Content publishing method and device and computer readable storage medium

Abstract

The invention relates to a content publishing method and device and a computer readable storage medium, and relates to the technical field of computers. The content publishing method comprises the steps that multimedia content to be published by an intelligent agent is generated according to acquired network information, and the multimedia content comprises related content generated according to the network information and key information in the network information; issuing the multimedia content; in response to an interaction request initiated by a user for the multimedia content, displaying a human-computer interaction interface of the intelligent agent; and in the human-computer interaction interface, interaction between the user and the intelligent agent is realized based on the multimedia content.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a content publishing method, a content publishing device, a computer-readable storage medium, a computer program product, and a computer program product. Background Art

[0002] With the rapid development of the Internet, the number of network users is increasing, and users can browse a variety of network information through the network. Therefore, by publishing network information, a wide range of information push can be achieved.

[0003] In related technologies, network information can be pushed to users through various websites, forums, social media and other network communication methods. Summary of the invention

[0004] According to some embodiments of the present disclosure, a content publishing method is provided, including: generating multimedia content to be published by an intelligent agent based on acquired network information, the multimedia content including related content generated based on the network information and key information in the network information; publishing the multimedia content; displaying a human-computer interaction interface of the intelligent agent in response to a user's interactive request for the multimedia content; and realizing interaction between the user and the intelligent agent in the human-computer interaction interface based on the multimedia content.

[0005] In some embodiments, the key information includes keywords and / or image information extracted from network information, and the related content includes topic information generated based on the key information using a machine learning model.

[0006] In some embodiments, displaying the human-computer interaction interface of the intelligent agent includes: displaying detailed information of the multimedia content in response to a user's selection operation on the multimedia content; and displaying the human-computer interaction interface in response to a user initiating an interactive operation on the detailed information.

[0007] In some embodiments, implementing interaction between a user and an intelligent agent based on multimedia content includes: in response to a user inputting question information related to detailed information in a human-computer interaction interface, generating reply information based on the detailed information and the question information; and feeding back the reply information to the user in the human-computer interaction interface.

[0008] In some embodiments, candidate question information for user selection is displayed in the human-computer interaction interface, and the candidate question information is generated based on historical question information for multimedia content and / or generated based on key information using a machine learning model.

[0009] In some embodiments, displaying the human-computer interaction interface includes: displaying the human-computer interaction interface in a window in the details page of the multimedia content; or jumping from the details page of the multimedia content to the interaction page between the user and the intelligent agent, and displaying the human-computer interaction interface in the interaction page.

[0010] In some embodiments, the detailed information includes summary information generated using a machine learning model based on the network information.

[0011] 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.

[0012] In some embodiments, displaying detailed information of the multimedia content includes: in response to the network information including the video information, playing the video information in a detail page of the multimedia content.

[0013] In some embodiments, publishing the multimedia content includes: publishing the multimedia content as dynamic content recommended by an agent in an online community.

[0014] In some embodiments, publishing the multimedia content includes: adding the multimedia content to a push information stream, wherein the push information stream includes a plurality of multimedia contents from different publishers.

[0015] According to other embodiments of the present disclosure, there is provided a content publishing device, comprising: a generation unit, for generating multimedia content to be published by an intelligent agent based on acquired network information, the multimedia content including related content generated based on the network information and key information in the network information; a publishing unit, for publishing the multimedia content; a display unit, for displaying a human-computer interaction interface of the intelligent agent in response to a user's request for interaction with the multimedia content; and an interaction unit, for realizing interaction between the user and the intelligent agent based on the multimedia content in the human-computer interaction interface.

[0016] In some embodiments, the key information includes keywords and / or image information extracted from network information, and the related content includes topic information generated based on the key information using a machine learning model.

[0017] In some embodiments, the display unit displays detailed information of the multimedia content in response to a user's selection operation on the multimedia content, and displays a human-computer interaction interface in response to a user initiating an interactive operation on the detailed information.

[0018] In some embodiments, the interaction unit generates reply information according to the detailed information and the question information in response to the user inputting question information related to the detailed information in the human-computer interaction interface, and feeds back the reply information to the user in the human-computer interaction interface.

[0019] In some embodiments, candidate question information for user selection is displayed in the human-computer interaction interface, and the candidate question information is generated based on historical question information for multimedia content and / or generated based on key information using a machine learning model.

[0020] In some embodiments, the display unit displays the human-computer interaction interface in a window in the details page of the multimedia content, or jumps from the details page of the multimedia content to the interaction page between the user and the agent, and displays the human-computer interaction interface in the interaction page.

[0021] In some embodiments, the detailed information includes summary information generated using a machine learning model based on the network information.

[0022] 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.

[0023] In some embodiments, in response to the network information including the video information, the display unit plays the video information in the detail page of the multimedia content.

[0024] In some embodiments, the publishing unit publishes the multimedia content as dynamic content recommended by the intelligent agent in the network community.

[0025] In some embodiments, the publishing unit adds the multimedia content to a push information flow, and the push information flow includes multiple multimedia contents from different publishers.

[0026] According to some further embodiments of the present disclosure, there is provided a content publishing apparatus, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the content publishing method in any of the above embodiments based on instructions stored in the memory.

[0027] According to some further embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the content publishing method in any of the above embodiments is implemented.

[0028] According to some further embodiments of the present disclosure, a computer program is provided, comprising instructions, which, when executed by a processor, cause the processor to execute the content publishing method according to any one of the above embodiments.

[0029] According to some further embodiments of the present disclosure, a computer program product is provided, comprising instructions, which, when executed by a processor, enable the processor to execute the content publishing method according to any one of the above embodiments.

[0030] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0032] Figure 1 A flowchart showing a content publishing method according to some embodiments of the present disclosure is shown;

[0033] Figure 2a-2b A schematic diagram showing a multimedia content publishing method according to some embodiments of the present disclosure;

[0034] Figure 3a-3b A schematic diagram showing a detailed information display interface according to some embodiments of the present disclosure;

[0035] Figure 3c-3d A schematic diagram showing a human-computer interaction interface according to some embodiments of the present disclosure;

[0036] Figure 4 A block diagram showing a content publishing device according to some embodiments of the present disclosure;

[0037] Figure 5 A block diagram showing a content publishing device according to some other embodiments of the present disclosure;

[0038] Figure 6 A block diagram of a content publishing device according to some further embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0040] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, numerical expressions and numerical values ​​do not limit the scope of the present disclosure. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technology, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be regarded as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0041] The inventor of the present disclosure has found that the above-mentioned related technologies have the following problems: the amount of network information released to the public is very large, and it is difficult for users to find network information of interest from the massive amount of network information, resulting in low efficiency of information push. In view of this, the present disclosure proposes a content publishing technical solution that can improve the efficiency of information push.

[0042] For example, the technical solution of the present disclosure can be implemented through the following embodiments.

[0043] Figure 1 A flowchart of a content publishing method according to some embodiments of the present disclosure is shown.

[0044] like Figure 1 As shown, in step 110, multimedia content to be published by the agent is generated based on the acquired network information, and the multimedia content includes relevant content generated based on the network information and key information in the network information.

[0045] In step 120, the multimedia content is published.

[0046] In step 130, in response to a user initiating an interactive request for multimedia content, a human-computer interaction interface of the intelligent agent is displayed.

[0047] In step 140, in the human-computer interaction interface, the interaction between the user and the agent is implemented based on the multimedia content.

[0048] In the above embodiment, the network information is processed by the agent to generate multimedia content for users to browse, and can interact with the user on the multimedia content. This is not only conducive to quickly screening out interesting network information from the massive network information, but also provides an interactive interface for further understanding of the network information, thereby improving the efficiency of information push.

[0049] In some embodiments, the agent may obtain network information such as news, information, blog posts, etc. through 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 may include keywords and / or image information extracted from the network information; the generated relevant content may include topic information generated using a machine learning model based on the key information.

[0050] For example, the intelligent agent obtains a piece of news about the revenue of XX company from the website as network information; the intelligent agent extracts multiple keywords from the network information through artificial intelligence (such as machine learning models with natural language processing capabilities, etc.), such as "XX company", "fourth quarter", "profit decline", "40%", etc., as the key information of the network information; based on these keywords, the intelligent agent generates the theme information of the network information "XX company's profit in the fourth quarter fell by 40%" as the relevant content of the network information through the machine learning model.

[0051] For another example, the agent obtains a news item about the revenue of XX Company from a website as network information; the agent detects that the network information includes at least one image through artificial intelligence (such as a machine learning model with image processing capabilities, etc.), and extracts the at least one image as the key information of the network information to intuitively display the key content of the network information, thereby improving the efficiency of information push. For example, the at least one image may include the main product images and revenue statistics of XX Company.

[0052] In addition, the agent can also extract feature information of images in network information through a machine learning model with image processing capabilities, and generate topic information of the network information based on the feature information. In this way, the relevance of the displayed topic information and the network information can be increased, thereby improving the efficiency of information push.

[0053] In the above embodiment, the agent processes the network information using the machine learning model and generates multimedia content containing the key content of the network information. In this way, the key content of the lengthy network information can be presented to the user in a short message, thereby improving the efficiency of information push.

[0054] After the multimedia content is generated through any of the above embodiments, the intelligent agent can publish the multimedia content on the network through the following embodiments so that users can browse the multimedia content.

[0055] In some embodiments, the agent may publish the generated multimedia content in the network community as the dynamic content recommended by the agent. For example, the agent may publish the generated multimedia content to the dynamic display page or content recommendation page of the agent for display. Exemplarily, in response to the agent's need to publish dynamic content, multimedia content may be generated based on the acquired network information as the dynamic content to be published, and the dynamic content may include video, image plus text, etc. For example, each dynamic content may correspond to a piece of network information.

[0056] For example, the agent may also add the generated multimedia content to a push information stream, which may also include multiple multimedia content from different publishers. Exemplarily, the agent may generate multiple multimedia content to form a push information stream for user consumption.

[0057] Below through Figure 2a-2b The embodiments in the drawings illustrate exemplary release of multimedia content.

[0058] Figure 2a-2b A schematic diagram showing a method for publishing multimedia content according to some embodiments of the present disclosure is shown.

[0059] like Figure 2a As shown, the intelligent agent obtains multiple network information through network sources such as websites, forums, and social media, and generates multiple multimedia contents; the intelligent agent publishes these multimedia contents in the form of dynamic contents in its dynamic display page, including dynamic contents 21a-25a.

[0060] For example, the agent can extract keywords and image information from each piece of network information as key information, and generate the subject information of each piece of network information as relevant content. Figure 2a As shown, dynamic content 21a includes image information 211a extracted from corresponding network information, and topic information 212a generated by using a machine learning model based on keywords of the image information 211a and / or the corresponding network information; similarly, dynamic content 22a includes image information 221a and topic information 222a, dynamic content 23a includes image information 231a and topic information 232a, dynamic content 24a includes image information 241a and topic information 242a, and dynamic content 25a includes image information 251a and topic information 252a.

[0061] like Figure 2b As shown, the intelligent agent can also publish these multimedia contents in the form of recommended contents in its content recommendation page, including recommended contents 21b-25b.

[0062] For example, the agent can extract keywords and image information from each piece of network information as key information, and generate the subject information of each piece of network information as relevant content. Figure 2b As shown, recommended content 21b includes image information 211a extracted from the corresponding network information, and topic information 212a generated by a machine learning model based on keywords of the image information 211a and / or the corresponding network information; similarly, recommended content 22b includes image information 221a and topic information 222a, recommended content 23b includes image information 231a and topic information 232a, recommended content 24b includes image information 241a and topic information 242a, and recommended content 25b includes image information 251a and topic information 252a.

[0063] In the above embodiment, the agent processes the network information using the machine learning model and generates multimedia content containing the key content of the network information. In this way, the key content of the lengthy network information can be intuitively displayed to the user with short information (such as image information 211a, theme information 212a, etc.), thereby improving the efficiency of information push.

[0064] After multimedia content is published through any of the above embodiments, the user may browse detailed information of the multimedia content of interest through the following embodiments.

[0065] In some embodiments, in response to a user's selection operation on multimedia content, detailed information of the multimedia content is displayed. For example, the detailed information includes summary information generated using a machine learning model based on network information corresponding to the multimedia content; the machine learning model may be a machine learning model with natural language processing capabilities. For another example, the detailed information may also 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, text information, etc. included therein may be extracted from the network information using a machine learning model.

[0066] Below through Figure 3a-3b The embodiments in the present invention exemplarily illustrate a method for displaying detailed information of multimedia content to a user.

[0067] Figure 3a-3b A schematic diagram showing a detailed information display interface according to some embodiments of the present disclosure.

[0068] like Figure 3aAs shown, in response to the user selecting one of the multimedia contents in the dynamic display page or content recommendation of the agent, the user jumps to the detail page from the dynamic display page or content recommendation page; the detail page may include an image information display area 31a and a text information display area 32a. The detail page may also include an agent related information display area 30a for displaying the relevant information of the agent that published the multimedia content, including the name and avatar of the agent.

[0069] 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 using a machine learning model based on the network information corresponding to the multimedia content, theme information generated using a machine learning model based on key information of the network information corresponding to the multimedia content, and link information related to the network information corresponding to the multimedia content.

[0070] Exemplarily, the detailed information of the multimedia content selected by the user may include: image information related to the network information corresponding to the multimedia content; and summary information generated by using a machine learning model based on the network information corresponding to the multimedia content. Figure 3a As shown, 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 the summary information of the network information corresponding to the multimedia content and the theme information of the multimedia content.

[0071] In this way, the key content of the network information that the user is interested in can be displayed to the user in a brief and intuitive manner (such as subject information, summary information, image information, etc.), thereby improving the efficiency of information push.

[0072] In some embodiments, in response to the network information including video information, the video information is played in the details 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 details 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 push.

[0073] like Figure 3bAs shown, in response to the user selecting multimedia content 311b in the dynamic display page or content recommendation of the intelligent agent, the dynamic display page or content recommendation page jumps to the detail page for displaying the detailed information of the multimedia content 311b. The detail page may include a multimedia content display area 31b and a text information display area 32b. The detail page may also include topic information generated by a machine learning model based on the key information of the network information corresponding to the multimedia content 311b.

[0074] 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 topic information generated by a machine learning model based on key information of the network information corresponding to the multimedia content 311b.

[0075] For example, the multimedia content display area 31b can also be used to display other multimedia content associated with the multimedia content 311b, such as multimedia content 312b. The multimedia content 312b includes image information related to the network information corresponding to the multimedia content 312b, and theme information generated by a machine learning model based on 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, it is possible to jump from the details page of the multimedia content 311b to the details page of the multimedia content 312b.

[0076] In this way, while the user is browsing the multimedia content that he is interested in, other multimedia content that he may be interested in can be displayed, thereby improving the efficiency of information push.

[0077] 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 a machine learning model based on the network information corresponding to the multimedia content 311b.

[0078] In the above embodiments, the key contents of the network information that the user is interested in can be displayed to the user in a brief and intuitive manner (such as subject information, summary information, image information, etc.), thereby improving the efficiency of information push.

[0079] On the basis of displaying the detailed information of the multimedia content that the user is interested in through any of the above embodiments, a human-computer interaction interface may be displayed in response to the user initiating an interactive operation on the detailed information, so that the user can interact with the agent with respect to the multimedia content. For example, the human-computer interaction interface is displayed in response to the user operating an interactive control in a display page of the detailed information.

[0080] Below through Figure 3aThe embodiments in the present invention exemplarily illustrate the triggering method of the human-computer interaction interface.

[0081] like Figure 3a As shown, in response to the user selecting one of the multimedia contents in the dynamic display page or content recommendation of the intelligent body, the page jumps from the dynamic display page or content recommendation page to the details page; the details page includes an interactive control 33a, which is used to display the human-computer interaction interface in response to the user's operation on the interactive control 33a.

[0082] For example, the user can trigger the display of the human-computer interaction interface by initiating a question operation. For example, the interactive control 33a may include a text input area 331a for inputting question 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 may also be used to display candidate question information for the user to select, and the human-computer interaction interface is displayed in response to the user selecting the candidate question information in the text input area 331a. Exemplarily, the candidate question information is generated based on historical question information for multimedia content and / or generated using a machine learning model based on key information.

[0083] For example, the interactive control 33a may also include a voice input control 332a for voice input of question information. In response to the user inputting a question voice through the voice input control 332a, the human-computer interaction interface is displayed, and a control for playing the question voice may be displayed in the human-computer interaction interface. For example, the interactive control 33a may also include an insert control 333a for inserting multimedia files such as images and videos into the question information. In response to the user inserting a multimedia file through the insert control 333a, the human-computer interaction interface is displayed, and a thumbnail of the multimedia file may be displayed in the human-computer interaction interface.

[0084] In this way, users can interact with publishers in a timely manner regarding multimedia content of interest, thereby improving the efficiency of information push.

[0085] After the human-computer interaction interface is triggered through any of the above embodiments, the user and the agent may interact with the multimedia content based on the human-computer interaction interface through the following embodiments.

[0086] In some embodiments, in response to a user inputting question information related to detailed information in a human-computer interaction interface, reply information is generated based on the detailed information and the question information; and the reply information is fed back to the user in the human-computer interaction interface. For example, the user may input question information related to detailed information in the human-computer interaction interface through voice input, text input, etc.; the intelligent agent generates reply information using a machine learning model based on the user input and the question information, and feeds back the reply information to the user through voice reply, text reply, etc.

[0087] In this way, users can interact with publishers in a timely manner regarding multimedia content of interest, thereby improving the efficiency of information push.

[0088] In some embodiments, candidate question information for user selection is displayed in the human-computer interaction interface. The candidate question information can be generated based on historical question information for multimedia content and / or generated using a machine learning model based on key information. For example, the intelligent agent can obtain historical question information of network information corresponding to the multimedia content through the network as candidate question information. The intelligent agent can also count the number of occurrences of each historical question information and use at least one historical question information with the largest number of occurrences as candidate question information. For example, the candidate question information can be displayed in the interaction interface for user selection, and in response to the user selecting one of the candidate question information, the intelligent agent replies to the candidate question information.

[0089] In this way, users can quickly ask questions about multimedia content of interest, thereby improving the efficiency of information push.

[0090] In some embodiments, the human-computer interaction interface is displayed in a window on the details page of the multimedia content; or the page for interacting with the user and the agent is jumped from the details page of the multimedia content, and the human-computer interaction interface is displayed on the interaction page.

[0091] Below through Figure 3c-3d The embodiments in the present invention exemplarily illustrate the relevant technical solutions of the human-computer interaction interface.

[0092] Figure 3c-3d A schematic diagram showing a human-computer interaction interface according to some embodiments of the present disclosure.

[0093] like Figure 3c As shown, in response to a user triggering operation on the interactive control 33a in the details page of any of the above embodiments, a human-computer interaction interface 301c is displayed in a window manner in the details page of the multimedia content. For example, the human-computer interaction interface 301c can be popped up in a window manner from a position (such as the bottom, top, side, etc.) of the detailed information display interface, and the human-computer interaction interface 301c can be covered on the detailed information display interface in the details page.

[0094] For example, the human-computer interaction interface 301c may include an interactive content display area 302c for displaying the interactive content between the user and the agent. The interactive content may include the user's question information about the current multimedia content and the agent's reply information to the question information.

[0095] For example, the human-computer interaction interface 301c may include a candidate question information display area 303c for displaying at least one candidate question information about the current multimedia content. Exemplarily, in response to the user selecting one of the candidate question information, the candidate question information may be displayed in the interactive content display area 302c; the agent responds to the candidate question information, and the response information is displayed in the interactive content display area 302c.

[0096] For example, the human-computer interaction interface 301c may include a pop-up window control. Figure 3c The double arrow control in is used to display the human-computer interaction interface 301c in full screen; Figure 3c The ×-shaped control in the figure is used to close the human-computer interaction interface 301c and restore the detailed information display interface covered by it.

[0097] like Figure 3d As shown, in response to the user triggering operation of the interactive control 33a in the detail page of any of the above embodiments, the page jumps from the detail page of the multimedia content to the user and the agent interaction page, and displays the human-computer interaction interface in the interaction page. For example, the human-computer interaction interface may include a multimedia content display area 31d for displaying the current multimedia content (image information, theme information, etc.).

[0098] For example, the human-computer interaction interface may include an interactive content display area 32d for displaying the interactive content between the user and the agent. The interactive content may include the user's question information about the current multimedia content and the agent's reply information to the question information.

[0099] In the above embodiment, the user can interact with the publisher in a timely manner with respect to the multimedia content of interest, thereby improving the efficiency of information push.

[0100] Figure 4 A block diagram of a content publishing device according to some embodiments of the present disclosure is shown.

[0101] like Figure 4 As shown, the content publishing device 4 includes: a generation unit 41, which is used to generate multimedia content to be published by the intelligent agent based on the acquired network information, and the multimedia content includes related content generated based on the network information and key information in the network information; a publishing unit 42, which is used to publish the multimedia content; a display unit 43, which is used to display the human-computer interaction interface of the intelligent agent in response to the user's interactive request for the multimedia content; an interactive unit 44, which is used to realize the interaction between the user and the intelligent agent based on the multimedia content in the human-computer interaction interface.

[0102] In some embodiments, the key information includes keywords and / or image information extracted from network information, and the related content includes topic information generated based on the key information using a machine learning model.

[0103] In some embodiments, the display unit 43 displays detailed information of the multimedia content in response to a user's selection operation on the multimedia content, and displays a human-computer interaction interface in response to a user's initiation of an interactive operation on the detailed information.

[0104] In some embodiments, the interaction unit 44 generates reply information according to the detailed information and the question information in response to the user inputting question information related to the detailed information in the human-computer interaction interface, and feeds back the reply information to the user in the human-computer interaction interface.

[0105] In some embodiments, candidate question information for user selection is displayed in the human-computer interaction interface, and the candidate question information is generated based on historical question information for multimedia content and / or generated based on key information using a machine learning model.

[0106] In some embodiments, the display unit 43 displays the human-computer interaction interface in a window in the details page of the multimedia content, or jumps from the details page of the multimedia content to the interaction page between the user and the agent, and displays the human-computer interaction interface in the interaction page.

[0107] In some embodiments, the detailed information includes summary information generated using a machine learning model based on the network information.

[0108] 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.

[0109] In some embodiments, in response to the network information including the video information, the display unit 43 plays the video information in the detail page of the multimedia content.

[0110] In some embodiments, the publishing unit 44 publishes the multimedia content as dynamic content recommended by the agent in the network community.

[0111] In some embodiments, the publishing unit 44 adds the multimedia content to a push information stream, and the push information stream includes multiple multimedia contents from different publishers.

[0112] In the above embodiment, the network information is processed by the agent to generate multimedia content for users to browse, and the agent can interact with the user on the multimedia content. In this way, it is not only helpful to quickly filter out the network information of interest from the massive network information, but also to provide an interactive interface for further understanding of the network information, thereby improving the efficiency of information push. In addition, the user can interact with the publisher in a timely manner on the multimedia content of interest, thereby improving the efficiency of information push.

[0113] Figure 5 A block diagram of a content publishing device according to some other embodiments of the present disclosure is shown.

[0114] like Figure 5 As shown, the content publishing device 5 of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51, and the processor 52 is configured to execute the content publishing method in any embodiment of the present disclosure based on the instructions stored in the memory 51.

[0115] The memory 51 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, a database, and other programs.

[0116] Figure 6 A block diagram of a content publishing device according to some further embodiments of the present disclosure is shown.

[0117] like Figure 6 As shown, the content publishing device 6 of this embodiment includes: a memory 610 and a processor 620 coupled to the memory 610 , and the processor 620 is configured to execute the method in any one of the aforementioned embodiments based on the instructions stored in the memory 610 .

[0118] The memory 610 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0119] The content publishing device 6 may also include an input / output interface 630, a network interface 640, a storage interface 650, etc. These interfaces 630, 640, 650, the memory 610, and the processor 620 may be connected, for example, via a bus 660. The input / output interface 630 provides a connection interface for input / output devices such as a display, a mouse, a keyboard, a touch screen, a microphone, and a speaker. The network interface 640 provides a connection interface for various networked devices. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a USB flash drive.

[0120] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] So far, 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. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0122] The method and system of the present disclosure may be implemented in many ways. For example, the method and system of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0123] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A content publishing method, comprising: Generate multimedia content to be published by the agent according to the acquired network information, wherein the multimedia content includes 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 intelligent agent; In the human-computer interaction interface, the interaction between the user and the intelligent agent is realized based on the multimedia content.

2. The content publishing method according to claim 1, wherein: The key information includes keywords and / or image information extracted from the network information, and the related content includes topic information generated using a machine learning model based on the key information.

3. The content publishing method according to claim 1, wherein: The human-computer interaction interface for displaying the intelligent agent comprises: In response to a user's selection operation on the multimedia content, displaying detailed information of the multimedia content; In response to the user initiating an interactive operation on the detailed information, the human-computer interaction interface is displayed.

4. The content publishing method according to claim 3, wherein: The realizing 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 on the human-computer interaction interface, generating reply information according to the detailed information and the question information; In the human-computer interaction interface, the reply information is fed back to the user.

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

6. The content publishing method according to claim 3, wherein: The displaying of the human-computer interaction interface comprises: In the details page of the multimedia content, the human-computer interaction interface is displayed in a window; or Jump from the details page of the multimedia content to the interaction page between the user and the agent, and display the human-computer interaction interface in the interaction page.

7. The content publishing method according to claim 3, wherein: The detailed information includes summary information generated by using a machine learning model based on the network information.

8. The content publishing method according to claim 3, wherein: The detailed information includes at least one of link information, image information, video information, and text information related to the network information.

9. The content publishing method according to claim 3, wherein: The displaying of detailed information of the multimedia content includes: In response to the network information including video information, the video information is played in the detail page of the multimedia content.

10. The content publishing method according to any one of claims 1 to 9, wherein: The publishing of the multimedia content comprises: In the network community, the multimedia content is published as dynamic content recommended by the intelligent agent.

11. The content publishing method according to any one of claims 1 to 9, wherein: The publishing of the multimedia content comprises: The multimedia content is added to a push information flow, wherein the push information flow includes a plurality of multimedia contents from different publishers.

12. A content publishing device, comprising: A generating unit, configured to generate multimedia content to be published by the agent according to the acquired network information, wherein the multimedia content includes relevant content generated according to the network information and key information in the network information; A publishing unit, used for publishing the multimedia content; A display unit, configured to display a human-computer interaction interface of the agent in response to a user's request for interaction with the multimedia content; An interaction unit is used to realize the interaction between the user and the intelligent agent based on the multimedia content in the human-computer interaction interface.

13. A content publishing device, comprising: Memory; and A processor coupled to the memory, wherein the processor is configured to execute the content publishing method according to any one of claims 1 to 11 based on instructions stored in the memory.

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

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

Images