CN116628313A

CN116628313A - Content recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN116628313A
Application number: CN202310344133.XA
Authority: CN
Inventors: 秦首科; 王海涛; 邓天生; 李涛
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-03-31
Filing date: 2023-03-31
Publication date: 2023-08-22

Abstract

The disclosure provides a content recommendation method and device, electronic equipment and a storage medium, relates to the technical field of artificial intelligence, and particularly relates to the technical field of intelligent recommendation and conversational recommendation. The implementation scheme is as follows: acquiring recommendation requirement information input by a user in a recommendation interface of client equipment, wherein the recommendation interface displays at least one first content recommended to the user; determining a first topic of current interest to the user based on the recommendation demand information; determining at least one second content to be recommended to the user based on the first topic; and returning the at least one second content to the client device.

Description

Content recommendation method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence, and in particular, to the field of intelligent recommendation and conversational recommendation technologies, and in particular, to a content recommendation method and apparatus, an electronic device, a computer readable storage medium, and a computer program product.

Background

Artificial intelligence (Artificial Intelligence, AI) is the discipline of studying the process of making a computer to simulate certain mental processes and intelligent behaviors of a person (e.g., learning, reasoning, thinking, planning, etc.), both hardware-level and software-level techniques. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge graph technology and the like.

The recommendation system is used for screening out content which is possibly interested by the user from the mass data and pushing the content to the user. At present, a recommendation system is widely applied to various scenes such as news information recommendation, commodity recommendation, audio and video recommendation, advertisement delivery, social friend recommendation and the like.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, the problems mentioned in this section should not be considered as having been recognized in any prior art unless otherwise indicated.

Disclosure of Invention

The present disclosure provides a content recommendation method and apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a content recommendation method including: displaying at least one first content recommended to the user in a recommendation interface; acquiring recommendation demand information input by the user in the recommendation interface; acquiring at least one second content to be recommended to the user based on the recommendation requirement information, wherein the at least one second content is determined based on a first topic of current interest of the user, and the first topic is determined based on the recommendation requirement information; and displaying the at least one second content in the recommendation interface.

According to an aspect of the present disclosure, there is provided a content recommendation method including: acquiring recommendation requirement information input by a user in a recommendation interface of client equipment, wherein the recommendation interface displays at least one first content recommended to the user; determining a first topic of current interest to the user based on the recommendation demand information; determining at least one second content to be recommended to the user based on the first topic; and returning the at least one second content to the client device.

According to an aspect of the present disclosure, there is provided a content recommendation apparatus including: a first display module configured to display at least one first content recommended to a user in a recommendation interface; the first acquisition module is configured to acquire recommendation requirement information input by the user in the recommendation interface; a second acquisition module configured to acquire at least one second content to be recommended to the user based on the recommendation demand information, wherein the at least one second content is determined based on a first topic of current interest to the user, the first topic being determined based on the recommendation demand information; and a second presentation module configured to present the at least one second content in the recommendation interface.

According to an aspect of the present disclosure, there is provided a content recommendation apparatus including: the system comprises a first acquisition module, a second acquisition module and a first display module, wherein the first acquisition module is configured to acquire recommendation requirement information input by a user in a recommendation interface of client equipment, and the recommendation interface displays at least one first content recommended to the user; a first determination module configured to determine a first topic of current interest to the user based on the recommendation demand information; a second determination module configured to determine at least one second content to be recommended to the user based on the first topic; and a return module configured to return the at least one second content to the client device.

According to an aspect of the present disclosure, there is provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the above aspects.

According to an aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of the above aspects.

According to an aspect of the present disclosure, there is provided a computer program product comprising computer program instructions which, when executed by a processor, implement the method of any of the above aspects.

According to one or more embodiments of the present disclosure, a dynamic demand of a user can be obtained through a dialogue manner, and a recommended content for the user is adjusted in real time according to the dynamic demand, so that the recommended content meets the user's desire, and accurate recommendation for the user is achieved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The accompanying drawings illustrate exemplary embodiments and, together with the description, serve to explain exemplary implementations of the embodiments. The illustrated embodiments are for exemplary purposes only and do not limit the scope of the claims. Throughout the drawings, identical reference numerals designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, in accordance with an embodiment of the present disclosure;

FIG. 2 illustrates a flow chart of a content recommendation method according to some embodiments of the present disclosure;

3A-3H illustrate schematic diagrams of recommendation interfaces, according to embodiments of the present disclosure;

FIG. 4 illustrates a flow chart of a content recommendation method according to further embodiments of the present disclosure;

FIG. 5 shows a schematic diagram of a content recommendation process according to an embodiment of the present disclosure;

FIG. 6 illustrates a block diagram of a content recommendation device, according to some embodiments of the present disclosure;

FIG. 7 is a block diagram illustrating a content recommendation device according to further embodiments of the present disclosure; and

fig. 8 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, the use of the terms "first," "second," and the like to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, unless otherwise indicated, and such terms are merely used to distinguish one element from another element. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on the description of the context.

The terminology used in the description of the various illustrated examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, the elements may be one or more if the number of the elements is not specifically limited. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

In the related art, a recommendation system recommends content for a user according to the historical behavior of the user, and the dynamic requirements of the user cannot be captured, so that the recommendation result does not accord with the user expectation.

In view of the above problems, the embodiments of the present disclosure provide a content recommendation method, which can obtain a dynamic requirement of a user through a dialogue manner, and adjust a recommended content for the user in real time according to the dynamic requirement, so that the recommended content meets a user's desire, and accurate recommendation for the user is achieved. Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented, in accordance with an embodiment of the present disclosure. Referring to fig. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the client devices 101, 102, 103, 104, 105, and 106 and the server 120 may run one or more services or software applications that enable execution of the content recommendation method.

In some embodiments, server 120 may also provide other services or software applications, which may include non-virtual environments and virtual environments. In some embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof that are executable by one or more processors. A user operating client devices 101, 102, 103, 104, 105, and/or 106 may in turn utilize one or more client applications to interact with server 120 to utilize the services provided by these components. It should be appreciated that a variety of different system configurations are possible, which may differ from system 100. Accordingly, FIG. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The client devices 101, 102, 103, 104, 105, and/or 106 may provide interfaces that enable a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that the present disclosure may support any number of client devices.

Client devices 101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, vehicle-mounted devices, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and the like. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, appli os, UNIX-like operating systems, linux, or Linux-like operating systems; or include various mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, windows Phone, android. Portable handheld devices may include cellular telephones, smart phones, tablet computers, personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays (such as smart glasses) and other devices. The gaming system may include various handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a number of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. For example only, the one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a blockchain network, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, wi-Fi), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture that involves virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain virtual storage devices of the server). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above as well as any commercially available server operating systems. Server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of client devices 101, 102, 103, 104, 105, and/or 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and/or 106.

In some implementations, the server 120 may be a server of a distributed system or a server that incorporates a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. The cloud server is a host product in a cloud computing service system, so as to solve the defects of large management difficulty and weak service expansibility in the traditional physical host and virtual private server (VPS, virtual Private Server) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of databases 130 may be used to store information such as audio files and video files. Database 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. Database 130 may be of different types. In some embodiments, the database used by server 120 may be, for example, a relational database. One or more of these databases may store, update, and retrieve the databases and data from the databases in response to the commands.

In some embodiments, one or more of databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key value stores, object stores, or conventional stores supported by the file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

For purposes of embodiments of the present disclosure, in the example of FIG. 1, client devices 101-106 may include a client application for content browsing, through which a user may browse corresponding content. The content browsed by the user can be news information, audio and video, commodity information and the like, and correspondingly, the client application can be a news information application, an audio and video entertainment application, a shopping application and the like. The client application may exist in the client device in a variety of ways. For example, the client application may be an application program that needs to be downloaded and installed before running, a website that is accessible through a browser, a lightweight applet that runs in a host application, and so on.

The server 120 may be a server corresponding to a client application for content browsing in the client device, accordingly. The server 120 may include a service program that may provide a content browsing service to users based on content information (including titles, drawings, text, authors, types, interactions (e.g., praise, comment, forward, etc.) of the content, etc., stored in the database 130.

According to some embodiments, the server 120 may comprise a recommendation system (essentially a computer program). The recommender system may determine content that may be of interest to the user (i.e., recommended content) based on the user's historical behavior, user portraits, etc., and transmit such content to the client devices 101-106. After receiving the first content, the client device 101-106 presents the recommended content to the user through a recommendation interface in the client application. According to the embodiment of the disclosure, a user can talk with a recommendation system in a recommendation interface to express current recommendation demand information while browsing first content in the recommendation interface. The recommendation system captures the current interest points of the user based on the recommendation demand information input by the user, and adjusts the recommendation content in real time according to the current interest points, so that the recommendation content meets the user expectations, and accurate recommendation of the user is realized.

Fig. 2 shows a flowchart of a content recommendation method 200 according to an embodiment of the present disclosure. The subject of execution of the various steps of method 200 is a client device (e.g., client devices 101-106 shown in FIG. 1).

As shown in fig. 2, the method 200 includes steps S210-S240.

In step S210, at least one first content recommended to the user is presented in a recommendation interface.

In step S220, recommendation requirement information input by the user in the recommendation interface is acquired.

In step S230, at least one second content to be recommended to the user is acquired based on the recommendation demand information. The at least one second content is determined based on a first topic of current interest to the user, the first topic being determined based on the recommendation requirement information.

In step S240, the at least one second content is presented in the recommendation interface.

According to embodiments of the present disclosure, a user may directly talk to a recommendation system in a recommendation interface while browsing recommended content (i.e., first content). Therefore, the user can express the recommendation requirement of the user in real time while guaranteeing the immersive recommendation experience of the user. The recommendation demand information input by the user can enable the recommendation system to capture the current interest point (namely the first topic) of the user, and the recommendation content (namely the second content) is adjusted in real time according to the current interest point (namely the first topic), so that the recommendation content meets the user expectation, and accurate recommendation to the user is achieved.

According to the embodiment of the disclosure, since the user performs a dialogue with the recommendation system in the recommendation interface, the dialogue content input by the user is the recommendation requirement of the user, and therefore the current interest point of the user can be directly extracted from the dialogue content without combining other information (such as dialogue environment information, preferences of similar users, topic knowledge graphs and the like).

The steps of method 200 are described in detail below.

The recommendation interface is a graphical user interface (Graphical User Interface, GUI) for presenting recommended content, which may be interacted with by a user. In an embodiment of the present disclosure, the first content, the second content, and the third content are all recommended content.

According to some embodiments, the at least one first content may be derived based on historical behavioral information of the user and the user representation. The user representation includes a series of attribute tags for the user, such as gender, age, topics of preference, and the like.

It should be noted that, the at least one first content may be obtained by any recommendation method, and the present disclosure is not limited to the obtaining manner of the at least one first content. For example, the at least one first content may be recommended content obtained through a recall, coarse ranking, fine ranking, rearrangement, etc. recommendation phase based on historical behavioral information of the user and the user representation.

The recommendation interface may present the at least one first content by means of a feed stream. In embodiments of the present disclosure, a feed stream refers to a recommended information stream that is continuously updated and presented to a user. In response to a user performing a page refresh operation (e.g., a slide up and down, click, etc.) in the recommendation interface, the recommendation interface will retrieve the next batch of first content (e.g., from a cache of the client device, or from a server) and present it to the user. As the user continues to perform page refresh operations, the first content in the recommendation interface is continuously updated, thereby providing a continuous, immersive recommendation experience to the user.

It should be noted that, in the embodiment of the present disclosure, the recommendation interface may display at least one first content in any arrangement, for example, single column (as shown in fig. 3A-3G), double column (as shown in fig. 3H), and so on. Embodiments of the present disclosure do not limit the arrangement of at least one first content in the recommendation interface.

In the embodiment of the disclosure, a user can perform a dialogue with a recommendation system in a recommendation interface to express current recommendation requirement information.

According to some embodiments, the recommendation interface may include a dialog component. The recommendation requirement information may be spontaneously entered by the user through interactive operation of the dialog component. Accordingly, the client device can acquire the recommendation requirement information input by the user in response to the interactive operation of the dialogue component by the user.

The dialog component may be, for example, an icon in a recommendation interface. The user can input the current recommendation requirement information by performing interactive operation (such as clicking, long-pressing and the like) on the icon. It should be noted that, embodiments of the present disclosure do not limit a specific manner in which the user inputs the recommendation requirement information. For example, the recommendation requirement information may be input by any means such as text, expression, voice, gesture, etc.

According to some embodiments, the recommendation requirement information may be entered by a user in response to a guide in the recommendation interface. For example, the recommendation interface may output a guide at a certain time to guide the user to express his own recommendation needs. Under the guidance of the guide language, the user can input the recommendation requirement information of the user in the recommendation interface. Similar to the user's spontaneous input of the recommendation requirement information, the user may also input the recommendation requirement information in response to the guide by interacting with a dialog component in the recommendation interface.

According to some embodiments, the output opportunity of the guidance language may be determined according to behavior information of the user.

According to some embodiments, behavior information of a user on at least one first content may be obtained. The behavior information includes, for example, the number of times the user refreshes the recommended interface, the number of first contents displayed by the recommended interface, the click condition of the user on the first contents, the browsing duration, and the like.

The degree of interest of the user in the at least one first content may be identified based on the behavior information of the user. For example, if the user refreshes the recommendation interface multiple times (i.e., the number of refreshes is greater than or equal to the first threshold) without clicking on any of the first content, or if the user's click rate on the first content is small (i.e., the ratio of the number of first content clicked to the number of first content already presented is less than the second threshold), the user may be deemed to be not interested in at least one first content already recommended. For another example, if the click rate of the at least one first content by the user gradually decreases, e.g., from 20% to 10%, the user's interest level in the at least one first content may be considered to gradually decrease.

In other embodiments, a trained machine learning model may also be utilized to identify a degree of interest of a user in at least one first content. Specifically, behavior information of the user may be input into the machine learning model to obtain a recognition result of the degree of interest output by the machine learning model.

According to some embodiments, the step of identifying the degree of interest of the user in the at least one first content may be performed locally at the client device. That is, the client device identifies a degree of interest of the user in the at least one first content based on the acquired behavior information. In other embodiments, the step of identifying the degree of interest of the user in the at least one first content may also be performed by the server. That is, the client device acquires behavior information of the user, and transmits the behavior information to the server so that the server identifies a degree of interest of the user in at least one first content according to the behavior information.

According to some embodiments, a guide for obtaining recommendation requirement information is output in the recommendation interface in response to the behavior information of the user indicating that the user is not interested in or is less interested in the at least one first content. According to the embodiment, when the click intention of the user is perceived to be reduced, the dialogue is triggered by outputting the guide language in the recommendation interface, and the user is guided to express the recommendation requirement of the user, so that the recommendation system can timely adjust the recommendation content according to the recommendation requirement of the user, and the recommendation content meets the user expectation.

The guide may be generated locally at the client device, or may be generated by the server and returned to the client device.

The guiding language is used for guiding the user to express the self recommendation requirement. According to some embodiments, the guidance language may be generated using a trained dialog model. The conversation model may also be referred to as a "chat robot". The dialogue model is a model which is obtained based on a large amount of natural corpus training and can perform natural and smooth dialogue with a user. By inputting at least the behavior information of the user into the trained dialog model, a guidance language output by the dialog model can be obtained, which corresponds to the response of the dialog model to the behavior information of the user. Spoken guidance can be generated using a dialog model. The guiding language sentence is smooth and ideographic, and can better guide the user to express the self recommendation requirement.

According to some embodiments, only the current behavior information of the user can be input into the dialogue model to obtain the guide language; the current behavior information of the user and the user portrait can be input into the dialogue model together to obtain the guidance.

According to some embodiments, the guide is a summary of the user's current behavioral information. The second topic that the user may be currently interested in, as determined based on the user's behavioral information, may be included in the guide. The second topic may be any physical label such as movie name, actor name, song name, etc. From the second topic, at least one third content of interest to the user may be determined.

Accordingly, at least one third content may be presented in the recommendation interface after the recommendation interface outputs the guide and before the user inputs the recommendation requirement information. That is, the at least one third content is located after the guide in the recommendation interface. According to the embodiment, the recommended content (i.e., the third content) can be updated according to the currently mined possible interest points (i.e., the second topics) of the user while waiting for the user to feed back the recommended demand, so that the possibility that the recommended content hits the user's interest is improved, and the satisfaction degree of the user on the recommended content is improved.

According to some embodiments, a candidate set (i.e., recall set) of third content may be derived based on the second topic. The candidate third content in the candidate set may have the same or similar topic tag as the second topic. Further, a degree of matching of each candidate third content in the candidate set to the user may be determined using the trained degree of matching prediction model. And sequencing the candidate third contents (according to the sequence of the matching degree from high to low) based on the matching degree of the candidate third contents and the user, so as to obtain at least one third content to be recommended to the user.

According to some embodiments, at least the topic tag of each candidate third content and the second topic that may be of interest to the user may be input into the matching degree prediction model, so as to obtain the matching degree between the candidate third content output by the matching degree prediction model and the user. Specifically, only the topic tag and the second topic may be input into the matching degree prediction model, or other information of the user and the candidate third content may be further input into the matching degree prediction model on the basis of the topic tag and the second topic. For example, the current behavior information, the historical behavior information, the user portrait, the second topic which may be interested in, the attribute information (such as name, author, description information, etc.) of the candidate third content, and the topic label of the showing/clicking information (such as showing amount, clicking amount, etc.) are input into the matching degree estimation model, so as to obtain the matching degree output by the matching degree estimation model.

According to some embodiments, the step of determining the at least one third content may be performed locally at the client device, i.e. the client device invokes a matching degree prediction model based on the second topic to obtain the at least one third content to be recommended to the user. In other embodiments, the step of determining the at least one third content may also be performed by the server, that is, the server invokes a matching degree prediction model based on the second topic to obtain the at least one third content to be recommended to the user, and returns the at least one third content to the client device for presentation.

After the recommended interface outputs the guide (if at least one third content is also output, at least one third content is output), the recommended need information expressed by the user under the guidance of the guide may be acquired.

In steps S230 and S240, at least one second content to be recommended to the user is acquired based on the recommendation demand information, and the at least one second content is displayed in the recommendation interface.

In embodiments of the present disclosure, a first topic of current interest to a user may be determined based on recommended needs information of the user. Further, based on the first topic, at least one second content to be recommended to the user may be determined.

It should be noted that the steps of determining the first topic and determining the at least one second content described above may be performed locally at the client device, i.e. the client device determines the second topic and the at least one second content based on the recommendation requirement information. And the recommendation interface acquires the at least one second content and displays the second content. The steps of determining the first topic and determining the at least one second content may also be performed by the server, i.e. the server determines the second topic and the at least one second content based on the recommendation requirement information and sends the at least one second content to the client device so that the recommendation interface obtains and presents the at least one second content.

According to some embodiments, at least the recommended need information may be input into the trained dialog model to derive a first topic of dialog model output. According to some embodiments, at least one of the user portrait, the current behavior information of the user, and the historical behavior information may be input into the dialogue model together with the recommendation requirement information to obtain a first topic output by the dialogue model.

According to some embodiments, a plurality of candidate content may be obtained based on the first topic. Each candidate content has a corresponding topic label, and the topic label is the same as or similar to the first topic. For each candidate content, a degree of matching of the candidate content to the user may be determined based on its topic tag and the first topic. And ordering the plurality of candidate contents according to the matching degree to obtain at least one second content to be recommended to the user.

According to some embodiments, at least the first topic and the topic tag may be input into a trained matching degree prediction model to obtain a matching degree of candidate content output by the matching degree prediction model and the user. Further, at least one of current behavior information, historical behavior information, user portrait, attribute information (such as name, author, description information, etc.) of candidate third content, and display/click information (such as display amount, click amount, etc.) of the user may be input into the matching degree prediction model together with the first topic and the topic tag, so as to obtain the matching degree outputted by the matching degree prediction model.

The matching degree estimation model can be obtained through training in a reinforcement learning mode. In the reinforcement learning process, the content in which the first topic matches the topic tag and the user has a positive behavior (e.g., click, praise, comment, collection, etc.) is taken as a positive example.

Fig. 3A-3D illustrate schematic diagrams of recommendation interfaces 300A-300D according to embodiments of the present disclosure. The recommendation interfaces 300A-300D depict the process by which a user actively dialogues with a recommender system to update their recommended content.

As shown in FIG. 3A, the recommendation interface 300A includes first content 302, 304, and 306 presented in a single column feed stream. Because of the limited size of the recommendation interface 300A, the first content 306 is only partially displayed and not fully displayed. The bottom of the recommendation interface 300A is provided with a conversation component 350, a video component 352, and a user component 354. The user may implement the corresponding functionality by clicking on the components 350-354.

The user clicks the dialogue component 350 in the recommendation interface 300A, which can trigger a dialogue with the recommendation system and input his own recommendation requirement information. For example, the recommendation requirement information entered by the user may be "do not interest the above content, come to me for a content bar related to television show a".

The recommendation requirement information entered by the user may be presented after the last recommended content in the recommendation interface 300A, i.e., after the first content 306, thereby obtaining the recommendation interface 300B.

As shown in fig. 3B, in the recommendation interface 300B, the first content 306 is followed by recommendation requirement information 308 of the user: "do not interest in the above content, let me come to point to the content bar related to television show a". Note that "me" in the interface 300B refers to the user.

The dialogue model may be responsive to the user's recommended needs information 308 to extract therefrom the first topic of current interest to the user as "television show a". Further, based on the first topic "television drama a", matching degrees of the plurality of candidate contents and the user can be estimated by using a matching degree estimation model. The plurality of candidate contents are ranked according to the degree of matching, the second contents 310 and 312 recommended to the user are determined, and the second contents 310 and 312 are presented in the recommendation interface 300C. As shown in fig. 3C, the second content 310 and 320 is located after the user's recommended need information 308.

Further, as shown in fig. 3D, after pushing the second content 310 and 312 to the user, the recommender system may further generate a response 314 "above the scenario profile and playout time that recommended a to you and reviewing the classical segments in a, to which is satisfied? ", and the answer 314 is presented in the recommendation interface 300D. Note that the "machine" in the interface 300D refers to a chat robot, i.e., a conversation model.

Fig. 3E-3G illustrate schematic diagrams of recommendation interfaces 300E-300G according to embodiments of the present disclosure. The recommendation interfaces 300E-300G depict the process by which a user can update their recommended content by talking to them under the direction of a chat bot.

As shown in fig. 3E, in response to the user not being interested in the first content 320 or being interested in a reduced degree as compared to the previous first content, the dialog model generates a guide 322 for guiding the user to express the recommendation requirement based on the user's behavior information and the user portraits in the recommendation interface 300E, and outputs it to the recommendation interface 300E.

The inputs and outputs of the dialog model are, for example, as follows:

input: user portrayal: men and young people like movies and television, cartoon; behavior information: recently clicked on the content: XXX (the name of the color in the second part of film B) shows that three children are not in the eyes, and the dog is afraid of getting next to the leg

Output (guide 322): it can be seen that you are interested in the second part of movie B, and you are recommended to the scenario introduction and the latest information of the second part of movie B

In the above embodiment, the guide 322 includes the second topic "movie B second part" that the dialog model predicts that the user may be interested in based on the behavior information of the user.

Further, the recommendation system may derive a plurality of candidate third content based on a second topic "movie B second portion" that may be of interest to the user. And predicting the matching degree of the plurality of candidate third contents and the user by using the matching degree prediction model, sequencing, determining third contents 324 and 326 to be recommended to the user, and displaying the third contents 324 in the recommendation interface 300E. With a refresh operation (e.g., a gesture operation of sliding up or down in the screen) by the user in the recommended interface 300E, the recommended interface 300F shown in fig. 3F is obtained. In the recommendation interface 300F, third content 326 is also presented.

As shown in fig. 3F, the user may input a response to the guide 322, i.e., the user's recommended need information 328, by interoperating with the dialogue component 350: "one would like to see the first highlight of movie B" in good touch.

The recommender system inputs the recommendation requirement information 328 into the dialog model to obtain the first topic of interest to the user, the "movie B first". Further, based on the first topic "movie B first portion", the matching degree of the plurality of candidate contents and the user is estimated and ranked by using the matching degree estimation model, and the second content 330 recommended to the user is determined and displayed in the recommendation interface 300G, as shown in fig. 3G.

According to some embodiments (not shown in fig. 3E-3G), the dialog model has the ability to discern whether the user's language is violated. If the user language is judged to be illegal, the recommendation requirement of the user is refused.

For example, for a guidance language output by a dialogue model, the recommended need information input by the user and the subsequent response of the dialogue model are as follows:

model (guide): it is seen that you are interested in movie B second, and you are recommended scenario introduction and up-to-date information of movie B second.

User (initial recommended need information): i do not want to see the passion video and have sexy beauty.

Model (reject initial recommended demand information): sorry, i cannot provide any inappropriate or unscrupulous content as an intelligent robot. You can be recommended the content of natural scenery.

User (new recommended need information): OK, recommending some natural wind and light content bars to me.

Model (accept new recommended demand information): preferably, you are next recommended some natural scenery content.

In the dialogue, the model identifies a first title of current interest of the user as 'natural wind and light', determines second content related to the 'natural wind and light', and displays the second content to the user through a recommendation interface.

FIG. 3H illustrates a schematic diagram of a recommendation interface 300H, according to an embodiment of the present disclosure. Unlike the previously described recommendation interfaces 300A-300G, the recommendation interface 300H presents recommended content in a double-row feed stream.

In interface 300H, the user enters recommendation need information 340 "help me recommend news related to some actor C" by interacting with dialog component 350. The recommender system determines a first topic of interest to the user, actor C, based on the recommendation demand information 340, further determines news content (second content) 342, 344, and 346 related to actor C, and presents it to the user.

Corresponding to the content recommendation method 200 performed by the client device described above, embodiments of the present disclosure also provide a content recommendation method 400 performed by a server. It is understood that the content recommendation method 400 corresponds to the steps of the content recommendation method 200.

Fig. 4 shows a flowchart of a content recommendation method 400 according to an embodiment of the present disclosure. As shown in fig. 4, the method 400 includes steps S410-S440.

In step S410, recommendation requirement information input by a user in a recommendation interface of a client device is obtained, wherein the recommendation interface displays at least one first content recommended to the user.

In step S420, a first topic of current interest to the user is determined based on the recommendation requirement information.

In step S430, at least one second content to be recommended to the user is determined based on the first topic.

In step S440, the at least one second content is returned to the client device.

According to the embodiment of the disclosure, when the user browses the first content, the user can directly conduct a dialogue with the recommendation system in the recommendation interface. Therefore, the user can express the recommendation requirement of the user in real time while guaranteeing the immersive recommendation experience of the user. The recommendation system can capture the current interest points (namely, the first topics) of the user according to the recommendation demand information input by the user, and adjust the recommendation content (namely, the second content) in real time according to the current interest points, so that the recommendation content meets the user expectations, and accurate recommendation to the user is realized.

The recommendation requirement information may be collected by a recommendation interface and sent to a server via a client device.

According to some embodiments, the method 400 further comprises: acquiring behavior information of the user on the at least one first content; generating a guide for acquiring the recommendation requirement information based on the behavior information in response to the behavior information indicating that the user is not interested in or is less interested in the at least one first content; and sending the guidance language to the client device.

According to some embodiments, the behavior information of the user on the at least one first content may include a number of times the user refreshes the recommendation interface, a number of first content presented by the recommendation interface, a click condition of the user on the first content, a browsing duration, and the like.

The degree of interest of the user in the at least one first content may be determined based on the behavior information of the user. For example, if the user refreshes the recommendation interface multiple times (i.e., the number of refreshes is greater than or equal to the first threshold) without clicking on any of the first content, or if the user's click rate on the first content is small (i.e., the ratio of the number of first content clicked to the number of first content already presented is less than the second threshold), the user may be deemed to be not interested in at least one first content already recommended. For another example, if the click rate of the at least one first content by the user gradually decreases, e.g., from 20% to 10%, the user's interest level in the at least one first content may be considered to gradually decrease.

In other embodiments, a trained machine learning model may also be utilized to determine a degree of user interest in at least one first content. Specifically, behavior information of the user may be input into the machine learning model to obtain a recognition result of the degree of interest output by the machine learning model.

In response to the behavior information of the user indicating that the user is not interested in or is less interested in the at least one first content, a guide for the user to obtain recommendation requirement information of the user is generated based on the behavior information. Further, the guidance is sent to the client device so that the client device outputs the guidance into the recommendation interface. According to the embodiment, when the click intention of the user is perceived to be reduced, the dialogue is triggered by outputting the guide language in the recommendation interface, and the user is guided to express the recommendation requirement of the user, so that the recommendation system can timely adjust the recommendation content according to the recommendation requirement of the user, and the recommendation content meets the user expectation.

According to some embodiments, the method 400 further comprises: before the recommendation requirement information input by the user in a recommendation interface of the client device is acquired, determining at least one third content to be recommended to the user based on the second topic; and transmitting the at least one third content to the client device. According to the embodiment, after the recommendation interface outputs the guide language and waits for the user to feed back the recommendation requirement, the recommendation content (namely, the third content) can be updated according to the currently mined possible interest points (namely, the second topic) of the user, so that the possibility that the recommendation content hits the user interest is improved, and the satisfaction degree of the user on the recommendation content is improved.

In step S420, a first topic of current interest to the user may be determined based on the recommended needs information of the user.

According to some embodiments, a plurality of candidate content may be obtained based on the first topic. Each candidate content has a corresponding topic label, and the topic label is the same as or similar to the first topic. For each candidate content, a degree of matching of the candidate content to the user may be determined based on its topic tag and the first topic. The plurality of candidate contents are ordered (in order of the degree of matching from large to small) based on the degree of matching of each of the plurality of candidate contents, and the at least one second content is determined from the plurality of candidate contents. The at least one second content is a candidate content having a larger matching degree among the plurality of candidate contents.

In step S440, the at least one second content is returned to the client device, so that the client device displays the at least one second content in the recommendation interface.

Fig. 5 shows a schematic diagram of a content recommendation process according to an embodiment of the present disclosure. As shown in fig. 5, a dialog model 522 is used to conduct a deep dialog with a user. Dialog model 522 mines the current real point of interest of the user (i.e., the first topic mentioned above) based on the recommended needs information currently entered by the user, the user portraits stored in the database, and the user historic behavior 532, and feeds the mined point of interest back to recall model 524 and ranking model 526.

Recall model 524 determines candidate content that may be of interest to the user from among the stored mass content 512 based on the user's current points of interest, resulting in candidate set 514 for the user.

Ranking model 526 (i.e., the matching degree prediction model mentioned above) determines the matching degree of each candidate content to the user based on the user's current points of interest, user portraits and user historic behavior 532, related information 534 of the candidate content (including topic labels, titles, authors, descriptive text, presentation amounts, click amounts, etc.). The plurality of candidate content is ranked according to the degree of matching to obtain the recommendation list 516.

The content in the recommendation list 516 (i.e., the second content mentioned above) is pushed in order and presented to the user to get the recommendation results 518 presented to the user.

According to an embodiment of the present disclosure, there is also provided a content recommendation apparatus applied to a client device. Fig. 6 shows a block diagram of a content recommendation device 600 according to an embodiment of the present disclosure. As shown in fig. 6, the apparatus 600 includes a first display module 610, a first acquisition module 620, a second acquisition module 630, and a second display module 640.

The first presentation module 610 is configured to present at least one first content recommended to a user in a recommendation interface.

The first obtaining module 620 is configured to obtain recommendation requirement information input by the user in the recommendation interface.

The second obtaining module 630 is configured to obtain at least one second content to be recommended to the user based on the recommendation requirement information, wherein the at least one second content is determined based on a first topic of current interest to the user, the first topic being determined based on the recommendation requirement information.

The second presentation module 640 is configured to present the at least one second content in the recommendation interface.

According to some embodiments, the recommendation interface includes a dialog component, and wherein the first acquisition module is further configured to: and responding to the interactive operation of the user on the dialogue component, and acquiring the recommendation requirement information input by the user.

According to some embodiments, the apparatus 600 further comprises: a third acquisition module configured to acquire behavior information of the user on the at least one first content; and an output module configured to output a guidance for acquiring the recommendation demand information in the recommendation interface in response to the behavior information indicating that the user is not interested in the at least one first content or the degree of interest is reduced.

According to some embodiments, the guidance includes a second topic determined based on the behavior information that the user is likely to be interested in at the present time, the apparatus further comprising: and a third display module configured to display at least one third content in the recommendation interface before the obtaining of the recommendation requirement information input by the user in the recommendation interface, wherein the at least one third content is determined based on the second topic, and the at least one third content is located after the guide in the recommendation interface.

It should be appreciated that the various modules and units of the apparatus 600 shown in fig. 6 may correspond to the various steps in the method 200 described with reference to fig. 2. Thus, the operations, features and advantages described above with respect to method 200 are equally applicable to apparatus 600 and the modules and units comprising the same. For brevity, certain operations, features and advantages are not described in detail herein.

According to an embodiment of the present disclosure, there is also provided a content recommendation apparatus applied to a server. Fig. 7 shows a block diagram of a content recommendation device 700 according to an embodiment of the present disclosure. As shown in fig. 7, the apparatus 700 includes a first acquisition module 710, a first determination module 720, a second determination module 730, and a return module 740.

The first obtaining module 710 is configured to obtain recommendation requirement information input by a user in a recommendation interface of a client device, wherein the recommendation interface displays at least one first content recommended to the user.

The first determination module 720 is configured to determine a first topic of current interest to the user based on the recommendation requirement information.

The second determination module 730 is configured to determine at least one second content to be recommended to the user based on the first topic.

The return module 740 is configured to return the at least one second content to the client device.

According to some embodiments, the apparatus 700 further comprises: a second acquisition module configured to acquire behavior information of the user on the at least one first content; a guidance module configured to generate a guidance phrase for acquiring the recommendation requirement information based on the behavior information in response to the behavior information indicating that the user is not interested in or is less interested in the at least one first content; and a first transmission module configured to transmit the guidance language to the client device.

According to some embodiments, the guidance module is further configured to: at least the behavioral information is input into a trained dialog model to derive the guidance language output by the dialog model.

According to some embodiments, the guidance includes a second topic that may be of current interest to the user, the apparatus further comprising: a third determining module configured to determine, based on the second topic, at least one third content to be recommended to the user before the obtaining of recommendation requirement information input by the user in a recommendation interface of a client device; and a second transmission module configured to transmit the at least one third content to the client device.

According to some embodiments, the first determination module is further configured to: at least the recommended need information is input into a trained dialog model to derive the first topic output by the dialog model.

According to some embodiments, the second determining module comprises: an acquisition unit configured to acquire a plurality of candidate contents, wherein any one of the plurality of candidate contents has a corresponding topic tag; a first determination unit configured to determine, for any one of the plurality of candidate contents, a degree of matching of the candidate content with the user based on the first topic and the topic tag; and a second determining unit configured to determine the at least one second content from the plurality of candidate contents based on the degree of matching of each of the plurality of candidate contents.

According to some embodiments, the first determining unit is further configured to: inputting at least the first topic and the topic tag into a trained matching degree estimation model to obtain the matching degree output by the matching degree estimation model.

It should be appreciated that the various modules and units of the apparatus 700 shown in fig. 7 may correspond to the various steps in the method 400 described with reference to fig. 4. Thus, the operations, features and advantages described above with respect to method 400 apply equally to apparatus 700 and the modules and units comprising it. For brevity, certain operations, features and advantages are not described in detail herein.

Although specific functions are discussed above with reference to specific modules, it should be noted that the functions of the various modules discussed herein may be divided into multiple modules and/or at least some of the functions of the multiple modules may be combined into a single module.

It should also be appreciated that various techniques may be described herein in the general context of software hardware elements or program modules. The various units described above with respect to fig. 6, 7 may be implemented in hardware or in hardware in combination with software and/or firmware. For example, the units may be implemented as computer program code/instructions configured to be executed in one or more processors and stored in a computer-readable storage medium. Alternatively, these units may be implemented as hardware logic/circuitry. For example, in some embodiments, one or more of the units 610-740 may be implemented together in a System on Chip (SoC). The SoC may include an integrated circuit chip including one or more components of a processor (e.g., a central processing unit (Central Processing Unit, CPU), microcontroller, microprocessor, digital signal processor (Digital Signal Processor, DSP), etc.), memory, one or more communication interfaces, and/or other circuitry, and may optionally execute received program code and/or include embedded firmware to perform functions.

There is also provided, in accordance with an embodiment of the present disclosure, an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor, the memory storing instructions executable by the at least one processor to enable the at least one processor to perform the content recommendation method of an embodiment of the present disclosure.

According to an embodiment of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the content recommendation method of the embodiment of the present disclosure.

There is also provided, in accordance with an embodiment of the present disclosure, a computer program product comprising computer program instructions which, when executed by a processor, implement a content recommendation method of an embodiment of the present disclosure.

Referring to fig. 8, a block diagram of an electronic device 800 that may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile apparatuses, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing apparatuses. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the electronic device 800 includes a computing unit 801 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 802 or a computer program loaded from a storage unit 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

Various components in electronic device 800 are connected to I/O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 may be any type of device capable of inputting information to the electronic device 800, the input unit 806 may receive input numeric or character information and generate key signal inputs related to user settings and/or function control of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone, and/or a remote control. The output unit 807 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, video/audio output terminals, vibrators, and/or printers. The storage unit 808 may include, but is not limited to, magnetic disks, optical disks. The communication unit 809 allows the electronic device 800 to exchange information/data with other devices over computer networks, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth devices, 802.11 devices, wi-Fi devices, wiMAX devices, cellular communication devices, and/or the like.

The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as method 200 and method 400. For example, in some embodiments, the methods 200 and 400 may be implemented as computer software programs tangibly embodied on a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 800 via the ROM 802 and/or the communication unit 809. When a computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of method 200 and method 400 described above may be performed. Alternatively, in other embodiments, computing unit 801 may be configured to perform method 200 or method 400 by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), the internet, and blockchain networks.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially or in a different order, provided that the desired results of the disclosed aspects are achieved, and are not limited herein.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the foregoing methods, systems, and apparatus are merely illustrative embodiments or examples and that the scope of the present disclosure is not limited by these embodiments or examples but only by the claims following the grant and their equivalents. Various elements of the embodiments or examples may be omitted or replaced with equivalent elements thereof. Furthermore, the steps may be performed in a different order than described in the present disclosure. Further, various elements of the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear after the disclosure.

Claims

1. A content recommendation method, comprising:

acquiring recommendation requirement information input by a user in a recommendation interface of client equipment, wherein the recommendation interface displays at least one first content recommended to the user;

Determining a first topic of current interest to the user based on the recommendation demand information;

determining at least one second content to be recommended to the user based on the first topic; and

the at least one second content is returned to the client device.

2. The method of claim 1, further comprising:

acquiring behavior information of the user on the at least one first content;

generating a guide for acquiring the recommendation requirement information based on the behavior information in response to the behavior information indicating that the user is not interested in or is less interested in the at least one first content; and

and sending the guide language to the client device.

3. The method of claim 2, wherein the generating a guide for obtaining the recommended need information based on the behavior information comprises:

at least the behavioral information is input into a trained dialog model to derive the guidance language output by the dialog model.

4. A method according to claim 2 or 3, wherein the guide includes a second topic of possible current interest to the user, the method further comprising:

Before the recommendation requirement information input by the user in a recommendation interface of the client device is acquired, determining at least one third content to be recommended to the user based on the second topic; and

the at least one third content is sent to the client device.

5. The method of any of claims 1-4, wherein the determining, based on the recommendation demand information, a first topic of current interest to the user comprises:

at least the recommended need information is input into a trained dialog model to derive the first topic output by the dialog model.

6. The method of any of claims 1-5, wherein the determining, based on the first topic, at least one second content to be recommended to the user comprises:

obtaining a plurality of candidate contents, wherein any one of the plurality of candidate contents has a corresponding topic label;

for any one of the plurality of candidate content, determining a degree of matching of the candidate content with the user based on the first topic and the topic tag; and

the at least one second content is determined from the plurality of candidate contents based on the degree of matching of each of the plurality of candidate contents.

7. The method of claim 6, wherein the determining, based on the first topic and the topic tag, a degree of matching of the candidate content with the user comprises:

inputting at least the first topic and the topic tag into a trained matching degree estimation model to obtain the matching degree output by the matching degree estimation model.

8. A content recommendation method, comprising:

displaying at least one first content recommended to the user in a recommendation interface;

acquiring recommendation demand information input by the user in the recommendation interface;

acquiring at least one second content to be recommended to the user based on the recommendation requirement information, wherein the at least one second content is determined based on a first topic of current interest of the user, and the first topic is determined based on the recommendation requirement information; and

and displaying the at least one second content in the recommendation interface.

9. The method of claim 8, wherein the recommendation interface comprises a dialog component, and wherein the obtaining recommendation demand information entered by the user in the recommendation interface comprises:

and responding to the interactive operation of the user on the dialogue component, and acquiring the recommendation requirement information input by the user.

10. The method of claim 8, further comprising:

acquiring behavior information of the user on the at least one first content; and

in response to the behavior information indicating that the user is not interested in or is less interested in the at least one first content, a guiding language for acquiring the recommendation requirement information is output in the recommendation interface.

11. The method of claim 10, wherein the guidance includes a second topic determined based on the behavior information that the user is currently likely to be interested in, the method further comprising:

and before the recommendation requirement information input by the user in the recommendation interface is acquired, at least one third content is displayed in the recommendation interface, wherein the at least one third content is determined based on the second topic, and the at least one third content is positioned behind the guide language in the recommendation interface.

12. A content recommendation device, comprising:

the system comprises a first acquisition module, a second acquisition module and a first display module, wherein the first acquisition module is configured to acquire recommendation requirement information input by a user in a recommendation interface of client equipment, and the recommendation interface displays at least one first content recommended to the user;

A first determination module configured to determine a first topic of current interest to the user based on the recommendation demand information;

a second determination module configured to determine at least one second content to be recommended to the user based on the first topic; and

a return module configured to return the at least one second content to the client device.

13. The apparatus of claim 12, further comprising:

a second acquisition module configured to acquire behavior information of the user on the at least one first content;

a guidance module configured to generate a guidance phrase for acquiring the recommendation requirement information based on the behavior information in response to the behavior information indicating that the user is not interested in or is less interested in the at least one first content; and

and the first sending module is configured to send the guide language to the client device.

14. The apparatus of claim 13, wherein the guidance module is further configured to:

15. The apparatus of claim 13 or 14, wherein the guide includes a second topic of possible interest to the user, the apparatus further comprising:

A third determining module configured to determine, based on the second topic, at least one third content to be recommended to the user before the obtaining of recommendation requirement information input by the user in a recommendation interface of a client device; and

and a second sending module configured to send the at least one third content to the client device.

16. The apparatus of any of claims 12-15, wherein the first determination module is further configured to:

17. The apparatus of any of claims 12-16, wherein the second determination module comprises:

an acquisition unit configured to acquire a plurality of candidate contents, wherein any one of the plurality of candidate contents has a corresponding topic tag;

a first determination unit configured to determine, for any one of the plurality of candidate contents, a degree of matching of the candidate content with the user based on the first topic and the topic tag; and

and a second determining unit configured to determine the at least one second content from the plurality of candidate contents based on the degree of matching of each of the plurality of candidate contents.

18. The apparatus of claim 17, wherein the first determination unit is further configured to:

19. A content recommendation device, comprising:

a first display module configured to display at least one first content recommended to a user in a recommendation interface;

the first acquisition module is configured to acquire recommendation requirement information input by the user in the recommendation interface;

a second acquisition module configured to acquire at least one second content to be recommended to the user based on the recommendation demand information, wherein the at least one second content is determined based on a first topic of current interest to the user, the first topic being determined based on the recommendation demand information; and

and a second display module configured to display the at least one second content in the recommendation interface.

20. The apparatus of claim 19, wherein the recommendation interface comprises a dialog component, and wherein the first acquisition module is further configured to:

21. The apparatus of claim 19, further comprising:

a third acquisition module configured to acquire behavior information of the user on the at least one first content; and

and an output module configured to output a guide for acquiring the recommendation requirement information in the recommendation interface in response to the behavior information indicating that the user is not interested in the at least one first content or the degree of interest is reduced.

22. The apparatus of claim 21, wherein the guidance includes a second topic determined based on the behavior information that the user is currently likely to be interested in, the apparatus further comprising:

and a third display module configured to display at least one third content in the recommendation interface before the obtaining of the recommendation requirement information input by the user in the recommendation interface, wherein the at least one third content is determined based on the second topic, and the at least one third content is located after the guide in the recommendation interface.

23. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the method comprises the steps of

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

24. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-11.

25. A computer program product comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1-11.