CN117252651A - Internet of things terminal advertisement putting method, device and medium based on digital identity - Google Patents

Internet of things terminal advertisement putting method, device and medium based on digital identity Download PDF

Info

Publication number
CN117252651A
CN117252651A CN202311538612.1A CN202311538612A CN117252651A CN 117252651 A CN117252651 A CN 117252651A CN 202311538612 A CN202311538612 A CN 202311538612A CN 117252651 A CN117252651 A CN 117252651A
Authority
CN
China
Prior art keywords
terminal
tag
user
label
internet
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.)
Granted
Application number
CN202311538612.1A
Other languages
Chinese (zh)
Other versions
CN117252651B (en
Inventor
范广彬
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.)
Shenzhen Rakinda Iot Technology Co ltd
Original Assignee
Shenzhen Rakinda Iot Technology 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 Shenzhen Rakinda Iot Technology Co ltd filed Critical Shenzhen Rakinda Iot Technology Co ltd
Priority to CN202311538612.1A priority Critical patent/CN117252651B/en
Publication of CN117252651A publication Critical patent/CN117252651A/en
Application granted granted Critical
Publication of CN117252651B publication Critical patent/CN117252651B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0257—User requested
    • 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
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Evolutionary Computation (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Databases & Information Systems (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Computer Interaction (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of face recognition, and discloses an internet of things terminal advertisement putting method, device and medium based on digital identity, wherein the method comprises the following steps: identifying face key points in a user video frame acquired by an internet of things terminal, and clustering the key frames according to the face key points to obtain key frames; reconstructing a face image of the key frame to obtain a target face image, and identifying user identity characteristics according to wavelet characteristics of the target face image; extracting corresponding identity terminal data, determining a product label set according to the identity terminal data, and calculating a label characteristic value of each product label; calculating a tag preference value according to the tag feature value, and calculating a feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value; and ordering the terminal advertisements according to the feature association degree to obtain an advertisement sequence, and putting the terminal advertisements to the Internet of things terminal according to the advertisement sequence. The invention can improve the accuracy of terminal advertisement delivery.

Description

Internet of things terminal advertisement putting method, device and medium based on digital identity
Technical Field
The invention relates to the technical field of face recognition, in particular to an internet of things terminal advertisement putting method, device and medium based on digital identity.
Background
Along with the increase of the network popularity, the advertising industry also enters an information age along with the development of internet technology, and develops towards global activities, all-round services and industry industrialization, and advertising media are gradually transited from traditional televisions, broadcasters and newspapers to the internet and intelligent display terminals. Accordingly, advertisement forms are also increasing, and search engine advertisements, APP advertisement implantation, mail advertisements, intelligent screen terminal advertisements and the like are developed from advertising to accurate delivery. With the popularization of networks and the development of communication technologies, more and more information, information and services are presented to users in a multimedia form, so that the intelligent terminal technology and the internet industry are mutually fused, and the characteristics of diversity and flexibility are also presented. For example, the intelligent terminal can be provided with game software to enable a user to play games through input modes such as a body feeling, a mouse, a keyboard and the like. The intelligent display terminal develops rapidly, and a large number of intelligent display terminals are arranged in public places such as a business hall, a market, a hotel lobby and the like. Therefore, research on targeted advertising to the internet of things terminal has important significance for prosperous development of advertising markets.
The intelligent advertisement developed by various informatization technologies in the market at present has various forms, such as: the intelligent rolling canvas advertisement window control system based on the singlechip realizes the cyclic rolling display of a plurality of advertisement pictures on the basis of the structure of the traditional advertisement window and has the function of intelligently identifying whether people watch the advertisement pictures. The functions of customizing pictures and the like by remote control are realized, so that the advertisement window is more humanized, intelligent and low-carbonization; the intelligent poster based on NFC realizes the interactive operation between the user and the advertiser through the NFC technology and the two-way communication thereof; the intelligent advertisement terminal system based on ARM and Linux updates the released content in real time aiming at the change of the surrounding environment by means of the feedback of the network and the field video image, thereby better adapting to the real-time and interactive requirements of the intelligent advertisement terminal system. However, the method cannot capture the age, sex and other characteristics of the current user in time and dynamically play the corresponding advertisement, so that the terminal advertisement playing accuracy is poor.
Disclosure of Invention
The invention provides an advertisement putting method, device and medium of an internet of things terminal based on digital identity, and mainly aims to solve the problem that the advertisement putting of the internet of things terminal is poor in accuracy.
In order to achieve the above purpose, the invention provides a digital identity-based internet of things terminal advertisement delivery method, which comprises the following steps:
acquiring a user video frame acquired by an internet of things terminal, identifying a face key point in the user video frame, and carrying out key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame;
reconstructing a face image of the key frame to obtain a target face image corresponding to the Internet of things terminal, extracting wavelet features of the target face image, and identifying user identity features corresponding to the user video frame according to the wavelet features;
extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product tag set of the user identity characteristics according to the identity terminal data, and calculating a tag characteristic value of each product tag in the product tag set;
calculating a tag preference value of the user identity feature according to the tag feature value, and calculating a feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
and sequencing the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and putting the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
Optionally, the identifying the face keypoints in the user video frame includes:
initializing an image coordinate system on the user video frame, and marking feature points on the image coordinate system to obtain face feature point coordinates;
and calculating the center coordinates of the left eye and the right eye on the user video frame according to the face feature point coordinates, and taking the center coordinates of the left eye and the right eye as face key points in the user video frame.
Optionally, the performing key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame includes:
initializing a plurality of class centroid coordinates, and calculating the coordinate distance from the face key point to each class centroid coordinate;
and calculating the coordinate distance from the face key point to the centroid coordinates of each category by using the following formula:wherein (1)>Represent the firstPersonal face key point to->Coordinate clustering of individual class centroid coordinates +.>、/>Respectively represent +.>Position coordinates of left and right eyes in key points of personal face,/->、/>Respectively represent +.>The position coordinates of the left eye and the right eye in the mass center coordinates of each category;
carrying out initial clustering on the user video frames according to the coordinate distance to obtain an initial cluster;
Iteratively updating the class centroid coordinates according to the initial cluster until the class centroid coordinates are not changed any more, so as to obtain a cluster center point;
calculating the center coordinate distance from the face key point to the clustering center point, and clustering the user video frames according to the center coordinate distance to obtain a video frame cluster;
and selecting a preset number of user video frames from each video frame cluster as key frames in the user video frames.
Optionally, the reconstructing the face image of the key frame to obtain a target face image corresponding to the internet of things terminal includes:
extracting depth features in the key frames by using convolution dense blocks in the face reconstruction network which is completed through pre-training;
deconvolution is carried out on the depth features to obtain deconvolution features, and feature mapping is carried out on the deconvolution features to obtain face features of the user video frames;
and reconstructing a face image according to the face characteristics to obtain a target face image corresponding to the Internet of things terminal.
Optionally, the determining the product tag set of the user identity feature according to the identity terminal data includes:
Extracting an operation record in the user terminal data, and determining the user requirement in the operation record;
and determining a product tag set of the user identity according to the user requirement.
Optionally, the calculating a tag characteristic value of each product tag in the product tag set includes:
counting the total number of the product tags in the product tag set and the number of the tags of each product tag;
calculating the ratio between the number of the labels and the total number of the labels to obtain the label dependence of each product label;
calculating label time data of each product label, and calculating label attention of each product label according to the label time data;
calculating the label attention of each product label by using the following formula:wherein (1)>Representing tag attention, ++>Representing time intervals in the tag time data, +.>Representing the latest time of use of the product label in the label time data, < >>Representing a time when the product label is first used;
and collecting the label dependence degree and the label attention degree to obtain the label characteristic value of each product label.
Optionally, the calculating the feature association degree between the user identity feature and the preset terminal advertisement according to the tag preference value includes:
Calculating the label weight of the product label corresponding to the label preference value according to the label preference value;
and obtaining a product label in the terminal advertisement, and calculating the characteristic association degree between the user identity characteristic and the terminal advertisement according to the label preference value and the label weight.
Optionally, the calculating the feature association degree between the user identity feature and the terminal advertisement according to the tag preference value and the tag weight includes:
calculating the feature association degree by using the following formula:wherein (1)>Representing the tag preference value and the tag weight and +.>Characteristic association between individual terminal advertisements, +.>Indicate->Product tag in personal terminal advertisement->Corresponding tag preference value,/->Indicate->Advertisement product label in personal terminal advertisement>Corresponding weights, ++>Indicate->Total number of advertised product tags in individual terminal advertisements.
In order to solve the above problems, the present invention further provides an internet of things terminal advertisement delivery device based on digital identity, the device comprising:
the key frame clustering module is used for acquiring user video frames acquired by the internet of things terminal, identifying face key points in the user video frames, and carrying out key frame clustering on the user video frames according to the face key points to obtain key frames in the user video frames;
The user identity feature recognition module is used for reconstructing the face image of the key frame to obtain a target face image corresponding to the internet of things terminal, extracting wavelet features of the target face image and recognizing user identity features corresponding to the user video frame according to the wavelet features;
the label characteristic value calculation module is used for extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product label set of the user identity characteristics according to the identity terminal data, and calculating a label characteristic value of each product label in the product label set;
the feature association degree calculation module is used for calculating a tag preference value of the user identity feature according to the tag feature value and calculating the feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
and the terminal advertisement delivery module is used for sequencing the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and delivering the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
In order to solve the above problem, the present invention further provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the method for delivering advertisements based on digital identity for an internet of things terminal as described above.
According to the embodiment of the invention, the user video frames are acquired by the Internet of things terminal and subjected to key frame clustering, so that the key frames are obtained, the face form of the user can be comprehensively acquired, and the accuracy of the subsequent user identity characteristic calculation is improved; reconstructing the key frame to obtain a target face image with higher face image quality, so that more accurate user identity characteristics can be calculated according to the target face image; determining a product label set of the user identity characteristics, calculating a label characteristic value of each product label, and comprehensively calculating the dependence and the attention of the user on each product label to obtain the preference degree of the user on each label; and calculating the feature association degree according to the preference degree, and sequencing the advertisements of the terminal, so that the advertisements with larger feature association degree are put into the internet of things terminal preferentially, and the accurate putting of the advertisements of the terminal is realized. Therefore, the method, the device and the medium for putting the advertisement of the internet of things terminal based on the digital identity can solve the problem of poor accuracy of the internet of things terminal when putting the advertisement.
Drawings
FIG. 1 is a schematic flow chart of an advertisement delivery method for an Internet of things terminal based on digital identity according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of face image reconstruction for a key frame according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for calculating a tag characteristic value of each product tag in a set of product tags according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of an advertisement delivery device of an Internet of things terminal based on digital identity according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides an Internet of things terminal advertisement putting method based on digital identity. The execution main body of the digital identity-based internet of things terminal advertisement delivery method comprises at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the digital identity-based internet of things advertising method may be performed by software or hardware installed in a terminal device or a server device, where the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of an advertisement delivery method of an internet of things terminal based on digital identity according to an embodiment of the present invention is shown. In this embodiment, the method for delivering advertisements to an internet of things terminal based on digital identity includes:
s1, acquiring a user video frame acquired by an Internet of things terminal, identifying a face key point in the user video frame, and carrying out key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame.
In the embodiment of the invention, the user video frames are video frames with user face pictures, which are acquired through the camera equipment installed on the internet of things terminal, and the key frames with key information of different user face shapes can be obtained through key frame clustering due to different face shapes in the video frames, such as left face, left offset face, positive face and the like.
In the embodiment of the present invention, the identifying the face key points in the user video frame includes:
initializing an image coordinate system on the user video frame, and marking feature points on the image coordinate system to obtain face feature point coordinates;
and calculating the center coordinates of the left eye and the right eye on the user video frame according to the face feature point coordinates, and taking the center coordinates of the left eye and the right eye as face key points in the user video frame.
In the embodiment of the invention, the key points of the face can be marked on each user video frame through a neural network with the face mark, for example, a deep convolutional neural network (Dynamic Convolution Neural Network, DCNN) and other neural networks mark the key points of eyebrows, eyes, noses, mouths, facial contours and the like in the face to obtain the coordinates of the feature points of the face, and the coordinates of the eyes in the coordinates of the feature points of the face are used for calculating the key points of the face corresponding to the central coordinates of the left eye and the right eye.
In the embodiment of the invention, the face key points are center coordinates of left and right eyes of the face, for example, the face key points are obtained according to the average value calculation of the characteristic coordinate points of the left and right eyes in the face characteristic point coordinates on the horizontal and vertical coordinate points.
In the embodiment of the present invention, the step of performing key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame includes:
initializing a plurality of class centroid coordinates, and calculating the coordinate distance from the face key point to each class centroid coordinate;
carrying out initial clustering on the user video frames according to the coordinate distance to obtain an initial cluster;
iteratively updating the class centroid coordinates according to the initial cluster until the class centroid coordinates are not changed any more, so as to obtain a cluster center point;
Calculating the center coordinate distance from the face key point to the clustering center point, and clustering the user video frames according to the center coordinate distance to obtain a video frame cluster;
and selecting a preset number of user video frames from each video frame cluster as key frames in the user video frames.
In the embodiment of the invention, the class centroid coordinates are the position coordinates of the left eye and the right eye under different face shapes, for example, the position coordinates of the left face, the right face, the left eye and the right eye when the right face is deviated, and the user video frames are clustered under different face shapes through different class centroid coordinates, so that key frames under different shapes are obtained.
In the embodiment of the present invention, the calculating the coordinate distance from the face key point to each class centroid coordinate includes:
and calculating the coordinate distance from the face key point to the centroid coordinates of each category by using the following formula:wherein (1)>Represent the firstPersonal face key point to->Coordinate clustering of individual class centroid coordinates +.>、/>Respectively represent +.>Position coordinates of left and right eyes in key points of personal face,/->、/>Respectively represent +.>The position coordinates of the left eye and the right eye in the mass center coordinates of each category;
In the embodiment of the invention, each user video frame is classified into the class centroid coordinates with the minimum coordinate distance through the coordinate distance to obtain the initial cluster, so that the class centroid coordinates are iteratively updated according to the mean value of the left eye position coordinates and the right eye position coordinates in the initial cluster until the coordinates of the class centroid coordinates are no longer changed, and the position coordinates of the left eye and the right eye when the clustering center point is closer to different face states are represented, so that the user video frames are clustered more accurately to obtain the video frame cluster.
In the embodiment of the invention, the face information contained in different face shapes is inconsistent, so that different numbers of user video frames need to be selected from each video frame cluster to obtain key frames containing the whole face shape information, for example, 5, 10, 20, 25 and 30 user video frames are selected from each video frame cluster as key frames respectively.
In the embodiment of the invention, the key frames can be used for extracting the face images of different face shapes from the user video so as to comprehensively acquire the face shapes of the user and improve the accuracy of the subsequent user identity characteristic calculation.
S2, reconstructing the face image of the key frame to obtain a target face image corresponding to the Internet of things terminal, extracting wavelet features of the target face image, and identifying user identity features corresponding to the user video frame according to the wavelet features.
In the embodiment of the invention, the face image in the user video frame acquired by the internet of things terminal is difficult to ensure the image quality, and the problems of lower resolution and unclear face can occur, so that the key frame is used for reconstructing the face image when different face forms are adopted, and the target face image with higher face image quality can be obtained.
In the embodiment of the present invention, referring to fig. 2, the step of reconstructing a face image of the key frame to obtain a target face image corresponding to the internet of things terminal includes:
s21, extracting depth features in the key frames by using convolution dense blocks in the face reconstruction network which is completed through pre-training;
s22, deconvoluting the depth features to obtain deconvolution features, and performing feature mapping on the deconvolution features to obtain face features of the user video frames;
s23, reconstructing a face image according to the face characteristics to obtain a target face image corresponding to the Internet of things terminal.
In the embodiment of the invention, the face reconstruction network may be a dense connection network (DenseNet), wherein the face reconstruction network comprises a plurality of face feature extraction modules consisting of convolution dense blocks, deconvolution layers and convolution layers, so as to obtain face features, and a target face image is predicted from the face features by utilizing convolution according to the face features, so that the face image reconstruction is completed.
Preferably, the convolution dense block is composed of a plurality of convolution layers of different convolution scales, each of which is followed by a batch normalization layer and a ReLU activation function, with the input of each convolution layer being a splice of all the preceding layers to obtain a more comprehensive depth characteristic.
In the embodiment of the present invention, the extracting the wavelet feature of the target face image includes:
wavelet filtering with multiple scales and multiple directions is carried out on the target face image, so that multiple filtering characteristics are obtained;
and carrying out feature fusion on the filtering features to obtain wavelet features of the target face features.
In the embodiment of the invention, gabor filtering can be carried out on the target face image by utilizing a plurality of Gabor filters with different scale directions to obtain a plurality of filtering characteristics, so that the image characteristics of the target face image in a plurality of directions and in the image size are extracted, and the wavelet characteristics with more comprehensive and more accurate characteristics are obtained.
Preferably, the filtering features can be mapped to the same scale dimension, and feature fusion is performed on the filtering features through channel superposition to obtain wavelet features containing multiple directions and multiple image sizes of the target face image, so that the user identity features can be calculated more accurately.
In the embodiment of the invention, the user identity characteristic is a characteristic for representing the identity characteristic of the user and comprises a plurality of identity tags, such as identity tags of age, gender and the like. The Euclidean distance between a plurality of preset identity tag vectors is calculated through the wavelet characteristics, so that corresponding identity tags in the wavelet characteristics are obtained, for example, the identity tags corresponding to the wavelet characteristics are calculated to be female, 20-25 years old, hairstyle and the like, and the user identity characteristics are obtained.
In the embodiment of the invention, the personalized identity characteristics of the user in the user video frame can be determined through the user identity characteristics, so that the advertisement is put in a targeted manner, and the accuracy of the advertisement is improved.
S3, extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product tag set of the user identity characteristics according to the identity terminal data, and calculating a tag characteristic value of each product tag in the product tag set.
In the embodiment of the invention, the terminal database is a database for storing data on the internet of things terminal, and the operation data of each user on the terminal can be acquired through the terminal database, so that the identity terminal data corresponding to the identity characteristics of the user can be extracted from the terminal database, for example, the identity characteristics of the user are 20 to 25 years old females, and the operation data, for example, purchase data, browsing data and the like, of the 20 to 25 years old females on a plurality of internet of things terminals are extracted from the terminal database, so that targeted advertisement delivery is performed.
In the embodiment of the invention, the product tag set is the identification mark for describing the user characteristics and behaviors in the identity terminal data, so that the identity characteristics of the user can be conveniently distinguished, for example, the product tag set can comprise makeup, home, food, leisure and the like, thereby determining the behavior preference of the user on the internet of things terminal and improving the accuracy of advertisement delivery.
In the embodiment of the present invention, the product tag set for determining the identity characteristics of the user according to the identity terminal data includes:
extracting an operation record in the user terminal data, and determining the user requirement in the operation record;
and determining a product tag set of the user identity according to the user requirement.
In the embodiment of the invention, the user requirement is a user purchase requirement corresponding to each operation record in the user terminal data, for example, the operation records are a purchase page for browsing beauty cosmetics, a purchase snack, and the like, so that a product tag set in the user terminal data is determined.
In the embodiment of the invention, the tag characteristic value comprises the tag dependence degree and the tag attention degree of each product tag, wherein the tag dependence degree indicates the occurrence times of each product tag in the user terminal data, and the more the occurrence times are, the higher the tag dependence degree is; the label attention degree represents the attention degree of the product label in the user terminal data, and the longer the attention time is, the higher the label dependence degree is, so as to comprehensively represent the label characteristic value of the product label.
In the embodiment of the invention, the data corresponding to the product label, the user requirements, the user characteristics and other user personal data can be obtained from the public database; or, the binding account authorization is obtained by the user on a local internet of things terminal (such as a vending machine, an unmanned vending rack and the like) in advance; or, after the user is authorized in advance, the data is acquired from the internal database of the terminal operator of the Internet of things, and the data is stored in the terminal of the Internet of things after being subjected to desensitization and encryption processing after being acquired, so that the data is prevented from being revealed, and the personal privacy of the user is protected.
In an embodiment of the present invention, referring to fig. 3, the calculating a tag characteristic value of each product tag in the product tag set includes:
s31, counting the total number of the product tags in the product tag set, and counting the number of the tags of each product tag;
s32, calculating the ratio between the number of the labels and the total number of the labels to obtain the label dependence of each product label;
s33, calculating label time data of each product label, and calculating label attention of each product label according to the label time data;
S34, collecting the label dependence degree and the label attention degree to obtain a label characteristic value of each product label.
In the embodiment of the invention, the tag time data is the use data of each product tag on the internet of things terminal, and comprises the following steps: using the latest time of the product tag, the time of the first time of using the product tag, and the time interval between the time of the last time of using the product tag and the time of using the first time of using the product tag, calculating the tag attention of each product tag in the user terminal data through the tag time data.
In an embodiment of the present invention, the calculating the label attention of each product label according to the label time data includes:
calculating the label attention of each product label by using the following formula:wherein (1)>Representing tag attention, ++>Representing time intervals in the tag time data, +.>Representing the latest time of use of the product label in the label time data, < >>Indicating the time when the product label was first used.
According to the embodiment of the invention, the dependence and the attention of the user on each product label can be comprehensively calculated through the label characteristic values, so that the advertisement is targeted.
And S4, calculating a tag preference value of the user identity feature according to the tag feature value, and calculating the feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value.
In the embodiment of the invention, the tag preference value represents the preference range of each user in the terminal data for each tag, specifically, the tag dependence and the tag attention in the tag characteristic value can be weighted and summed to obtain the tag characteristic value, so that the tag dependence and the tag attention are comprehensively considered, and the tag preference value is calculated more accurately.
In the embodiment of the invention, the feature association degree represents the similarity between each user identity feature and the preset terminal advertisement, and the larger the similarity is, the larger the feature association degree is, so that the terminal advertisement which is more attached to the user identity feature is obtained.
In the embodiment of the present invention, the calculating the feature association degree between the user identity feature and the preset terminal advertisement according to the tag preference value includes:
calculating the label weight of the product label corresponding to the label preference value according to the label preference value;
and obtaining a product label in the terminal advertisement, and calculating the characteristic association degree between the user identity characteristic and the terminal advertisement according to the label preference value and the label weight.
In the embodiment of the invention, the tag weight is the importance degree of each product tag, and the greater the tag weight is, the higher the importance degree is, so that the tag weight of each product tag can be obtained by performing equal proportion calculation according to the tag preference value, wherein the sum of the tag weights is 1.
In the embodiment of the invention, each terminal advertisement has obvious product label, wherein the product label corresponds to the product label, such as a whitening label, a home advertisement label and the like, and the characteristic association degree between the user identity characteristic and the terminal advertisement is calculated more accurately through the product label in each terminal advertisement.
In the embodiment of the present invention, the calculating the tag preference value and the feature association degree between the tag weight and the product tag in the terminal advertisement includes:
calculating the feature association degree by using the following formula:wherein (1)>Representing the tag preference value and the tag weight and +.>Characteristic association between individual terminal advertisements, +.>Indicate->Product tag in personal terminal advertisement->Corresponding tag preference value,/->Indicate->Advertisement product label in personal terminal advertisement>Corresponding weights, ++>Indicate->Total number of advertised product tags in individual terminal advertisements.
In the embodiment of the invention, the tag weight is the importance degree of each product tag, and the greater the tag weight is, the higher the importance degree is, the weight of the product tag can be calculated by weighting the weight of each user tag, for example, in the user tag 1, the weights of the product tags 1, 2 and 3 are 30%,40% and 30% occasionally respectively; in the user tag 2, the weights of the product tags 1, 2 and 3 are respectively 50%,10% and 40% occasionally, and then average value calculation is respectively carried out on the weight of the product tag under each user tag, so that the weight of the product tag in the user identity characteristic is obtained.
In the embodiment of the invention, the similarity between the terminal data corresponding to the identity characteristics of the user and each terminal advertisement can be calculated through the characteristic association degree, so that terminal advertisement delivery is carried out in a targeted manner, the delivered terminal advertisement is closer to the identity characteristics of the user, and accurate delivery of the terminal advertisement is realized.
S5, ordering the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and putting the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
In the embodiment of the invention, the terminal advertisements are ordered according to the size of the characteristic association degree to obtain the advertisement sequence, so that the advertisements with larger characteristic association degree are preferentially put into the internet-of-things terminal, preferably, when the video frames containing the face images are acquired again, the calculation of the characteristic association degree between the user identity characteristics and the terminal advertisements can be performed again, so that the putting accuracy of the terminal advertisements is improved.
In the embodiment of the invention, the terminal advertisement can be in a video form or an image-text form, and the advertisement sequence is sequentially put on the front-end display page of the internet of things terminal until the internet of things terminal acquires the user video frames with different identity characteristics again, so that the accurate putting of the terminal advertisement is realized.
According to the embodiment of the invention, the user video frames are acquired by the Internet of things terminal and subjected to key frame clustering, so that the key frames are obtained, the face form of the user can be comprehensively acquired, and the accuracy of the subsequent user identity characteristic calculation is improved; reconstructing the key frame to obtain a target face image with higher face image quality, so that more accurate user identity characteristics can be calculated according to the target face image; determining a product label set of the user identity characteristics, calculating a label characteristic value of each product label, and comprehensively calculating the dependence and the attention of the user on each product label to obtain the preference degree of the user on each label; and calculating the feature association degree according to the preference degree, and sequencing the advertisements of the terminal, so that the advertisements with larger feature association degree are put into the internet of things terminal preferentially, and the accurate putting of the advertisements of the terminal is realized. Therefore, the digital identity-based internet of things terminal advertisement putting method provided by the invention can solve the problem of poor accuracy of the internet of things terminal when putting advertisements.
Fig. 4 is a functional block diagram of an advertisement delivery device of an internet of things terminal based on digital identity according to an embodiment of the present invention.
The digital identity-based internet of things terminal advertisement delivery device 400 can be installed in electronic equipment. According to the functions implemented, the digital identity-based internet of things terminal advertisement delivery device 400 may include a key frame clustering module 401, a user identity feature recognition module 402, a tag feature value calculation module 403, a feature association calculation module 404, and a terminal advertisement delivery module 405. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the key frame clustering module 401 is configured to obtain a user video frame collected by an internet of things terminal, identify a face key point in the user video frame, and perform key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame;
the user identity feature recognition module 402 is configured to reconstruct a face image of the key frame to obtain a target face image corresponding to the internet of things terminal, extract wavelet features of the target face image, and recognize user identity features corresponding to the user video frame according to the wavelet features;
The tag feature value calculating module 403 is configured to extract corresponding identity terminal data from a preset terminal database according to the user identity feature, determine a product tag set of the user identity feature according to the identity terminal data, and calculate a tag feature value of each product tag in the product tag set;
the feature association degree calculating module 404 is configured to calculate a tag preference value of the user identity feature according to the tag feature value, and calculate a feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
the terminal advertisement delivery module 405 is configured to sort the terminal advertisements according to the feature association degree, obtain an advertisement sequence, and deliver the terminal advertisements to the internet of things terminal according to the advertisement sequence.
In detail, each module in the digital identity-based internet of things terminal advertisement delivery device 400 in the embodiment of the present invention adopts the same technical means as the digital identity-based internet of things terminal advertisement delivery method described in fig. 1 to 3, and can produce the same technical effects, which are not repeated here.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 501 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The invention also provides an electronic device which can comprise a processor, a memory, a communication bus and a communication interface, and can also comprise a computer program which is stored in the memory and can run on the processor, such as a welding stability improving method program of a heterogeneous titanium alloy laser welding technology.
The processor may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and the like. The processor is a Control Unit (Control Unit) of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory (for example, a welding stability improvement method program for performing a heterogeneous titanium alloy laser welding technique, etc.), and invokes data stored in the memory to perform various functions of the electronic device and process the data.
The memory includes at least one type of readable storage medium including flash memory, removable hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory may also include both internal storage units and external storage devices of the electronic device. The memory can be used for storing application software installed in electronic equipment and various data, such as codes of welding stability improving method programs of heterogeneous titanium alloy laser welding technology, and the like, and can be used for temporarily storing data which are output or are to be output.
The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory and at least one processor or the like.
The communication interface is used for communication between the electronic equipment and other equipment, and comprises a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Only an electronic device having components is shown, and it will be understood by those skilled in the art that the structures shown in the figures do not limit the electronic device, and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for powering the respective components, and preferably, the power source may be logically connected to the at least one processor through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
Specifically, the specific implementation method of the above instruction by the processor may refer to descriptions of related steps in the corresponding embodiment of the drawings, which are not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring a user video frame acquired by an internet of things terminal, identifying a face key point in the user video frame, and carrying out key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame;
reconstructing a face image of the key frame to obtain a target face image corresponding to the Internet of things terminal, extracting wavelet features of the target face image, and identifying user identity features corresponding to the user video frame according to the wavelet features;
extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product tag set of the user identity characteristics according to the identity terminal data, and calculating a tag characteristic value of each product tag in the product tag set;
calculating a tag preference value of the user identity feature according to the tag feature value, and calculating a feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
And sequencing the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and putting the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims (10)

1. The method for putting the advertisement on the internet of things terminal based on the digital identity is characterized by comprising the following steps:
acquiring a user video frame acquired by an internet of things terminal, identifying a face key point in the user video frame, and carrying out key frame clustering on the user video frame according to the face key point to obtain a key frame in the user video frame;
reconstructing a face image of the key frame to obtain a target face image corresponding to the Internet of things terminal, extracting wavelet features of the target face image, and identifying user identity features corresponding to the user video frame according to the wavelet features;
extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product tag set of the user identity characteristics according to the identity terminal data, and calculating a tag characteristic value of each product tag in the product tag set;
Calculating a tag preference value of the user identity feature according to the tag feature value, and calculating a feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
and sequencing the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and putting the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
2. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the identifying the face key points in the user video frame comprises:
initializing an image coordinate system on the user video frame, and marking feature points on the image coordinate system to obtain face feature point coordinates;
and calculating the center coordinates of the left eye and the right eye on the user video frame according to the face feature point coordinates, and taking the center coordinates of the left eye and the right eye as face key points in the user video frame.
3. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the step of performing key frame clustering on the user video frames according to the face key points to obtain key frames in the user video frames comprises the steps of:
Initializing a plurality of class centroid coordinates, and calculating the coordinate distance from the face key point to each class centroid coordinate;
and calculating the coordinate distance from the face key point to the centroid coordinates of each category by using the following formula:wherein (1)>Indicate->Personal face key point to->Coordinate clustering of individual class centroid coordinates +.>、/>Respectively represent +.>Position coordinates of left and right eyes in key points of personal face,/->、/>Respectively represent +.>The position coordinates of the left eye and the right eye in the mass center coordinates of each category;
carrying out initial clustering on the user video frames according to the coordinate distance to obtain an initial cluster;
iteratively updating the class centroid coordinates according to the initial cluster until the class centroid coordinates are not changed any more, so as to obtain a cluster center point;
calculating the center coordinate distance from the face key point to the clustering center point, and clustering the user video frames according to the center coordinate distance to obtain a video frame cluster;
and selecting a preset number of user video frames from each video frame cluster as key frames in the user video frames.
4. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the step of reconstructing the face image of the key frame to obtain a target face image corresponding to the internet of things terminal comprises the steps of:
Extracting depth features in the key frames by using convolution dense blocks in the face reconstruction network which is completed through pre-training;
deconvolution is carried out on the depth features to obtain deconvolution features, and feature mapping is carried out on the deconvolution features to obtain face features of the user video frames;
and reconstructing a face image according to the face characteristics to obtain a target face image corresponding to the Internet of things terminal.
5. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the determining the product tag set of the user identity according to the identity terminal data comprises:
extracting an operation record in the user terminal data, and determining the user requirement in the operation record;
and determining a product tag set of the user identity according to the user requirement.
6. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the calculating the tag characteristic value of each product tag in the product tag set comprises:
counting the total number of the product tags in the product tag set and the number of the tags of each product tag;
Calculating the ratio between the number of the labels and the total number of the labels to obtain the label dependence of each product label;
calculating label time data of each product label, and calculating label attention of each product label according to the label time data;
calculating the label attention of each product label by using the following formula:wherein (1)>Representing tag attention, ++>Representing time intervals in the tag time data, +.>Representing the latest time of use of the product label in the label time data, < >>Representing a time when the product label is first used;
and collecting the label dependence degree and the label attention degree to obtain the label characteristic value of each product label.
7. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the calculating the feature association degree between the user identity feature and the preset terminal advertisement according to the tag preference value comprises:
calculating the label weight of the product label corresponding to the label preference value according to the label preference value;
and obtaining a product label in the terminal advertisement, and calculating the characteristic association degree between the user identity characteristic and the terminal advertisement according to the label preference value and the label weight.
8. The method for advertising an internet of things terminal based on digital identity according to claim 1, wherein the calculating the feature association degree between the user identity feature and the terminal advertisement according to the tag preference value and the tag weight comprises:
calculating the feature association degree by using the following formula:wherein (1)>Representing the tag preference value and the tag weight and +.>Characteristic association between individual terminal advertisements, +.>Indicate->Product tag in personal terminal advertisement->Corresponding tag preference value,/->Indicate->Advertisement product label in personal terminal advertisement>Corresponding weights, ++>Represent the firstTotal number of advertised product tags in individual terminal advertisements.
9. An internet of things terminal advertisement putting device based on digital identity, which is characterized by comprising:
the key frame clustering module is used for acquiring user video frames acquired by the internet of things terminal, identifying face key points in the user video frames, and carrying out key frame clustering on the user video frames according to the face key points to obtain key frames in the user video frames;
the user identity feature recognition module is used for reconstructing the face image of the key frame to obtain a target face image corresponding to the internet of things terminal, extracting wavelet features of the target face image and recognizing user identity features corresponding to the user video frame according to the wavelet features;
The label characteristic value calculation module is used for extracting corresponding identity terminal data from a preset terminal database according to the user identity characteristics, determining a product label set of the user identity characteristics according to the identity terminal data, and calculating a label characteristic value of each product label in the product label set;
the feature association degree calculation module is used for calculating a tag preference value of the user identity feature according to the tag feature value and calculating the feature association degree between the user identity feature and a preset terminal advertisement according to the tag preference value;
and the terminal advertisement delivery module is used for sequencing the terminal advertisements according to the characteristic association degree to obtain an advertisement sequence, and delivering the terminal advertisements to the Internet of things terminal according to the advertisement sequence.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the digital identity based internet of things terminal advertisement delivery method according to any one of claims 1 to 8.
CN202311538612.1A 2023-11-17 2023-11-17 Internet of things terminal advertisement putting method, device and medium based on digital identity Active CN117252651B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311538612.1A CN117252651B (en) 2023-11-17 2023-11-17 Internet of things terminal advertisement putting method, device and medium based on digital identity

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311538612.1A CN117252651B (en) 2023-11-17 2023-11-17 Internet of things terminal advertisement putting method, device and medium based on digital identity

Publications (2)

Publication Number Publication Date
CN117252651A true CN117252651A (en) 2023-12-19
CN117252651B CN117252651B (en) 2024-03-19

Family

ID=89137297

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311538612.1A Active CN117252651B (en) 2023-11-17 2023-11-17 Internet of things terminal advertisement putting method, device and medium based on digital identity

Country Status (1)

Country Link
CN (1) CN117252651B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017113741A1 (en) * 2015-12-29 2017-07-06 乐视控股（北京）有限公司 Face-recognition-based advertisement recommendation method and device
CN111813986A (en) * 2020-07-10 2020-10-23 重庆中科云从科技有限公司 Intelligent advertisement pushing method, device, system, medium and electronic terminal
CN113378764A (en) * 2021-06-25 2021-09-10 深圳市斯博科技有限公司 Video face acquisition method, device, equipment and medium based on clustering algorithm
CN114066534A (en) * 2021-11-29 2022-02-18 中国平安人寿保险股份有限公司 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence
CN114943549A (en) * 2021-02-10 2022-08-26 中国科学技术大学 Advertisement delivery method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017113741A1 (en) * 2015-12-29 2017-07-06 乐视控股（北京）有限公司 Face-recognition-based advertisement recommendation method and device
CN111813986A (en) * 2020-07-10 2020-10-23 重庆中科云从科技有限公司 Intelligent advertisement pushing method, device, system, medium and electronic terminal
CN114943549A (en) * 2021-02-10 2022-08-26 中国科学技术大学 Advertisement delivery method and device
CN113378764A (en) * 2021-06-25 2021-09-10 深圳市斯博科技有限公司 Video face acquisition method, device, equipment and medium based on clustering algorithm
CN114066534A (en) * 2021-11-29 2022-02-18 中国平安人寿保险股份有限公司 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence

Also Published As

Publication number Publication date
CN117252651B (en) 2024-03-19

Similar Documents

Publication Publication Date Title
CN110662484B (en) System and method for whole body measurement extraction
CN109635680B (en) Multitask attribute identification method and device, electronic equipment and storage medium
CN107704834A (en) Householder method, device and storage medium are examined in micro- expression face
CN110727860A (en) User portrait method, device, equipment and medium based on internet beauty platform
CN110503076A (en) Video classification methods, device, equipment and medium based on artificial intelligence
Yu et al. AI-based targeted advertising system
CN114066534A (en) Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence
CN113345083A (en) Product display method and device based on virtual reality, electronic equipment and medium
CN113705469A (en) Face recognition method and device, electronic equipment and computer readable storage medium
CN116129473A (en) Identity-guide-based combined learning clothing changing pedestrian re-identification method and system
CN116405712A (en) OTT video-based multimedia pushing method, device, equipment and storage medium
CN116347045A (en) Monitoring method, device, equipment and storage medium based on communication and satellite technology
US20210117987A1 (en) Fraud estimation system, fraud estimation method and program
CN107392191A (en) Method for judging identity, device and electronic equipment
CN114595321A (en) Question marking method and device, electronic equipment and storage medium
CN110008922A (en) Image processing method, unit, medium for terminal device
CN116797864B (en) Auxiliary cosmetic method, device, equipment and storage medium based on intelligent mirror
CN117252651B (en) Internet of things terminal advertisement putting method, device and medium based on digital identity
CN109299378B (en) Search result display method and device, terminal and storage medium
CN117194780A (en) Travel route customization method, device and equipment for generating artificial intelligence
CN115098644B (en) Image and text matching method and device, electronic equipment and storage medium
CN114973374A (en) Expression-based risk evaluation method, device, equipment and storage medium
CN110942056A (en) Clothing key point positioning method and device, electronic equipment and medium
CN111652064B (en) Face image generation method, electronic device and readable storage medium
CN113869218A (en) Face living body detection method and device, electronic equipment and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant