WO2021160119A1 - 一种信息展示方法及装置 - Google Patents

一种信息展示方法及装置 Download PDF

Info

Publication number
WO2021160119A1
WO2021160119A1 PCT/CN2021/076227 CN2021076227W WO2021160119A1 WO 2021160119 A1 WO2021160119 A1 WO 2021160119A1 CN 2021076227 W CN2021076227 W CN 2021076227W WO 2021160119 A1 WO2021160119 A1 WO 2021160119A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
account
demand
characteristic
multimedia resource
Prior art date
Application number
PCT/CN2021/076227
Other languages
English (en)
French (fr)
Inventor
张昭
李伟佳
杨卓
Original Assignee
北京达佳互联信息技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京达佳互联信息技术有限公司 filed Critical 北京达佳互联信息技术有限公司
Publication of WO2021160119A1 publication Critical patent/WO2021160119A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/435—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/44—Browsing; Visualisation therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Definitions

  • the present disclosure relates to the field of Internet technology, and in particular to an information display method and device.
  • multimedia resources that carry more information can spread quickly and become one of the important channels for people to obtain information.
  • users usually can only obtain the information reflected by the content of the multimedia resources by playing the multimedia resources for viewing.
  • a user is watching the content of a multimedia resource, if the user is triggered to have a need for more information, he needs to continue to search on the Internet and other means.
  • a user is watching a live broadcast of a certain anchor and is interested in the scenic spots in the live broadcast, and wants to obtain travel guides for the scenic spots or book transportation and accommodation to travel to the scenic spots, they need to search for more corresponding information on the Internet by themselves.
  • the present disclosure provides an information display method and device.
  • the technical solutions of the present disclosure are as follows:
  • an information display method including:
  • a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • the obtaining the associated information corresponding to the information demand feature and displaying the associated information to the first account includes:
  • the account characteristic information includes preference information types
  • the preference information type of the first account is determined by the following methods:
  • the display information type within the range is used as the preference information type of the first account.
  • the account characteristic information includes preference information types
  • the preference information type of the first account is determined by the following methods:
  • the preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • the selecting the second account based on the similarity with the first account includes:
  • the account with the highest degree of similarity to the first account is used as the second account.
  • the obtaining the information source address corresponding to the information demand feature includes:
  • At least one information page is obtained by information retrieval according to the information requirement feature, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information requirement feature.
  • the information source address corresponding to the information requirement feature is determined according to a preset mapping relationship between the information requirement feature and the information source address, and the method further includes:
  • the second historical behavior data corresponding to the first account includes: whether the first account views the associated information corresponding to the different information demand characteristics displayed by the client, and/or the first account for the associated information Account feedback.
  • the update condition includes:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • the determining the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information includes:
  • the attribute word set and the feature word set are input into the trained demand recognition model as first input parameters, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the attribute information is determined in the following manner:
  • the content classification information of the multimedia resource is extracted as the attribute information.
  • the attribute information is determined in the following manner:
  • a word segmentation algorithm is used to extract the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource as the attribute information.
  • the attribute information is determined in the following manner:
  • the resource frame image of the multimedia resource is input into a trained image recognition model, and the image content feature of the resource frame image output by the image recognition model is obtained as the attribute information.
  • the obtaining a corresponding feature word set according to the account feature information includes:
  • the preset key information type information that matches the key information type is extracted from the account characteristic information to form a characteristic word set.
  • the detecting the preset operation performed on the played multimedia resource and acquiring the account characteristic information of the first account corresponding to the preset operation includes:
  • the server In response to detecting a preset operation performed on the played multimedia resource through the client, the server acquires account characteristic information of the first account corresponding to the preset operation;
  • the server determines the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information;
  • the acquiring the associated information corresponding to the information demand feature and displaying the associated information to the first account includes:
  • the server obtains the associated information corresponding to the information demand feature, and displays the associated information to the first account through the client.
  • an information display method applied to a server including:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • an information display method applied to a client including:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • an information display system including: a client and a server;
  • the client is configured to send an information acquisition instruction to the server in response to detecting a preset operation performed on the played multimedia resource; receive the associated information returned by the server, and send it to the first account that performs the preset operation Display the related information;
  • the server is configured to, in response to receiving an information acquisition instruction sent by a client, acquire account characteristic information of a first account that implements a preset operation; determine the account characteristic information according to the attribute information of the multimedia resource and the account characteristic information The information demand characteristics of the first account; obtain associated information corresponding to the information demand characteristics, and return the associated information to the client.
  • an information display device applied to a server including:
  • the second information acquisition unit is configured to execute, in response to receiving an information acquisition instruction sent by the client, acquiring account characteristic information of the first account that implements a preset operation, wherein the information acquisition instruction is that the client detects that Triggered after the preset operation performed by the played multimedia resource;
  • the second feature detection unit is configured to perform determining the information demand feature of the first account based on the attribute information of the multimedia resource and the account feature information;
  • the second information display unit is configured to perform acquisition of associated information corresponding to the information demand characteristics, and return the associated information to the client, so that the client displays the associated information to the first account .
  • an information display device applied to a client including:
  • the preset operation detection unit is configured to perform an information acquisition instruction to the server in response to detecting a preset operation performed on the played multimedia resource;
  • the third information display unit is configured to receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, wherein the associated information is the server according to the multimedia
  • the attribute information of the resource and the account characteristic information are associated information corresponding to the information demand characteristic obtained after the information demand characteristic of the first account is determined.
  • an electronic device including:
  • a memory for storing executable instructions of the processor
  • processor is configured to execute the instructions to implement the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • another electronic device including:
  • a memory for storing executable instructions of the processor
  • processor is configured to execute the instructions to implement the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • a non-volatile readable storage medium When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • a non-volatile readable storage medium When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • a computer program product runs on an electronic device, the electronic device is caused to perform the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • a computer program product runs on an electronic device, the electronic device is caused to perform the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • the embodiments of the present disclosure can effectively identify the information acquisition requirements generated by the user when viewing the multimedia resource in the process of viewing the multimedia resource according to the account characteristic information of the first account for operating the multimedia resource and the attribute information of the multimedia resource, that is, the first
  • the information demand characteristics of one account, and the multimedia resources are used as the information entry to provide the first account with associated information corresponding to the information demand characteristics, so as to quickly and efficiently meet the user's information acquisition needs.
  • the account characteristic information of the first account is taken into account when obtaining the associated information, so the associated information displayed to the first account is related to the information acquisition needs of the first account, which can effectively reduce the situation that users are not interested in the associated information Occurs, improving the applicability of related information display.
  • Fig. 1 is a schematic diagram showing an application scenario according to an exemplary embodiment
  • Fig. 2 is a flowchart showing a first information display method according to an exemplary embodiment
  • Fig. 3 is a schematic diagram showing a multimedia resource playing interface according to an exemplary embodiment
  • Fig. 4 is a schematic diagram showing another type of associated information according to an exemplary embodiment
  • Fig. 5 is a schematic diagram showing a preset operation according to an exemplary embodiment
  • Fig. 6 is a schematic diagram showing another preset operation according to an exemplary embodiment
  • Fig. 7 is a flowchart showing a second information display method according to an exemplary embodiment
  • Fig. 8 is a flowchart showing a third information display method according to an exemplary embodiment
  • Fig. 9 is a flow chart showing a complete method for displaying information according to an exemplary embodiment
  • Fig. 10 is a block diagram showing a first information display device according to an exemplary embodiment
  • Fig. 11 is a block diagram showing a second information display device according to an exemplary embodiment
  • Fig. 12 is a block diagram showing a third information display device according to an exemplary embodiment
  • Fig. 13 is a block diagram showing an information display system according to an exemplary embodiment
  • Fig. 14 is a block diagram showing an electronic device according to an exemplary embodiment
  • Fig. 15 is a block diagram showing a terminal device according to an exemplary embodiment
  • Fig. 16 is a flow chart showing a method for training a demand recognition model according to an exemplary embodiment.
  • association relationship of the associated object which means that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone.
  • the character "/" generally indicates that the associated objects before and after are in an "or" relationship.
  • Electronic equipment can be servers, mobile phones, computers, digital broadcasting terminals, messaging devices, game consoles, tablet devices, medical equipment, fitness equipment, personal digital assistants, etc.
  • Terminal equipment refers to mobile communication equipment such as mobile phones, tablets, computers, computers, and personal digital assistants.
  • Multimedia resources refer to the resources of digital transmission, such as videos, short videos, live broadcasts, etc.
  • Attribute information of multimedia resources used to describe the inherent attributes of the multimedia resources, which may include one or more of the content classification information of the multimedia resources, the resource subject name, the resource description information, and the image content characteristics of the resource frame image.
  • Account characteristic information including account attribute information and/or preference information type.
  • the account attribute information is used to describe the attribute information of the user when registering the account, such as the user's gender, age, region, occupation, and so on.
  • User portrait also known as user role
  • preference information types are Refers to the type of information that the account likes to obtain.
  • Information demand characteristics used to describe the user's information acquisition needs, such as whether the user needs to order takeaways, shop, or check travel guides, etc.
  • Artificial Intelligence The theory, method, technology and application of using digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results system.
  • artificial intelligence is a comprehensive technology of computer science, which attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
  • Artificial intelligence technology is a comprehensive discipline, covering a wide range of fields, including both hardware-level technology and software-level technology.
  • Basic artificial intelligence technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, and mechatronics.
  • Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
  • Machine Learning is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other subjects. Specializing in the study of how computers simulate or realize human learning behaviors in order to acquire new knowledge or skills, and reorganize the existing knowledge structure to continuously improve its own performance.
  • Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are in all fields of artificial intelligence.
  • Machine learning and deep learning usually include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and style teaching learning.
  • the image recognition model and the demand recognition model in the information display method proposed in the embodiments of the present disclosure all belong to machine learning models. These models relate to the technical field of machine learning, and the above models can be trained through machine learning technology. .
  • the image recognition model is mainly used for image recognition of resource frame images to obtain image content characteristics
  • the demand recognition model is mainly used for identifying the information demand characteristics of the first account based on account characteristic information and attribute information of multimedia resources, so as to be effective Satisfy users' information acquisition needs.
  • some preset advertising links can also be embedded in multimedia resources.
  • the advertising links may or may not be related to the content of the multimedia resources. Users can click on the controls and pop-up windows corresponding to these advertising links in the multimedia resource playback interface. , Buttons, etc. to jump to the corresponding advertisement page to obtain the corresponding information.
  • the embodiments of the present disclosure propose a method, system, device, client, server, and storage medium for information display.
  • the process of users viewing multimedia resources based on the attribute information of the multimedia resources and the account characteristic information of the first account, it can effectively identify the information acquisition needs generated by the user when viewing the multimedia resources, and further use the multimedia resources as the information portal to provide corresponding information, which is fast Efficiently meet users' information acquisition needs.
  • the account characteristic information of the first account is taken into account when obtaining the associated information, so the associated information displayed to the first account is related to the information acquisition needs of the first account, which can effectively reduce the situation that users are not interested in the associated information Occurs, improving the applicability of related information display.
  • FIG. 1 is a schematic diagram of an application scenario of an embodiment of the disclosure.
  • the application scenario diagram includes two terminal devices 110 and a server 130, and the playback interface 120 of the multimedia resource can be logged in through the terminal device 110.
  • the terminal device 110 and the server 130 may communicate with each other through a communication network.
  • the communication network may be a wired network or a wireless network.
  • the terminal device 110 is an electronic device used by the user.
  • the electronic device may be a personal computer, a mobile phone, a tablet computer, a notebook, an e-book reader, etc. It has certain computing capabilities and runs instant messaging software and websites. Or social software and computer equipment for websites.
  • Each terminal device 110 is connected to a server 130 via a wireless network.
  • the server 130 is a server cluster or a cloud computing center composed of a server or several servers, or a virtualization platform.
  • the terminal device 110 is used to respond to a preset operation triggered by the user through the playback interface 120 of the multimedia resource, and after detecting the preset operation performed by the user on the played multimedia resource, communicates with the server 130 The communication sends an information acquisition instruction to the server 130.
  • the server 130 is configured to obtain attribute information of multimedia resources, account attribute information of the account used by the user to perform preset operations, preference information type, and other account characteristic information, and determine the information demand characteristics of the user account according to the attribute information and account characteristic information.
  • the server 130 then returns the associated information corresponding to the information demand characteristics to the terminal device 110, and the terminal device 110 displays the associated information to the user.
  • the live broadcast interface 120 For example, when a user is watching a certain food live broadcast, he directly double-clicks the live broadcast interface 120. At this time, it is recognized that the user's information demand feature is takeaway, and then the user jumps to the takeaway order page of the food displayed in the corresponding gourmet live broadcast. Alternatively, the user directly double-clicks on the live broadcast interface 120 while watching the food live broadcast. At this time, it is recognized that the user's information requirement characteristic is cooking, and the user jumps to the guide page of the food displayed in the corresponding gourmet live broadcast.
  • Fig. 2 is a flowchart showing a first information display method according to an exemplary embodiment, which is applied to an information display system including a client and a server. As shown in Fig. 2, the method includes the following steps.
  • step S21 a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • the server obtains account characteristic information of the first account corresponding to the preset operation in response to a preset operation performed on the played multimedia resource detected by the client.
  • multimedia resources can refer to videos, short videos, live broadcasts, and so on.
  • the account characteristic information may include, but is not limited to, some or all of the following:
  • Account attribute information preference information type.
  • step S22 the information demand characteristics of the first account are determined according to the attribute information of the multimedia resources and the account characteristic information;
  • the server determines the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information.
  • step S23 the associated information corresponding to the information demand feature is obtained, and the associated information is displayed to the first account.
  • the server obtains the associated information corresponding to the information demand feature, and displays the associated information to the first account through the client.
  • the associated information is the information page corresponding to the information source address corresponding to the information demand feature.
  • the multimedia resource currently being played is the video work uploaded by user B, and the content in the currently displayed frame image is related to the ski resort, as shown in Figure 3 for example.
  • FIG. 4 is a schematic diagram of another demand-related information provided by an embodiment of the present disclosure.
  • the related information shown in Figure 4 is the ski resort travel guide information page. This page details the practical information of the Hongya Valley ski resort, introduction to the scenic spots and other information, including the number of ski trails, playing time, time, and scenic spots. Facilities, etc.
  • the information acquisition demand generated by the user when viewing the multimedia resource is effectively identified during the user viewing the multimedia resource, that is, the information demand characteristic of the first account , And then use multimedia resources as information portals to provide the first account with associated information corresponding to the characteristics of the information needs, so as to quickly and efficiently meet the user's information acquisition needs.
  • the account characteristic information of the first account is taken into account when obtaining the associated information, so the associated information displayed to the first account is related to the information acquisition needs of the first account, which can effectively reduce the user’s disinterest in the associated information. Circumstances occur, improving the applicability of related information display.
  • a preset operation refers to a preset information acquisition operation, which may be a preset fixed operation, such as a double-click operation, a sliding touch operation, etc. defined in the multimedia resource playing area, or it may be a user-defined setting , Define other operations in the multimedia resource play area, etc.
  • the terminal may first set a sliding touch operation, and when the user triggers the sliding touch operation on the play area of the multimedia resource, the account characteristic information of the first account that operates the multimedia resource can be obtained.
  • the sliding touch operation can be divided into the following types:
  • the terminal may set a special symbol first, and when the user performs a sliding touch operation of the special symbol on the playing area, the corresponding account characteristic information is obtained.
  • the terminal sets the V-shaped sliding touch operation track as the response mechanism of the preset operation according to the setting operation instruction triggered by the user.
  • the preset operation can be detected and the corresponding Account characteristic information. Assuming that the user's information demand feature is determined to view ski resort travel guides based on the account characteristics information, then directly jump to the ski resort travel guide information page, as shown in Figure 5.
  • the terminal sets the one-point upward sliding touch operation as the response mechanism of the preset operation.
  • the preset operation can be detected and the corresponding Account characteristic information. Assuming that the user's information demand feature is determined to view the ski resort travel guide based on the account characteristic information, then the ski resort travel guide information page is directly jumped to, as shown in Figure 6.
  • the attribute information is determined by any one or more of the following methods:
  • the resource frame image of the multimedia resource is input into the trained image recognition model, and the image content characteristics of the resource frame image output by the image recognition model are obtained as attribute information.
  • the attribute information of the multimedia resource in the embodiment of the present disclosure includes any one or more of the content classification information of the multimedia resource, the resource subject name, the resource description information, and the image content characteristics of the resource frame image.
  • content classification information refers to information used to classify the content of multimedia resources, and specific words used to represent content classification can be directly extracted as attribute words.
  • content classification information can refer to: games, entertainment, education, sports, etc.; or: horror, funny, suspense, etc.
  • the content classification information of the multimedia resource may be customized by the user (for example, the author) who provides the multimedia resource, or it may be classified according to a preset classification rule.
  • the content classification information may be a single classification, corresponding to only one classification label, or it may be a non-single classification, corresponding to multiple classification labels.
  • this video corresponds to one classification label: education; taking game video B as an example, this video corresponds to two classification labels: game, horror, where horror refers to the content in the game video or game background music, etc. It is scary, for example, the game contains horror elements, zombies, and the game scene is dark.
  • the resource subject name and resource description information may be set by the user of the media resource (for example, the author who publishes the video).
  • relevant word segmentation algorithms can be used for word segmentation, and the corresponding vocabulary can be extracted as attribute words.
  • the resource theme name refers to the theme name of the multimedia resource, such as "Carnival”, “Happy Chinese Year”, etc.
  • Resource description information refers to the information describing the content of multimedia resources, which can be realized through the description, indexing, and evaluation of multimedia resources. Resource description information not only facilitates users to understand multimedia resource objects, but also facilitates user retrieval and information integration.
  • the main video content of funny video C is a funny scene when a cat first sees snow.
  • the description information of video C can be described as: a cat that sees snow for the first time.
  • the word segmentation algorithm is used to directly extract texts such as the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource, which is convenient and efficient.
  • the resource frame image is the image of the corresponding frame in the multimedia resource extracted at the moment when the information acquisition operation is received in the play area, that is, the frame image when the user triggers the preset information acquisition operation.
  • the trained image recognition model can be used to perform recognition processing to identify the image content features of the output resource frame image, and then describe the image content features through corresponding vocabulary, that is, attribute words.
  • the image content characteristics include the type of object in the image, the state of the object, and so on.
  • the training process of the image recognition model in the embodiment of the present disclosure is as follows:
  • image recognition models are trained through related machine learning algorithms to recognize input images and output image content characteristics, including object types, object states, etc.
  • the input feature of the image recognition model is the sample image
  • the output feature is the image content feature.
  • some requirements related to the content of the multimedia resource will be generated when the user is viewing the multimedia resource. Therefore, it is very accurate to use the image content feature of the resource frame image of the multimedia resource as the attribute information.
  • the user triggers a preset operation When feature extraction is performed on the current resource frame image, it is more relevant to the user.
  • the account characteristic information includes account attribute information and/or preference information type.
  • the account attribute information refers to the age, gender, region, occupation and other information entered by the user when registering the first account.
  • the preference information type refers to the type of information that the first account likes to obtain or the type of information that is frequently obtained.
  • the preference information type of the first account can be determined in the following manner:
  • Determination method 1 In the case of the first historical behavior data corresponding to the first account in the historical statistical period, determine the display information obtained according to the first historical behavior data;
  • the acquisition frequency corresponding to different display information types determines the acquisition frequency corresponding to different display information types, and display the display information types whose acquisition frequency is higher than the first frequency threshold or the descending order of acquisition frequency within the preset order range
  • the information type is used as the preference information type of the first account.
  • the first historical behavior data is mainly the information acquisition behavior of the first account in the historical statistical period.
  • This method is suitable for old users. It collects statistics on the information acquisition behavior of the user account, that is, the first account in the historical statistical period.
  • the historical statistical period can be flexibly set according to needs, for example, set to 3 months.
  • the display information obtained according to the information acquisition behavior within 3 months includes: takeaway, shopping, and cooking, and then various types are determined based on the number of takeaway display information, shopping display information, and cooking display information obtained per unit time The acquisition frequency corresponding to the displayed information.
  • the acquisition frequencies corresponding to the three types of display information are f1, f2, and f3, respectively, and the first frequency threshold is t1, where f1>t1>f2>f3. If the information type higher than the first frequency threshold is used as the preference information type corresponding to the first account, the takeaway type is the determined preference information type.
  • the preference information type of the first account can be determined to include takeaway and shopping.
  • Determination method 2 In the case that there is no first historical behavior data corresponding to the first account in the historical statistical period, select the second account according to the similarity with the first account, where the second account has the preference information type; The preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • the similarity between a certain account and the first account is determined based on the account attribute information of the account and the account attribute information of the first account.
  • the new user account does not have the information acquisition behavior in the historical statistical period.
  • the preference information type of the second account is used as the preference information type of the first account.
  • the selected second account is also a similar account of the first account.
  • the specific process when selecting the second account, the specific process may be as follows:
  • the similarity between the first account and each account in the account set is determined; the account with the highest similarity to the first account is taken as the second account.
  • the account set there are 3 accounts in the account set. Among these 3 accounts, only one account A1 corresponds to the user's age, gender, and region, and the first account corresponds to the user's age, gender, and region. The other two accounts are the same.
  • the age, gender, and region of the user corresponding to A2 and A3 are the same as those of the user corresponding to the first account.
  • A2 only has the same age
  • A3 only has the same gender; therefore, it can be determined that the account A1 and the first account have the same age, gender, and region.
  • the degree of similarity is the highest, so account A1 is used as the second account, which is the similar account of the first account. Since the preference information type corresponding to the similar account includes travel and shopping, the preference information type of the first account is also travel and shopping.
  • the first account in the embodiment of the present disclosure is different from the second account.
  • the first account can be a new user or an old user, and the second account is generally an old user.
  • the type of preference information corresponding to the second account is It can be determined by the method in the determination method 1, or it can be directly customized by the user, and the preference information type corresponding to the account is preset, which is not limited in detail here.
  • the preference information type of the first account can be obtained based on the first historical behavior data of the first account or similar accounts, and the information demand characteristics determined according to the preference information type of the first account are more in line with the first account. The accuracy is higher and the user experience can be greatly improved.
  • the attribute word set is input into the trained demand recognition model as the first input parameter, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the attribute information of the multimedia resource Take the attribute information of the multimedia resource as the attribute word as an example. If the attribute information includes multiple items among the content classification information of the multimedia resource, the resource subject name, the resource description information, the image content characteristics of the resource frame image, etc., the attribute is determined according to the attribute information In the case of word collection, some examples are:
  • the attribute word set is obtained. The following is a detailed description:
  • the video type can be extracted directly according to the classification label, so the key information that can be extracted is "funny".
  • the resource description information corresponding to the video is "the cat who saw snow for the first time”, and the corresponding words “first time”, “snow”, and “cat” can be extracted.
  • the obtained object type is expressed as "cat” in vocabulary
  • the object form is expressed as "playing in snow” in vocabulary.
  • the remaining vocabulary after de-duplication processing on the vocabulary obtained in (1), (2), (3) above can form an attribute word set.
  • the attribute word set corresponding to funny video C is:
  • attribute word set according to the vocabulary in (1), (2), (3) listed in the above embodiment is just an example, in fact, it can be based on (1), (2), (3) Any one or more of the above forms the attribute word set, or determines the attribute word set according to other information of the multimedia resource, which is not specifically limited here.
  • the information that meets the key information type can be extracted from the account feature according to the preset key information type, that is, the feature words that meet the key information type form the feature word set .
  • specific vocabulary in the user portrait is obtained, including one or more of the user's age, gender, region, specific preference information type, etc., and these vocabularies are combined to obtain a feature word set.
  • the preset key information types are: age, gender, occupation, region, etc.
  • the characteristic words that meet these types are selected, such as: 31 years old, female, doctor, Beijing, etc.
  • the feature words are extracted from the account feature information directly according to the preset key information types to construct the feature word set, which is convenient and efficient, and the feature words are used as the input parameters of the model, which can reduce the calculation amount of the model.
  • the information demand characteristics of the first account can be acquired.
  • the specific process may be as follows:
  • the attribute word set and the feature word set obtained in the above process are input as the first input parameter to the trained demand recognition model, processed by the demand recognition model, and the corresponding information demand characteristics are output.
  • the output information demand characteristics can be in the form of a set of characteristic words, such as ⁇ travel, shopping, takeaway ⁇ , and the characteristic words in the set are used to describe the information demand characteristics of the first account.
  • the trained demand recognition model can accurately and efficiently recognize the user's information acquisition intention when viewing multimedia resources, so as to provide the user with a corresponding personalized information acquisition channel according to the identified information acquisition intention. It should be noted that the training method of the demand recognition model will be introduced in the following embodiments, and will not be repeated here.
  • the information source address can be a web page address, an information resource address, etc., where the information resource address can be directly opened to download information.
  • the information resource address can be the download address of the application, based on the information resource Address can directly open the download page of the application to download the installation package of the application, etc.
  • the information page is directly used as the associated information, so that it can directly jump to the information page corresponding to the information demand feature and display it to the user, which is more intuitive and convenient, and improves the efficiency of information display.
  • the information source address corresponding to the information demand feature can be determined in the following ways:
  • Determination method 1 Determine the information source address corresponding to the information demand feature according to the preset mapping relationship between the information demand feature and the information source address.
  • mapping table of information demand characteristics-information source address is set in advance, and if the determined information demand characteristic is take-out, the information source address corresponding to the take-out is queried from the mapping table.
  • the information requirement feature-information source address mapping table can be manually preset, that is, the information source address corresponding to different information requirement features (such as different feature words or different groups of feature phrases) can be preset manually, and the initial information can be manually set. Mapping table.
  • the response is based on the second historical behavior data corresponding to the first account Confirm that the update conditions are met and update the mapping relationship.
  • the second historical behavior data corresponding to the first account includes whether the first account views related information corresponding to different information demand characteristics displayed by the client terminal, and/or feedback on the first account of related information.
  • the platform according to the historical behavior data collected by the platform, check the actual feedback of the information page triggered by the characteristic words corresponding to the different information acquisition behaviors of the user, such as whether the user actually opens the information page, whether there is any further operation in the information page, To adjust the settings mapping table.
  • the update conditions include but are not limited to some or all of the following:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • the number of at least one may be one or more than one.
  • the demand determined according to the user's historical behavior does not match the demand obtained according to the demand recognition model, it indicates that the user's actual demand at this time is not recognized by the demand recognition model.
  • the recommended information page may be wrong.
  • the update conditions are determined according to different frequencies or times of demand, which can more directly reflect the problems of the mapping relationship.
  • the demand recognition model determines that the information demand characteristic of user C is takeaway, and the information page corresponding to address 1 is displayed to user C according to the information demand characteristic-information source address mapping table. User C does not actually click to view the information page. It is determined that the demand corresponding to the displayed related information is different from the demand of the first account corresponding to user C, that is, it does not match, indicating that the demand of the first account corresponding to user C is not actually takeaway at this time, or the user does not like the information The takeaway recommended on the page, the information page itself has problems, etc.
  • user D is determined to be shopping through the requirement recognition model. After displaying the information page corresponding to address 2 to user D according to the information requirement feature-information source address mapping table, user D does not actually click to view the information page. It can be determined that the needs corresponding to the displayed related information are different from the needs of the first account corresponding to user D, that is to say, in fact, the needs of user D at this time are not shopping, or the user does not like the products recommended on the information page or the products themselves There are problems, etc.
  • the mapping table is updated based on the collected historical behavior data; or, the calculation unit time If the frequency of the demand does not match, if the frequency reaches the second frequency threshold, it is determined that the update condition is satisfied, and the mapping table is updated according to the collected historical behavior data.
  • mapping relationship shown in Table 1 may further include the number of recommendations, the timing of recommendations, and the like.
  • takeaway does not necessarily correspond to address 1, but can also correspond to other addresses, and different addresses are set with different recommendation times or recommended times.
  • the second historical behavior data of the first account can be collected periodically according to the update conditions.
  • the mapping relationship is updated. Personalized processing of user historical behavior data improves the accuracy of the mapping relationship.
  • Determination method 2 Information retrieval is performed according to the information demand characteristics to obtain at least one information page, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information demand characteristic.
  • the information page with the highest confidence is retrieved in real time, and the address of the information page is used as the information source address.
  • the search algorithm can be related or directly call related search engine.
  • Fig. 7 is a flow chart showing a second information display method according to an exemplary embodiment, which is applied to a server. As shown in Fig. 7, it includes the following steps.
  • step S71 in response to receiving the information acquisition instruction sent by the client, the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset operation performed on the played multimedia resource Post-triggered
  • step S72 the information demand characteristics of the first account are determined according to the attribute information of the multimedia resources and the account characteristic information;
  • step S73 the associated information corresponding to the information requirement feature is obtained, and the associated information is returned to the client, so that the client can display the associated information to the first account.
  • the server can effectively identify the information acquisition requirements generated by the user when viewing the multimedia resource in the process of viewing the multimedia resource according to the account characteristic information of the first account that operates the multimedia resource and the attribute information of the multimedia resource, that is, The information demand characteristics of the first account, and the multimedia resources are used as the information entry, to provide the first account with associated information corresponding to the information demand characteristics, so as to quickly and efficiently meet the user's information acquisition needs.
  • the account characteristic information of the first account is taken into account when obtaining the associated information, so the associated information displayed to the first account is related to the information acquisition needs of the first account, which can effectively reduce the situation that users are not interested in the associated information Occurs, improving the applicability of related information display.
  • obtaining the associated information corresponding to the information requirement feature includes:
  • the account characteristic information includes preference information types
  • the acquisition frequency corresponding to different display information types determines the acquisition frequency corresponding to different display information types, and display the display information types whose acquisition frequency is higher than the first frequency threshold or the descending order of acquisition frequency within the preset order range
  • the information type is used as the preference information type of the first account.
  • the account characteristic information includes preference information types
  • the second account has the preference information type
  • the preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • selecting the second account based on the similarity with the first account includes:
  • the account with the highest similarity to the first account is taken as the second account.
  • obtaining the information source address corresponding to the information demand feature includes:
  • At least one information page is obtained by information retrieval according to the information requirement feature, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information requirement feature.
  • the information source address corresponding to the information requirement feature is determined according to a preset mapping relationship between the information requirement feature and the information source address, and the method may further include:
  • the second historical behavior data corresponding to the first account includes: whether the first account views the associated information corresponding to different information demand characteristics displayed by the client, and/or the feedback on the first account of associated information.
  • the update conditions include:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • determining the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information includes:
  • the attribute word set and the feature word set are input into the trained demand recognition model as the first input parameters, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the attribute information is determined in the following manner:
  • the attribute information is determined in the following manner:
  • a word segmentation algorithm is used to extract the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource as attribute information.
  • the attribute information is determined in the following manner:
  • the resource frame image of the multimedia resource is input into the trained image recognition model, and the image content characteristics of the resource frame image output by the image recognition model are obtained as attribute information.
  • obtaining the corresponding feature word set according to account feature information includes:
  • the information that meets the key information type is extracted from the account characteristic information to form a feature word set.
  • Fig. 8 is a flow chart showing a third information display method according to an exemplary embodiment, which is applied to a client terminal, as shown in Fig. 8, including the following steps.
  • step S81 in response to detecting a preset operation performed on the played multimedia resource, send an information acquisition instruction to the server;
  • step S82 the associated information returned by the server is received, and the associated information is displayed to the first account that performs the preset operation, where the associated information is that the server determines the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information Later, the associated information corresponding to the information demand characteristics is obtained.
  • the client may send an information acquisition instruction to the server in response to detecting a preset operation, triggering the server to display the multimedia resource during the user viewing the multimedia resource according to the account characteristic information of the first account that operates the multimedia resource and the attribute information of the multimedia resource.
  • the account characteristic information of the first account is taken into account when obtaining the associated information, so the associated information displayed to the first account is related to the information acquisition needs of the first account, which can effectively reduce the situation that users are not interested in the associated information Occurs, improving the applicability of related information display.
  • Fig. 9 is a flow chart showing a complete method for displaying information according to an exemplary embodiment.
  • the method for displaying information may include the following steps:
  • the client detects a preset operation in the play area of the multimedia resource while the user is watching the multimedia resource;
  • S92 The client sends an information acquisition instruction to the server
  • S93 The server obtains the attribute information of the multimedia resource and the account characteristic information of the user account that implements the preset operation;
  • S94 The server processes the attribute information to obtain the corresponding attribute word set, and processes the account characteristic information to obtain the corresponding characteristic word set;
  • S95 The server inputs the attribute word set and the feature word set into the trained demand recognition model, and obtains the information demand characteristics output by the demand recognition model;
  • S96 The server obtains the corresponding information source address according to the information demand characteristics
  • S98 The client receives the associated information, and displays the associated information to the user.
  • the embodiments of the present disclosure can effectively identify the user’s personalized information acquisition intention during the user’s viewing of multimedia resources, quickly provide corresponding personalized information acquisition channels for users to obtain information, and realize the use of multimedia resources as information acquisition.
  • a new way of providing information at the entrance enriches the user's information acquisition experience.
  • Fig. 10 is a block diagram showing a first information display device 1000 according to an exemplary embodiment. 10, the device includes a first information acquisition unit 1001, a first feature detection unit 1002, and a first information display unit 1003.
  • the first information obtaining unit 1001 is configured to perform a preset operation detected on the played multimedia resource, and obtain account characteristic information of the first account corresponding to the preset operation;
  • the first feature detection unit 1002 is configured to determine the information requirement feature of the first account according to the attribute information of the multimedia resource and the account feature information;
  • the first information display unit 1003 is configured to perform acquisition of associated information corresponding to the information demand characteristics, and display the associated information to the first account.
  • the first information display unit 1003 may be configured to execute:
  • the account characteristic information includes preference information types
  • the first information obtaining unit 1001 is further configured to determine the preference information type of the first account in the following manner:
  • the acquisition frequency corresponding to different display information types determines the acquisition frequency corresponding to different display information types, and display the display information types whose acquisition frequency is higher than the first frequency threshold or the descending order of acquisition frequency within the preset order range
  • the information type is used as the preference information type of the first account.
  • the account characteristic information includes preference information types
  • the first information obtaining unit 1001 is further configured to determine the preference information type of the first account in the following manner:
  • the second account has the preference information type
  • the preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • the first information acquiring unit 1001 may be configured to execute:
  • the account with the highest similarity to the first account is taken as the second account.
  • the first information display unit 1003 may be configured to execute:
  • At least one information page is obtained by information retrieval according to the information requirement feature, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information requirement feature.
  • the information source address corresponding to the information requirement feature is determined according to a preset mapping relationship between the information requirement feature and the information source address, and the device further includes:
  • the first update unit 1004 is configured to update the mapping relationship in response to determining that the update condition is satisfied according to the second historical behavior data corresponding to the first account;
  • the second historical behavior data corresponding to the first account includes: whether the first account views the associated information corresponding to different information demand characteristics displayed by the client, and/or the feedback on the first account of associated information.
  • the update conditions include:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • the first feature detection unit may be configured to perform:
  • the attribute word set and the feature word set are input into the trained demand recognition model as the first input parameters, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the first feature detection unit is further configured to determine the attribute information in the following manner:
  • the first feature detection unit is further configured to perform the determination of the attribute information in the following manner:
  • a word segmentation algorithm is used to extract the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource as attribute information.
  • the first feature detection unit is further configured to determine the attribute information in the following manner:
  • the resource frame image of the multimedia resource is input into the trained image recognition model, and the image content characteristics of the resource frame image output by the image recognition model are obtained as attribute information.
  • the first feature detection unit may be configured to perform:
  • the information that meets the key information type is extracted from the account characteristic information to form a feature word set.
  • the device further includes:
  • the first model training unit 1005 is configured to perform training to obtain a demand recognition model in the following manner:
  • the second input parameter is used as the input feature of the demand recognition model, and the information demand characteristic corresponding to the sample account during the playback process of the sample multimedia resource is used as the output characteristic of the demand recognition model, and the demand recognition model is trained.
  • the second input parameter further includes third historical behavior data corresponding to the sample account
  • the third historical behavior data corresponding to the sample account includes whether the sample account views related information and/or feedback on the related information sample account.
  • the first information acquiring unit 1001 may be configured to execute:
  • the first information display unit 1003 may be configured to execute:
  • FIG. 11 it is a schematic diagram of a second information display device 1100 provided by an embodiment of the present disclosure, which is applied to a server, and the device includes:
  • the second information acquisition unit 1101 is configured to perform, in response to receiving an information acquisition instruction sent by the client, acquiring account characteristic information of the first account that implements a preset operation, wherein the information acquisition instruction is that the client detects that the multimedia player is playing multimedia. Triggered after a preset operation implemented by the resource;
  • the second feature detection unit 1102 is configured to determine the information requirement feature of the first account according to the attribute information of the multimedia resource and the account feature information;
  • the second information display unit 1103 is configured to perform acquisition of associated information corresponding to the information requirement characteristics, and return the associated information to the client, so that the client can display the associated information to the first account.
  • the second information display unit 1103 may be configured to execute:
  • the account characteristic information includes preference information types
  • the second information obtaining unit 1101 is further configured to perform the following methods to determine the preference information type of the first account:
  • the acquisition frequency corresponding to different display information types determine the acquisition frequency corresponding to different display information types, and display the display information type whose acquisition frequency is higher than the first frequency threshold or the descending order of acquisition frequency within the preset order range
  • the information type is used as the preference information type of the first account.
  • the account characteristic information includes preference information types
  • the second information obtaining unit 1101 is further configured to perform the following methods to determine the preference information type of the first account:
  • the second account has the preference information type
  • the preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • the second information acquiring unit 1101 may be configured to execute:
  • the account with the highest similarity to the first account is taken as the second account.
  • the second information display unit 1103 may be configured to execute:
  • At least one information page is obtained by information retrieval according to the information requirement feature, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information requirement feature.
  • the information source address corresponding to the information requirement feature is determined by the second information display unit 1103 according to the preset mapping relationship between the information requirement feature and the information source address, and the device further includes:
  • the second update unit 1104 may be configured to perform an update of the mapping relationship in response to determining that the update condition is satisfied according to the second historical behavior data corresponding to the first account;
  • the second historical behavior data corresponding to the first account includes: whether the first account views the associated information corresponding to different information demand characteristics displayed by the client, and/or the feedback on the first account of associated information.
  • the update conditions include:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • the second feature detection unit 1102 may be configured to perform:
  • the attribute word set and the feature word set are input into the trained demand recognition model as the first input parameters, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the second feature detection unit 1102 is further configured to determine the attribute information in the following manner:
  • the second feature detection unit 1102 is also configured to determine the attribute information in the following manner:
  • a word segmentation algorithm is used to extract the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource as attribute information.
  • the second feature detection unit 1102 is further configured to determine the attribute information in the following manner:
  • the resource frame image of the multimedia resource is input into the trained image recognition model, and the image content characteristics of the resource frame image output by the image recognition model are obtained as attribute information.
  • the second feature detection unit 1102 may be configured to perform:
  • the information that meets the key information type is extracted from the account characteristic information to form a feature word set.
  • the device further includes:
  • the second model training unit 1105 is configured to perform training to obtain a demand recognition model in the following manner:
  • the second input parameter is used as the input feature of the demand recognition model, and the information demand characteristic corresponding to the sample account in the playback process of the sample multimedia resource is used as the output characteristic of the demand recognition model to train the demand recognition model.
  • the second input parameter further includes third historical behavior data corresponding to the sample account
  • the third historical behavior data corresponding to the sample account includes whether the sample account views related information and/or feedback on the related information sample account.
  • the preset operation detection unit 1201 is configured to perform an information acquisition instruction to the server in response to detecting a preset operation performed on the played multimedia resource;
  • the third information display unit 1202 is configured to receive the associated information returned by the server and display the associated information to the first account that implements the preset operation.
  • the associated information is that the server determines the first account based on the attribute information of the multimedia resource and the account characteristic information. After the information demand characteristics of an account, the associated information corresponding to the information demand characteristics is obtained.
  • Fig. 13 is a block diagram showing an information display system according to an exemplary embodiment, which includes a client 1301 and a server 1302;
  • the client 1301 is configured to send an information acquisition instruction to the server 1302 in response to detecting a preset operation performed on the played multimedia resource; receive the associated information returned by the server 1302, and display the associated information to the first account that performs the preset operation ;
  • the server 1302 is configured to, in response to receiving the information acquisition instruction sent by the client 1301, acquire the account characteristic information of the first account that implements the preset operation; determine the information requirements of the first account according to the attribute information of the multimedia resources and the account characteristic information Features; obtain the associated information corresponding to the information demand feature, and return the associated information to the client 1301.
  • the server 1302 can also be used to execute any of the information display methods applied to the server listed in the foregoing embodiments, and the repetition will not be repeated here.
  • Some embodiments of the present disclosure provide an electronic device, including:
  • a memory for storing executable instructions of the processor
  • processor is configured to execute the instructions to implement the following steps:
  • a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • Some embodiments of the present disclosure provide an electronic device, including:
  • a memory for storing executable instructions of the processor
  • processor is configured to execute the instructions to implement the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • Some embodiments of the present disclosure provide another electronic device, including:
  • a memory for storing executable instructions of the processor
  • processor is configured to execute the instructions to implement the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • Some embodiments of the present disclosure provide a storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the following steps:
  • a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • Some embodiments of the present disclosure provide a storage medium, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • Some embodiments of the present disclosure provide another storage medium, wherein when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is enabled to execute the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • Fig. 14 is a block diagram showing an electronic device 1400 according to an exemplary embodiment.
  • the electronic device 1400 may be the client or the server in the foregoing embodiment.
  • the electronic equipment includes:
  • a memory 1420 for storing executable instructions of the processor 1410
  • the processor 1410 is configured to execute instructions to implement any one of the foregoing information display methods in the embodiments of the present disclosure, for example, the method in FIG. 2.
  • a storage medium including instructions is also provided, such as a memory 1420 including instructions, and the foregoing instructions may be executed by the processor 1410 of the electronic device 1400 to complete the foregoing method.
  • the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage Equipment, etc.
  • the client may be a terminal device, or an application program installed on the terminal device.
  • the client is a terminal device
  • its structure is shown in FIG. 15.
  • the embodiment of the present disclosure provides a The terminal 1500 for information display includes: a radio frequency (RF) circuit 1510, a power supply 1520, a processor 1530, a memory 1540, an input unit 1550, a display unit 1560, a camera 1570, a communication interface 1580, and wireless fidelity ( Wireless Fidelity, Wi-Fi) module 1590 and other components.
  • RF radio frequency
  • the terminal provided in the embodiments of the present disclosure may include more or less components than those shown in the figure, or some components may be combined. Or different component arrangements.
  • the RF circuit 1510 can be used to receive and send data during a communication or call. In particular, after receiving the downlink data from the base station, the RF circuit 1510 sends it to the processor 1530 for processing; in addition, it sends the uplink data to be sent to the base station.
  • the RF circuit 1510 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (LNA), a duplexer, and the like.
  • LNA low noise amplifier
  • the RF circuit 1510 can also communicate with the network and other terminals through wireless communication.
  • Wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile Communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division Multiple) Access, CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), Email, Short Messaging Service (SMS), etc.
  • GSM Global System of Mobile Communication
  • GPRS General Packet Radio Service
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • LTE Long Term Evolution
  • Email Short Messaging Service
  • the Wi-Fi technology is a short-range wireless transmission technology.
  • the terminal 1500 can connect to an access point (Access Point, AP) through the Wi-Fi module 1590, thereby achieving data network access.
  • the Wi-Fi module 1590 can be used to receive and send data during the communication process.
  • the terminal 1500 may be physically connected with other terminals through the communication interface 1580.
  • the communication interface 1580 is connected to the communication interfaces of other terminals through cables to implement data transmission between the terminal 1500 and the other terminals.
  • the terminal 1500 can implement communication services and send information to other contacts, the terminal 1500 needs to have a data transmission function, that is, the terminal 1500 needs to include a communication module inside.
  • FIG. 15 shows communication modules such as the RF circuit 1510, the Wi-Fi module 1590, and the communication interface 1580, it is understandable that there are at least one of the above-mentioned components or other communication modules for implementing communication in the terminal 1500 (such as Bluetooth module) for data transmission.
  • the terminal 1500 when the terminal 1500 is a mobile phone, the terminal 1500 may include an RF circuit 1510 and may also include a Wi-Fi module 1590; when the terminal 1500 is a computer, the terminal 1500 may include a communication interface 1580 and may also include a Wi-Fi module 1590; When the terminal 1500 is a tablet computer, the terminal 1500 may include a Wi-Fi module.
  • the memory 1540 can be used to store software programs and modules.
  • the processor 1530 executes various functional applications and data processing of the terminal 1500 by running the software programs and modules stored in the memory 1540, and when the processor 1530 executes the program codes in the memory 1540, the embodiments of the present disclosure can be implemented.
  • FIG. 8 Part or all of the process in.
  • the memory 1540 may mainly include a program storage area and a data storage area.
  • the storage program area can store the operating system, various application programs (such as communication applications), and face recognition modules, etc.;
  • the storage data area can store data created according to the use of the terminal (such as various pictures, video files and other multimedia files) , And face information templates) and so on.
  • the memory 1540 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • a non-volatile memory such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
  • the input unit 1550 may be used to receive numeric or character information input by the object, and generate key signal input related to the object setting and function control of the terminal 1500.
  • the input unit 1550 may include a touch panel 1551 and other input terminals 1552.
  • the touch panel 1551 can collect touch operations on or near objects (for example, the objects use fingers, stylus and other suitable objects or accessories on the touch panel 1551 or on the touch panel 1551). Nearby operations), and drive the corresponding connection device according to the preset program.
  • the touch panel 1551 may include two parts: a touch detection device and a touch controller.
  • the touch detection device detects the touch position of the object, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it To the processor 1530, and can receive and execute the commands sent by the processor 1530.
  • the touch panel 1551 can be implemented in multiple types such as resistive, capacitive, infrared, and surface acoustic wave.
  • the other input terminal 1552 may include, but is not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackball, mouse, joystick, and the like.
  • the display unit 1560 may be used to display information input by the object or information provided to the object and various menus of the terminal 1500.
  • the display unit 1560 is the display system of the terminal 1500, and is used to present an interface and realize human-computer interaction.
  • the display unit 1560 may include a display panel 1561.
  • the display panel 1561 can be configured in the form of a liquid crystal display (Liquid Crystal Display, LCD), an organic light-emitting diode (Organic Light-Emitting Diode, OLED), etc.
  • the touch panel 1551 can cover the display panel 1561.
  • the touch panel 1551 detects a touch operation on or near it, it transmits it to the processor 1530 to determine the type of the touch event, and then the processor 1530 responds to the touch event.
  • the type provides corresponding visual output on the display panel 1561.
  • the touch panel 1551 and the display panel 1561 are used as two independent components to implement the input and input functions of the terminal 1500, in some embodiments, the touch panel 1551 and the display panel 1561 can be integrated And realize the input and output functions of the terminal 1500.
  • the processor 1530 is the control center of the terminal 1500. It uses various interfaces and lines to connect various components, and executes the terminal 1500 by running or executing software programs and/or modules stored in the memory 1540, and calling data stored in the memory 1540. The various functions and processing data of the device, so as to realize a variety of terminal-based services.
  • the processor 1530 may include one or more processing units. In some embodiments, the processor 1530 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, an object interface, and an application program, and the modem processor mainly processes wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 1530.
  • the camera 1570 is used to implement the shooting function of the terminal 1500, and shoot pictures or videos.
  • the camera 1570 can also be used to implement the scanning function of the terminal 1500 to scan the scanned object (two-dimensional code/barcode).
  • the terminal 1500 also includes a power source 1520 (such as a battery) for supplying power to various components.
  • a power source 1520 such as a battery
  • the power supply 1520 may be logically connected to the processor 1530 through a power management system, so that functions such as charging, discharging, and power consumption can be managed through the power management system.
  • processor 1530 in the embodiment of the present disclosure may execute the functions of the processor 1415 in FIG. 14, and the memory 1540 stores content in the memory 1420.
  • Some embodiments of the present disclosure also provide a method for training a demand recognition model.
  • Fig. 16 is a flowchart showing a method for training a demand recognition model according to an exemplary embodiment. As shown in Fig. 16, the method includes the following steps.
  • step S161 the account characteristic information of the sample account and the attribute information of the sample multimedia resource are acquired, and the second input parameter is determined according to the attribute information and the account characteristic information.
  • step S162 the corresponding information requirement characteristics of the sample account during the playback of the sample multimedia resource are obtained.
  • step S163 the second input parameter is used as the input feature of the demand identification model, and the information demand feature is used as the output feature of the demand identification model, and the demand identification model is trained.
  • the information acquisition behavior instructs takeaways, viewing travel guides and other behaviors.
  • Each sample is determined based on the information acquisition behavior that occurs when a user views a multimedia resource, that is, a sample corresponds to a sample account and a multimedia resource.
  • the second input parameter may include the attribute word set obtained according to the attribute information of the multimedia resource, and the characteristic word set obtained according to the user portrait of the sample account; the information demand characteristic may refer to the corresponding characteristic word set when the user obtains the information page, which can be analyzed manually Obtain, you can also use page analysis tools to identify the acquisition, etc.
  • the second input parameters can be used as the input characteristics of the demand recognition model, and the information demand characteristics can be used as the output characteristics of the demand recognition model. Train the demand recognition model.
  • the deep learning method performs better on large data sets, so the demand recognition model can be trained through deep learning.
  • the second input parameter can be used as input, and information demand characteristics can be used as output characteristics of the demand recognition model.
  • the demand recognition model can be iteratively trained by continuously adjusting the model parameters of the demand recognition model. Until the accuracy rate of the output result of the demand recognition model meets the preset threshold, the training ends, and a trained demand recognition model is obtained.
  • the parameters of the demand recognition model can be accurately adjusted according to the user’s historical behavior data.
  • the trained demand recognition model is used for processing according to the input attribute word set, feature word set, etc., and output a set of corresponding feature words obtained by recognition, as Information demand characteristics.
  • the user can view the associated information corresponding to the information demand characteristics, so as to improve the accuracy of the demand recognition model as much as possible.
  • the second input parameter may also include third historical behavior data corresponding to the sample account; where the third historical behavior data corresponding to the sample account includes whether the sample account views related information and/or the related information sample account. Feedback.
  • the third historical behavior data refers to whether the user implements the information acquisition behavior, the information acquisition feedback after the information acquisition behavior is implemented, for example, whether the user directly closes the information page or opens the information page, whether the user has any further operations after opening the information page, etc.
  • the user's third historical behavior data is also used as input parameters for training, and the model is trained in combination with the user's posterior information, which can effectively adjust the model parameters to make the model identification accurate higher.
  • Some embodiments of the present disclosure also provide a computer program product.
  • the computer program product runs on an electronic device, the electronic device executes the following steps:
  • a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • another computer program product which when the computer program product runs on an electronic device, causes the electronic device to perform the following steps:
  • the account characteristic information of the first account that implements the preset operation is acquired, where the information acquisition instruction is that the client detects the preset implemented on the played multimedia resource Triggered after the operation;
  • another computer program product which when the computer program product runs on an electronic device, causes the electronic device to perform the following steps:
  • the server Receive the associated information returned by the server, and display the associated information to the first account that implements the preset operation, where the associated information is the attribute information of the multimedia resource and the account characteristic information according to the server After determining the information requirement characteristic of the first account, the associated information corresponding to the information requirement characteristic is acquired.
  • Some embodiments of the present disclosure also provide an information display method, wherein the method includes:
  • a preset operation performed on the played multimedia resource is detected, and account characteristic information of the first account corresponding to the preset operation is acquired;
  • the acquiring associated information corresponding to the information demand feature in the information display method and displaying the associated information to the first account includes:
  • the account characteristic information in the information display method includes preference information types
  • the preference information type of the first account is determined in the following manner:
  • the display information type within the range is used as the preference information type of the first account.
  • the account characteristic information in the information display method includes preference information types
  • the preference information type of the first account is determined in the following manner:
  • the preference information type corresponding to the selected second account is used as the preference information type of the first account.
  • the selection of the second account based on the similarity with the first account in the information display method includes:
  • the account with the highest degree of similarity to the first account is used as the second account.
  • the obtaining of the information source address corresponding to the information demand characteristic in the information display method includes:
  • At least one information page is obtained by information retrieval according to the information requirement feature, and the address of the information page with the highest confidence among the at least one information page is used as the information source address corresponding to the information requirement feature.
  • the information source address corresponding to the information requirement feature is determined according to a preset mapping relationship between the information requirement feature and the information source address, and the information display method further includes:
  • the second historical behavior data corresponding to the first account includes: whether the first account views the associated information corresponding to the different information demand characteristics displayed by the client, and/or the first account for the associated information Account feedback.
  • the update condition in the information display method includes:
  • the second historical behavior data it is determined that the demand corresponding to the displayed associated information is different from the demand of the at least one first account for a preset number of times;
  • the frequency at which the demand corresponding to the displayed associated information is different from the demand of the at least one first account reaches the second frequency threshold.
  • the determining the information demand characteristics of the first account according to the attribute information of the multimedia resources and the account characteristic information in the information display method includes:
  • the attribute word set and the feature word set are input into the trained demand recognition model as first input parameters, and the information demand characteristics of the first account output by the demand recognition model are obtained.
  • the attribute information is determined in the following manner:
  • the content classification information of the multimedia resource is extracted as the attribute information.
  • the attribute information is determined in the following manner:
  • a word segmentation algorithm is used to extract the resource subject name of the multimedia resource and/or the resource description information of the multimedia resource as the attribute information.
  • the attribute information is determined in the following manner:
  • the resource frame image of the multimedia resource is input into a trained image recognition model, and the image content feature of the resource frame image output by the image recognition model is obtained as the attribute information.
  • obtaining a corresponding feature word set according to the account feature information includes:
  • the preset key information type information that matches the key information type is extracted from the account characteristic information to form a characteristic word set.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种信息展示方法及装置，涉及互联网技术领域。所述方法包括：响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息（S71）；根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征（S72）；获取与信息需求特征对应的关联信息，并将关联信息返回给客户端（S73）。所述方法能够根据第一账户的账户特征信息以及多媒体资源的属性信息有效识别出用户观看多媒体资源时所产生的信息获取需求，进而以多媒体资源作为信息入口向第一账户提供需求特征对应的关联信息，快捷高效地满足用户的信息获取需求。

Description

一种信息展示方法及装置
相关申请的交叉引用
本公开要求北京达佳互联信息技术有限公司于2020年2月14日提交的、申请名称为“一种信息展示方法、系统、装置、电子设备及存储介质”的、中国专利申请号“202010093249.7”的优先权。
技术领域
本公开涉及互联网技术领域，尤其涉及一种信息展示方法及装置。
背景技术
随着多媒体技术的迅速发展以及智能终端的普及，承载更多信息量的多媒体资源得以快速传播，成为人们获取信息的重要渠道之一。
但是，目前用户通常只能通过播放多媒体资源进行观看，来获取多媒体资源内容反映的信息。用户在观看多媒体资源的内容时，若用户被触发产生获取更多信息的需求，就需要继续进行网络搜索等手段。例如，用户在观看某个主播的直播，对直播中的景点发生了兴趣，想要获取景点的旅游攻略或者预订去该景点旅游的交通住宿时，还需要自行上网搜索更多对应的信息。
发明内容
本公开提供一种信息展示方法及装置。本公开的技术方案如下：
根据本公开的一些实施例，提供一种信息展示方法，包括：
检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息信息需求特征；
获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息。
在一些实施例中，所述获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息，包括：
获取与所述信息需求特征对应的信息来源地址；
获取与所述信息来源地址对应的信息页面作为所述关联信息进行展示。
在一些实施例中，所述账户特征信息包括偏好信息类型；
通过下列方式确定所述第一账户的偏好信息类型：
获取历史统计时段内所述第一账户的第一历史行为数据，并确定由所述第一账户的第一历史行为数据获取的信息页面中的展示信息；
根据单位时间内获取所述展示信息的数量，确定不同的展示信息类型对应的获取频率，并将所述获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型作为所述第一账户的偏好信息类型。
在一些实施例中，所述账户特征信息包括偏好信息类型；
通过下列方式确定所述第一账户的偏好信息类型：
根据与所述第一账户的相似度，选择第二账户，所述第二账户具有偏好信息类型；
将选择的所述第二账户对应的偏好信息类型作为所述第一账户的偏好信息类型。
在一些实施例中，所述根据与所述第一账户的相似度，选择第二账户，包括：
将与所述第一账户相似度最高的账户作为所述第二账户。
在一些实施例中，所述获取与所述信息需求特征对应的信息来源地址，包括：
根据预设的信息需求特征与信息来源地址之间的映射关系，确定与所述信息需求特征对应的信息来源地址；或
根据所述信息需求特征进行信息检索得到至少一个信息页面，并将所述至少一个信息页面中置信度最高的信息页面的地址作为所述信息需求特征对应的信息来源地址。
在一些实施例中，基于所述信息需求特征对应的信息来源地址是根据预设的信息需求特征与信息来源地址之间的映射关系确定的，所述方法还包括：
响应于根据所述第一账户对应的第二历史行为数据确定满足更新条件，更新所述映射关系；
其中，所述第一账户对应的第二历史行为数据包括：所述第一账户是否查看所述客户端展示的不同信息需求特征对应的关联信息，和/或针对所述关联信息所述第一账户的反馈。
在一些实施例中，所述更新条件包括：
根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；或
根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
在一些实施例中，所述根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息信息需求特征，包括：
根据所述多媒体资源的属性信息，获取对应的属性词集合，以及，根据所述账户特征信息，获取对应的特征词集合；
将所述属性词集合以及所述特征词集合作为第一输入参数输入已训练的需求识别模型，获取所述需求识别模型输出的所述第一账户的信息需求特征。
在一些实施例中，通过下列方式确定所述属性信息：
提取所述多媒体资源的内容分类信息，作为所述属性信息。
在一些实施例中，通过下列方式确定所述属性信息：
通过分词算法提取所述多媒体资源的资源主题名称和/或所述多媒体资源的资源描述信息，作为所述属性信息。
在一些实施例中，通过下列方式确定所述属性信息：
将所述多媒体资源的资源帧图像输入已训练的图像识别模型，获取所述图像识别模型输出的资源帧图像的图像内容特征，作为所述属性信息。
在一些实施例中，所述根据所述账户特征信息，获取对应的特征词集合，包括：
根据预设的关键信息类型，从所述账户特征信息中提取符合所述关键信息类型的信息组成特征词集合。
在一些实施例中，所述检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息，包括：
服务器响应于通过客户端检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
所述根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征，包括：
所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
所述获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息，包括：
所述服务器获取与所述信息需求特征对应的关联信息，并将所述关联信息通过所述客户端向所述第一账户展示。
根据本公开的一些实施例，提供一种信息展示方法，应用于服务器，包括：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操 作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，提供一种信息展示方法，应用于客户端，包括：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
根据本公开的一些实施例，提供一种信息展示系统，包括：客户端和服务器；
所述客户端，用于响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息；
所述服务器，用于响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息；根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端。
根据本公开的一些实施例，提供一种信息展示装置，应用于服务器，包括：
第二信息获取单元，被配置为执行响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
第二特征检测单元，被配置为执行根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
第二信息展示单元，被配置为执行获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，提供一种信息展示装置，应用于客户端，包括：
预设操作检测单元，被配置为执行响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
第三信息展示单元，被配置为执行接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所 述信息需求特征对应的关联信息。
根据本公开的一些实施例，提供一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令，以实现以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，提供另一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令，以实现以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
根据本公开的一些实施例，提供一种非易失性可读存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，提供一种非易失性可读存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
根据本公开的一些实施例，提供一种计算机程序产品，当所述计算机程序产品在电子设备上运行时，使得所述电子设备执行以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，提供一种计算机程序产品，当所述计算机程序产品在电子设备上运行时，使得所述电子设备执行以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
由于本公开实施例能根据操作多媒体资源的第一账户的账户特征信息以及多媒体资源的属性信息，在用户观看多媒体资源过程中有效识别出用户观看多媒体资源时所产生的信息获取需求，也就是第一账户的信息需求特征，进而以多媒体资源作为信息入口，向第一账户提供信息需求特征对应的关联信息，快捷高效地满足用户的信息获取需求。此外，在获取关联信息时考虑了第一账户的账户特征信息，因而向第一账户展示的关联信息都是与第一账户的信息获取需求相关的，可以有效减少用户对关联信息不感兴趣的情况发生，提升关联信息展示的适用性。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是根据一示例性实施例示出的一种应用场景的示意图；
图2是根据一示例性实施例示出的第一种信息展示方法的流程图；
图3是根据一示例性实施例示出的一种多媒体资源播放界面的示意图；
图4是根据一示例性实施例示出的另一种关联信息的示意图；
图5是根据一示例性实施例示出的一种预设操作的示意图；
图6是根据一示例性实施例示出的另一种预设操作的示意图；
图7是根据一示例性实施例示出的第二种信息展示方法的流程图；
图8是根据一示例性实施例示出的第三种信息展示方法的流程图；
图9是根据一示例性实施例示出的一种信息展示的完整方法的流程图；
图10是根据一示例性实施例示出的第一种信息展示装置的框图；
图11是根据一示例性实施例示出的第二种信息展示装置的框图；
图12是根据一示例性实施例示出的第三种信息展示装置的框图；
图13是根据一示例性实施例示出的一种信息展示系统的框图；
图14是根据一示例性实施例示出的一种电子设备的框图；
图15是根据一示例性实施例示出的一种终端设备的框图；
图16是根据一示例性实施例示出的需求识别模型的训练方法的流程图。
具体实施方式
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。需要说明的是，本公开的所有实施例均可以单独被执行，也可以与其他实施例相结合共同被执行，本公开对此不做限制。
下面对文中出现的一些词语进行解释：
1、和/或：描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
2、电子设备：可以是服务器、移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
3、终端设备：指手机、平板、电脑、计算机、个人数字助理等移动通信设备。
4、多媒体资源：指数字传输的资源，例如视频、短视频、直播等。
5、多媒体资源的属性信息：用于描述多媒体资源固有的属性，可以包括多媒体资源的内容分类信息、资源主题名称、资源描述信息、资源帧图像的图像内容特征等中的一项或多项。
6、账户特征信息：包括账户属性信息和/或偏好信息类型。其中，账户属性信息用于描述注册账户时的用户的属性信息，例如用户的性别、年龄、区域、职业等。用户画像(又称用户角色)即账户属性信息的一种形式，作为一种勾画目标用户、联系用户诉求与设计方向的有效工具，用户画像在各领域得到了广泛的应用；偏好信息类型则是指该账户喜欢获取的信息的类型。
7、信息需求特征：用于描述用户的信息获取需求，例如用户是需要点外卖，需要购物，还是需要查看旅游攻略等等。
8、人工智能(Artificial Intelligence，AI)：是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能，感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说，人工智能是计算机科学的一个综合技术，它企图了解智能的实质，并生产出一种新的能以人类智能相似的方式做出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法，使机器具有感知、推理与决策的功能。
人工智能技术是一门综合学科，涉及领域广泛，既有硬件层面的技术也有软件层面的技术。人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。人工智能软件技术主要包括计算机视觉技术、语音处理技术、自然语言处理技术以及机器学习/深度学习等几大方向。
机器学习(Machine Learning，ML)是一门多领域交叉学科，涉及概率论、统计学、逼近论、凸分析、算法复杂度理论等多门学科。专门研究计算机怎样模拟或实现人类的学习行为，以获取新的知识或技能，重新组织已有的知识结构使之不断改善自身的性能。机器学习是人工智能的核心，是使计算机具有智能的根本途径，其应用遍及人工智能的各个领域。机器学习和深度学习通常包括人工神经网络、置信网络、强化学习、迁移学习、归纳学习、式教学习等技术。
在本公开实施例中提出的信息展示方法中的图像识别模型以及需求识别模型等都属于机器学习模型，这些模型就涉及到机器学习这一技术领域，通过机器学习这一技术可训练得到上述模型。其中，图像识别模型主要用于对资源帧图像进行图像识别，获取图像内容特征；需求识别模型则主要用于根据账户特征信息以及多媒体资源的属性信息识别出第一账户的信息需求特征，以便有效满足用户的信息获取需求。
本公开实施例描述的应用场景是为了更加清楚的说明本公开实施例的技术方案，并不构成对于本公开实施例提供的技术方案的限定，本领域普通技术人员可知，随着新应用场景的出现，本公开实施例提供的技术方案对于类似的技术问题，同样适用。
下面对本公开实施例的设计思想进行简要介绍：
相关技术中，针对用户在观看多媒体资源时所产生的信息获取需求，需要通过网络搜索等手段获取相应信息。此外，还可在多媒体资源中嵌入一些预设的广告链接，其中该广告链接可能与多媒体资源的内容相关，也可能不相关，用户可以点击多媒体资源播放界面中这些广告链接对应的控件、弹窗、按钮等来跳转到对应的广告页面以获取相应信息。
然而，在多媒体资源中插入广告链接会影响对广告不感兴趣的用户的资源观看体验，也无法有效满足用户观看多媒体资源所产生的信息获取需求。
有鉴于此，本公开实施例提出了一种信息展示的方法、系统、装置、客户端、服务器及存储介质。在用户观看多媒体资源过程中，基于多媒体资源的属性信息以及第一账户的账户特征信息能有效识别用户观看多媒体资源时所产生的信息获取需求，进一步以多媒体资源为信息入口提供对应的信息，快捷高效地满足用户的信息获取需求。此外，在获取关联信息时考虑了第一账户的账户特征信息，因而向第一账户展示的关联信息都是与第一账户的信息获取需求相关的，可以有效减少用户对关联信息不感兴趣的情况发生，提升关联信息展示的适用性。
下面对本公开实施例的应用场景进行简要介绍：
参阅图1所示，其为本公开实施例的应用场景示意图。该应用场景图中包括两个终端设备110和一个服务器130，可通过终端设备110登录多媒体资源的播放界面120。终端设备110与服务器130之间可以通过通信网络进行通信。
在一些实施例中，通信网络可以是有线网络或无线网络。
在本公开实施例中，终端设备110为用户使用的电子设备，该电子设备可以是个人计算机、手机、平板电脑、笔记本、电子书阅读器等具有一定计算能力并且运行有即时通讯类软件及网站或者社交类软件及网站的计算机设备。各终端设备110通过无线网络与服务器130连接，服务器130是一台服务器或若干台服务器组成的服务器集群或云计算中心，或者是一个虚拟化平台。
在本公开实施例中，终端设备110用于响应用户通过多媒体资源的播放界面120触发的预设操作，并在检测到用户对播放的多媒体资源实施的预设操作后，通过与服务器130之间的通信向服务器130发送信息获取指令。服务器130用于获取多媒体资源的属性信息以及用户实施预设操作时所使用的账户的账户属性信息、偏好信息类型等账户特征信息，并根据属性信息以及账户特征信息确定用户账户的信息需求特征。之后服务器130将与信 息需求特征对应的关联信息返回给终端设备110，由终端设备110向用户展示关联信息。
例如用户在观看某个美食直播时，直接双击直播播放界面120，此时识别该用户的信息需求特征是外卖，则跳转到对应的美食直播中展示的食物的外卖下单页面。或者，用户在观看该美食直播时，直接双击直播播放界面120，此时识别该用户的信息需求特征是下厨，则跳转到对应的美食直播中展示的食物的攻略页面等。
图2是根据一示例性实施例示出的第一种信息展示方法的流程图，应用于包含客户端及服务器的信息展示系统，如图2所示，包括以下步骤。
在步骤S21中，检测到对播放的多媒体资源实施的预设操作，获取与预设操作对应的第一账户的账户特征信息；
在一些实施例中，服务器响应于通过客户端检测到对播放的多媒体资源实施的预设操作，获取与预设操作对应的第一账户的账户特征信息。
其中，多媒体资源可以指视频、短视频、直播等。
其中，账户特征信息可以包括但不限于下列的部分或全部：
账户属性信息、偏好信息类型。
在步骤S22中，根据多媒体资源的属性信息以及账户特征信息确定第一账户的信息需求特征；
在一些实施例中，服务器根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征。
在步骤S23中，获取与信息需求特征对应的关联信息，并向第一账户展示关联信息。
在一些实施例中，服务器获取与信息需求特征对应的关联信息，并将关联信息通过客户端向第一账户展示。
其中，关联信息为与信息需求特征对应的信息来源地址所对应的信息页面。
例如用户A通过短视频软件浏览短视频作品时，当前播放的多媒体资源为用户B上传的视频作品，当前显示的帧图像中的内容与滑雪场相关，例如图3所示。响应于在当前播放区域中检测到用户A触发的预设操作，根据操作多媒体资源的第一账户的账户特征信息确定用户A的信息需求特征，在信息需求特征为获取滑雪场的游玩攻略的情况下，可直接跳转至滑雪场旅游攻略相关的信息界面，向用户A展示该信息需求特征的关联信息，如图4所示。
参阅图4所示，为本公开实施例提供的另一种需求关联信息的示意图。在图4中展示的关联信息即为滑雪场旅游攻略信息页面，该页面中详细介绍了红崖谷滑雪场的实用信息，景点简介等信息，具体包括雪道的数量，游玩时长、时间、景点的设施等。
该方式下，无需用户A再通过操作入口触发信息页面的展示，而是响应于检测到用户 A触发的预设操作，直接跳转至滑雪场旅游攻略信息页面，更加快捷高效地满足用户的信息获取需求。
通过上述方案，根据多媒体资源的属性信息以及第一账户的账户特征信息，在用户观看多媒体资源过程中有效识别出用户观看多媒体资源时所产生的信息获取需求，也就是第一账户的信息需求特征，进而以多媒体资源作为信息入口，向第一账户提供信息需求特征对应的关联信息，快捷高效地满足用户的信息获取需求。此外，在获取关联信息时考虑了第一账户的账户特征信息，因而向第一账户展示的关联信息都是与第一账户的信息获取需求相关的，因而可以有效减少用户对关联信息不感兴趣的情况发生，提升关联信息展示的适用性。
在本公开实施例中，预设操作指预设的信息获取操作，可以是预先设置的固定操作，例如定义为在多媒体资源播放区域的双击操作、滑动触摸操作等，或者可以是用户自定义设置，定义在多媒体资源播放区域的其他操作等。
在一些实施例中，终端可先设置一种滑动触摸操作，当用户对多媒体资源的播放区域触发该滑动触摸操作时，即可获取操作该多媒体资源的第一账户的账户特征信息。
根据终端对滑动触摸操作的具体设置，滑动触摸操作又可分为以下几种：
(1)特殊符号滑动触摸操作。
终端可先设置一个特殊符号，当用户对播放区域进行特殊符号滑动触摸操作时，则获取相应的账户特征信息。
假设终端根据用户触发的设置操作指令，将V型滑动触摸操作轨迹设置为预设操作的响应机制，当用户对播放区域进行V型轨迹滑动触摸操作时，则可检测到预设操作，获取相应账户特征信息。假设根据账户特征信息确定用户信息需求特征为查看滑雪场旅游攻略，则直接跳转至滑雪场旅游攻略信息页面，如图5所示。
(2)单指向上滑动触摸操作。
在终端根据用户触发的设置操作指令，将单指向上滑动触摸操作设置为预设操作的响应机制，当用户对播放区域进行单指向上滑动触摸操作时，则可检测到预设操作，获取相应账户特征信息。假设根据账户特征信息确定用户信息需求特征为查看滑雪场旅游攻略，则直接跳转至滑雪场旅游攻略信息页面，如图6所示。
需要说明的是，上述对滑动触摸操作的介绍只是举例说明，任何可以应用到本公开实施例中的触发获取第一账户的账户特征信息的滑动触摸操作都适用本公开实施例。
在一些实施例中，通过下列方式中的任意一种或多种方式确定属性信息：
提取多媒体资源的内容分类信息，作为属性信息；
通过分词算法提取多媒体资源的资源主题名称和/或多媒体资源的资源描述信息，作为 属性信息；
将多媒体资源的资源帧图像输入已训练的图像识别模型，获取图像识别模型输出的资源帧图像的图像内容特征，作为属性信息。
也就是说，本公开实施例中的多媒体资源的属性信息包括多媒体资源的内容分类信息、资源主题名称、资源描述信息、资源帧图像的图像内容特征中的任意一项或多项。
在一些实施例中，内容分类信息指用于表示对多媒体资源的内容进行分类的信息，可以直接提取用于表示内容分类的具体词汇作为属性词。
以多媒体资源为视频为例，内容分类信息可以指：游戏、娱乐、教育、体育等；或者是：恐怖、搞笑、悬疑等。
其中，多媒体资源的内容分类信息可以是提供多媒体资源的用户(例如作者)自定义的，也可以根据预设的分类规则进行分类得到的。
在一些实施例中，内容分类信息可以是单一分类，仅对应一个分类标签；也可以是非单一分类，对应多个分类标签。
以教育视频A为例，该视频对应一个分类标签：教育；以游戏视频B为例，该视频对应两个分类标签：游戏、恐怖，其中恐怖是指该游戏视频中的内容或者游戏背景音乐等比较恐怖，例如游戏中包含恐怖元素僵尸、游戏场景阴暗等。
在上述实施方式中，一般情况下用户会有较为偏爱的多媒体资源的内容分类，因而将内容分类信息作为属性信息以识别用户的信息需求特征更加直观。
在本公开实施例中，资源主题名称、资源描述信息可以是媒体资源的用户(例如发布视频的作者)设置的。针对资源主题名称或资源描述信息等文本，可以采用相关分词算法进行分词，提取对应的词汇作为属性词。
其中，资源主题名称指多媒体资源的主题名称，例如“合家欢”、“欢乐中国年”等。
资源描述信息指对多媒体资源内容进行描述的信息，可通过对多媒体资源进行著录、标引、评价等实现，资源描述信息不仅仅方便用户了解多媒体资源对象，而且还能方便用户检索和信息整合。
例如，搞笑视频C主要的视频内容为猫第一见到雪时的搞笑场景，此时视频C的描述信息可以描述为：第一次看见雪的猫。
在上述实施方式中，通过分词算法直接提取多媒体资源的资源主题名称和/或多媒体资源的资源描述信息等文本，便捷高效。
在本公开实施例中，资源帧图像是根据在播放区域接收信息获取操作的时刻抽取到的多媒体资源中对应帧的图像，也就是用户触发预设的信息获取操作时的帧图像。可以通过已训练的图像识别模型进行识别处理，识别输出该资源帧图像的图像内容特征，之后将图 像内容特征通过对应的词汇，也就是属性词来描述。其中，图像内容特征包括图像中的物体类型、物体状态等。
例如，在用户观看搞笑视频C的过程中，在播放视频C的某一资源帧图像时触发了预设操作，则将该帧资源帧图像输入已训练的图像识别模型，获取图像识别模型输出的图像内容特征，并从图像内容特征中提取出关键信息，假设对应的物体类型用词汇表示为“猫”，物体形态用词汇表示为“玩雪”。
其中，本公开实施例中的图像识别模型的训练过程如下：
采集大量图像作为样本，通过相关的机器学习算法来训练图像识别模型，用于对输入的图像进行识别，输出图像内容特征，包括物体类型、物体状态等。其中，图像识别模型的输入特征为样本图像，输出特征为图像内容特征。
在上述实施方式中，在用户观看多媒体资源时会产生一些与多媒体资源的内容相关的需求，因而将多媒体资源的资源帧图像的图像内容特征作为属性信息十分准确，此外，采取用户触发预设操作时的资源帧图像进行特征提取时，与用户关联性更强。
下面对账户特征信息进行详细说明：
在本申请实施例中，账户特征信息包括账户属性信息和/或偏好信息类型。
其中，账户属性信息指用户注册第一账户时输入的年龄、性别、地域、职业等信息。
偏好信息类型指第一账户喜欢获取的信息类型或者是常常获取的信息类型等。
在一些实施例中，可通过下列方式确定第一账户的偏好信息类型：
确定方式一、在历史统计时段内存在与第一账户对应的第一历史行为数据的情况下，确定根据第一历史行为数据获取的展示信息；
根据单位时间内获取展示信息的数量，确定不同的展示信息类型对应的获取频率，并将获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型作为第一账户的偏好信息类型。
其中，第一历史行为数据主要是第一账户在历史统计时段内的信息获取行为。
该方式适用于老用户，通过对用户账户也就是第一账户在历史统计时段内的信息获取行为进行统计，其中的历史统计时段可根据需求灵活设置，例如设置为3个月，第一账户在3个月内根据信息获行为获取到的展示信息包括：外卖、购物、下厨，进而根据单位时间内获取的外卖类展示信息、购物类展示信息以及下厨类展示信息的数量确定出各类展示信息对应的获取频率。
假设这三类展示信息对应的获取频率分别为f1、f2、f3，第一频率阈值为t1，其中f1>t1>f2>f3。若将高于第一频率阈值的信息类型作为第一账户对应的偏好信息类型，则外卖类型即为确定的偏好信息类型。
若根据频率的降序排序次序来确定偏好信息类型时，假设f3<f2<f1，假设预设次序范围为取频率最高的前两个，则可确定第一账户的偏好信息类型包括外卖以及购物。
确定方式二、在历史统计时段内不存在与第一账户对应的第一历史行为数据的情况下，根据与第一账户的相似度，选择第二账户，其中第二账户具有偏好信息类型；将选择的第二账户对应的偏好信息类型作为第一账户的偏好信息类型。
其中，某个账户与第一账户的相似度是根据该账户的账户属性信息以及第一账户的账户属性信息确定的。
该方式既适用于新用户，也适用于老用户，但是相比更加适用于新用户。一般新用户账户不存在历史统计时段内的信息获取行为，此时则可根据第一账户的账户属性信息，也就是年龄、性别、地域等信息，从一个账户集合来选择第二账户，使用选择的第二账户的偏好信息类型作为第一账户的偏好信息类型。其中，选择的第二账户也就是第一账户的相似账户。
在一些实施例中，根据与第一账户的相似度，选择第二账户时，具体过程可以如下：
根据第一账户的账户属性信息以及账户集合中各账户的账户属性信息，确定第一账户与账户集合中各账户的相似度；将与第一账户相似度最高的账户作为第二账户。
例如，账户集合中有3个账户，这3个账户中，只有一个账户A1对应的用户的年龄、性别、地域和第一账户对应的用户的年龄、性别、地域都相同，而其余两个账户A2、A3对应的用户的年龄、性别、地域与第一账户对应的用户的年龄、性别、地域部分相同，例如A2仅年龄相同，A3仅性别相同；因而则可确定账户A1与第一账户的相似度最高，故将账户A1作为第二账户，也就是第一账户的相似账户。由于该相似账户对应的偏好信息类型为包括旅游、购物，因而第一账户的偏好信息类型也为旅游、购物。
该方式下，一般情况下年龄、职业、性别相同的用户，其信息获取需求的相似度也较高，因而基于账户属性信息确定第一账户的相似账户，可以有效确定新用户的偏好信息类型，提出了一种可行的偏好信息类型获取方法。
需要说明的是，本公开实施例中的第一账户与第二账户不同，其中第一账户可以是新用户也可以是老用户，第二账户一般为老用户，第二账户对应的偏好信息类型可采用确定方式一中的方式确定，也可以直接由用户自定义，预先设置出该账户对应的偏好信息类型等，在此不做详细限定。
在上述实施方式中，基于第一账户的第一历史行为数据或者相似账户则可获取到第一账户的偏好信息类型，依据第一账户的偏好信息类型确定出的信息需求特征更加符合第一账户的需求，准确性更高，可以极大提升用户体验。
在一些实施例中，根据多媒体资源的属性信息以及账户特征信息确定第一账户的信息 需求特征时，首先需要确定账户特征信息组成的特征词集合以及属性信息组成的属性词集合，将特征词集合以及属性词集合作为第一输入参数输入已训练的需求识别模型，获取需求识别模型输出的第一账户的信息需求特征。
以多媒体资源的属性信息为属性词为例，若属性信息包括多媒体资源的内容分类信息、资源主题名称、资源描述信息、资源帧图像的图像内容特征等中的多项，则根据属性信息确定属性词集合时，一些实施例为：
将属性信息进行去重处理后得到属性词集合。下面进行详细说明：
(1)针对内容分类信息，以搞笑视频C为例，则可直接根据分类标签提取视频类型，因而可提取到的关键信息为“搞笑”。
(2)针对资源主题名称或资源描述信息，仍以搞笑视频C为例，假设该视频的资源主题名称为“宠物搞笑视频集锦”，则可提取对应的词汇：“宠物”、“搞笑”。
该视频对应的资源描述信息为“第一次看见雪的猫”，则可提取对应的词汇“第一次”、“雪”、“猫”。
(3)针对资源帧图像，仍以搞笑视频C为例，得到的物体类型用词汇表示为“猫”，物体形态用词汇表示为“玩雪”。
对于上述(1)、(2)、(3)得到的词汇进行去重处理后剩余的词汇即可组成属性词集合，由上述实施例可知，搞笑视频C对应的属性词集合为：
{搞笑、宠物、猫、雪、第一次}。
需要说明的是，上述实施例中所列举的根据(1)、(2)、(3)中的词汇组成属性词集合只是举例说明，实际上可以根据(1)、(2)、(3)中的任意一种或多种来组成属性词集合，或者是根据多媒体资源的其它信息确定属性词集合，在此处不做具体限定。
在一些实施例中，根据账户特征信息确定特征词集合时，可根据预设的关键信息类型，从账户特征中提取符合关键信息类型的信息，也就是符合关键信息类型的特征词组成特征词集合。
在一些实施例中，获取用户画像中具体的词汇，包括用户年龄、性别、地域、具体的偏好信息类型等中的一种或多种，将这些词汇组合得到特征词集合。
例如预设的关键信息类型为：年龄、性别、职业、地域等，则根据账户特征信息从中筛选出符合这些类型的特征词，例如：31岁、女、医生、北京等。
在上述实施方式中，直接根据预设的关键信息类型从账户特征信息中提取特征词来构建特征词集合，便捷高效，并且以特征词作为模型的输入参数，可以减小模型的计算量。
在一些实施例中，根据已获取的属性词集合及特征词集合，基于已训练的需求识别模型，则可获取第一账户的信息需求特征，具体过程可以如下：
将上述过程中获取的属性词集合和特征词集合作为第一输入参数输入已训练的需求识别模型，通过需求识别模型进行处理，输出对应的信息需求特征。
其中，输出的信息需求特征可以是特征词集合的形式，例如{旅游、购物、外卖}，集合中的特征词用于描述第一账户的信息需求特征。
在上述实施方式中，通过已训练的需求识别模型则可准确高效地识别出用户观看多媒体资源时产生的信息获取意图，以便根据识别的信息获取意图，为用户提供对应的个性化信息获取渠道。需要说明的是，需求识别模型的训练方法，将在下述实施例中进行介绍，此处不作赘述。
在本公开实施例中，获取用户的信息需求特征之后，基于信息需求特征对应的信息来源地址，则可向用户展示相应的关联信息。其中，信息来源地址可以是网页地址、信息资源地址等，其中信息资源地址可以直接打开下载信息，例如用户的需求为下载某一应用时，信息资源地址可以是该应用的下载地址，基于信息资源地址则可直接打开该应用的下载页面下载该应用的安装包等。
上述实施方式中，将信息页面直接作为关联信息，因而可直接跳转至于信息需求特征对应的信息页面，并向用户展示，更加直观便捷，提高了信息展示的效率。
在一些实施例中，可通过下列几种方式确定与信息需求特征对应的信息来源地址：
确定方式一、根据预设的信息需求特征与信息来源地址之间的映射关系，确定与信息需求特征对应的信息来源地址。
例如预先设置信息需求特征-信息来源地址映射表，假设确定的信息需求特征为外卖时，则从映射表中查询获取与外卖对应的信息来源地址。
其中，信息需求特征-信息来源地址映射表可以是人工预先设置的，即预先设置不同的信息需求特征(例如不同的特征词或者不同组的特征词组)对应的信息来源地址，可以是人工设置初始的映射表。
表1信息需求特征-信息来源地址映射表
特征词(组) 信息来源地址
外卖 地址1
购物 地址2
下厨 地址3
旅游 地址4
… …
例如表1所示，其中不同的特征词对应有不同的信息来源地址，假设信息需求特征为外卖时，则对应的信息来源地址为地址1。
该方式下，根据预设映射关系则可直接确定出不同信息需求特征对应的不同的信息来源地址，便捷高效。
在一些实施例中，在根据信息需求特征-信息来源地址映射表确定出信息需求特征，并向用户展示不同信息需求特征对应的关联信息后，响应于根据第一账户对应的第二历史行为数据确定满足更新条件，更新映射关系。其中，第一账户对应的第二历史行为数据包括第一账户是否查看客户端展示的不同信息需求特征对应的关联信息，和/或针对关联信息第一账户的反馈。
在一些实施例中，根据平台收集的历史行为数据，查看用户的不同信息获取行为对应的特征词触发的信息页面的实际反馈，例如用户是否实际打开信息页面、是否在信息页面中有进一步操作，来调整设置映射表。
在一些实施例中，更新条件包括但不限于下列的部分或全部：
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
其中，至少一个的个数可以为一个，或者也可以为多个。
该方式下，根据用户的历史行为确定的需求与根据需求识别模型得到的需求不匹配时，则表明用户此时的实际需求并非需求识别模型识别得到的，此时可能是推荐的信息页面有误，或者是其它原因，因而依据需求不同的频率或次数来确定更新条件，可以更加直接地反映出映射关系存在的问题。
例如通过需求识别模型确定用户C信息需求特征为外卖，根据信息需求特征-信息来源地址映射表向用户C展示地址1对应的信息页面后，用户C实际并没有点击查看该信息页面，此时可确定展示的关联信息所对应的需求与用户C对应的第一账户的需求不同，也就是不匹配，表明实际上此时用户C所对应的第一账户的需求并非外卖，或者用户不喜欢该信息页面推荐的外卖、信息页面本身有问题等。
同样地，通过需求识别模型确定用户D信息需求特征为购物，根据信息需求特征-信息来源地址映射表向用户D展示地址2对应的信息页面后，用户D实际并没有点击查看该信息页面，此时可确定展示的关联信息所对应的需求与用户D对应的第一账户的需求不同，也就是说实际上此时用户D的需求并非购物，或者用户不喜欢该信息页面推荐的商品、商品本身有问题等。
若统计时间段内包含上述两次一共有15次需求不匹配的情况，假设预设数量为10，则可确定满足更新条件，并依据收集的历史行为数据更新映射表；或者，计算单位时间内 需求不匹配的频率，若频率达到第二频率阈值，则确定满足更新条件，并依据收集的历史行为数据更新映射表。
需要说明的是，表1所示的映射关系中还可进一步包括推荐次数、推荐时机等。例如外卖不一定仅对应地址1，还可对应其它地址，并且不同地址设置有不同的推荐时机或者推荐次数等。在更新映射关系时，可以判断是否是推荐本身的问题，比如在一个非就餐时段推荐的外卖页面，此时可能就是推荐时机的问题，该情况下可以通过模型校准推荐时机；再或者判断是否推荐的商品用户不喜欢，该情况下可以降低推荐频次或者尝试推荐其他可能的商品，并更新信息来源地址信息和信息需求特征的对应关系，以及相应的推荐次数、推荐时机等。
该方式下，可依据更新条件，周期采集第一账户的第二历史行为数据，根据第二历史行为数据确定满足更新条件时，则对映射关系进行更新，基于不断增加的历史行为数据，实现基于用户历史行为数据的个性化处理，提高映射关系的准确性。
确定方式二、根据信息需求特征进行信息检索得到至少一个信息页面，并将至少一个信息页面中置信度最高的信息页面的地址作为信息需求特征对应的信息来源地址。
例如，根据表示信息需求特征的特征词作为query(搜索词)，实时检索得到置信度最高的信息页面，并将该信息页面的地址作为信息来源地址，其中检索算法可以采用相关或者直接调用相关的搜索引擎。
该方式下可基于实时检索的方式向用户提供更加可靠的信息页面，快捷高效地满足用户的信息获取体验。
图7是根据一示例性实施例示出的第二种信息展示方法的流程图，应用于服务器，如图7所示，包括以下步骤。
在步骤S71中，响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中信息获取指令为客户端检测到对播放的多媒体资源实施的预设操作后触发的；
在步骤S72中，根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征；
在步骤S73中，获取与信息需求特征对应的关联信息，并将关联信息返回给客户端，以使客户端向第一账户展示关联信息。
上述实施方式中，服务器能根据操作多媒体资源的第一账户的账户特征信息以及多媒体资源的属性信息，在用户观看多媒体资源过程中有效识别出用户观看多媒体资源时所产生的信息获取需求，也就是第一账户的信息需求特征，进而以多媒体资源作为信息入口，向第一账户提供信息需求特征对应的关联信息，快捷高效地满足用户的信息获取需求。此 外，在获取关联信息时考虑了第一账户的账户特征信息，因而向第一账户展示的关联信息都是与第一账户的信息获取需求相关的，可以有效减少用户对关联信息不感兴趣的情况发生，提升关联信息展示的适用性。
在一些实施例中，获取与信息需求特征对应的关联信息，包括：
获取与信息需求特征对应的信息来源地址；
获取与信息来源地址对应的信息页面作为关联信息。
在一些实施例中，账户特征信息包括偏好信息类型；
通过下列方式确定第一账户的偏好信息类型：
获取历史统计时段内第一账户的第一历史行为数据，并确定由第一账户的第一历史行为数据获取的信息页面中的展示信息；
根据单位时间内获取展示信息的数量，确定不同的展示信息类型对应的获取频率，并将获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型，作为第一账户的偏好信息类型。
在一些实施例中，账户特征信息包括偏好信息类型；
通过下列方式确定第一账户的偏好信息类型：
根据与第一账户的相似度，选择第二账户，第二账户具有偏好信息类型；
将选择的第二账户对应的偏好信息类型作为第一账户的偏好信息类型。
在一些实施例中，根据与第一账户的相似度，选择第二账户，包括：
将与第一账户相似度最高的账户作为第二账户。
在一些实施例中，获取与信息需求特征对应的信息来源地址，包括：
根据预设的信息需求特征与信息来源地址之间的映射关系，确定与信息需求特征对应的信息来源地址；或
根据信息需求特征进行信息检索得到至少一个信息页面，并将至少一个信息页面中置信度最高的信息页面的地址作为信息需求特征对应的信息来源地址。
在一些实施例中，基于信息需求特征对应的信息来源地址是根据预设的信息需求特征与信息来源地址之间的映射关系确定的，方法还可以包括：
响应于根据第一账户对应的第二历史行为数据确定满足更新条件，更新映射关系；
其中，第一账户对应的第二历史行为数据包括：第一账户是否查看客户端展示的不同信息需求特征对应的关联信息，和/或针对关联信息第一账户的反馈。
在一些实施例中，更新条件包括：
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；或
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
在一些实施例中，根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征，包括：
根据多媒体资源的属性信息，获取对应的属性词集合，以及，根据账户特征信息，获取对应的特征词集合；
将属性词集合以及特征词集合作为第一输入参数输入已训练的需求识别模型，获取需求识别模型输出的第一账户的信息需求特征。
在一些实施例中，通过下列方式确定属性信息：
提取多媒体资源的内容分类信息，作为属性信息。
在一些实施例中，通过下列方式确定属性信息：
通过分词算法提取多媒体资源的资源主题名称和/或多媒体资源的资源描述信息，作为属性信息。
在一些实施例中，通过下列方式确定属性信息：
将多媒体资源的资源帧图像输入已训练的图像识别模型，获取图像识别模型输出的资源帧图像的图像内容特征，作为属性信息。
在一些实施例中，根据账户特征信息，获取对应的特征词集合，包括：
根据预设的关键信息类型，从账户特征信息中提取符合关键信息类型的信息组成特征词集合。
图8是根据一示例性实施例示出的第三种信息展示方法的流程图，应用于客户端，如图8所示，包括以下步骤。
在步骤S81中，响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
在步骤S82中，接收服务器返回的关联信息，并向实施预设操作的第一账户展示关联信息，其中关联信息为服务器根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征后，获取的与信息需求特征对应的关联信息。
上述实施方式中，客户端可以响应于检测到预设操作，向服务器发送信息获取指令，触发服务器根据操作多媒体资源的第一账户的账户特征信息以及多媒体资源的属性信息，在用户观看多媒体资源过程中有效识别出用户观看多媒体资源时所产生的信息获取需求，也就是第一账户的信息需求特征，进而以多媒体资源作为信息入口，向第一账户提供信息需求特征对应的关联信息，快捷高效地满足用户的信息获取需求。此外，在获取关联信息时考虑了第一账户的账户特征信息，因而向第一账户展示的关联信息都是与第一账户的信 息获取需求相关的，可以有效减少用户对关联信息不感兴趣的情况发生，提升关联信息展示的适用性。
图9是根据一示例性实施例示出的一种信息展示的完整方法流程图，该信息展示方法可以包括以下步骤：
S91：客户端在用户观看多媒体资源过程中，在该多媒体资源的播放区域中检测到预设操作；
S92：客户端向服务器发送信息获取指令；
S93：服务器获取多媒体资源的属性信息以及实施预设操作的用户账户的账户特征信息；
S94：服务器对属性信息进行处理，得到对应的属性词集合，以及对账户特征信息进行处理，得到对应的特征词集合；
S95：服务器将属性词集合以及特征词集合输入已训练的需求识别模型，获取需求识别模型输出的信息需求特征；
S96：服务器根据信息需求特征获取对应的信息来源地址；
S97：服务器将与信息来源地址对应的关联信息发送给客户端；
S98：客户端接收到关联信息，并将关联信息向用户进行展示。
需要说明的是，本公开实施例能在用户观看多媒体资源的过程中，有效识别用户的个性化信息获取意图，快速提供对应的个性化信息获取渠道供用户获取信息，实现以多媒体资源为信息获取入口的一种新的信息提供方式，丰富了用户的信息获取体验。
图10是根据一示例性实施例示出的第一种信息展示装置1000框图。参照图10，该装置包括第一信息获取单元1001，第一特征检测单元1002和第一信息展示单元1003。
第一信息获取单元1001，被配置为执行检测到对播放的多媒体资源实施的预设操作，获取与预设操作对应的第一账户的账户特征信息；
第一特征检测单元1002，被配置为执行根据多媒体资源的属性信息以及账户特征信息确定第一账户的信息需求特征；
第一信息展示单元1003，被配置为执行获取与信息需求特征对应的关联信息，并向第一账户展示关联信息。
在一些实施例中，第一信息展示单元1003可以被配置为执行：
获取与信息需求特征对应的信息来源地址；
获取与信息来源地址对应的信息页面作为关联信息进行展示。
在一些实施例中，账户特征信息包括偏好信息类型；
第一信息获取单元1001还被配置为执行通过下列方式确定第一账户的偏好信息类型：
获取历史统计时段内第一账户的第一历史行为数据，并确定由第一账户的第一历史行为数据获取的信息页面中的展示信息；
根据单位时间内获取展示信息的数量，确定不同的展示信息类型对应的获取频率，并将获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型作为第一账户的偏好信息类型。
在一些实施例中，账户特征信息包括偏好信息类型；
第一信息获取单元1001还被配置为执行通过下列方式确定第一账户的偏好信息类型：
根据与第一账户的相似度，选择第二账户，第二账户具有偏好信息类型；
将选择的第二账户对应的偏好信息类型作为第一账户的偏好信息类型。
在一些实施例中，第一信息获取单元1001可以被配置为执行：
将与第一账户相似度最高的账户作为第二账户。
在一些实施例中，第一信息展示单元1003可以被配置为执行：
根据预设的信息需求特征与信息来源地址之间的映射关系，确定与信息需求特征对应的信息来源地址；或
根据信息需求特征进行信息检索得到至少一个信息页面，并将至少一个信息页面中置信度最高的信息页面的地址作为信息需求特征对应的信息来源地址。
在一些实施例中，基于信息需求特征对应的信息来源地址是根据预设的信息需求特征与信息来源地址之间的映射关系确定的，装置还包括：
第一更新单元1004，被配置为执行在响应于根据第一账户对应的第二历史行为数据确定满足更新条件，更新映射关系；
其中，第一账户对应的第二历史行为数据包括：第一账户是否查看客户端展示的不同信息需求特征对应的关联信息，和/或针对关联信息第一账户的反馈。
在一些实施例中，更新条件包括：
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；或
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
在一些实施例中，第一特征检测单元可以被配置为执行：
确定属性信息组成的属性词集合以及账户特征信息组成的特征词集合；
将属性词集合以及特征词集合作为第一输入参数输入已训练的需求识别模型，获取需求识别模型输出的第一账户的信息需求特征。
在一些实施例中，第一特征检测单元还被配置为执行通过下列方式确定属性信息：
提取多媒体资源的内容分类信息，作为属性信息。
第一特征检测单元还被配置为执行通过下列方式确定属性信息：
通过分词算法提取多媒体资源的资源主题名称和/或多媒体资源的资源描述信息，作为属性信息。
在一些实施例中，第一特征检测单元还被配置为执行通过下列方式确定属性信息：
将多媒体资源的资源帧图像输入已训练的图像识别模型，获取图像识别模型输出的资源帧图像的图像内容特征，作为属性信息。
在一些实施例中，第一特征检测单元可以被配置为执行：
根据预设的关键信息类型，从账户特征信息中提取符合关键信息类型的信息组成特征词集合。
在一些实施例中，装置还包括：
第一模型训练单元1005，被配置为执行通过下列方式训练得到需求识别模型：
获取样本账户的账户特征信息以及样本多媒体资源的属性信息，并根据属性信息以及账户特征信息确定第二输入参数；
获取样本账户在样本多媒体资源的播放过程中对应的信息需求特征；
将第二输入参数作为需求识别模型的输入特征，将样本账户在所述样本多媒体资源的播放过程中对应的信息需求特征作为需求识别模型的输出特征，对需求识别模型进行训练。
在一些实施例中，第二输入参数还包括样本账户对应的第三历史行为数据；
其中，样本账户对应的第三历史行为数据包括样本账户是否查看关联信息和/或针对关联信息样本账户的反馈。
在一些实施例中，第一信息获取单元1001可以被配置为执行：
响应于通过客户端检测到对播放的多媒体资源实施的预设操作，获取与预设操作对应的第一账户的账户特征信息；
第一信息展示单元1003可以被配置为执行：
获取与信息需求特征对应的关联信息，并将关联信息通过客户端向第一账户展示。
如图11所示，为本公开实施例提供的第二种信息展示装置1100的示意图，应用于服务器，该装置包括：
第二信息获取单元1101，被配置为执行响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中信息获取指令为客户端检测到对播放的多媒体资源实施的预设操作后触发的；
第二特征检测单元1102，被配置为执行根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征；
第二信息展示单元1103，被配置为执行获取与信息需求特征对应的关联信息，并将关联信息返回给客户端，以使客户端向第一账户展示关联信息。
在一些实施例中，第二信息展示单元1103可以被配置为执行：
获取与信息需求特征对应的信息来源地址；
获取与信息来源地址对应的信息页面作为关联信息。
在一些实施例中，账户特征信息包括偏好信息类型；
第二信息获取单元1101还被配置为执行通过下列方式确定第一账户的偏好信息类型：
获取历史统计时段内第一账户的第一历史行为数据，并确定由第一账户的第一历史行为数据获取的信息页面中的展示信息；
根据单位时间内获取展示信息的数量，确定不同的展示信息类型对应的获取频率，并将获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型，作为第一账户的偏好信息类型。
在一些实施例中，账户特征信息包括偏好信息类型；
第二信息获取单元1101还被配置为执行通过下列方式确定第一账户的偏好信息类型：
根据与第一账户的相似度，选择第二账户，第二账户具有偏好信息类型；
将选择的第二账户对应的偏好信息类型作为第一账户的偏好信息类型。
在一些实施例中，第二信息获取单元1101可以被配置为执行：
将与第一账户相似度最高的账户作为第二账户。
在一些实施例中，第二信息展示单元1103可以被配置为执行：
根据预设的信息需求特征与信息来源地址之间的映射关系，确定与信息需求特征对应的信息来源地址；或
根据信息需求特征进行信息检索得到至少一个信息页面，并将至少一个信息页面中置信度最高的信息页面的地址作为信息需求特征对应的信息来源地址。
在一些实施例中，基于信息需求特征对应的信息来源地址是第二信息展示单元1103根据预设的信息需求特征与信息来源地址之间的映射关系确定的，装置还包括：
第二更新单元1104，可以被配置为执行响应于根据第一账户对应的第二历史行为数据确定满足更新条件，更新映射关系；
其中，第一账户对应的第二历史行为数据包括：第一账户是否查看客户端展示的不同信息需求特征对应的关联信息，和/或针对关联信息第一账户的反馈。
在一些实施例中，更新条件包括：
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；或
根据第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
在一些实施例中，第二特征检测单元1102可以被配置为执行：
根据多媒体资源的属性信息，获取对应的属性词集合，以及，根据账户特征信息，获取对应的特征词集合；
将属性词集合以及特征词集合作为第一输入参数输入已训练的需求识别模型，获取需求识别模型输出的第一账户的信息需求特征。
在一些实施例中，第二特征检测单元1102还被配置为执行通过下列方式确定属性信息：
提取多媒体资源的内容分类信息，作为属性信息。
第二特征检测单元1102还被配置为执行通过下列方式确定属性信息：
通过分词算法提取多媒体资源的资源主题名称和/或多媒体资源的资源描述信息，作为属性信息。
在一些实施例中，第二特征检测单元1102还被配置为执行通过下列方式确定属性信息：
将多媒体资源的资源帧图像输入已训练的图像识别模型，获取图像识别模型输出的资源帧图像的图像内容特征，作为属性信息。
在一些实施例中，第二特征检测单元1102可以被配置为执行：
根据预设的关键信息类型，从账户特征信息中提取符合关键信息类型的信息组成特征词集合。
在一些实施例中，装置还包括：
第二模型训练单元1105，被配置为执行通过下列方式训练得到需求识别模型：
获取样本账户的账户特征信息以及样本多媒体资源的属性信息，并根据属性信息以及账户特征信息确定第二输入参数；
获取样本账户在样本多媒体资源的播放过程中对应的信息需求特征；
将第二输入参数作为需求识别模型的输入特征，将样本账户在样本多媒体资源的播放过程中对应的信息需求特征作为需求识别模型的输出特征，对需求识别模型进行训练。
在一些实施例中，第二输入参数还包括样本账户对应的第三历史行为数据；
其中，样本账户对应的第三历史行为数据包括样本账户是否查看关联信息和/或针对关联信息样本账户的反馈。
如图12所示，为本公开实施例提供的第三种信息展示装置1200的示意图，应用于客户端，该装置包括：
预设操作检测单元1201，被配置为执行响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
第三信息展示单元1202，被配置为执行接收服务器返回的关联信息，并向实施预设操作的第一账户展示关联信息，其中关联信息为服务器根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征后，获取的与信息需求特征对应的关联信息。
关于上述实施例中的装置，其中各个单元执行请求的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图13是根据一示例性实施例示出的一种信息展示系统的框图，包括客户端1301和服务器1302；
客户端1301，用于响应于检测到对播放的多媒体资源实施的预设操作，向服务器1302发送信息获取指令；接收服务器1302返回的关联信息，并向实施预设操作的第一账户展示关联信息；
服务器1302，用于响应于接收到客户端1301发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息；根据多媒体资源的属性信息以及账户特征信息，确定第一账户的信息需求特征；获取与信息需求特征对应的关联信息，并将关联信息返回给客户端1301。
其中，服务器1302还可用于执行上述实施例所列举的任意一种应用于服务器的信息展示方法，重复之处不再赘述。
本公开的一些实施例提供了一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令，以实现以下步骤：
检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息。
本公开的一些实施例提供了一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令，以实现以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征 信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
本公开的一些实施例提供了另一种电子设备，包括：
处理器；
用于存储所述处理器可执行指令的存储器；
其中，所述处理器被配置为执行所述指令，以实现以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
本公开的一些实施例提供了一种存储介质，其中，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息。
本公开的一些实施例提供了一种存储介质，其中，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
本公开的一些实施例提供了另一种存储介质，其中，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
图14是根据一示例性实施例示出的一种电子设备1400的框图，其中，该电子设备1400可以为上述实施例中的客户端或服务器。该电子设备包括：
处理器1410；
用于存储处理器1410可执行指令的存储器1420；
其中，处理器1410被配置为执行指令，以实现本公开实施例中上述任意一项信息展示方法，例如图2的方法。
在示例性实施例中，还提供了一种包括指令的存储介质，例如包括指令的存储器1420，上述指令可由电子设备1400的处理器1410执行以完成上述方法。在一些实施例中，存储介质可以是非临时性计算机可读存储介质，例如，非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
在本公开实施例中，客户端可以是终端设备，或者安装在终端设备上的应用程序，在客户端为终端设备的情况下，其结构如图15所示，本公开实施例给出一种用于信息展示的终端1500，包括：射频(Radio Frequency，RF)电路1510、电源1520、处理器1530、存储器1540、输入单元1550、显示单元1560、摄像头1570、通信接口1580、以及无线保真(Wireless Fidelity，Wi-Fi)模块1590等部件。本领域技术人员可以理解，图15中示出的终端的结构并不构成对终端的限定，本公开实施例提供的终端可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
下面结合图15对终端1500的各个构成部件进行具体的介绍：
RF电路1510可用于通信或通话过程中，数据的接收和发送。特别地，RF电路1510在接收到基站的下行数据后，发送给处理器1530处理；另外，将待发送的上行数据发送给基站。通常，RF电路1510包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(Low Noise Amplifier，LNA)、双工器等。
此外，RF电路1510还可以通过无线通信与网络和其他终端通信。无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯系统(Global System of Mobile communication，GSM)、通用分组无线服务(General Packet Radio Service，GPRS)、码分多址(Code Division Multiple Access，CDMA)、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)、长期演进(Long Term Evolution，LTE)、电子邮件、短消息服务(Short Messaging Service，SMS)等。
Wi-Fi技术属于短距离无线传输技术，终端1500通过Wi-Fi模块1590可以连接接入点(Access Point，AP)，从而实现数据网络的访问。Wi-Fi模块1590可用于通信过程中，数据的接收和发送。
终端1500可以通过通信接口1580与其他终端实现物理连接。在一些实施例中，通信接口1580与其他终端的通信接口通过电缆连接，实现终端1500和其他终端之间的数据传输。
由于在本公开实施例中，终端1500能够实现通信业务，向其他联系人发送信息，因此终端1500需要具有数据传输功能，即终端1500内部需要包含通信模块。虽然图15示出了RF电路1510、Wi-Fi模块1590、和通信接口1580等通信模块，但是可以理解的是，终端1500中存在上述部件中的至少一个或者其他用于实现通信的通信模块(如蓝牙模块)，以进行数据传输。
例如，当终端1500为手机时，终端1500可以包含RF电路1510，还可以包含Wi-Fi模块1590；当终端1500为计算机时，终端1500可以包含通信接口1580，还可以包含Wi-Fi模块1590；当终端1500为平板电脑时，终端1500可以包含Wi-Fi模块。
存储器1540可用于存储软件程序以及模块。处理器1530通过运行存储在存储器1540的软件程序以及模块，从而执行终端1500的各种功能应用以及数据处理，并且当处理器1530执行存储器1540中的程序代码后，可以实现本公开实施例图8中的部分或全部过程。
在一些实施例中，存储器1540可以主要包括存储程序区和存储数据区。其中，存储程序区可存储操作系统、各种应用程序(比如通信应用)以及人脸识别模块等；存储数据区可存储根据终端的使用所创建的数据(比如各种图片、视频文件等多媒体文件，以及人脸信息模板)等。
此外，存储器1540可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
输入单元1550可用于接收对象输入的数字或字符信息，以及产生与终端1500的对象设置以及功能控制有关的键信号输入。
在一些实施例中，输入单元1550可包括触控面板1551以及其他输入终端1552。
其中，触控面板1551，也称为触摸屏，可收集对象在其上或附近的触摸操作(比如对象使用手指、触笔等任何适合的物体或附件在触控面板1551上或在触控面板1551附近的操作)，并根据预先设定的程式驱动相应的连接装置。在一些实施例中，触控面板1551可以包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测对象的触摸方位，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成触点坐标，再送给处理器1530，并能接收处理器1530发来的 命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板1551。
在一些实施例中，其他输入终端1552可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
显示单元1560可用于显示由对象输入的信息或提供给对象的信息以及终端1500的各种菜单。显示单元1560即为终端1500的显示系统，用于呈现界面，实现人机交互。
显示单元1560可以包括显示面板1561。在一些实施例中，显示面板1561可以采用液晶显示屏(Liquid Crystal Display，LCD)、有机发光二极管(Organic Light-Emitting Diode，OLED)等形式来配置。
进一步的，触控面板1551可覆盖显示面板1561，当触控面板1551检测到在其上或附近的触摸操作后，传送给处理器1530以确定触摸事件的类型，随后处理器1530根据触摸事件的类型在显示面板1561上提供相应的视觉输出。
虽然在图15中，触控面板1551与显示面板1561是作为两个独立的部件来实现终端1500的输入和输入功能，但是在某些实施例中，可以将触控面板1551与显示面板1561集成而实现终端1500的输入和输出功能。
处理器1530是终端1500的控制中心，利用各种接口和线路连接各个部件，通过运行或执行存储在存储器1540内的软件程序和/或模块，以及调用存储在存储器1540内的数据，执行终端1500的各种功能和处理数据，从而实现基于终端的多种业务。
在一些实施例中，处理器1530可包括一个或多个处理单元。在一些实施例中，处理器1530可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、对象界面和应用程序等，调制解调处理器主要处理无线通信。可以理解的是，上述调制解调处理器也可以不集成到处理器1530中。
摄像头1570，用于实现终端1500的拍摄功能，拍摄图片或视频。摄像头1570还可以用于实现终端1500的扫描功能，对扫描对象(二维码/条形码)进行扫描。
终端1500还包括用于给各个部件供电的电源1520(比如电池)。在一些实施例中，电源1520可以通过电源管理系统与处理器1530逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗等功能。
需要说明的是，本公开实施例处理器1530可以执行图14中处理器1415的功能，存储器1540存储存储器1420中的内容。
本公开的一些实施例还提供一种需求识别模型的训练方法。
下面结合图16，对本公开实施例中的需求识别模型的训练方法进行说明。
图16是根据一示例性实施例示出的需求识别模型的训练方法的流程图，如图16所示， 包括以下步骤。
在步骤S161中，获取样本账户的账户特征信息以及样本多媒体资源的属性信息，并根据属性信息以及账户特征信息确定第二输入参数。
在步骤S162中，获取样本账户在样本多媒体资源的播放过程中对应的信息需求特征。
在步骤S163中，将第二输入参数作为需求识别模型的输入特征，将信息需求特征作为需求识别模型的输出特征，对需求识别模型进行训练。
以短视频应用A为例，首先采集历史时段内该应用的整个用户群体在播放多媒体资源时发生的信息获取行为数据来构建样本集合；之后根据采集的样本，利用相关的机器学习算法来训练需求识别模型。
其中，信息获取行为指点外卖、查看旅游攻略等行为。每个样本是根据一个用户观看一个多媒体资源时发生的信息获取行为确定的，也就是一个样本对应一个样本账户以及一个多媒体资源。第二输入参数可以包括根据多媒体资源的属性信息得到的属性词集合、根据样本账户的用户画像得到的特征词集合；信息需求特征可以指用户获取信息页面时对应的特征词集合，可以通过人工分析获取，也可以另外采用页面分析工具来识别获取等。
获取第二输入参数及样本账户在样本多媒体资源的播放过程中对应的信息需求特征后，即可将第二输入参数作为需求识别模型的输入特征，将信息需求特征作为需求识别模型的输出特征，对需求识别模型进行训练。
由于相比于其他机器学习方法，深度学习的方式在大数据集上的表现更好，因此可以通过深度学习的方式训练需求识别模型。通过深度学习的方式训练需求识别模型时，可以将第二输入参数作为输入，将信息需求特征作为需求识别模型的输出特征，通过不断的调整需求识别模型的模型参数对需求识别模型进行迭代训练，直至需求识别模型输出结果的准确率满足预先设定的阈值，训练结束，得到训练好的需求识别模型。
根据用户的历史行为数据可以准确调整需求识别模型的参数，训练得到的需求识别模型用于根据输入的属性词集合、特征词集合等结合进行处理，输出识别得到的对应的一组特征词，作为信息需求特征。以保证根据需求识别模型得到信息需求特征后，用户能够查看与该信息需求特征对应的关联信息，尽可能提高需求识别模型的准确率。
在一些实施方式中，第二输入参数还可以包括样本账户对应的第三历史行为数据；其中，样本账户对应的第三历史行为数据包括样本账户是否查看关联信息和/或针对关联信息样本账户的反馈。
其中，第三历史行为数据指用户是否实施信息获取行为、实施信息获取行为后的信息获取反馈，例如用户是否直接关闭信息页面或者打开信息页面、用户打开信息页面后是否有进一步的操作等。
在上述实施方式中，对需求识别模型训练过程中，将用户的第三历史行为数据也作为输入参数进行训练，结合用户后验信息对模型进行训练，可以有效调整模型参数，使得模型识别的准确更高。
本公开的一些实施例还提供一种计算机程序产品，当计算机程序产品在电子设备上运行时，使得电子设备执行以下步骤：
检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息。
根据本公开的一些实施例，还提供了另一种计算机程序产品，当所述计算机程序产品在电子设备上运行时，使得所述电子设备执行以下步骤：
响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
根据本公开的一些实施例，还提供了另一种计算机程序产品，当所述计算机程序产品在电子设备上运行时，使得所述电子设备执行以下步骤：
响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
本公开的一些实施例，还提供了一种信息展示方法，其中，该方法包括：
检测到对播放的多媒体资源实施的预设操作，获取与所述预设操作对应的第一账户的账户特征信息；
根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
获取与所述信息需求特征对应的关联信息，并向所述第一账户展示所述关联信息。
在一些实施例中，该信息展示方法中的所述获取与所述信息需求特征对应的关联信息， 并向所述第一账户展示所述关联信息，包括：
获取与所述信息需求特征对应的信息来源地址；
获取与所述信息来源地址对应的信息页面作为所述关联信息进行展示。
在一些实施例中，该信息展示方法中的所述账户特征信息包括偏好信息类型；
相应的，通过下列方式确定所述第一账户的偏好信息类型：
获取历史统计时段内所述第一账户的第一历史行为数据，并确定由所述第一账户的第一历史行为数据获取的信息页面中的展示信息；
根据单位时间内获取所述展示信息的数量，确定不同的展示信息类型对应的获取频率，并将所述获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型，作为所述第一账户的偏好信息类型。
在一些实施例中，该信息展示方法中的所述账户特征信息包括偏好信息类型；
相应的，通过下列方式确定所述第一账户的偏好信息类型：
根据与所述第一账户的相似度，选择第二账户，所述第二账户具有偏好信息类型；
将选择的所述第二账户对应的偏好信息类型作为所述第一账户的偏好信息类型。
在一些实施例中，该信息展示方法中的所述根据与所述第一账户的相似度，选择第二账户，包括：
将与所述第一账户相似度最高的账户作为所述第二账户。
在一些实施例中，该信息展示方法中的所述获取与所述信息需求特征对应的信息来源地址，包括：
根据预设的信息需求特征与信息来源地址之间的映射关系，确定与所述信息需求特征对应的信息来源地址；或
根据所述信息需求特征进行信息检索得到至少一个信息页面，并将所述至少一个信息页面中置信度最高的信息页面的地址作为所述信息需求特征对应的信息来源地址。
在一些实施例中，基于所述信息需求特征对应的信息来源地址是根据预设的信息需求特征与信息来源地址之间的映射关系确定的，该信息展示方法还包括：
响应于根据所述第一账户对应的第二历史行为数据确定满足更新条件，更新所述映射关系；
其中，所述第一账户对应的第二历史行为数据包括：所述第一账户是否查看所述客户端展示的不同信息需求特征对应的关联信息，和/或针对所述关联信息所述第一账户的反馈。
在一些实施例中，该信息展示方法中的所述更新条件包括：
根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的 需求不同的次数达到预设数量；或
根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
在一些实施例中，该信息展示方法中的所述根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征，包括：
根据所述多媒体资源的属性信息，获取对应的属性词集合，以及，根据所述账户特征信息，获取对应的特征词集合；
将所述属性词集合以及所述特征词集合作为第一输入参数输入已训练的需求识别模型，获取所述需求识别模型输出的所述第一账户的信息需求特征。
在一些实施例中，该信息展示方法中通过下列方式确定所述属性信息：
提取所述多媒体资源的内容分类信息，作为所述属性信息。
在一些实施例中，该信息展示方法中通过下列方式确定所述属性信息：
通过分词算法提取所述多媒体资源的资源主题名称和/或所述多媒体资源的资源描述信息，作为所述属性信息。
在一些实施例中，该信息展示方法中通过下列方式确定所述属性信息：
将所述多媒体资源的资源帧图像输入已训练的图像识别模型，获取所述图像识别模型输出的资源帧图像的图像内容特征，作为所述属性信息。
在一些实施例中，该信息展示方法中的所述根据所述账户特征信息，获取对应的特征词集合，包括：
根据预设的关键信息类型，从所述账户特征信息中提取符合所述关键信息类型的信息组成特征词集合。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (21)

  1. 一种信息展示方法，其中，应用于服务器，包括：
    响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
    根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
    获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
  2. 如权利要求1所述的方法，其中，所述获取与所述信息需求特征对应的关联信息，包括：
    获取与所述信息需求特征对应的信息来源地址；
    获取与所述信息来源地址对应的信息页面作为所述关联信息。
  3. 如权利要求1所述的方法，其中，所述账户特征信息包括偏好信息类型；
    通过下列方式确定所述第一账户的偏好信息类型：
    获取历史统计时段内所述第一账户的第一历史行为数据，并确定由所述第一账户的第一历史行为数据获取的信息页面中的展示信息；
    根据单位时间内获取所述展示信息的数量，确定不同的展示信息类型对应的获取频率，并将所述获取频率高于第一频率阈值的展示信息类型或获取频率的降序排序次序在预设次序范围内的展示信息类型，作为所述第一账户的偏好信息类型。
  4. 如权利要求1所述的方法，其中，所述账户特征信息包括偏好信息类型；
    通过下列方式确定所述第一账户的偏好信息类型：
    根据与所述第一账户的相似度，选择第二账户，所述第二账户具有偏好信息类型；
    将选择的所述第二账户对应的偏好信息类型作为所述第一账户的偏好信息类型。
  5. 如权利要求4所述的方法，其中，根据与所述第一账户的相似度，选择第二账户，包括：
    将与所述第一账户相似度最高的账户作为所述第二账户。
  6. 如权利要求2所述的方法，其中，所述获取与所述信息需求特征对应的信息来源地址，包括：
    根据预设的信息需求特征与信息来源地址之间的映射关系，确定与所述信息需求特征对应的信息来源地址；或
    根据所述信息需求特征进行信息检索得到至少一个信息页面，并将所述至少一个信息页面中置信度最高的信息页面的地址作为所述信息需求特征对应的信息来源地址。
  7. 如权利要求6所述的方法，其中，基于所述信息需求特征对应的信息来源地址是根据预设的信息需求特征与信息来源地址之间的映射关系确定的，所述方法还包括：
    响应于根据所述第一账户对应的第二历史行为数据确定满足更新条件，更新所述映射关系；
    其中，所述第一账户对应的第二历史行为数据包括：所述第一账户是否查看所述客户端展示的不同信息需求特征对应的关联信息，和/或针对所述关联信息所述第一账户的反馈。
  8. 如权利要求7所述的方法，其中，所述更新条件包括：
    根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的次数达到预设数量；或
    根据所述第二历史行为数据确定展示的关联信息所对应的需求与至少一个第一账户的需求不同的频率达到第二频率阈值。
  9. 如权利要求1所述的方法，其中，所述根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征，包括：
    根据所述多媒体资源的属性信息，获取对应的属性词集合，以及，根据所述账户特征信息，获取对应的特征词集合；
    将所述属性词集合以及所述特征词集合作为第一输入参数输入已训练的需求识别模型，获取所述需求识别模型输出的所述第一账户的信息需求特征。
  10. 如权利要求1～9任一所述的方法，其中，通过下列方式确定所述属性信息：
    提取所述多媒体资源的内容分类信息，作为所述属性信息。
  11. 如权利要求1～9任一所述的方法，其中，通过下列方式确定所述属性信息：
    通过分词算法提取所述多媒体资源的资源主题名称和/或所述多媒体资源的资源描述信息，作为所述属性信息。
  12. 如权利要求1～9任一所述的方法，其中，通过下列方式确定所述属性信息：
    将所述多媒体资源的资源帧图像输入已训练的图像识别模型，获取所述图像识别模型输出的资源帧图像的图像内容特征，作为所述属性信息。
  13. 如权利要求9所述的方法，其中，所述根据所述账户特征信息，获取对应的特征词集合，包括：
    根据预设的关键信息类型，从所述账户特征信息中提取符合所述关键信息类型的信息组成特征词集合。
  14. 一种信息展示方法，其中，应用于客户端，包括：
    响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
    接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
  15. 一种信息展示系统，其中，包括：客户端和服务器；
    所述客户端，用于响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息；
    所述服务器，用于响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息；根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端。
  16. 一种信息展示装置，其中，包括：
    第二信息获取单元，被配置为执行响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
    第二特征检测单元，被配置为执行根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
    第二信息展示单元，被配置为执行获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给客户端，以使所述客户端向所述第一账户展示所述关联信息。
  17. 一种信息展示装置，其中，包括：
    预设操作检测单元，被配置为执行响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
    第三信息展示单元，被配置为执行接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
  18. 一种电子设备，其中，包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令，以实现以下步骤：
    响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
    根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
    获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
  19. 一种电子设备，其中，包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令，以实现以下步骤：
    响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
    接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
  20. 一种存储介质，其中，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
    响应于接收到客户端发送的信息获取指令，获取实施预设操作的第一账户的账户特征信息，其中所述信息获取指令为所述客户端检测到对播放的多媒体资源实施的所述预设操作后触发的；
    根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征；
    获取与所述信息需求特征对应的关联信息，并将所述关联信息返回给所述客户端，以使所述客户端向所述第一账户展示所述关联信息。
  21. 一种存储介质，其中，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行以下步骤：
    响应于检测到对播放的多媒体资源实施的预设操作，向服务器发送信息获取指令；
    接收所述服务器返回的关联信息，并向实施所述预设操作的第一账户展示所述关联信息，其中所述关联信息为所述服务器根据所述多媒体资源的属性信息以及所述账户特征信息，确定所述第一账户的信息需求特征后，获取的与所述信息需求特征对应的关联信息。
PCT/CN2021/076227 2020-02-14 2021-02-09 一种信息展示方法及装置 WO2021160119A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010093249.7A CN111309940A (zh) 2020-02-14 2020-02-14 一种信息展示方法、系统、装置、电子设备及存储介质
CN202010093249.7 2020-02-14

Publications (1)

Publication Number Publication Date
WO2021160119A1 true WO2021160119A1 (zh) 2021-08-19

Family

ID=71161663

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/076227 WO2021160119A1 (zh) 2020-02-14 2021-02-09 一种信息展示方法及装置

Country Status (2)

Country Link
CN (1) CN111309940A (zh)
WO (1) WO2021160119A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111309940A (zh) * 2020-02-14 2020-06-19 北京达佳互联信息技术有限公司 一种信息展示方法、系统、装置、电子设备及存储介质
CN111698564B (zh) * 2020-07-27 2021-12-21 腾讯科技（深圳）有限公司 信息推荐方法、装置、设备及存储介质
CN114154050A (zh) * 2020-09-07 2022-03-08 北京达佳互联信息技术有限公司 推荐方法、特征生成网络的训练方法、装置、电子设备
CN112256967A (zh) * 2020-10-27 2021-01-22 北京字跳网络技术有限公司 一种行程推荐方法、装置、设备及存储介质
CN113157370B (zh) * 2021-04-14 2024-01-12 北京达佳互联信息技术有限公司 页面展示方法、装置、电子设备及存储介质
CN113254135A (zh) * 2021-05-28 2021-08-13 北京达佳互联信息技术有限公司 界面处理方法、装置及电子设备
CN113901114A (zh) * 2021-10-25 2022-01-07 北京达佳互联信息技术有限公司 数据展示方法、装置、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170366834A1 (en) * 2015-11-20 2017-12-21 Tencent Technology (Shenzhen) Company Limited Method, device and system for presenting information
CN108184143A (zh) * 2016-12-08 2018-06-19 腾讯科技（深圳）有限公司 获取资源的方法及装置
CN108833948A (zh) * 2018-06-14 2018-11-16 广州视源电子科技股份有限公司 商品推送方法、系统、可读存储介质及终端
CN110035314A (zh) * 2019-03-08 2019-07-19 腾讯科技（深圳）有限公司 信息的展示方法和装置、存储介质、电子装置
CN111309940A (zh) * 2020-02-14 2020-06-19 北京达佳互联信息技术有限公司 一种信息展示方法、系统、装置、电子设备及存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150296250A1 (en) * 2014-04-10 2015-10-15 Google Inc. Methods, systems, and media for presenting commerce information relating to video content
CN106598998B (zh) * 2015-10-20 2020-10-27 北京安云世纪科技有限公司 信息获取方法和信息获取装置
US9838743B2 (en) * 2016-02-25 2017-12-05 Adobe Systems Incorporated Techniques for context aware video recommendation
CN109831684B (zh) * 2019-03-11 2022-08-19 深圳前海微众银行股份有限公司 视频优化推荐方法、装置及可读存储介质
CN110442790B (zh) * 2019-08-07 2024-05-10 深圳市雅阅科技有限公司 推荐多媒体数据的方法、装置、服务器和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170366834A1 (en) * 2015-11-20 2017-12-21 Tencent Technology (Shenzhen) Company Limited Method, device and system for presenting information
CN108184143A (zh) * 2016-12-08 2018-06-19 腾讯科技（深圳）有限公司 获取资源的方法及装置
CN108833948A (zh) * 2018-06-14 2018-11-16 广州视源电子科技股份有限公司 商品推送方法、系统、可读存储介质及终端
CN110035314A (zh) * 2019-03-08 2019-07-19 腾讯科技（深圳）有限公司 信息的展示方法和装置、存储介质、电子装置
CN111309940A (zh) * 2020-02-14 2020-06-19 北京达佳互联信息技术有限公司 一种信息展示方法、系统、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN111309940A (zh) 2020-06-19

Similar Documents

Publication Publication Date Title
WO2021160119A1 (zh) 一种信息展示方法及装置
US11290775B2 (en) Computerized system and method for automatically detecting and rendering highlights from streaming videos
US11810576B2 (en) Personalization of experiences with digital assistants in communal settings through voice and query processing
CN109086439B (zh) 信息推荐方法及装置
CN106792003B (zh) 一种智能广告插播方法、装置及服务器
US10621220B2 (en) Method and system for providing a personalized snippet
US20210218696A1 (en) Method and device for commenting on multimedia resource
CN110209810B (zh) 相似文本识别方法以及装置
KR20160055930A (ko) 연속적인 소셜 커뮤니케이션에 사용되는 콘텐츠를 능동적으로 구성하기 위한 시스템 및 방법
US20150254349A1 (en) System and Method for Providing Content in Real-Time
JP7197930B2 (ja) ロケーションベースの個人用コンテンツを提供する方法及びシステム
CN112104642B (zh) 一种异常账号确定方法和相关装置
CN110175223A (zh) 一种实现问题生成的方法及装置
CN110035302B (zh) 信息推荐及模型训练方法和装置、计算设备、存储介质
CN111259257A (zh) 一种信息展示方法、系统、装置、电子设备及存储介质
CN111722766A (zh) 多媒体资源的展示方法及装置
WO2017210644A1 (en) System and method for a platform to identify and connect like-minded individuals based on interaction
CN109101505A (zh) 一种推荐方法、推荐装置和用于推荐的装置
CN110162691B (zh) 在线内容服务中的话题推荐、运营方法、装置和机器设备
CN116016421A (zh) 促进在计算装置中执行的基于媒体的内容共享的方法、计算装置可读存储介质以及计算装置
CN115168568A (zh) 一种数据内容的识别方法、装置以及存储介质
CN116340550A (zh) 一种文本标签的确定方法和相关装置
CN116453005A (zh) 一种视频封面的提取方法以及相关装置
CN113420209A (zh) 基于天气搜索的推荐方法、装置、设备及存储介质
CN114969493A (zh) 一种内容推荐方法和相关装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21753152

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21753152

Country of ref document: EP

Kind code of ref document: A1