content and / or generated by using a machine learning model according to the key information.

[0021] In some embodiments, the display unit displays the human-computer interaction interface in a window manner in a detail page of the multimedia content, or jumps from the detail page of the multimedia content to an interaction page of the user and the intelligent agent, and displays the human-computer interaction interface in the interaction page.

[0022] In some embodiments, the detailed information includes summary information generated by using a machine learning model according to the network information.

[0023] In some embodiments, the detailed information includes at least one of link information, image information, video information, and text information related to the network information.

[0024] In some embodiments, the display unit plays the video information in a detail page of the multimedia content in response to the network information including the video information.

[0025] In some embodiments, the publishing unit publishes the multimedia content as dynamic content recommended by the intelligent agent in a network community.

[0026] In some embodiments, the publishing unit adds the multimedia content into a push information stream including a plurality of multimedia contents from different publishers.

[0027] According to still other embodiments of the present disclosure, there is provided a content publishing apparatus, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute a content publishing method according to any of the above embodiments based on instructions stored in the memory.

[0028] According to still other embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program, the program being executed by a processor to implement a content publishing method according to any of the above embodiments.

[0029] According to still other embodiments of the present disclosure, there is provided a computer program comprising instructions which, when executed by a processor, cause the processor to perform a content publishing method according to any of the above embodiments.

[0030] According to still other embodiments of the present disclosure, there is provided a computer program product comprising instructions which, when executed by a processor, cause the processor to perform a content publishing method according to any of the above embodiments.

[0031] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments thereof, taken in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0032] The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this application, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure. In the drawings:

[0033] FIG. 1 shows a flow chart of a content publishing method according to some embodiments of the present disclosure;

[0034] FIGS. 2a-2b show schematic diagrams of a multimedia content publishing method according to some embodiments of the present disclosure;

[0035] FIGS. 3a-3b show schematic diagrams of a detailed information display interface according to some embodiments of the present disclosure;

[0036] FIGS. 3c-3d show schematic diagrams of a human-computer interaction interface according to some embodiments of the present disclosure;

[0037] FIG. 4 shows a block diagram of a content publishing apparatus according to some embodiments of the present disclosure;

[0038] FIG. 5 shows a block diagram of a content publishing apparatus according to some other embodiments of the present disclosure;

[0039] FIG. 6 shows a block diagram of a content publishing apparatus according to some further embodiments of the present disclosure. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative, but not as any limitation on the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without any creative work, fall within the scope of protection of the present disclosure.

[0041] The foregoing and other embodiments of the present disclosure are presented by way of example only and are not intended to limit the scope of the present disclosure. The relative arrangement, numerical expressions, and numerical values of the components and steps set forth in these embodiments are not intended to limit the scope of the present disclosure unless otherwise specifically stated. Meanwhile, it should be understood that the sizes of the various parts shown in the drawings are not drawn in actual proportion. Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered as part of the authorized description where appropriate. In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limiting. Therefore, other examples of exemplary embodiments can have different values. It should be noted that similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0042] The inventors of the present disclosure found that the above-mentioned related art has the following problems: the amount of network information published to the public is very large, and users have difficulty finding interesting network information from the vast amount of network information, resulting in low efficiency of information pushing. In view of this, the present disclosure proposes a content publishing technical solution that can improve the efficiency of information pushing.

[0043] For example, the technical solution of the present disclosure can be implemented through the following embodiments.

[0044] FIG. 1 shows a flowchart of a content publishing method according to some embodiments of the present disclosure.

[0045] As shown in FIG. 1, in step 110, according to the obtained network information, a multimedia content to be published by an agent is generated, and the multimedia content includes related content generated according to the network information and key information in the network information.

[0046] In step 120, the multimedia content is published.

[0047] In step 130, in response to a user initiating an interaction request for the multimedia content, a human-computer interaction interface of the agent is displayed.

[0048] In step 140, in the human-computer interaction interface, the user and the agent interact based on the multimedia content.

[0049] In the above embodiments, the network information is processed by the agent to generate multimedia content for the user to browse, and the user can interact with the agent for the multimedia content. In this way, not only is it beneficial to quickly filter out interesting network information from the vast amount of network information, but also an interactive interface is provided to further understand the network information, thereby improving the efficiency of information pushing.

[0050] In some embodiments, the agent can obtain network information such as news, information, blog, etc. from network sources such as websites, forums, social media, etc., extract key information from the network information and / or generate relevant content of the network information. For example, the extracted key information can include keywords and / or image information extracted from the network information; the generated relevant content includes topic information generated by a machine learning model according to the key information.

[0051] For example, the agent obtains a piece of news about the revenue of XX company from a website as network information; the agent extracts a plurality of keywords such as “XX company”, “fourth quarter”, “profit decline”, “40%” from the network information as key information of the network information by means of artificial intelligence such as a machine learning model with natural language processing capability; the agent generates the topic information “XX company’s profit in the fourth quarter decreased by 40%” of the network information as relevant content of the network information according to the keywords by means of the machine learning model.

[0052] For another example, the agent obtains a piece of news about the revenue of XX company from a website as network information; the agent detects that the network information includes at least one image by means of artificial intelligence such as a machine learning model with image processing capability, and extracts the at least one image as key information of the network information to visually show the key content of the network information, thereby improving the efficiency of information pushing. For example, the at least one image can include a main product image of XX company, a revenue statistical chart, etc.

[0053] In addition, for example, the agent can also extract feature information of the image in the network information by means of a machine learning model with image processing capability, and generate the topic information of the network information according to the feature information. In this way, the relevance between the displayed topic information and the network information can be increased, thereby improving the efficiency of information pushing.

[0054] In the above embodiments, the agent generates multimedia content containing the key content of the network information by means of a machine learning model. In this way, the key content of lengthy network information can be displayed to the user in a short information, thereby improving the efficiency of information pushing.

[0055] After the multimedia content is generated by any of the above embodiments, the agent can publish the multimedia content on the network for the user to browse the multimedia content by the following embodiments.

[0056] In some embodiments, the agent can post the generated multimedia content in the network community as dynamic content recommended by the agent. For example, the agent can post the generated multimedia content in a dynamic display page or a content recommendation page of the agent for display. Illustratively, in response to a need of the agent to post dynamic content, the multimedia content can be generated as the dynamic content to be posted according to the obtained network information, and the dynamic content can include a video, an image plus text, etc. For example, each dynamic content can correspond to a piece of network information.

[0057] For example, the agent can also add the generated multimedia content to a push information stream that also includes a plurality of multimedia contents from different publishers. Illustratively, the agent can generate a plurality of multimedia contents to form a push information stream for a user to consume.

[0058] The publication of the multimedia content is exemplarily illustrated below by the embodiments in FIGS. 2a-2b.

[0059] FIGS. 2a-2b show a schematic diagram of a multimedia content publication method according to some embodiments of the present disclosure.

[0060] As shown in FIG. 2a, the agent obtains a plurality of pieces of network information through a website, a forum, a social media, etc. network source, and generates a plurality of multimedia contents; the agent publishes these multimedia contents in the form of dynamic content in a dynamic display page of the agent, including dynamic contents 21a-25a.

[0061] For example, the agent can extract keywords and image information in each piece of obtained network information as key information, and generate theme information of each piece of network information as related content. As shown in FIG. 2a, the dynamic content 21a includes image information 211a extracted from the corresponding network information, and theme information 212a generated by using a machine learning model according to the image information 211a and / or keywords of the corresponding network information; similarly, the dynamic content 22a includes image information 221a and theme information 222a, the dynamic content 23a includes image information 231a and theme information 232a, the dynamic content 24a includes image information 241a and theme information 242a, and the dynamic content 25a includes image information 251a and theme information 252a.

[0062] As shown in FIG. 2b, the agent can also publish these multimedia contents in the form of recommended content in a content recommendation page of the agent, including recommended contents 21b-25b.

[0063] For example, the agent can extract keywords and image information in each piece of obtained network information as key information, and generate topic information of each piece of network information as relevant content. As shown in FIG. 2b, the recommended content 21b includes image information 211a extracted from the corresponding network information, and topic information 212a generated by using a machine learning model according to the image information 211a and / or keywords of the corresponding network information; similarly, the recommended content 22b includes image information 221a and topic information 222a, the recommended content 23b includes image information 231a and topic information 232a, the recommended content 24b includes image information 241a and topic information 242a, and the recommended content 25b includes image information 251a and topic information 252a.

[0064] In the above embodiments, the agent processes the network information by using the machine learning model, and generates multimedia content containing key content of the network information. In this way, the key content of lengthy network information can be intuitively presented to the user in the form of short information (such as image information 211a, topic information 212a, etc.), and the efficiency of information pushing is improved.

[0065] After the multimedia content is published through any of the above embodiments, the user can browse detailed information of the multimedia content of interest through the following embodiments.

[0066] In some embodiments, in response to a selection operation of the multimedia content by the user, detailed information of the multimedia content is displayed. For example, the detailed information includes summary information generated by using a machine learning model according to network information corresponding to the multimedia content; the machine learning model can be a machine learning model with natural language processing capability. For another example, the detailed information can further include at least one of link information, image information, video information, and text information related to the network information corresponding to the multimedia content; the link information, image information, video information, and text information included in the network information can be extracted by using a machine learning model.

[0067] The following embodiments in FIGS. 3a-3b exemplarily illustrate a method of presenting detailed information of multimedia content to a user.

[0068] FIGS. 3a-3b show schematic diagrams of a detailed information presentation interface according to some embodiments of the present disclosure.

[0069] As shown in FIG. 3a, in response to the user selecting one piece of multimedia content in the dynamic display page or the content recommendation of the intelligent agent, the detail page is jumped from the dynamic display page or the content recommendation page; the detail page can include an image information display area 31a and a text information display area 32a. The detail page can also include an intelligent agent related information display area 30a for displaying the related information of the intelligent agent publishing the multimedia content, including the name, avatar, etc. of the intelligent agent.

[0070] The image information display area 31a can be used to display image information, video information, etc. related to the network information corresponding to the multimedia content. The text information display area 32a can be used to display text information corresponding to the network information corresponding to the multimedia content, such as summary information generated by a machine learning model according to the network information corresponding to the multimedia content, theme information generated by a machine learning model according to the key information of the network information corresponding to the multimedia content, link information related to the network information corresponding to the multimedia content, etc.

[0071] Exemplarily, the detailed information of the multimedia content selected by the user can include image information related to the network information corresponding to the multimedia content, and summary information generated by a machine learning model according to the network information corresponding to the multimedia content. As shown in FIG. 3a, the image information display area 31a can display image information related to the network information corresponding to the multimedia content; the text information display area 32a can display summary information of the network information corresponding to the multimedia content and theme information of the multimedia content.

[0072] In this way, the key content of the network information interested by the user can be displayed in a concise and intuitive manner (such as theme information, summary information, image information, etc.), and the efficiency of information pushing is improved.

[0073] In some embodiments, in response to the network information including video information, the video information is played in the detail page of the multimedia content. For example, the network information corresponding to the multimedia content selected by the user includes video information, and in response to the user entering the detail page of the multimedia content, the video information is played in the image information display area 31a, so that the user can quickly understand the network information, thereby improving the efficiency of information pushing.

[0074] As shown in FIG. 3b, in response to the user selecting the multimedia content 311b in the dynamic display page or the content recommendation of the intelligent agent, the detail page is jumped from the dynamic display page or the content recommendation page for displaying detailed information of the multimedia content 311b. The detail page can include a multimedia content display area 31b and a text information display area 32b. The detail page can also include theme information generated by the machine learning model according to the key information of the network information corresponding to the multimedia content 311b,

[0075] For example, the multimedia content display area 31b can be used to display the multimedia content 311b selected by the user. The multimedia content 311b includes image information related to the network information corresponding to the multimedia content 311b, and theme information generated by the machine learning model according to the key information of the network information corresponding to the multimedia content 311b.

[0076] For example, the multimedia content display area 31b can also be used to display other multimedia content, such as multimedia content 312b, which has relevance to the multimedia content 311b. The multimedia content 312b includes image information related to the network information corresponding to the multimedia content 312b, and theme information generated by the machine learning model according to the key information of the network information corresponding to the multimedia content 312b. In response to the user's selection operation on the multimedia content 312b, the detail page of the multimedia content 312b can be jumped from the detail page of the multimedia content 311b.

[0077] In this way, in the process of the user browsing the multimedia content of interest, other multimedia content that the user may be interested in can be displayed, thereby improving the efficiency of information pushing.

[0078] For example, the text information display area 32b can be used to display text information corresponding to the network information corresponding to the multimedia content 311b, such as summary information generated by the machine learning model according to the network information corresponding to the multimedia content 311b, etc.

[0079] In the above embodiments, the key content of the network information of interest of the user can be displayed in a concise and intuitive manner (such as theme information, summary information, image information, etc.), thereby improving the efficiency of information pushing.

[0080] On the basis of displaying the detailed information of the multimedia content of interest of the user through any of the above embodiments, a human-computer interaction interface can also be displayed in response to the user initiating an interactive operation on the detailed information, for the user to interact with the intelligent agent for the multimedia content. For example, in response to the user's operation on the interactive control in the display page of the detailed information, the human-computer interaction interface is displayed.

[0081] The triggering method of the human-computer interaction interface is exemplarily illustrated below by the embodiment in FIG. 3a.

[0082] As shown in FIG. 3a, in response to the user selecting one piece of multimedia content in the dynamic display page or the content recommendation of the intelligent agent, the page is jumped to a detail page; the detail page includes an interaction control 33a for displaying the human-computer interaction interface in response to the user operation on the interaction control 33a.

[0083] For example, the user can trigger the display of the human-computer interaction interface by initiating a question-asking operation. The interaction control 33a can include a text input area 331a for inputting question-asking information, and the human-computer interaction interface is displayed in response to the user selecting the text input area 331a; the text input area 331a can also be used to display candidate question-asking information for the user to select, and the human-computer interaction interface is displayed in response to the user selecting the candidate question-asking information in the text input area 331a. Exemplarily, the candidate question-asking information is generated according to historical question-asking information for the multimedia content and / or by using a machine learning model according to the key information.

[0084] For example, the interaction control 33a can also include a voice input control 332a for voice input of question-asking information. The human-computer interaction interface is displayed in response to the user inputting question-asking voice through the voice input control 332a, and a control for playing the question-asking voice can be displayed in the human-computer interaction interface. For example, the interaction control 33a can also include an insertion control 333a for inserting multimedia files such as images and videos in the question-asking information. The human-computer interaction interface is displayed in response to the user inserting multimedia files through the insertion control 333a, and a thumbnail of the multimedia file can be displayed in the human-computer interaction interface.

[0085] In this way, the user can interact with the publisher in a timely manner for the multimedia content of interest, thereby improving the efficiency of information pushing.

[0086] After the human-computer interaction interface is triggered through any of the above embodiments, the user and the intelligent agent can interact for the multimedia content based on the human-computer interaction interface through the following embodiments.

[0087] In some embodiments, in response to the user inputting question-asking information related to the detailed information in the human-computer interaction interface, reply information is generated according to the detailed information and the question-asking information; and the reply information is fed back to the user in the human-computer interaction interface. For example, the user can input question-asking information related to the detailed information in the human-computer interaction interface by voice input, text input, etc.; the intelligent agent generates reply information by using a machine learning model according to the user input and the question-asking information, and feeds back the reply information to the user by voice reply, text reply, etc.

[0088] In this way, the user can interact with the publisher in a timely manner for the multimedia content of interest, thereby improving the efficiency of information pushing.

[0089] In some embodiments, candidate question information is displayed in the human-computer interaction interface for the user to select. The candidate question information can be generated according to historical question information for the multimedia content and / or generated by using a machine learning model according to the key information. For example, the agent can obtain historical question information of network information corresponding to the multimedia content through the network as the candidate question information. The agent can also select at least one historical question information with the highest occurrence frequency as the candidate question information by counting the occurrence frequencies of the historical question information. For example, the candidate question information can be displayed in the interaction interface for the user to select, and the agent responds to the candidate question information in response to the user selecting one of the candidate question information.

[0090] In this way, the user can quickly ask questions for the multimedia content of interest, thereby improving the efficiency of information pushing.

[0091] In some embodiments, the human-computer interaction interface is displayed in the form of a window in the detail page of the multimedia content, or the human-computer interaction interface is displayed in the interaction page jumped from the detail page of the multimedia content.

[0092] The technical solutions of the human-computer interaction interface are exemplarily described below by the embodiments in FIGS. 3c-3d.

[0093] FIGS. 3c-3d show schematic diagrams of a human-computer interaction interface according to some embodiments of the present disclosure.

[0094] As shown in FIG. 3c, in response to the user triggering the operation of the interaction control 33a in the detail page of any of the above embodiments, the human-computer interaction interface 301c is displayed in the form of a window in the detail page of the multimedia content. For example, the human-computer interaction interface 301c can be popped up from a position (such as the bottom, top, side, etc.) of the detail information display interface in the form of a window, and the human-computer interaction interface 301c can be overlaid on the detail information display interface in the detail page.

[0095] For example, the human-computer interaction interface 301c can include an interaction content display area 302c for displaying the interaction content between the user and the agent. The interaction content can include the question information of the user about the current multimedia content and the reply information of the agent to the question information.

[0096] For example, the human-computer interaction interface 301c can include a candidate question information display area 303c for displaying at least one candidate question information about the current multimedia content. For example, in response to the user selecting one of the candidate question information, the candidate question information can be displayed in the interactive content display area 302c; the agent replies to the candidate question information and displays the reply information in the interactive content display area 302c.

[0097] For example, the human-computer interaction interface 301c can include a pop-up window control. For example, the double arrow control in FIG. 3c is used to display the human-computer interaction interface 301c in full screen; the ×-shaped control in FIG. 3c is used to close the human-computer interaction interface 301c and restore the display of the detailed information display interface covered thereby.

[0098] As shown in FIG. 3d, in response to the user triggering the interactive control 33a in the detail page of any of the above embodiments, the user jumps from the detail page of the multimedia content to the user-agent interaction page and displays the human-computer interaction interface in the interaction page. For example, the human-computer interaction interface can include a multimedia content display area 31d for displaying the current multimedia content (image information, theme information, etc.).

[0099] For example, the human-computer interaction interface can include an interactive content display area 32d for displaying the user-agent interaction content. The interaction content can include the user's question information about the current multimedia content and the agent's reply information to the question information.

[0100] In the above embodiments, the user can interact with the publisher in a timely manner for the multimedia content of interest, thereby improving the efficiency of information pushing.

[0101] FIG. 4 shows a block diagram of a content publishing device according to some embodiments of the present disclosure.

[0102] As shown in FIG. 4, the content publishing device 4 includes a generation unit 41 for generating a multimedia content to be published by an agent according to the obtained network information, the multimedia content including related content generated according to the network information and key information in the network information; a publishing unit 42 for publishing the multimedia content; a display unit 43 for displaying a human-computer interaction interface of the agent in response to the user initiating an interaction request for the multimedia content; and an interaction unit 44 for implementing the user-agent interaction in the human-computer interaction interface based on the multimedia content.

[0103] In some embodiments, the key information includes keywords and / or image information extracted from the network information, and the related content includes theme information generated according to the key information using a machine learning model.

[0104] In some embodiments, the display unit 43 displays detailed information of the multimedia content in response to a selection operation of the user on the multimedia content, and displays the human-computer interaction interface in response to an initiation of an interaction operation of the user on the detailed information.

[0105] In some embodiments, the interaction unit 44 generates reply information according to the detailed information and question information input by the user in the human-computer interaction interface in response to the user inputting the question information related to the detailed information, and feeds back the reply information to the user in the human-computer interaction interface.

[0106] In some embodiments, candidate question information for the user to select is displayed in the human-computer interaction interface, and the candidate question information is generated according to historical question information for the multimedia content and / or generated by using a machine learning model according to the key information.

[0107] In some embodiments, the display unit 43 displays the human-computer interaction interface in a window manner in a detail page of the multimedia content, or jumps from the detail page of the multimedia content to an interaction page of the user and the intelligent agent, and displays the human-computer interaction interface in the interaction page.

[0108] In some embodiments, the detailed information includes summary information generated by using a machine learning model according to the network information.

[0109] In some embodiments, the detailed information includes at least one of link information, image information, video information, and text information related to the network information.

[0110] In some embodiments, the display unit 43 plays the video information in a detail page of the multimedia content in response to the network information including the video information.

[0111] In some embodiments, the publishing unit 44 publishes the multimedia content as dynamic content recommended by the intelligent agent in a network community.

[0112] In some embodiments, the publishing unit 44 adds the multimedia content into a push information stream including a plurality of multimedia contents from different publishers.

[0113] In the above embodiments, the network information is processed by the intelligent agent to generate multimedia content for the user to browse, and the user can perform human-computer interaction on the multimedia content. In this way, it is not only beneficial to quickly filter out interested network information from a large amount of network information, but also provides an interaction interface for further understanding the network information, thereby improving the efficiency of information pushing. In addition, the user can perform timely interaction with the publisher on the interested multimedia content, thereby improving the efficiency of information pushing.

[0114] FIG. 5 shows a block diagram of a content publishing apparatus according to some other embodiments of the present disclosure.

[0115] As shown in FIG. 5, the content publishing apparatus 5 of this embodiment includes a memory 51 and a processor 52 coupled to the memory 51, the processor 52 being configured to perform the content publishing method in any one of the embodiments of the present disclosure based on instructions stored in the memory 51.

[0116] The memory 51 may, for example, include a system memory, a fixed nonvolatile storage medium, etc. The system memory may, for example, store an operating system, an application program, a Boot Loader, a database, and other programs, etc.

[0117] FIG. 6 shows a block diagram of a content publishing apparatus according to yet other embodiments of the present disclosure.

[0118] As shown in FIG. 6, the content publishing apparatus 6 of this embodiment includes a memory 610 and a processor 620 coupled to the memory 610, the processor 620 being configured to perform the method in any one of the preceding embodiments based on instructions stored in the memory 610.

[0119] The memory 610 may, for example, include a system memory, a fixed nonvolatile storage medium, etc. The system memory may, for example, store an operating system, an application program, a Boot Loader, and other programs, etc.

[0120] The content publishing apparatus 6 may, for example, further include an input / output interface 630, a network interface 640, a storage interface 650, etc. These interfaces 630, 640, 650 and the memory 610 and the processor 620 may, for example, be connected through a bus 660. The input / output interface 630 provides a connection interface for display, mouse, keyboard, touch screen, microphone, speaker, and other input / output devices. The network interface 640 provides a connection interface for various networking devices. The storage interface 650 provides a connection interface for external storage devices such as SD card and U disk.

[0121] Those skilled in the art should understand that the embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Therefore, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present disclosure can take the form of a computer program product implemented on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0122] So far, the content publishing apparatus according to the present disclosure has been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein according to the above description.

[0123] The methods and systems of the present disclosure can be implemented in a number of ways. For example, the methods and systems of the present disclosure can be implemented via software, hardware, firmware, or any combination of software, hardware, and firmware. The above described order of steps for the methods is merely for illustration, and the steps of the methods of the present disclosure are not limited to the order specifically described above unless otherwise specifically stated. Furthermore, in some embodiments, the present disclosure can also be implemented as a program recorded in a recording medium, which includes machine readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the methods according to the present disclosure.

[0124] While certain specific embodiments of the present disclosure have been described in detail above, those skilled in the art will appreciate that the examples described above are merely illustrative of the present disclosure and are not intended to be limiting. Those skilled in the art will appreciate modifications to the above embodiments that fall within the scope and spirit of the present disclosure. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. A content publishing method, comprising: generating, according to obtained network information, multimedia content to be published by an agent, the multimedia content comprising relevant content generated according to the network information and key information in the network information; publishing the multimedia content; in response to a user initiating an interaction request for the multimedia content, displaying a human-computer interaction interface of the agent; in the human-computer interaction interface, enabling interaction between the user and the agent based on the multimedia content.

2. The content distribution method according to claim 1, wherein The key information comprises keywords and / or image information extracted from the network information, and the relevant content comprises theme information generated according to the key information using a machine learning model.

3. The content distribution method according to Claim 1, wherein The display of the human-computer interaction interface of the agent comprises: in response to a selection operation of the user on the multimedia content, displaying detailed information of the multimedia content; in response to the user initiating an interaction operation on the detailed information, displaying the human-computer interaction interface.

4. The content distribution method according to Claim 3, wherein The interaction between the user and the agent based on the multimedia content comprises: in response to the user inputting question information related to the detailed information in the human-computer interaction interface, generating reply information according to the detailed information and the question information; in the human-computer interaction interface, feeding back the reply information to the user.

5. The content distribution method according to Claim 4, wherein The human-computer interaction interface displays candidate question information for the user to select, which is generated according to historical question information for the multimedia content and / or using a machine learning model according to the key information.

6. The content distribution method according to Claim 3, wherein The display of the human-computer interaction interface comprises: in a detail page of the multimedia content, displaying the human-computer interaction interface in a window; or jumping from a detail page of the multimedia content to an interaction page of the user and the agent, and displaying the human-computer interaction interface in the interaction page.

7. The content distribution method according to Claim 3, wherein The detailed information comprises summary information generated using a machine learning model according to the network information.

8. The content distribution method according to Claim 3, wherein The detailed information comprises at least one of link information, image information, video information, and text information related to the network information.

9. The content distribution method according to Claim 3, wherein The display of the detailed information of the multimedia content comprises: in response to the network information comprising video information, playing the video information in a detail page of the multimedia content.

10. The content distribution method according to any one of claims 1-9, wherein, The publishing of the multimedia content comprises: in a network community, publishing the multimedia content as dynamic content recommended by the agent.

11. The content distribution method according to any one of claims 1-9, wherein, The publishing of the multimedia content comprises: adding the multimedia content to a push information stream, the push information stream comprising a plurality of multimedia contents from different publishers.

12. A content publishing apparatus, comprising: a generation unit configured to generate, according to obtained network information, multimedia content to be published by an agent, the multimedia content comprising relevant content generated according to the network information and key information in the network information; a publishing unit configured to publish the multimedia content; a display unit configured to, in response to a user initiating an interaction request for the multimedia content, display a human-computer interaction interface of the agent; an interaction unit configured to implement interaction between the user and the agent based on the multimedia content in the human-computer interaction interface.

13. A content publishing apparatus, comprising: a memory; and a processor coupled to the memory, the processor configured to perform the content publishing method according to any one of claims 1-11 based on instructions stored in the memory.

14. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the content publishing method according to any one of claims 1-11.

15. A computer program product comprising instructions which, when executed by a processor, cause the processor to perform the content publishing method according to any one of claims 1-11.

16. A computer program comprising instructions which, when executed by a processor, cause the processor to perform the content publishing method according to any one of claims 1-11. ​

Images