CN114092166A - Information recommendation processing method, device, equipment and computer readable storage medium - Google Patents

Information recommendation processing method, device, equipment and computer readable storage medium Download PDF

Info

Publication number
CN114092166A
CN114092166A CN202010761072.3A CN202010761072A CN114092166A CN 114092166 A CN114092166 A CN 114092166A CN 202010761072 A CN202010761072 A CN 202010761072A CN 114092166 A CN114092166 A CN 114092166A
Authority
CN
China
Prior art keywords
image
information
information flow
displaying
page
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
CN202010761072.3A
Other languages
Chinese (zh)
Inventor
张鹏元
蔡博仑
张华薇
林满琪
何翼
黄华杰
许典平
赵宇
项梦
罗文柱
蒙剑琴
梁尚韬
林榆耿
彭菁
袁延钊
于鸿洋
刘泳文
魏智鹏
盛晟
李娜
梁超才
邓德胜
卢子建
阳福林
石光敏
闫青青
陈添
彭崇
叶绿珊
郑炜城
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
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 Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN202010761072.3A priority Critical patent/CN114092166A/en
Publication of CN114092166A publication Critical patent/CN114092166A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0641—Shopping interfaces
    • G06Q30/0643—Graphical representation of items or shoppers

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The application provides an information recommendation processing method, an information recommendation processing device, electronic equipment and a computer-readable storage medium; the method comprises the following steps: displaying an information flow page; displaying the acquired image in response to an image recognition trigger operation received in the information flow page; and when the acquired image comprises an interactive object and the interactive object is associated with the article to be recommended in the information flow page, presenting an interactive result related to the article to be recommended. Through the method and the device, the recommendation efficiency of the article to be recommended can be improved.

Description

Information recommendation processing method, device, equipment and computer readable storage medium
Technical Field
The present disclosure relates to internet technologies, and in particular, to an information recommendation method and apparatus, an electronic device, and a computer-readable storage medium.
Background
With the development of the internet technology, the recommendation information is inserted into the information flow page, so that diversified information display of information flow can be realized, and recommendation information drainage can also be realized.
Disclosure of Invention
The embodiment of the application provides an information recommendation processing method and device, an electronic device and a computer-readable storage medium, which can realize accurate recommendation of information.
The technical scheme of the embodiment of the application is realized as follows:
the embodiment of the application provides an information recommendation processing method, which comprises the following steps:
displaying an information flow page;
displaying the acquired image in response to an image recognition trigger operation received in the information flow page;
and when the acquired image comprises an interactive object and the interactive object is associated with the article to be recommended in the information flow page, presenting an interactive result related to the article to be recommended.
In the above aspect, the method further includes:
responding to the sharing operation aiming at the interaction result, and sending a sharing message corresponding to the interaction object;
and the sharing message is used for jumping to the image recognition entrance when being triggered.
In the above scheme, the presenting the interaction result related to the item to be recommended includes:
determining a difference between an interactive object identified from the acquired image and an interactive object graph, determining a score of the acquired image according to the difference, and presenting an interactive result associated with the score;
wherein the difference comprises at least one of:
a difference in position between the identified interactive object and the interactive object representation;
a state difference between the identified interactive object and the interactive object representation;
an image quality difference between the identified interactive object and the interactive object representation.
In the above scheme, the presenting the interaction result related to the item to be recommended includes:
determining a score for each of the captured images based on differences between the interactive object identified from each of the captured images and the graphical representation of the interactive object;
determining the number of images with scores exceeding a score threshold, and presenting interaction results associated with the number.
An embodiment of the present application provides an information recommendation processing apparatus, including:
the display module is used for displaying the information flow page;
the triggering module is used for responding to the image identification triggering operation received in the information flow page and displaying the acquired image;
and the interaction module is used for presenting an interaction result related to the to-be-recommended article when the acquired image comprises an interaction object and the interaction object is related to the to-be-recommended article in the information flow page.
In the foregoing solution, the display module is further configured to:
displaying a first hierarchical information flow page;
the first-level information flow page is an information flow page displayed by default when a client is started, and information flow in the first-level information flow page comprises at least one of the following: logging in at least one historical session in which an account participates; a subscription message of a login account; and (4) notification information of the login account.
In the foregoing solution, the display module is further configured to:
displaying an image recognition entry in the first hierarchical information flow page;
determining to be the image recognition trigger operation when a trigger for the image recognition portal is received.
In the foregoing solution, the display module is further configured to:
displaying a second level information flow page;
and the information flow of the second-level information flow page comprises the social dynamics of the login account.
In the foregoing solution, the display module is further configured to:
inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page;
and determining the received trigger operation aiming at the recommendation information as the image recognition trigger operation.
In the foregoing solution, the display module is further configured to:
inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page;
in response to a trigger operation for the recommendation information, presenting a detail page of the recommendation information, and displaying an image recognition entry in the detail page;
and determining that the trigger operation aiming at the image recognition entrance is received as the image recognition trigger operation.
In the above solution, the apparatus further comprises: a sharing module to:
responding to the sharing operation aiming at the interaction result, and sending a sharing message corresponding to the interaction object;
and the sharing message is used for jumping to the image recognition entrance when being triggered.
In the foregoing solution, when displaying the image recognition entry, the display module is further configured to:
displaying first prompt information to prompt an interactive object to be acquired;
wherein the first prompt message includes at least one of: introduction information of the interactive object and a graphic representation of the interactive object.
In the foregoing solution, the display module is further configured to:
when the acquired image does not comprise an interactive object associated with the article to be recommended in the information flow page, presenting second prompt information to prompt the image acquisition to be continued;
when the acquired image comprises an interactive object associated with the item to be recommended, presenting a special effect corresponding to the interactive object;
wherein the special effects include at least one of:
animation, warning sound and vibration feedback.
In the above scheme, the interaction module is further configured to:
identifying the state of the interactive object and presenting an interactive result associated with the state of the interactive object;
wherein the interactive object comprises at least one of: limb, hand, face;
the state of the interactive object comprises at least one of: limb movements, gestures, facial expressions;
the interaction result comprises at least one of the following: electronic red envelope, electronic redemption ticket, electronic discount ticket.
In the above scheme, the interaction module is further configured to:
determining a valid image for target recognition from the acquired images;
calling an object recognition model to perform target recognition on the effective image so as to determine the type of an object included in the effective image;
and calling a state type identification model to perform key point positioning processing on the object included in the effective image to obtain the state of the object.
In the above scheme, the interaction module is further configured to:
when the acquired image is a static image acquired by taking a picture, determining the static image as an effective image for target identification;
when the collected image is a dynamic video frame collected by shooting a video, determining a video frame meeting at least one of the following conditions in a plurality of video frames as an effective image for target identification:
the average value of the frame difference between the video frame and the adjacent video frame is smaller than a still frame threshold value;
the variance of the first order gradient of the video frame is greater than a sharpness threshold.
In the above scheme, the interaction module is further configured to: before determining a valid image for object recognition from the acquired images:
acquiring a recommended validity period;
determining that an operation of determining a valid image for object recognition from the captured images is to be performed when the capturing time of the captured images is within the recommended validity period.
In the above scheme, the interaction module is further configured to:
determining a difference between an interactive object identified from the acquired image and an interactive object graph, determining a score of the acquired image according to the difference, and presenting an interactive result associated with the score;
wherein the difference comprises at least one of:
a difference in position between the identified interactive object and the interactive object representation;
a state difference between the identified interactive object and the interactive object representation;
an image quality difference between the identified interactive object and the interactive object representation.
In the above scheme, the interaction module is further configured to:
determining a score for each of the captured images based on differences between the interactive object identified from each of the captured images and the graphical representation of the interactive object;
determining the number of images with scores exceeding a score threshold, and presenting interaction results associated with the number.
An embodiment of the present application provides an electronic device, including:
a memory for storing executable instructions;
and the processor is used for realizing the information recommendation processing method provided by the embodiment of the application when the executable instructions stored in the memory are executed.
The embodiment of the application provides a computer-readable storage medium, which stores executable instructions and is used for causing a processor to execute the method for processing information recommendation provided by the embodiment of the application.
The embodiment of the application has the following beneficial effects:
the interaction of the recommended articles is fused in the information flow page, so that the recommended information accurately meets the requirements of a user in an information flow browsing scene, and the interaction result related to the articles to be recommended is presented in a man-machine interaction mode, so that the presentation mode of the articles to be recommended can be enriched to improve the recommendation efficiency of the articles to be recommended, and diversified user interaction experience can be provided.
Drawings
Fig. 1 is a schematic structural diagram of an information recommendation processing system architecture provided in an embodiment of the present application;
fig. 2 is a schematic structural diagram of a terminal of an information recommendation processing method provided in an embodiment of the present application;
3A-3C are schematic flow charts of information recommendation processing methods provided by embodiments of the present application;
FIGS. 4A-4L are schematic interface diagrams of an information recommendation processing method provided in an embodiment of the application;
FIG. 5 is a schematic view of an identification process of an information recommendation processing method provided in an embodiment of the application;
6A-6B are schematic model diagrams of an information recommendation processing method provided by the embodiment of the application;
fig. 7 is a schematic diagram illustrating an identification principle of an information recommendation processing method according to an embodiment of the present application.
Detailed Description
In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, references to the terms "first", "second", and the like are only used for distinguishing similar objects and do not denote a particular order or importance, but rather the terms "first", "second", and the like may be used interchangeably with the order of priority or the order in which they are expressed, where permissible, to enable embodiments of the present application described herein to be practiced otherwise than as specifically illustrated and described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.
Before further detailed description of the embodiments of the present application, terms and expressions referred to in the embodiments of the present application will be described, and the terms and expressions referred to in the embodiments of the present application will be used for the following explanation.
1) Information stream ((Feeds) advertisement: advertisements displayed in social media user friend trends, or information media and audiovisual media content streams;
2) single-point Detector (SSD): the characteristic pyramid structure is adopted for detection, namely, the characteristic graphs with different sizes are used for simultaneously carrying out classification and position regression on a plurality of characteristic graphs during detection.
In the related technology, the interaction form of the article to be recommended is usually to attract a user to click in a format of characters, buttons, cards, pictures, videos and the like, the article to be recommended enters an advertisement page of the article to be recommended after the clicking operation of the user is received, and an applicant finds that the recommending mode of the article to be recommended in the related technology is lack of clicking power for the user in the process of implementing the embodiment of the application, so that the conversion of advertisements is influenced.
Embodiments of the present application provide an information recommendation processing method and apparatus, an electronic device, and a computer-readable storage medium, which can improve recommendation efficiency of an item to be recommended, and an exemplary application of the electronic device provided in the embodiments of the present application is described below. In the following, an exemplary application will be explained when the device is implemented as a terminal.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an information recommendation processing system architecture provided in an embodiment of the present application, fig. 1 shows an information recommendation processing system 100, a terminal 400 is connected to a delivery server 200-1 and a computing server 200-2 through a network 300-1, and the network 300-1 may be a wide area network or a local area network, or a combination of the two. According to different releasing contents, the releasing server can be used for releasing advertisements for the advertisement server, and can also be used for releasing news for the news server.
The launching server 200-1 launches the monitoring task and the advertisement configuration to the terminal 400, the terminal 400 presents an information stream, an image recognition entrance is presented in the information stream, when the image recognition triggering operation is monitored, an image is collected and the collected image and the advertisement configuration are sent to the computing server 200-2 for target recognition, when the recognized result is consistent with the advertisement configuration, the recognition result is returned to the terminal 400, and the terminal 400 presents the advertisement information corresponding to the recognition result.
Referring to fig. 1, both the server and the terminal may join the blockchain network 300-2 as one of the nodes. The type of blockchain network 300-2 is flexible and may be, for example, any of a public chain, a private chain, or a federation chain. Taking a public link as an example, an electronic device such as a terminal of any service subject may access the blockchain network 300-2 without authorization, so as to serve as a common node of the blockchain network 300-2, for example, the delivery server 200-1 is mapped to the common node 300-1 in the blockchain network 300-2, the calculation server 200-2 is mapped to the common node 300-2 in the blockchain network 300-2, and the terminal 400 is mapped to the common node 300-0 in the blockchain network 300-2.
Taking the blockchain network 300-2 as an example of a alliance chain, the electronic devices under the jurisdiction of the server and the terminal can access the blockchain network after obtaining authorization. The client side of the terminal 400 receives an interactive object acquisition request of an initiator, the computing server 200-2 sends a proposal for determining an interactive object to the releasing server 200-1 and other terminals, the releasing server 200-1 and other terminals can verify the proposal for determining an interactive result by executing an intelligent contract, when the verification is confirmed by nodes exceeding a number threshold value, the verifying mode is to inquire whether the terminal 400 has the authority for acquiring the interactive result in an account book of a block chain network and whether the interactive result corresponding to a category has a stock, each releasing server 200-1 and other terminals sign digital signatures (i.e. endorsements) after the verification is passed, when one proposal for determining the interactive result has enough endorsements, the jump page address of the interactive result is determined, and the jump page address of the interactive result is returned to the terminal to present the interactive result, the method for carrying out consensus verification on the virtual resource proposal to be presented through the plurality of nodes can save the cost for verifying the proposal of the determined interaction result to be presented by the server, and the virtual resources are encapsulated in the interaction result, so that the risk of repeatedly issuing the interaction result or excessively issuing the interaction result can be reduced by ensuring the reliability of the proposal.
In some embodiments, the terminal implements the session processing method provided by the embodiments of the present application by running a computer program, where the computer program may be a native program or a software module in an operating system; can be a local (Native) Application program (APP), i.e. a program that needs to be installed in an operating system to run; or may be an applet, i.e. a program that can be run only by downloading it to the browser environment; but also an instant messaging applet or file management applet that can be embedded in any APP. In general, the computer program may be any application, module or plug-in that may be in any form.
In some embodiments, the server may be an independent physical server, may also be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform. The terminal 400 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, and the like. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the embodiment of the present application is not limited.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a terminal applying the information recommendation method according to an embodiment of the present application, and the terminal 400 shown in fig. 2 includes: at least one processor 410, memory 450, at least one network interface 420, and a user interface 430. The various components in the terminal 400 are coupled together by a bus system 440. It is understood that the bus system 440 is used to enable communications among the components. The bus system 440 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 440 in fig. 2.
The Processor 410 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The user interface 430 includes one or more output devices 431, including one or more speakers and/or one or more visual displays, that enable the display of media content. The user interface 430 also includes one or more input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
The memory 450 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 450 optionally includes one or more storage devices physically located remote from processor 410.
The memory 450 includes either volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The nonvolatile memory may be a Read Only Memory (ROM), and the volatile memory may be a Random Access Memory (RAM). The memory 450 described in embodiments herein is intended to comprise any suitable type of memory.
In some embodiments, memory 450 is capable of storing data, examples of which include programs, modules, and data structures, or a subset or superset thereof, to support various operations, as exemplified below.
An operating system 451, including system programs for handling various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and handling hardware-based tasks;
a network communication module 452 for communicating to other computing devices via one or more (wired or wireless) network interfaces 420, exemplary network interfaces 420 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;
a display module 453 for enabling display of information (e.g., user interfaces for operating peripherals and displaying content and information) via one or more output devices 431 (e.g., display screens, speakers, etc.) associated with user interface 430;
an input processing module 454 for detecting one or more user inputs or interactions from one of the one or more input devices 432 and translating the detected inputs or interactions.
In some embodiments, the information recommendation processing apparatus provided in the embodiments of the present application may be implemented in software, and fig. 2 shows the information recommendation processing apparatus 455 stored in the memory 450, which may be software in the form of programs and plug-ins, and includes the following software modules: a display module 4551, a trigger module 4552, an interaction module 4553 and a sharing module 4554, which are logical and thus may be arbitrarily combined or further divided according to functions implemented, and functions of the respective modules will be described hereinafter.
The information recommendation processing method provided by the embodiment of the present application will be described in conjunction with exemplary applications and implementations of the terminal provided by the embodiment of the present application, and an execution subject of the following method is the terminal, and specifically, the terminal may be implemented by running the above various computer programs; of course, as will be understood from the following description, it is understood that the information recommendation processing method provided in the embodiments of the present application may be cooperatively implemented by a terminal and a server.
Referring to fig. 3A, fig. 3A is a schematic flowchart of an information recommendation processing method provided in an embodiment of the present application, and will be described with reference to the steps shown in fig. 3A.
In step 101, an information flow page is displayed.
In some embodiments, the displaying the information flow page in step 101 may be implemented by the following technical solutions: displaying a first hierarchical information flow page; the first-level information flow page is an information flow page displayed by default when the client is started, and the information flow in the first-level information flow page comprises at least one of the following: logging in at least one historical session in which an account participates; a subscription message of a login account; and (4) notification information of the login account.
By way of example, the information flow page includes a first hierarchical information flow page and a second hierarchical information flow page, the first hierarchical information flow page may be a social information flow in a social media client having a social relationship with a social network account, for example, the login account of lee has three friends, and the three friends and the login account of lee both have history sessions, the first hierarchical information flow includes history sessions between the three friends and the login account of lee, there is a subscription message for the login account of lee, for example, there is a history message for the login account of lee subscribing to the public number, these history messages may also be part of the first level information flow page, and notification messages of services used by the lee's login account, which are services purchased in the identity of the login account, may also be part of the first level information flow page.
In some embodiments, when displaying the first hierarchical information flow page, the following technical solutions may also be performed: displaying an image recognition entry in a first hierarchical information flow page; and determining that the trigger aiming at the image recognition entrance is received as the image recognition trigger operation.
As an example, an image recognition entry is displayed in a first hierarchical information flow page, where the image recognition entry in the first hierarchical information flow page may be a function control that hovers within the first hierarchical information flow page, or may be a top or bottom component of the first hierarchical information flow, and a trigger received to be sent by a display driver of the operating system to the image recognition entry is determined to be an image recognition trigger operation.
In some embodiments, the displaying the information flow page in step 101 may be implemented by the following technical solutions: displaying a second level information flow page; and the information flow of the second-level information flow page comprises the social dynamics of the login account.
As an example, the information flow in the second-level information flow page includes social dynamics of the login account, for example, the microblog homepage is the second-level information flow page, and the social dynamics of the login account and the social dynamics of the account having a social relationship with the login account are presented in the second-level information flow page. The second hierarchical information flow page may also present information presented by a particular application client, for example, the second hierarchical information flow page may be a first page information flow of a news client, including a plurality of news information.
In some embodiments, when displaying the second-level information flow page, the following technical scheme can be further executed: inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page; and determining the received trigger operation aiming at the recommendation information as an image recognition trigger operation.
As an example, a piece of recommendation information is inserted and displayed in the information stream of the second-level information stream page, for example, a piece of recommendation information is inserted and displayed in the social dynamics of the login account and the social dynamics of the account having a social relationship with the login account, where the piece of recommendation information is neither published by the login account nor published by the account having a social relationship with the login account, for example, a piece of recommendation information is inserted and displayed in the information stream (pieces of news information) of the top page of the news client, and the piece of recommendation information is not published by the news information.
Referring to fig. 3B, fig. 3B is a schematic flowchart of an information recommendation processing method provided in an embodiment of the present application, and will be described with reference to the steps shown in fig. 3B. The displaying of the information flow page in step 101 can be implemented in steps 1011 and 1013.
In step 1011, at least one piece of recommendation information is inserted and displayed in the information flow of the second level information flow page.
In step 1012, in response to a trigger operation for the recommendation information, a detail page of the recommendation information is presented, and an image recognition entry is displayed in the detail page.
As an example, displaying the image recognition entry in the detail page may be specifically implemented by: displaying the image recognition entry in a page floating on the detail page, wherein the page floating on the detail page can be a floating area control, or displaying the image recognition entry in a bottom component of the detail page, and displaying an interactive prompt message at the same time of displaying the image recognition entry so as to prompt activity details and prompt a user to generate an operation triggering the image recognition entry.
In step 1013, the trigger operation for the image recognition portal is received and determined as the image recognition trigger operation.
In some embodiments, when displaying the image recognition entry, the following technical solutions may also be performed: displaying first prompt information to prompt an interactive object to be acquired; wherein the first prompt message includes at least one of: introduction information of the interactive object and a graphic representation of the interactive object.
By way of example, the introductory information of the interactive object includes the brand name of the item to be recommended, the type of the interactive object, such as limb, hand, face, etc., the type of the interactive object may also be an item, such as flower, ticket, poster, cola, etc., and the introductory information may further include the status of the interactive object, such as limb movement, gesture, facial expression, cola placement, etc.
In step 102, an image acquisition interface is called to acquire an image in response to an image identification triggering operation received in an information flow page, and the acquired image is displayed in a preview page and target identification is performed.
In some embodiments, the following technical solutions may also be implemented: determining a valid image for target identification from the acquired images; calling an object recognition model to perform target recognition on the effective image so as to determine the type of an object included in the effective image; and calling a state type identification model to perform key point positioning processing on the object included in the effective image to obtain the state of the object.
As an example, the object recognition model may be a single-point detector, and a lightweight and efficient backbone network structure is constructed on the basis of the single-point detector by using a BlazeBlock-like base unit, wherein the multi-scale output of the single-point detector is improved to be a single-head output, so that the processing maximum threshold and the complexity of calculation are reduced. The state type recognition model is a 21-point three-dimensional skeleton regression model, the 21-point three-dimensional skeleton regression model is constructed through a backbone network structure similar to a single-point detector, the classification probability of gestures is output while the key points of the regression skeleton are positioned, and the false detection is restrained while the model learning is assisted. And finally, normalizing (subtracting the mean value and removing the variance) the three-dimensional skeleton coordinates on each dimension to obtain normalized feature vectors, and realizing the classification of multiple states of each interactive object through a 3-layer fully-connected multilayer perceptron.
As an example, the process of calling the object recognition model and the process of calling the state type recognition model may be implemented at a server, the server returns a recognition result, the recognition result includes a skip identifier, that is, a page of a corresponding interaction result is skipped to, and the recognition result may include second prompt information to prompt that the recognition cannot pass and information that image acquisition needs to be performed again.
In some embodiments, the above determining the effective image for target recognition from the acquired images may be implemented by the following technical solutions: when the acquired image is a static image acquired by taking a picture, determining the static image as an effective image for target identification; when the collected image is a dynamic video frame collected by shooting a video, determining a video frame meeting at least one of the following conditions in a plurality of video frames as an effective image for target identification: the average value of the frame difference between the video frame and the adjacent video frame is smaller than the still frame threshold value; the variance of the first order gradient of the video frame is greater than the sharpness threshold.
As an example, the static image may be a photo, the photo may be a shot photo or the photo may be a stored photo (locally stored or remotely stored), the static image may be directly used as an effective image for performing target recognition, further sharpness recognition may be performed on the static image, that is, a variance of a first-order gradient of the static image is calculated, and if the variance of the first-order gradient is greater than a set sharpness threshold, the static image is represented to be sharp, that is, the clear static image is used as an effective image for performing target recognition, otherwise, prompt information is presented to prompt that the static image does not meet recognition requirements and needs to be acquired for a second time.
As an example, the collected images may be dynamic videos, that is, the collected images are a plurality of dynamic video frames collected by shooting a video, an effective image for target identification needs to be obtained from the plurality of video frames, and a clear video frame, a still video frame, or a clear and still video frame in all the video frames needs to be used as an effective image for target identification, so as to ensure accuracy of subsequent object and state identification, thereby improving the calculation efficiency of the calculation server and reducing the waste of server resources.
In some embodiments, before determining a valid image for target recognition from the acquired images, the following technical solutions may also be performed: acquiring a recommended validity period; when the acquisition time of the acquired image is within the recommended validity period, it is determined that an operation of determining a valid image for object recognition from the acquired image will be performed.
As an example, the recommendation validity period may be obtained from a background server, the recommendation validity period may be a presentation time of the recommendation information, for example, if a piece of recommendation information is released from 8 o 'clock at 1 month 1 morning of 2020 and is displayed until 8 o' clock at 1 month 3 morning of 2020, the time period during this period is the recommendation validity period, determining that the operation of determining a valid image for target recognition from the captured images is to be performed within a recommended validity period, which may be a valid participation time of an interactive activity in the recommendation information, such as including an interactive activity in the recommendation information, the interactive activity starts from 8 o 'clock at 1 month 1 morning of 2020, and will continue to 8 o' clock at 1 month 3 morning of 2020, the time period during this is the recommended validity period, when the recommended validity period is within, it is determined that an operation of determining a valid image for object recognition from the captured images will be performed.
In step 103, when the acquired image includes an interactive object and the interactive object is associated with an item to be recommended in the information flow page, an interactive result related to the item to be recommended is presented.
As an example, the item to be recommended may be a physical product, such as a cosmetic; the item to be recommended may be a virtual item, such as a game item; the item to be recommended may be a software product, such as software that provides various services.
In some embodiments, the following technical solutions may also be implemented: responding to the sharing operation aiming at the interaction result, and sending a sharing message corresponding to the interaction object; and the sharing message is used for jumping to an image recognition entrance when being triggered.
As an example, the sharing message includes a captured photo/video and an interaction result, in the process of image capture, if a still image is captured, the sharing message includes the captured still image, if a plurality of video frames in a dynamic video are captured, the sharing message includes all video frames, that is, the dynamic video, the interaction result includes an electronic red envelope, an electronic coupon, and an electronic discount coupon, the sharing message may further include an image recognition portal link, so that more users may participate in the interaction through the link, and the link may jump to the image recognition portal.
In some embodiments, the following technical solutions may also be implemented: when the acquired image does not comprise an interactive object associated with the article to be recommended in the information flow page, presenting second prompt information to prompt the image acquisition to be continued; when the acquired image comprises an interactive object associated with the article to be recommended, presenting a special effect corresponding to the interactive object; wherein the special effects include at least one of: animation, warning sound and vibration feedback.
As an example, when the acquired image does not include an interactive object associated with an item to be recommended in the information flow page, for example, the interactive object is a hand, if the acquired image does not include the hand, the second prompt information is directly returned to prompt that image acquisition needs to be continued, and when the acquired image includes the hand, a special effect corresponding to the interactive object is presented; wherein the special effects include at least one of: the animation, the prompt tone, the vibration feedback and the special effect can further comprise a screen capture effect, namely the special effect of capturing a screen of a video frame serving as an effective image in a static image or a dynamic video is presented.
In some embodiments, the presenting of the interaction result related to the item to be recommended in step 103 may be implemented by the following technical solutions: identifying the state of the interactive object and presenting an interactive result associated with the state of the interactive object; wherein the interactive object comprises at least one of: limb, hand, face; the state of the interactive object includes at least one of: limb movements, gestures, facial expressions; the interaction result comprises at least one of the following: electronic red envelope, electronic redemption ticket, electronic discount ticket.
As an example, the interaction result associated with the interaction object or the interaction result associated with the interaction object may be pre-stored in the client, or stored in the server, for the former, the server only returns the identification result (the type of the interaction object, the type and the state of the interaction object), the client queries the corresponding interaction result according to the returned identification result, i.e., jumps to the page corresponding to the interaction result, for the latter, the server returns not only the identification result (the type of the interaction object, the type and the state of the interaction object) but also the page address of the corresponding interaction result, and the client directly jumps to the page presenting the interaction result according to the page address.
As an example, the interactive object may be two hands or two feet, and the two hands are considered as one interactive object as a whole, that is, there may be multiple objects in each interactive object, and the number of the objects is not limited to the number of the objects, and learning according to the corresponding training set before the model application may realize recognition of the interactive object with two hands, and further recognize a state of the two hands, for example, a holding state of the two hands is an interactive state of the interactive object (two hands).
In some embodiments, the presenting of the interaction result related to the item to be recommended in step 103 may be implemented by the following technical solutions: determining a difference between an interactive object identified from the acquired image and an interactive object diagram, determining a score of the acquired image according to the difference, and presenting an interactive result associated with the score; wherein the difference comprises at least one of: a difference in position between the identified interactive object and the interactive object graphical representation; a state difference between the identified interactive object and the interactive object graphical representation; and image quality difference between the identified interactive object and the interactive object graph.
In some embodiments, the presenting of the interaction result related to the item to be recommended in step 103 may be implemented by the following technical solutions: determining a score for each captured image based on differences between the interactive object identified from each captured image and the interactive object graphical representation; determining the number of images with scores exceeding a score threshold value, and presenting interaction results related to the number.
As an example, the interactive object may be divided finely, and the interactive result may include benefit information of different levels, for example, the interactive result includes electronic discount coupons of various preferential degrees, the collected image is scored for the difference between the identified interactive object and the interactive object diagram, and the interactive result associated with the scoring is presented; for example, the recognized interaction result coincides with a position between the interaction object diagrams, the state coincides (for example, an angle between gestures coincides with an angle between gestures in the diagrams), the score obtained when the image quality also coincides (pixel approach) is not coincident with the position between the interaction object diagrams compared with the recognized interaction result and the position between the interaction object diagrams, the state is relatively coincident (for example, the model output probability of the recognized gesture is greater than the probability threshold of the diagram gesture, but only just reaches the probability threshold, it can be understood that the gesture is recognized but not standard), the score obtained when the image quality does not coincide (pixel approach, for example, the definition is relatively low) is relatively high, the score is specifically higher according to the position (the position score is higher as the position is closer to the diagram position, the distance from the diagram position can be regarded as the position score), the probability value of the state output (the probability value can be directly multiplied to obtain the state score), and the definition (the definition can be obtained as the position score is relatively inverse ratio (the probability value is directly multiplied) The definition score can be directly evaluated by using the variance of the first-order gradient) to score, each dimension has a corresponding weight, the final score can be obtained by carrying out weighted average according to the corresponding weight, and the identification result with higher score corresponds to the interaction result with higher preferential grade.
As an example, when there are multiple effective images identified, the interaction result may be further divided based on scores and numbers in scoring, that is, the number of images with scores exceeding a score threshold is determined after the score of each collected image is determined according to the above manner, and the interaction result associated with the number is presented, and benefit information of different levels may be included in the interaction result, for example, the interaction result includes electronic discounts with various degrees of benefit, the number of effective images with scores higher than the score threshold is proportional to the degree of benefit of the interaction result, and the higher the number is, the greater the degree of benefit is.
Referring to fig. 3C, fig. 3C is a schematic flow chart of the information recommendation processing method provided in the embodiment of the present application, and in step 201, the launch server issues recommendation information, a display duration, and an interactive image icon to the terminal; in step 202, the terminal displays recommendation information in an information stream according to a display duration; receiving an image identification triggering operation aiming at the recommendation information in step 203, and acquiring an image to be identified; in step 204, the terminal sends the image to be identified and the interactive image graphic to a computing server; in step 205, the computing server identifies an image to be identified; in step 206, when the interactive image matched with the interactive image graph is identified, returning an identification result and an interactive result skip identifier corresponding to the identification result to the terminal; in step 207, the terminal presents the interaction result according to the received recognition result and the interaction result jump identifier corresponding to the recognition result.
Next, an exemplary application of the information recommendation processing method provided in the embodiment of the present application in an actual application scenario will be described.
In some embodiments, an information recommendation processing method is implemented in an information stream of a social media, referring to fig. 4A, where fig. 4A is an interface schematic diagram of the information recommendation processing method provided in the application embodiment, the information stream of the social media may be a social dynamic information stream, the social dynamic information stream is presented in an information stream display page 401A, recommendation information (advertisement) 402A is presented in the social dynamic information stream, a guidance map 403A is presented in response to receiving a click operation (image recognition trigger operation) for the recommendation information 402A, and a guidance text and a background map are presented in the guidance map.
In some embodiments, an information recommendation processing method is implemented in an information stream of a social media, and referring to fig. 4B, fig. 4B is an interface schematic diagram of the information recommendation processing method provided in the application embodiment, a social dynamic information stream is presented in an information stream display page 401B, recommendation information (advertisement) 402B is presented in the social dynamic information stream, a detail page 403B of the recommendation information is presented in response to receiving a click operation for the recommendation information, an image identification entry is presented in a floating area 404B or a bottom component 405B in the detail page, a guide map 406B is presented in response to a trigger operation for the image identification entry, and a guide text and a background map are presented in the guide map.
In some embodiments, referring to fig. 4C, fig. 4C is an interface schematic diagram of an information recommendation processing method provided in the embodiments, when the acquisition control 402C in the guide map 401C receives a trigger operation and scans a specific gesture in the guide map 401C, a cardioid animation 403C, a green dot pattern accompanied by vibration, customization, and a picture pause special effect appear in the guide map 401C. Referring to fig. 4D, fig. 4D is an interface schematic diagram of the information recommendation processing method according to the embodiment, and the guide map 405D (401C in fig. 4C) includes a presentation layer 401D for presenting page elements, an atmosphere presentation map 402D, a circular focus mask layer 403D, and a camera capture presentation layer 404D. Referring to fig. 4E, fig. 4E is an interface schematic diagram of the information recommendation processing method provided in the application embodiment, 401E in fig. 4E is a complete display in the atmosphere presentation diagram 402D in fig. 4D, a semitransparent picture with 1242 × 2688 configured in 401E, and a decorative element does not invade a red region and is aligned and adapted at the bottom, referring to fig. 4F, fig. 4F is an interface schematic diagram of the information recommendation processing method provided in the application embodiment, and the guidance diagram 401F, the guidance diagram 402F, and the guidance diagram 403F in fig. 4F are complete display effects after the atmosphere presentation diagram 402D is merged with the camera capturing presentation layer 404D in fig. 4, which are different only in size of the terminal devices presented by the three.
Referring to fig. 4G, fig. 4G is an interface schematic diagram of the information recommendation processing method according to the embodiment, when a specific gesture is scanned in the guidance map 401G, the half screen 402G is popped up to display an interaction result (benefit type), but in the case of a weak network, the loading is displayed in the half screen 402G.
Referring to fig. 4H, fig. 4H is an interface schematic diagram of an information recommendation processing method provided in the embodiment of the application, when a specific gesture is scanned in the guide map 401H, the half screen 402H is popped up to display an interactive result including a discount coupon, the half screen 403H is popped up to display an interactive result including a red package, the half screen 404H is popped up to display an interactive result including a redemption coupon, the half screen 405H is popped up to display an interactive result including a blessing video, or the interactive result may include the blessing video and the redemption coupon, the red package and the discount coupon, and the interactive result includes but is not limited to a card coupon, a discount coupon, a red package cover, a real object, and the like.
Referring to fig. 4I, fig. 4I is an interface schematic diagram of an information recommendation processing method provided in the application embodiment, and in response to receiving a click operation of a user on an interaction result, the method may obtain a coupon, a discount coupon, a red envelope cover, and a real object, in response to receiving a receiving operation of the user on a neutral discount coupon in a half-screen 401I, present a pickup page 404I, in response to receiving a pickup operation of the user on a redeemed coupon in the half-screen 402I, present a pickup page 405I, receive address information in the pickup page 405I to complete a pickup flow, and in response to receiving a pickup operation of the user on a red envelope in the half-screen 403I, present a pickup page 406I.
Referring to fig. 4J, fig. 4J is an interface schematic diagram of an information recommendation processing method provided in the application embodiment, and during half-screen loading or when loading fails, the toast information shown in fig. 4J is used to prompt that a network environment is poor, please try again later, the prompt information 402J is used to prompt that a stock lottery ticket has been received completely, and the prompt information 403J is used to prompt that a lottery ticket cannot be received temporarily.
Referring to fig. 4K, fig. 4K is an interface schematic diagram of the information recommendation processing method provided in the embodiment of the application, and the guidance diagram 401K is presented directly through the object scanning recognition function of the client, the guidance text and the background diagram are presented in the guidance diagram, the specific heart gesture is recognized in the guidance diagram 402K, when the specific heart gesture is scanned in the guidance diagram 403K, a heart-shaped animation, a prompt tone and a vibration appear in the guidance diagram 403K, and a half screen 404K is flicked to show the interaction result (benefit type).
Referring to fig. 4L, fig. 4L is an interface schematic diagram of an information recommendation processing method provided in the application embodiment, when a specific gesture is scanned in a guide map 401L, a heart-shaped animation, a prompt tone, and a vibration appear in the guide map 401L, and at the same time, a half screen 402L is popped up to display an interaction result (benefit type), the half screen can be pulled up to a page 403L, the interaction result includes, but is not limited to, a card ticket, a discount ticket, a red envelope, a real object, and the like, the card ticket, the discount ticket, the red envelope, the real object can be retrieved after a click operation of a user on the interaction result is received, when the interaction result is a redemption ticket, a pickup page 404L is presented, a trigger pickup operation is received in the pickup page 404L, and a redemption page 405L is presented, so that a pickup process is completed.
In some embodiments, referring to fig. 5, fig. 5 is a schematic view of an identification flow of an information recommendation processing method provided in the application embodiment, referring to fig. 7, and fig. 7 is a schematic view of an identification flow of an information recommendation processing method provided in the application embodiment, first performing palm detection, then performing palm detection, obtaining a palm region of interest, presenting the palm region of interest through a dashed box 701A in fig. 7, then performing skeleton positioning processing on content in the dashed box, obtaining a key point skeleton 702A in fig. 7 through 21-point three-dimensional positioning processing, and obtaining a gesture classification result as a bixin picking-up result based on a positioning result after performing the skeleton positioning processing.
In some embodiments, referring to fig. 6A-6B, fig. 6A-6B are schematic model diagrams of an information recommendation processing method provided in the embodiments, and a single-point detector is used as a palm detection framework, and a Blaz eBlock-like base unit is used to construct a lightweight and efficient backbone network structure, where the base unit is as shown in fig. 6A-6B, and the difference between the two diagrams is only that the step size in fig. 6A is 1 and the step size in fig. 6B is 2, where the multi-scale output of the single-point detector is improved to be a single-head output, so as to reduce the complexity of post-processing (maximum threshold) and computation. A21-point three-dimensional framework regression model is constructed through a backbone network structure similar to an SSD detector, the classification probability of gestures is output while the key points of the regression framework are positioned, and the false detection is suppressed while the model learning is assisted. Finally, three-dimensional skeleton coordinates are normalized (mean value reduction and variance removal) on all dimensions to obtain normalized feature vectors, and 16 gestures are classified (including 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'first', 'good', 'bar', 'one point', 'nine', 'love', 'rock', and 'love') through a 3-layer fully-connected (FC + RELU) multi-layer perceptron.
In some embodiments, an implementation process of the information recommendation processing method provided by the embodiment of the present application is as follows: the method comprises the following steps that an advertisement putting end issues advertisement configuration information and a monitoring task to a client, the client sends collected images and the advertisement configuration information to a computing server, the computing server returns an identification result to the client, the client displays the identification result and skips to present an interaction result, the interaction result comprises an electronic discount coupon and the like, the advertisement configuration information comprises advertisement material information, display time and a set skip gesture, namely, the client executes the monitoring task within the display time, the display time restricts the starting time of the monitoring task and the ending time of the monitoring task, the client executes the monitoring task, and when the client presents information streams: after receiving a trigger operation in a legal time period (display time period), calling a camera to start gesture detection; in the gesture collecting process, effective images are selected through a 'static frame' strategy and a 'clear frame' strategy, the 'static frame' strategy restricts that the frame difference between adjacent frames is smaller than a frame difference threshold value, the 'clear frame' strategy restricts that the variance of the first-order gradient of the frame is smaller than a definition threshold value, namely, the clear and static frames are determined to be effective images and are sent to a background computing server; the calculation server identifies the corresponding gesture type through a gesture detection algorithm and returns a jump mark; and after receiving the jump flag bit, the client triggers the interaction logic, presents the interaction result, and restarts monitoring if the corresponding gesture is not recognized.
By the information recommendation processing method provided by the embodiment of the application, the attraction of information flow advertisement materials can be improved, the interactive interest of advertisements is increased, and the advertisement click conversion efficiency is improved.
Continuing with the exemplary structure of the information recommendation processing device 455 provided in the embodiments of the present application implemented as software modules, in some embodiments, as shown in fig. 2, the software modules stored in the information recommendation processing device 455 of the memory 450 may include: a display module 4551, configured to display an information flow page; a trigger module 4552 configured to display the acquired image in response to an image recognition trigger operation received in the information flow page; and the interaction module 4553 is configured to, when the acquired image includes an interaction object and the interaction object is associated with an item to be recommended in the information flow page, present an interaction result related to the item to be recommended.
In the foregoing solution, the display module 4551 is further configured to: displaying a first hierarchical information flow page; the first-level information flow page is an information flow page displayed by default when the client is started, and the information flow in the first-level information flow page comprises at least one of the following: logging in at least one historical session in which an account participates; a subscription message of a login account; and (4) notification information of the login account.
In the foregoing solution, the display module 4551 is further configured to: displaying an image recognition entry in a first hierarchical information flow page; when the trigger for the image recognition entry is received, the trigger is determined to be an image recognition trigger operation.
In the foregoing solution, the display module 4551 is further configured to: displaying a second level information flow page; and the information flow of the second-level information flow page comprises the social dynamics of the login account.
In the foregoing solution, the display module 4551 is further configured to: inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page; and determining the received trigger operation aiming at the recommendation information as an image recognition trigger operation.
In the foregoing solution, the display module 4551 is further configured to: inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page; in response to the trigger operation aiming at the recommendation information, a detail page of the recommendation information is presented, and an image recognition entry is displayed in the detail page; and determining that the trigger operation aiming at the image recognition entrance is received as the image recognition trigger operation.
In the above solution, the apparatus 455 further includes: a sharing module 4554 configured to: responding to the sharing operation aiming at the interaction result, and sending a sharing message corresponding to the interaction object; and the sharing message is used for jumping to an image recognition entrance when being triggered.
In the foregoing solution, when displaying the image recognition entry, the display module 4551 is further configured to: displaying first prompt information to prompt an interactive object to be acquired; wherein the first prompt message includes at least one of: introduction information of the interactive object and a graphic representation of the interactive object.
In the foregoing solution, the display module 4551 is further configured to: when the acquired image does not comprise an interactive object associated with the article to be recommended in the information flow page, presenting second prompt information to prompt the image acquisition to be continued; when the acquired image comprises an interactive object associated with the article to be recommended, presenting a special effect corresponding to the interactive object; wherein the special effects include at least one of: animation, warning sound and vibration feedback.
In the above scheme, the interaction module 4553 is further configured to: identifying the state of the interactive object and presenting an interactive result associated with the state of the interactive object; wherein the interactive object comprises at least one of: limb, hand, face; the state of the interactive object includes at least one of: limb movements, gestures, facial expressions; the interaction result comprises at least one of the following: electronic red envelope, electronic redemption ticket, electronic discount ticket.
In the above scheme, the interaction module 4553 is further configured to: determining a valid image for target identification from the acquired images; calling an object recognition model to perform target recognition on the effective image so as to determine the type of an object included in the effective image; and calling a state type identification model to perform key point positioning processing on the object included in the effective image to obtain the state of the object.
In the above scheme, the interaction module 4553 is further configured to: when the acquired image is a static image acquired by taking a picture, determining the static image as an effective image for target identification; when the collected image is a dynamic video frame collected by shooting a video, determining a video frame meeting at least one of the following conditions in a plurality of video frames as an effective image for target identification: the average value of the frame difference between the video frame and the adjacent video frame is smaller than the still frame threshold value; the variance of the first order gradient of the video frame is greater than the sharpness threshold.
In the above scheme, the interaction module 4553 is further configured to: before determining a valid image for object recognition from the acquired images: acquiring a recommended validity period; when the acquisition time of the acquired image is within the recommended validity period, it is determined that an operation of determining a valid image for object recognition from the acquired image will be performed.
In the above scheme, the interaction module 4553 is further configured to: determining a difference between an interactive object identified from the acquired image and an interactive object diagram, determining a score of the acquired image according to the difference, and presenting an interactive result associated with the score; wherein the difference comprises at least one of: a difference in position between the identified interactive object and the interactive object graphical representation; a state difference between the identified interactive object and the interactive object graphical representation; and image quality difference between the identified interactive object and the interactive object graph.
In the above scheme, the interaction module 4553 is further configured to: determining a score for each captured image based on differences between the interactive object identified from each captured image and the interactive object graphical representation; determining the number of images with scores exceeding a score threshold value, and presenting interaction results related to the number.
Embodiments of the present application provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, so that the computer device executes the information recommendation processing method described in the embodiment of the present application.
Embodiments of the present application provide a computer-readable storage medium storing executable instructions, which when executed by a processor, cause the processor to perform a method provided by embodiments of the present application, for example, an information recommendation processing method as shown in fig. 3A-3C.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EP ROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (H TML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
In summary, the interactive result related to the to-be-recommended article is presented in a man-machine interaction mode, the presenting mode of the to-be-recommended article can be enriched to improve the recommending efficiency of the to-be-recommended article, diversified user interaction experience can be provided, the interaction pleasure in reading the related information of the to-be-recommended article is enriched, and therefore the interestingness in reading the related information of the to-be-recommended article is increased.
The above description is only an example of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present application are included in the protection scope of the present application.

Claims (15)

1. An information recommendation processing method, characterized in that the method comprises:
displaying an information flow page;
displaying the acquired image in response to an image recognition trigger operation received in the information flow page;
and when the acquired image comprises an interactive object and the interactive object is associated with the article to be recommended in the information flow page, presenting an interactive result related to the article to be recommended.
2. The method of claim 1,
the display information flow page includes:
displaying a first hierarchical information flow page;
the first-level information flow page is an information flow page displayed by default when a client is started, and information flow in the first-level information flow page comprises at least one of the following: logging in at least one historical session in which an account participates; a subscription message of a login account; and (4) notification information of the login account.
3. The method of claim 2, further comprising:
displaying an image recognition entry in the first hierarchical information flow page;
determining that a trigger for the image recognition portal is received as the image recognition trigger operation.
4. The method of claim 1, wherein displaying the information flow page comprises:
displaying a second level information flow page;
and the information flow of the second-level information flow page comprises the social dynamics of the login account.
5. The method of claim 4, further comprising:
inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page;
and determining the received trigger operation aiming at the recommendation information as the image recognition trigger operation.
6. The method of claim 4, the displaying an information flow page, comprising:
inserting and displaying at least one piece of recommendation information in the information flow of the second-level information flow page;
in response to a trigger operation for the recommendation information, presenting a detail page of the recommendation information, and displaying an image recognition entry in the detail page;
and determining that the trigger operation aiming at the image recognition entrance is received as the image recognition trigger operation.
7. The method of claim 3 or 6, wherein when displaying the image recognition portal, the method further comprises:
displaying first prompt information to prompt an interactive object to be acquired;
wherein the first prompt message includes at least one of: introduction information of the interactive object and a graphic representation of the interactive object.
8. The method of claim 3 or 6, further comprising:
when the acquired image does not comprise an interactive object associated with the article to be recommended in the information flow page, presenting second prompt information to prompt the image acquisition to be continued;
when the acquired image comprises an interactive object associated with the item to be recommended, presenting a special effect corresponding to the interactive object;
wherein the special effects include at least one of:
animation, warning sound and vibration feedback.
9. The method according to claim 8, wherein the presenting of the interaction result related to the item to be recommended comprises:
identifying the state of the interactive object and presenting an interactive result associated with the state of the interactive object;
wherein the interactive object comprises at least one of: limb, hand, face;
the state of the interactive object comprises at least one of: limb movements, gestures, facial expressions;
the interaction result comprises at least one of the following: electronic red envelope, electronic redemption ticket, electronic discount ticket.
10. The method of claim 1, further comprising:
determining a valid image for target recognition from the acquired images;
calling an object recognition model to perform target recognition on the effective image so as to determine the type of an object included in the effective image;
and calling a state type identification model to perform key point positioning processing on the object included in the effective image to obtain the state of the object.
11. The method of claim 10, wherein determining a valid image for object recognition from the acquired images comprises:
when the acquired image is a static image acquired by taking a picture, determining the static image as an effective image for target identification;
when the collected image is a dynamic video frame collected by shooting a video, determining a video frame meeting at least one of the following conditions in a plurality of video frames as an effective image for target identification:
the average value of the frame difference between the video frame and the adjacent video frame is smaller than a still frame threshold value;
the variance of the first order gradient of the video frame is greater than a sharpness threshold.
12. The method of claim 11, wherein prior to determining a valid image for target recognition from the acquired images, the method further comprises:
acquiring a recommended validity period;
determining that an operation of determining a valid image for object recognition from the captured images is to be performed when the capturing time of the captured images is within the recommended validity period.
13. An information recommendation processing apparatus characterized by comprising:
the display module is used for displaying the information flow page;
the triggering module is used for responding to the image identification triggering operation received in the information flow page and displaying the acquired image;
and the interaction module is used for presenting an interaction result related to the to-be-recommended article when the acquired image comprises an interaction object and the interaction object is related to the to-be-recommended article in the information flow page.
14. An electronic device, comprising:
a memory for storing executable instructions;
a processor configured to implement the information recommendation processing method of any one of claims 1 to 12 when executing the executable instructions stored in the memory.
15. A computer-readable storage medium storing executable instructions for implementing the information recommendation processing method according to any one of claims 1 to 12 when executed by a processor.
CN202010761072.3A 2020-07-31 2020-07-31 Information recommendation processing method, device, equipment and computer readable storage medium Pending CN114092166A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010761072.3A CN114092166A (en) 2020-07-31 2020-07-31 Information recommendation processing method, device, equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010761072.3A CN114092166A (en) 2020-07-31 2020-07-31 Information recommendation processing method, device, equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN114092166A true CN114092166A (en) 2022-02-25

Family

ID=80295037

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010761072.3A Pending CN114092166A (en) 2020-07-31 2020-07-31 Information recommendation processing method, device, equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN114092166A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023241154A1 (en) * 2022-06-16 2023-12-21 腾讯科技（深圳）有限公司 Interaction method and apparatus based on news feed advertisement, and device and medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023241154A1 (en) * 2022-06-16 2023-12-21 腾讯科技（深圳）有限公司 Interaction method and apparatus based on news feed advertisement, and device and medium

Similar Documents

Publication Publication Date Title
JP6267861B2 (en) Usage measurement techniques and systems for interactive advertising
CN106605218A (en) Method of collecting and processing computer user data during interaction with web-based content
Xu et al. Security and Usability Challenges of {Moving-Object}{CAPTCHAs}: Decoding Codewords in Motion
CN108337909A (en) System and method for providing interactive streaming media
US20230362438A1 (en) Resource interacting method, apparatus, computer device, and readable storage medium
CN110703913A (en) Object interaction method and device, storage medium and electronic device
CN110677685B (en) Network live broadcast display method and device
WO2018103653A1 (en) Media pushing method and system
CN111881395A (en) Page presenting method, device, equipment and computer readable storage medium
CN113824983A (en) Data matching method, device, equipment and computer readable storage medium
CN113326709B (en) Display method, device, equipment and computer readable storage medium
CN113301421B (en) Live broadcast segment display method and device, storage medium and electronic equipment
CN113271251B (en) Virtual resource activity control method and device, electronic equipment and storage medium
CN110677698B (en) Multimedia data processing method and device and related equipment
CN114092166A (en) Information recommendation processing method, device, equipment and computer readable storage medium
CN111181839B (en) Data processing method, device and equipment in application sharing
CN116798129A (en) Living body detection method and device, storage medium and electronic equipment
CN115022702B (en) Display method, device, equipment and medium for live broadcast room gift
US10589172B1 (en) Embedding metadata in rendered content
CN114917590A (en) Virtual reality's game system
CN113779440A (en) Game strategy collection method, device, equipment and storage medium
CN112799514A (en) Information recommendation method and device, electronic equipment and medium
CN115222406A (en) Resource distribution method based on business service account and related equipment
US20160154552A1 (en) Smart books
US20130267311A1 (en) Identity game

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40064635

Country of ref document: HK

SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination