CN114066534A - Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence - Google Patents

Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence Download PDF

Info

Publication number
CN114066534A
CN114066534A CN202111436088.8A CN202111436088A CN114066534A CN 114066534 A CN114066534 A CN 114066534A CN 202111436088 A CN202111436088 A CN 202111436088A CN 114066534 A CN114066534 A CN 114066534A
Authority
CN
China
Prior art keywords
advertisement
client
face
information data
attention
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
CN202111436088.8A
Other languages
Chinese (zh)
Inventor
周冰为
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.)
Ping An Life Insurance Company of China Ltd
Original Assignee
Ping An Life Insurance Company of China 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 Ping An Life Insurance Company of China Ltd filed Critical Ping An Life Insurance Company of China Ltd
Priority to CN202111436088.8A priority Critical patent/CN114066534A/en
Publication of CN114066534A publication Critical patent/CN114066534A/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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06Q30/0242—Determining effectiveness of advertisements
    • G06Q30/0244—Optimization
    • 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
    • G06Q30/0254—Targeted advertisements based on statistics
    • 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
    • G06Q30/0272—Period of advertisement exposure

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Probability & Statistics with Applications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides an elevator advertisement delivery method, device, electronic equipment and storage medium based on artificial intelligence, and the elevator advertisement delivery method based on artificial intelligence comprises: acquiring a face image of a client to acquire information data of the client, wherein the information data comprises age information data and gender information data of the client; matching the information data with preset advertisement data to obtain advertisement matching degree; sequentially delivering advertisements based on the sequence of the advertisement matching degree from high to low; counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value to obtain the attention degree of the client; and updating the release time length of the advertisement currently being released based on the customer attention. The method and the device can deliver the advertisements which are interested by the clients aiming at different clients, and flexibly adjust the delivery duration of the advertisements according to the interest degree of the clients in the currently delivered advertisements, so that the advertising effect of the advertisements is improved.

Description

Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an elevator advertisement delivery method and device based on artificial intelligence, electronic equipment and a storage medium.
Background
The elevator is a narrow and small confined space, and the interference degree is extremely low, and the elevator space is relatively boring simultaneously, consequently sets up the display screen and puts in the advertisement and has very high attention degree in the elevator.
However, the problem of personalized delivery is not considered in the current common elevator advertisement, only a unified advertisement file is played in the elevator, audience of the advertisement is not distinguished, and whether the client is interested in the currently delivered advertisement is not considered, so that the advertising effect of the advertisement cannot be further improved.
Disclosure of Invention
In view of the foregoing, there is a need for an elevator advertisement delivery method based on artificial intelligence and related devices, so as to solve the technical problem of how to improve the advertising effect of elevator advertisements, where the related devices include an elevator advertisement delivery apparatus based on artificial intelligence, an electronic device, and a storage medium.
The application provides an elevator advertisement delivery method based on artificial intelligence, including:
acquiring a face image of a client to acquire information data of the client, wherein the information data comprises age information data and gender information data of the client;
matching the information data with preset advertisement data to obtain advertisement matching degree;
sequentially delivering advertisements based on the sequence of the advertisement matching degree from high to low;
counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value to obtain the attention degree of the client;
and updating the release time length of the advertisement currently being released based on the customer attention.
Therefore, the corresponding advertisements are delivered by acquiring the information data of the clients in the elevator, the advertisements which are interested by the clients can be delivered for different clients, and the delivery duration of the advertisements is flexibly adjusted according to the interest degree of the clients in the currently delivered advertisements, so that the advertising effect of the advertisements is improved.
In some embodiments, the acquiring the face image of the customer to acquire the information data of the customer comprises:
detecting the face image according to a key point detection network to obtain a face area, wherein the key points comprise a face contour, eyes, eyebrows, lips and a nose contour;
and identifying the face area according to a preset neural network identification model to acquire the information data, wherein the neural network identification model comprises an age identification model and a gender identification model.
Therefore, the trained key point detection network can be used for collecting and rapidly identifying the face image of the client in the elevator in real time, and the information data of the client can be rapidly and accurately acquired according to the preset neural network identification model.
In some embodiments, the age recognition model recognizes the face region to obtain age information data of the customer, including:
taking a plurality of pictures containing human faces as a training library, and sequentially arranging the plurality of pictures in the training library according to ages to obtain a plurality of picture groups;
respectively extracting a plurality of human face features of each picture in each picture group, wherein the plurality of human face features comprise human face contour features, eye features, eyebrow features, lip features and nose contour features, and respectively extracting an initial feature vector of each human face feature of each picture in each picture group;
weighting and averaging the initial feature vectors of each kind of face features of all pictures in each picture group, and taking the current average value as the feature vector of the kind of face features in the picture group;
taking the feature vectors of various human face features in each picture group as a set, and sequencing the feature vectors in sequence according to the ages corresponding to the picture groups to obtain a human face age identification model with a plurality of groups of human face feature vectors;
inputting the collected current face region image into the age identification model to obtain each face feature vector;
matching the face feature vector with the face feature vector in the age identification model to obtain face similarity;
determining age information data of the client based on the face similarity.
Therefore, the age identification model identifies the age of the client more accurately in a plurality of angles through the face feature vector, so as to acquire the age information data of the client.
In some embodiments, the matching the information data and preset advertisement data to obtain the advertisement matching degree includes:
classifying preset advertisement data according to age group and gender information to obtain advertisement classification data, wherein the advertisement classification data comprises an age group audience tag and a gender audience tag;
and acquiring the advertisement matching degree according to whether the information data is in the label range of the advertisement classification data.
Therefore, the preset advertisement data are classified, the matching degree of the classified data and the information data of the client can be obtained on the basis, so that the advertisements which the client is interested in are sequentially released in the follow-up process according to the advertisement matching degree, and the advertising effect of the elevator advertisement is improved.
In some embodiments, the counting, according to a preset threshold, the number of times of attention of the customer to the advertisement currently being delivered to obtain the customer attention comprises:
continuously acquiring the face images of the client to obtain a face image set;
detecting the human face image set according to the key point detection network to obtain a human eye data set;
and counting the attention frequency of the customer to the advertisement currently put on the basis of the human eye data set and a preset threshold value to obtain the customer attention.
Therefore, the action of the human eye part can be accurately acquired through the key point detection network, so that the attention of a client is acquired, the interest degree of the client in the currently delivered advertisement is mastered according to the attention degree of the client, and the delivery time of the advertisement is conveniently adjusted in the subsequent process on the basis to further improve the advertising effect of the elevator advertisement.
In some embodiments, said updating the impression duration of the currently-being-delivered advertisement based on said customer attention comprises:
acquiring the original advertisement putting time length of the advertisement currently being put based on the preset advertisement data;
adjusting the original playing speed of the current advertisement according to the attention of the client to obtain a dynamic playing speed;
and updating the release time length of the advertisement currently being released based on the dynamic play rate.
Therefore, the dynamic adjustment of the advertisement putting time length can be realized according to the attention of the client to the currently-put advertisement, and a new advertisement can be put in time when the advertisement content which is not interested by the client appears, so that the advertising effect of the effective elevator advertisement is improved.
In some embodiments, the adjusting the original playing rate of the current advertisement according to the customer attention degree to obtain that the dynamic playing rate satisfies the relation:
Vi＝i·-0.τi
wherein v isiRepresents the original playing speed of the ith advertisement currently being delivered, τ i represents the client attention of the client to the ith advertisement currently being delivered, ViIndicating the dynamic play rate of the ith advertisement currently being delivered.
Therefore, the playing speed of the currently-released advertisement can be improved along with the reduction of the attention of the client through the relational expression, so that the currently-released advertisement can be played quickly, the next advertisement is released for the client in time, the man-machine interaction between the client and the elevator advertisement is improved, and the releasing of the elevator advertisement is more humanized.
The embodiment of the application still provides an elevator advertisement delivery device based on artificial intelligence, includes:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a face image of a client to acquire information data of the client, and the information data comprises age information data and gender information data of the client;
the matching unit is used for matching the information data with preset advertisement data to obtain advertisement matching degree;
the releasing unit is used for sequentially releasing advertisements based on the sequence of the advertisement matching degree from high to low;
the statistical unit is used for counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value so as to obtain the attention degree of the client;
and the updating unit is used for updating the release time length of the advertisement currently released based on the customer attention.
An embodiment of the present application further provides an electronic device, including:
a memory storing at least one instruction;
a processor executing instructions stored in the memory to implement the artificial intelligence based elevator advertising delivery method.
The embodiment of the application also provides a computer-readable storage medium, wherein at least one instruction is stored in the computer-readable storage medium and is executed by a processor in an electronic device to realize the artificial intelligence based elevator advertisement delivery method.
Drawings
Fig. 1 is a flow chart of a preferred embodiment of an artificial intelligence based elevator advertising method to which the present application relates.
Fig. 2 is a flowchart illustrating a preferred embodiment of counting the number of times a customer pays attention to an advertisement currently being delivered according to a preset threshold value to obtain the customer attention.
Fig. 3 is a flow diagram of a preferred embodiment of updating the placement duration of an advertisement currently being placed based on customer attention in accordance with the present application.
Fig. 4 is a functional block diagram of a preferred embodiment of an artificial intelligence based elevator advertising delivery apparatus to which the present application relates.
Fig. 5 is a schematic structural diagram of an electronic device of a preferred embodiment of an artificial intelligence based elevator advertisement delivery method to which the present application relates.
Detailed Description
For a clearer understanding of the objects, features and advantages of the present application, reference is made to the following detailed description of the present application along with the accompanying drawings and specific examples. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict. In the following description, numerous specific details are set forth to provide a thorough understanding of the present application, and the described embodiments are merely a subset of the embodiments of the present application and are not intended to be a complete embodiment.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
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 in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The embodiment of the Application provides an elevator advertisement delivery method based on artificial intelligence, which can be applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and hardware of the electronic devices includes but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device and the like.
The electronic device may be any electronic product capable of performing human-computer interaction with a client, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), a game machine, an Internet Protocol Television (IPTV), an intelligent wearable device, and the like.
The electronic device may also include a network device and/or a client device. The network device includes, but is not limited to, a single network server, a server group consisting of a plurality of network servers, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network servers.
The Network where the electronic device is located includes, but is not limited to, the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.
Fig. 1 is a flow chart of a preferred embodiment of the elevator advertisement delivery method based on artificial intelligence according to the present application. The order of the steps in the flow chart may be changed and some steps may be omitted according to different needs.
And S10, acquiring the face image of the client to acquire the information data of the client, wherein the information data comprises age information data and gender information data of the client.
In an alternative embodiment, the real-time video stream can be acquired through a network camera installed in the elevator, and the acquired real-time video stream is intercepted into a continuous single-frame picture by using an Opencv2 module in Python language. The Python is a common computer programming language and can provide rich standard libraries to be suitable for source codes or machine codes of various main system platforms, and the Opencv2 is a cross-platform computer vision library and can run in the Python, so that various general algorithms in the aspects of image processing and computer vision are realized.
In an optional embodiment, the acquiring the face image of the customer to acquire the information data of the customer comprises:
s101, detecting the face image according to a key point detection network to obtain a face area, wherein the key points comprise face contours, eyes, eyebrows, lips and nose contours.
In this optional embodiment, a PFLD (functional Facial Landmark detector) face key point detection network may be used to detect the face image to obtain a face region, where the PFLD is a face key point detection network model with high precision, high speed and a small model, and the whole network structure includes two parts, namely, a predicting Landmark main network and a head pool auxiliary network, where the main network uses a MobilenetV2 lightweight network and performs certain structural modification, and the detection capability of the network on the face key point is increased by multi-scale fusion, and the auxiliary network structure is used to supervise and assist detection of the key point.
In this optional embodiment, the labels of the face contour, the eyes, the eyebrows, the lips, and the nose contour in the face image are set to 1, and the other areas are set to 0, the main network of the PFLD trains the input face image according to the labels corresponding to the key points, so as to regress the positions of the key points in the face image, and meanwhile, the auxiliary network of the PFLD can acquire face pose information in each face image, and further correct the position information of the key points regressed by the main network according to the face pose in the current input image, so as to acquire a more accurate face key point image conforming to the current face pose to form a face area.
And S102, identifying the face area according to a preset neural network identification model to acquire information data.
In this alternative embodiment, the neural network identification model includes an age identification model and a gender identification model.
The age recognition model recognizes the face region to acquire age information data of the client, including:
taking a plurality of pictures containing human faces as a training library, and sequentially arranging the plurality of pictures in the training library according to ages to obtain a plurality of picture groups;
respectively extracting a plurality of human face features of each picture in each picture group, wherein the plurality of human face features comprise human face contour features, eye features, eyebrow features, lip features and nose contour features, and respectively extracting an initial feature vector of each human face feature of each picture in each picture group;
weighting and averaging the initial feature vectors of each kind of face features of all pictures in each picture group, and taking the current average value as the feature vector of the kind of face features in the picture group;
taking the feature vectors of various human face features in each picture group as a set, and sequencing the feature vectors in sequence according to the ages corresponding to the picture groups to obtain a human face age identification model with a plurality of groups of human face feature vectors;
inputting the collected current face region image into the age identification model to obtain each face feature vector;
matching the face feature vector with the face feature vector in the age identification model to obtain face similarity;
determining age information data of the client based on the face similarity.
In this alternative embodiment, the age identification model outputs a probability distribution of 101 values (ranging from 0 to 100 ages), and the probabilities of all 101 values add up to 1. Each age value is multiplied by its probability and then summed to give the final predicted age.
In this alternative embodiment, the current face region image is input into an age recognition model to obtain each face feature vector, these various face feature vectors form a feature vector set, and then similarity matching is performed on the face feature vector set of each group in the age recognition model to obtain a plurality of groups of face similarities, and the age corresponding to the group with the highest similarity is the age of the current face image.
The gender identification model identifies the face area to obtain gender information data of the customer.
In the optional embodiment, more than one hundred thousand face pictures with different genders are collected through Python, all the face pictures are respectively subjected to cleaning operation and cutting operation to serve as samples, wherein the cleaning operation comprises face deflection correction, picture brightness adjustment and graying, and the cutting operation is used for enhancing the robustness of training.
In this optional embodiment, a mode of training the full connection layer by using a simulator may be used to obtain a gender recognition model, a large number of obtained pictures containing different genders of men and women are sent to simulator software, wherein a male label is set to 1, a female label is set to 0, training is performed by using the simulator, and the inputted pictures are classified and output by using the full connection layer to determine the gender corresponding to the inputted face image.
Therefore, the trained key point detection network can be used for collecting and rapidly identifying the face image of the client in the elevator in real time, and the information data of the client can be rapidly and accurately acquired according to the preset neural network identification model.
And S11, matching the information data with preset advertisement data to obtain the advertisement matching degree.
In an optional embodiment, matching the information data with preset advertisement data to obtain the advertisement matching degree includes:
s111, classifying preset advertisement data according to age groups and gender information to obtain advertisement classification data, wherein the advertisement classification data comprise age group audience tags and gender audience tags.
In this optional embodiment, because the audience targeted by each advertisement is different, the preset advertisement data is classified based on the age information and gender information of the client, wherein each advertisement has a corresponding age group audience tag and gender audience tag, and the preset advertisement data can be primarily classified according to the age group audience tag and the gender audience tag to obtain the classification data.
Illustratively, advertisement A is categorized as female for its audience of age label, and is categorized as female for advertisement A, while being categorized as 35-65 for its audience of age label, and is categorized as 35-65 for advertisement A.
S112, acquiring the advertisement matching degree according to whether the information data is in the label range of the classification data.
In an optional embodiment, the advertisement matching degree is obtained according to whether the collected age information data and gender information data of the client are in a range included by the label of the advertisement data, wherein when the gender information data of the client is inconsistent with the label of the advertisement data, the corresponding advertisement matching degree is 0, the age matching degree is determined according to the position distance between the age of the client and the average value of the age-audience range of the advertisement, the average value of the age-audience range of the advertisement is used as the optimal age of the advertisement audience, and the closer the distance is, the higher the advertisement matching degree is.
Illustratively, if the age audience tags of the advertisement A, B, C are female, male and male, respectively, the corresponding age audience ranges are [35-65], [45-65], [25-55], the age of the client is 50 years, and the gender is male, then in the classification data of all advertisements, the advertisement matching degree of the advertisement a is found to be 0, the average value of the age audience ranges of the advertisement B, C is 55 and 40, respectively, the corresponding advertisement matching degrees are 5 and 10, the advertisement matching degree of the final advertisement B is the highest, the advertisement matching degree of the final advertisement C is the next advertisement matching degree, and the advertisement matching degree of the advertisement a is 0.
Therefore, the preset advertisement data are classified, the matching degree of the classified data and the information data of the client can be obtained on the basis, so that the advertisements which the client is interested in are sequentially released in the follow-up process according to the advertisement matching degree, and the advertising effect of the elevator advertisement is improved.
And S12, sequentially delivering the advertisements based on the sequence of the advertisement matching degree from high to low.
In an optional embodiment, corresponding advertisements are sequentially delivered to the playing terminal of the elevator to be played according to the sequence of the advertisement matching degree from high to low.
Therefore, the method can ensure that the delivered advertisements have better attraction to customers, thereby improving the advertising effect of the elevator advertisements.
And S13, counting the attention frequency of the client to the advertisement currently put according to a preset threshold value to obtain the client attention degree.
In an optional embodiment, counting the number of times that the customer pays attention to the currently delivered advertisement according to a preset threshold to obtain the customer attention comprises:
s131, continuously collecting the face images of the client to obtain a face image set.
In the optional embodiment, the face images of the clients are continuously acquired all the way according to the video stream acquired by the network camera in the elevator, so that a face image set continuous in time is formed.
S132, detecting the human face image set according to the key point detection network to obtain a human eye data set.
In an optional embodiment, the positions of the eye key points of all images in the face image set are detected according to a key point detection network, wherein for a single frame of face image, two eye key points are connected to obtain an eye connecting line, whether a perpendicular bisector of the eye connecting line perpendicular to the face region intersects with a terminal display screen for putting an advertisement is calculated, if the eye connecting line intersects with the terminal display screen for putting the advertisement, the client watches the advertisement, otherwise, the client does not interest the currently played advertisement, and finally, the face image of the client watching the advertisement is reserved as a eye data set.
And S133, counting the attention frequency of the customer to the advertisement currently put on the basis of the human eye data set and a preset threshold value to acquire the customer attention.
In an alternative embodiment, if the client in the image is watching the advertisement, the number of times of attention is recorded as one time, since the time represented by a single frame image is short, the preset threshold value may be 60 times, when more than 60 consecutive image frames in the human eye data set are the client watching the advertisement, the number of times of effective attention of the client from entering the elevator is counted, and the degree of attention of the client is represented as one time of effective attention.
Therefore, the action of the human eye part can be accurately acquired through the key point detection network, so that the attention of a client is acquired, the interest degree of the client in the currently delivered advertisement is mastered according to the attention degree of the client, and the delivery time of the advertisement is conveniently adjusted in the subsequent process on the basis to further improve the advertising effect of the elevator advertisement.
And S14, updating the release time length of the advertisement currently being released based on the customer attention.
In an alternative embodiment, updating the impression duration of the currently-being-delivered advertisement based on the customer attention comprises:
and S141, acquiring the original advertisement putting time length of the advertisement currently being put based on the preset advertisement data.
In an optional embodiment, the preset advertisement data includes an original placement time length of each advertisement, and the original placement time length is a complete playing time length from the beginning of the advertisement to the completion of the advertisement of a single advertisement.
S142, adjusting the original playing speed of the current advertisement according to the customer attention to obtain the dynamic playing speed.
In an optional embodiment, the original playing rate of the current advertisement is adjusted according to the customer attention to obtain that the dynamic playing rate satisfies the relation:
Vi＝vi·e-0.01τi
wherein v isiRepresents the original playing speed of the ith advertisement currently being delivered, τ i represents the client attention of the client to the ith advertisement currently being delivered, ViIndicating the dynamic play rate of the ith advertisement currently being delivered.
In this alternative embodiment, the rate of playback of the advertisement, v, is such that the customer is in the elevator for a short period of timeiMay be 2, i.e. the advertisement may be played at twice the rate when viewed without a person, with the customer's attention increasing, where ViCan be in the range of [0.5-2 ]]That is, the advertisement is played at the playing speed interval of 0.5 times to 2 times, and the value range of τ i can be [0-140]I.e. as the customer's attention increases, e-0.01τiIt will approach 0.25, thereby making the playing rate of the advertisement approach 0.5 times the rate.
In this alternative embodiment, when more than 60 consecutive image frames in the human eye data set are that the client is watching the advertisement, it is marked as a valid attention, and usually 1s of video contains about 30 pictures, i.e. the time of a valid attention is about 2s, and the time of the client in the elevator is generally within 280s, so the maximum number of valid attention can be set to 140.
And S143, updating the release time length of the advertisement currently released based on the dynamic play rate.
In an optional embodiment, the playing rate of the currently delivered advertisement is updated according to the obtained dynamic playing rate, so as to dynamically update the delivery duration of the currently delivered advertisement.
Illustratively, a client Zusanli is not interested in the advertisement D being released in the elevator, the advertisement D is played at twice the playing speed at the moment, the client Zusanli starts to watch the advertisement D in the middle of the process, and the playing speed of the advertisement D is gradually slowed down along with the higher attention of Zusanli, so that the client Zusanli can conveniently know the interested part in more detail.
In an alternative embodiment, the display screen of the play terminal may be a touch display screen for human-computer interaction, and when the customer is interested in the currently delivered advertisement, the customer may further view detailed information of the advertised product or leave a contact address by clicking a relevant button on the touch display screen.
In an optional embodiment, the passenger can also scan the two-dimensional code displayed by the touch display screen through an intelligent terminal such as a mobile phone, and the mobile phone sends an access request to the advertisement product database based on the internet link information coded in the two-dimensional code; and when the advertisement product database receives an access request sent by the intelligent terminal, finding a page address corresponding to the internet link information, and returning a response indicating that the intelligent terminal jumps to the page address to the intelligent terminal. Therefore, detailed information of products and a customer information acquisition page are displayed for customers, and accurate acquisition is realized.
Therefore, the dynamic adjustment of the advertisement putting time length can be realized according to the attention of the client to the currently-put advertisement, and a new advertisement can be put in time when the advertisement content which is not interested by the client appears, so that the advertising effect of the effective elevator advertisement is improved.
Therefore, the corresponding advertisements are delivered by acquiring the information data of the clients in the elevator, the advertisements which are interested by the clients can be delivered for different clients, and the delivery duration of the advertisements is flexibly adjusted according to the interest degree of the clients in the currently delivered advertisements, so that the advertising effect of the advertisements is improved.
Referring to fig. 4, fig. 4 is a functional block diagram of a preferred embodiment of the elevator advertisement delivery apparatus based on artificial intelligence according to the present application. The artificial intelligence-based elevator advertisement delivery device 11 comprises an acquisition unit 110, a matching unit 111, a delivery unit 112, a statistic unit 113 and an updating unit 114. A module/unit as referred to herein is a series of computer readable instruction segments capable of being executed by the processor 13 and performing a fixed function, and is stored in the memory 12. In the present embodiment, the functions of the modules/units will be described in detail in the following embodiments.
In an alternative embodiment, the obtaining unit 110 is configured to acquire a face image of the customer to obtain information data of the customer, where the information data includes age information data and gender information data of the customer.
In an alternative embodiment, the acquiring the face image of the client to acquire the information data of the client comprises:
detecting the face image according to a key point detection network to obtain a face area, wherein the key points comprise a face contour, eyes, eyebrows, lips and a nose contour;
and identifying the face area according to a preset neural network identification model to acquire the information data, wherein the neural network identification model comprises an age identification model and a gender identification model.
In an alternative embodiment, the real-time video stream can be acquired through a network camera installed in the elevator, and the acquired real-time video stream is intercepted into a continuous single-frame picture by using an Opencv2 module in Python language. The Python is a common computer programming language and can provide rich standard libraries to be suitable for source codes or machine codes of various main system platforms, and the Opencv2 is a cross-platform computer vision library and can run in the Python, so that various general algorithms in the aspects of image processing and computer vision are realized.
In this optional embodiment, a PFLD (functional Facial Landmark detector) face key point detection network may be used to detect the face image to obtain a face region, where the PFLD is a face key point detection network model with high precision, high speed and a small model, and the whole network structure includes two parts, namely, a predicting Landmark main network and a head pool auxiliary network, where the main network uses a MobilenetV2 lightweight network and performs certain structural modification, and the detection capability of the network on the face key point is increased by multi-scale fusion, and the auxiliary network structure is used to supervise and assist detection of the key point.
In this alternative embodiment, the neural network identification model includes an age identification model and a gender identification model;
the age recognition model recognizes the face region to acquire age information data of the client, including:
taking a plurality of pictures containing human faces as a training library, and sequentially arranging the plurality of pictures in the training library according to ages to obtain a plurality of picture groups;
respectively extracting a plurality of human face features of each picture in each picture group, wherein the plurality of human face features comprise human face contour features, eye features, eyebrow features, lip features and nose contour features, and respectively extracting an initial feature vector of each human face feature of each picture in each picture group;
weighting and averaging the initial feature vectors of each kind of face features of all pictures in each picture group, and taking the current average value as the feature vector of the kind of face features in the picture group;
taking the feature vectors of various human face features in each picture group as a set, and sequencing the feature vectors in sequence according to the ages corresponding to the picture groups to obtain a human face age identification model with a plurality of groups of human face feature vectors;
inputting the collected current face region image into the age identification model to obtain each face feature vector;
matching the face feature vector with the face feature vector in the age identification model to obtain face similarity;
determining age information data of the client based on the face similarity.
In this alternative embodiment, the age identification model outputs a probability distribution of 101 values (ranging from 0 to 100 ages), and the probabilities of all 101 values add up to 1. Each age value is multiplied by its probability and then summed to give the final predicted age.
In this alternative embodiment, the current face region image is input into an age recognition model to obtain each face feature vector, these various face feature vectors form a feature vector set, and then similarity matching is performed on the face feature vector set of each group in the age recognition model to obtain a plurality of groups of face similarities, and the age corresponding to the group with the highest similarity is the age of the current face image.
The gender identification model identifies the face area to acquire gender information data of the customer, and comprises the following steps:
analyzing the face region based on the gender recognition model to obtain gender probability;
determining gender information data for the customer based on the gender probability.
In this alternative embodiment, the training steps of the gender identification model are as follows:
acquiring more than one hundred thousand face pictures with different genders by Python, and respectively performing cleaning operation and cutting operation on all the face pictures to serve as samples, wherein the cleaning operation comprises face deflection correction, picture brightness adjustment and graying, and the cutting operation is used for enhancing the robustness of training;
in this optional embodiment, a mode of training the full connection layer by using a simulator may be used to obtain a gender recognition model, a large number of obtained pictures containing different genders of men and women are sent to simulator software, wherein a male label is set to 1, a female label is set to 0, training is performed by using the simulator, and the inputted pictures are classified and output by using the full connection layer to determine the gender corresponding to the inputted face image.
Therefore, the trained key point detection network can be used for collecting and rapidly identifying the face image of the client in the elevator in real time, and the information data of the client can be rapidly and accurately acquired according to the preset neural network identification model.
In an optional embodiment, the matching unit 111 is configured to match the information data with preset advertisement data to obtain an advertisement matching degree.
In an optional embodiment, matching the information data with preset advertisement data to obtain the advertisement matching degree includes:
classifying preset advertisement data according to age group and gender information to obtain advertisement classification data, wherein the advertisement classification data comprises an age group audience tag and a gender audience tag;
and acquiring the advertisement matching degree according to whether the information data is in the label range of the classification data.
In this optional embodiment, because the audience targeted by each advertisement is different, the preset advertisement data is classified based on the age information and gender information of the client, wherein each advertisement has a corresponding age group audience tag and gender audience tag, and the preset advertisement data can be primarily classified according to the age group audience tag and the gender audience tag to obtain the classification data.
Illustratively, advertisement A is categorized as female for its audience of age label, and is categorized as female for advertisement A, while being categorized as 35-65 for its audience of age label, and is categorized as 35-65 for advertisement A.
In an optional embodiment, the advertisement matching degree is obtained according to whether the collected age information data and gender information data of the client are in a range included by the label of the advertisement data, wherein when the gender information data of the client is inconsistent with the label of the advertisement data, the corresponding advertisement matching degree is 0, the age matching degree is determined according to the position distance between the age of the client and the average value of the age-audience range of the advertisement, the average value of the age-audience range of the advertisement is used as the optimal age of the advertisement audience, and the closer the distance is, the higher the advertisement matching degree is.
Illustratively, if the age audience tags of the advertisement A, B, C are female, male and male, respectively, the corresponding age audience ranges are [35-65], [45-65], [25-55], the age of the client is 50 years, and the gender is male, then in the classification data of all advertisements, the advertisement matching degree of the advertisement a is found to be 0, the average value of the age audience ranges of the advertisement B, C is 55 and 40, respectively, the corresponding advertisement matching degrees are 5 and 10, the advertisement matching degree of the final advertisement B is the highest, the advertisement matching degree of the final advertisement C is the next advertisement matching degree, and the advertisement matching degree of the advertisement a is 0.
And a delivering unit 112, configured to sequentially deliver advertisements based on the order of the advertisement matching degrees from high to low.
In an optional embodiment, corresponding advertisements are sequentially delivered to the playing terminal of the elevator to be played according to the sequence of the advertisement matching degree from high to low.
In an alternative embodiment, the counting unit 113 is configured to count the number of times that the customer pays attention to the currently delivered advertisement according to a preset threshold to obtain the customer attention.
In an optional embodiment, counting the number of times that the customer pays attention to the currently delivered advertisement according to a preset threshold to obtain the customer attention comprises:
continuously acquiring the face images of the client to obtain a face image set;
detecting the human face image set according to the key point detection network to obtain a human eye data set;
and counting the attention frequency of the customer to the advertisement currently put on the basis of the human eye data set and a preset threshold value to obtain the customer attention.
In the optional embodiment, the face images of the clients are continuously acquired all the way according to the video stream acquired by the network camera in the elevator, so that a face image set continuous in time is formed.
In an optional embodiment, the positions of the eye key points of all images in the face image set are detected according to a key point detection network, wherein for a single frame of face image, two eye key points are connected to obtain an eye connecting line, whether a perpendicular bisector of the eye connecting line perpendicular to the face region intersects with a terminal display screen for putting an advertisement is calculated, if the eye connecting line intersects with the terminal display screen for putting the advertisement, the client watches the advertisement, otherwise, the client does not interest the currently played advertisement, and finally, the face image of the client watching the advertisement is reserved as a eye data set.
In an alternative embodiment, if the client in the image is watching the advertisement, the number of times of attention is recorded as one time, since the time represented by a single frame image is short, the preset threshold value may be 60 times, when more than 60 consecutive image frames in the human eye data set are the client watching the advertisement, the number of times of effective attention of the client from entering the elevator is counted, and the degree of attention of the client is represented as one time of effective attention.
In an alternative embodiment, the updating unit 114 is configured to update the impression time length of the advertisement currently being impression based on the customer attention.
In an alternative embodiment, updating the impression duration of the currently-being-delivered advertisement based on the customer attention comprises:
acquiring the original advertisement putting time length of the advertisement currently being put based on the preset advertisement data;
adjusting the original playing speed of the current advertisement according to the attention of the client to obtain a dynamic playing speed;
and updating the release time length of the advertisement currently being released based on the dynamic play rate.
In an optional embodiment, the preset advertisement data includes an original placement time length of each advertisement, and the original placement time length is a complete playing time length from the beginning of the advertisement to the completion of the advertisement of a single advertisement.
In an optional embodiment, the original playing rate of the current advertisement is adjusted according to the customer attention to obtain that the dynamic playing rate satisfies the relation:
Vi＝vi·e-0.01τi
wherein v isiRepresents the original playing speed of the ith advertisement currently being delivered, τ i represents the client attention of the client to the ith advertisement currently being delivered, ViIndicating the dynamic play rate of the ith advertisement currently being delivered.
In this alternative embodiment, the advertisement is played because the customer is in the elevator for a short period of timeVelocity viMay be 2, i.e. the advertisement may be played at twice the rate when viewed without a person, with the customer's attention increasing, where ViCan be in the range of [0.5-2 ]]That is, the advertisement is played at the playing speed interval of 0.5 times to 2 times, and the value range of τ i can be [0-140]I.e. as the customer's attention increases, e-0.01τiIt will approach 0.25, thereby making the playing rate of the advertisement approach 0.5 times the rate.
In this alternative embodiment, when more than 60 consecutive image frames in the human eye data set are that the client is watching the advertisement, it is marked as a valid attention, and usually 1s of video contains about 30 pictures, i.e. the time of a valid attention is about 2s, and the time of the client in the elevator is generally within 280s, so the maximum number of valid attention can be set to 140.
In an optional embodiment, the playing rate of the currently delivered advertisement is updated according to the obtained dynamic playing rate, so as to dynamically update the delivery duration of the currently delivered advertisement.
Illustratively, a client Zusanli is not interested in the advertisement D being released in the elevator, the advertisement D is played at twice the playing speed at the moment, the client Zusanli starts to watch the advertisement D in the middle of the process, and the playing speed of the advertisement D is gradually slowed down along with the higher attention of Zusanli, so that the client Zusanli can conveniently know the interested part in more detail.
In an alternative embodiment, the display screen of the play terminal may be a touch display screen for human-computer interaction, and when the customer is interested in the currently delivered advertisement, the customer may further view detailed information of the advertised product or leave a contact address by clicking a relevant button on the touch display screen.
In an optional embodiment, the passenger can also scan the two-dimensional code displayed by the touch display screen through an intelligent terminal such as a mobile phone, and the mobile phone sends an access request to the advertisement product database based on the internet link information coded in the two-dimensional code; and when the advertisement product database receives an access request sent by the intelligent terminal, finding a page address corresponding to the internet link information, and returning a response indicating that the intelligent terminal jumps to the page address to the intelligent terminal. Therefore, detailed information of products and a customer information acquisition page are displayed for customers, and accurate acquisition is realized.
According to the technical scheme, the corresponding advertisements can be released by acquiring the information data of the clients in the elevator, the advertisements which are interested by the clients can be released for different clients, and the releasing time of the advertisements is flexibly adjusted according to the interest degree of the clients to the currently released advertisements, so that the advertising effect of the advertisements is improved.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 1 comprises a memory 12 and a processor 13. The memory 12 is used for storing computer readable instructions, and the processor 13 is used for executing the computer readable instructions stored in the memory to realize the artificial intelligence based elevator advertisement delivery method of any one of the above embodiments.
In an alternative embodiment the electronic device 1 further comprises a bus, a computer program stored in said memory 12 and executable on said processor 13, such as an artificial intelligence based elevator advertising program.
Fig. 5 shows only the electronic device 1 with the memory 12 and the processor 13, and it will be understood by those skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
In conjunction with fig. 1, the memory 12 in electronic device 1 stores a plurality of computer-readable instructions to implement an artificial intelligence based elevator advertising method, and the processor 13 is executable by the plurality of instructions to implement:
acquiring a face image of a client to acquire information data of the client, wherein the information data comprises age information data and gender information data of the client;
matching the information data with preset advertisement data to obtain advertisement matching degree;
sequentially delivering advertisements based on the sequence of the advertisement matching degree from high to low;
counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value to obtain the attention degree of the client;
and updating the release time length of the advertisement currently being released based on the customer attention.
Specifically, the processor 13 may refer to the description of the relevant steps in the embodiment corresponding to fig. 1 for a specific implementation method of the instruction, which is not described herein again.
It will be understood by those skilled in the art that the schematic diagram is merely an example of the electronic device 1, and does not constitute a limitation to the electronic device 1, the electronic device 1 may have a bus-type structure or a star-type structure, and the electronic device 1 may further include more or less hardware or software than those shown in the figures, or different component arrangements, for example, the electronic device 1 may further include an input and output device, a network access device, etc.
It should be noted that the electronic device 1 is only an example, and other existing or future electronic products, such as those that may be adapted to the present application, should also be included in the scope of protection of the present application, and are included by reference.
Memory 12 includes at least one type of readable storage medium, which may be non-volatile or volatile. The readable storage medium includes flash memory, removable hard disks, multimedia cards, card type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. The memory 12 may in some embodiments be an internal storage unit of the electronic device 1, for example a removable hard disk of the electronic device 1. The memory 12 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the electronic device 1. The memory 12 can be used not only for storing application software installed in the electronic device 1 and various kinds of data, such as codes of an artificial intelligence based elevator advertisement delivery program, etc., but also for temporarily storing data that has been output or is to be output.
The processor 13 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 13 is a Control Unit (Control Unit) of the electronic device 1, connects various components of the electronic device 1 by various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules stored in the memory 12 (for example, executing an artificial intelligence-based elevator advertisement delivery program and the like) and calling data stored in the memory 12.
The processor 13 executes an operating system of the electronic device 1 and various installed application programs. The processor 13 executes the application program to implement the steps in the various artificial intelligence based elevator advertising method embodiments described above, such as the steps shown in fig. 1-3.
Illustratively, the computer program may be partitioned into one or more modules/units, which are stored in the memory 12 and executed by the processor 13 to accomplish the present application. The one or more modules/units may be a series of computer-readable instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the electronic device 1. For example, the computer program may be divided into an acquisition unit 110, a matching unit 111, a delivery unit 112, a statistics unit 113, an update unit 114.
The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a computer device, or a network device) or a processor (processor) to execute the parts of the artificial intelligence based elevator advertisement delivery method according to the embodiments of the present application.
The integrated modules/units of the electronic device 1 may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, all or part of the processes in the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer-readable storage medium and executed by a processor, to implement the steps of the embodiments of the methods described above.
Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), random-access Memory and other Memory, etc.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus. The bus is arranged to enable connection communication between the memory 12 and at least one processor 13 or the like.
Although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 13 through a power management device, so that functions such as charge management, discharge management, and power consumption management are implemented through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, which may optionally include a wired interface and/or a wireless interface (such as a Wi-Fi interface, a bluetooth interface, etc.), and is generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a client interface, which may be a Display (Display), an input unit (such as a Keyboard (Keyboard)), and optionally 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 device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visual customer interface.
The embodiment of the present application further provides a computer-readable storage medium (not shown), in which computer-readable instructions are stored, and the computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence based elevator advertisement delivery method according to any of the above embodiments.
It is to be understood that the described embodiments are for purposes of illustration only and are not to be construed as limiting the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus 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 only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the specification may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.

Claims (10)

1. An elevator advertisement delivery method based on artificial intelligence is characterized by comprising the following steps:
acquiring a face image of a client to acquire information data of the client, wherein the information data comprises age information data and gender information data of the client;
matching the information data with preset advertisement data to obtain advertisement matching degree;
sequentially delivering advertisements based on the sequence of the advertisement matching degree from high to low;
counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value to obtain the attention degree of the client;
and updating the release time length of the advertisement currently being released based on the customer attention.
2. The artificial intelligence based elevator advertising method according to claim 1, wherein the collecting a face image of the customer to obtain information data of the customer comprises:
detecting the face image according to a key point detection network to obtain a face area, wherein the key points comprise a face contour, eyes, eyebrows, lips and a nose contour;
and identifying the face area according to a preset neural network identification model to acquire the information data, wherein the neural network identification model comprises an age identification model and a gender identification model.
3. The artificial intelligence based elevator advertising method according to claim 2,
the age recognition model recognizes the face region to acquire age information data of the client, including:
taking a plurality of pictures containing human faces as a training library, and sequentially arranging the plurality of pictures in the training library according to ages to obtain a plurality of picture groups;
respectively extracting a plurality of human face features of each picture in each picture group, wherein the plurality of human face features comprise human face contour features, eye features, eyebrow features, lip features and nose contour features, and respectively extracting an initial feature vector of each human face feature of each picture in each picture group;
weighting and averaging the initial feature vectors of each kind of face features of all pictures in each picture group, and taking the current average value as the feature vector of the kind of face features in the picture group;
taking the feature vectors of various human face features in each picture group as a set, and sequencing the feature vectors in sequence according to the ages corresponding to the picture groups to obtain a human face age identification model with a plurality of groups of human face feature vectors;
inputting the collected current face region image into the age identification model to obtain each face feature vector;
matching the face feature vector with the face feature vector in the age identification model to obtain face similarity;
determining age information data of the client based on the face similarity.
4. The artificial intelligence based elevator advertising method according to claim 1, wherein the matching the information data with preset advertisement data to obtain an advertisement matching degree comprises:
classifying preset advertisement data according to age group and gender information to obtain advertisement classification data, wherein the advertisement classification data comprises an age group audience tag and a gender audience tag;
and acquiring the advertisement matching degree according to whether the information data is in the label range of the classification data.
5. The artificial intelligence based elevator advertisement delivery method according to claim 2, wherein the counting the number of times that a customer pays attention to the currently delivered advertisement according to a preset threshold to obtain the customer attention comprises:
continuously acquiring the face images of the client to obtain a face image set;
detecting the human face image set according to the key point detection network to obtain a human eye data set;
and counting the attention frequency of the customer to the advertisement currently put on the basis of the human eye data set and a preset threshold value to obtain the customer attention.
6. The artificial intelligence based elevator advertising method of claim 1, wherein said updating a placement duration of an advertisement currently being placed based on said customer attention comprises:
acquiring the release time length of the currently released advertisement based on the preset advertisement data;
adjusting the original playing speed of the current advertisement according to the attention of the client to obtain a dynamic playing speed;
and updating the release time length of the advertisement currently being released based on the dynamic play rate.
7. The artificial intelligence based elevator advertisement delivery method according to claim 6, wherein the original playing rate of the current advertisement is adjusted according to the customer attention to obtain a dynamic playing rate satisfying the relation:
Vi＝vi·e-0.01τi
wherein v isiRepresents the original playing speed of the ith advertisement currently being delivered, τ i represents the client attention of the client to the ith advertisement currently being delivered, ViIndicating the dynamic play rate of the ith advertisement currently being delivered.
8. An artificial intelligence elevator advertisement delivery device, comprising:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring a face image of a client to acquire information data of the client, and the information data comprises age information data and gender information data of the client;
the matching unit is used for matching the information data with preset advertisement data to obtain advertisement matching degree;
the releasing unit is used for sequentially releasing advertisements based on the sequence of the advertisement matching degree from high to low;
the statistical unit is used for counting the attention frequency of a client to the currently delivered advertisement according to a preset threshold value so as to obtain the attention degree of the client;
and the updating unit is used for updating the release time length of the advertisement currently released based on the customer attention.
9. An electronic device, comprising:
a memory storing computer readable instructions; and
a processor executing computer readable instructions stored in the memory to implement the artificial intelligence based elevator advertising method of any of claims 1-7.
10. A computer-readable storage medium having computer-readable instructions stored thereon which, when executed by a processor, implement the artificial intelligence based elevator advertisement delivery method of any of claims 1-7.
CN202111436088.8A 2021-11-29 2021-11-29 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence Pending CN114066534A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111436088.8A CN114066534A (en) 2021-11-29 2021-11-29 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111436088.8A CN114066534A (en) 2021-11-29 2021-11-29 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN114066534A true CN114066534A (en) 2022-02-18

Family

ID=80277095

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111436088.8A Pending CN114066534A (en) 2021-11-29 2021-11-29 Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN114066534A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114936885A (en) * 2022-07-21 2022-08-23 成都薯片科技有限公司 Advertisement information matching pushing method, device, system, equipment and storage medium
CN115392980A (en) * 2022-09-06 2022-11-25 杭州储秀网络科技股份有限公司 Accurate delivery system of new media advertisement
CN116863864A (en) * 2023-07-11 2023-10-10 浙江雨林电子科技有限公司 LED lamp control method and system based on Internet of things
CN117172855A (en) * 2023-09-20 2023-12-05 南通捷米科技有限公司 Elevator advertisement playing method and system based on face recognition
CN117252651A (en) * 2023-11-17 2023-12-19 深圳市远景达物联网技术有限公司 Internet of things terminal advertisement putting method, device and medium based on digital identity

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114936885A (en) * 2022-07-21 2022-08-23 成都薯片科技有限公司 Advertisement information matching pushing method, device, system, equipment and storage medium
CN114936885B (en) * 2022-07-21 2022-11-04 成都薯片科技有限公司 Advertisement information matching pushing method, device, system, equipment and storage medium
CN115392980A (en) * 2022-09-06 2022-11-25 杭州储秀网络科技股份有限公司 Accurate delivery system of new media advertisement
CN115392980B (en) * 2022-09-06 2023-05-05 杭州储秀网络科技股份有限公司 New media advertisement accurate delivery system
CN116863864A (en) * 2023-07-11 2023-10-10 浙江雨林电子科技有限公司 LED lamp control method and system based on Internet of things
CN116863864B (en) * 2023-07-11 2024-03-22 浙江雨林电子科技有限公司 LED lamp control method and system based on Internet of things
CN117172855A (en) * 2023-09-20 2023-12-05 南通捷米科技有限公司 Elevator advertisement playing method and system based on face recognition
CN117172855B (en) * 2023-09-20 2024-05-14 南通捷米科技有限公司 Elevator advertisement playing method and system based on face recognition
CN117252651A (en) * 2023-11-17 2023-12-19 深圳市远景达物联网技术有限公司 Internet of things terminal advertisement putting method, device and medium based on digital identity
CN117252651B (en) * 2023-11-17 2024-03-19 深圳市远景达物联网技术有限公司 Internet of things terminal advertisement putting method, device and medium based on digital identity

Similar Documents

Publication Publication Date Title
CN114066534A (en) Elevator advertisement delivery method, device, equipment and medium based on artificial intelligence
US9892316B2 (en) Method and apparatus for pattern tracking
CN111770317B (en) Video monitoring method, device, equipment and medium for intelligent community
US20130067513A1 (en) Content output device, content output method, content output program, and recording medium having content output program recorded thereon
US20130138499A1 (en) Usage measurent techniques and systems for interactive advertising
CN111860377A (en) Live broadcast method and device based on artificial intelligence, electronic equipment and storage medium
CN110689367A (en) Data acquisition method and device, computer device and storage medium
CN112860848B (en) Information retrieval method, device, equipment and medium
US20220083783A1 (en) Enhancing detection of occluded objects in a multiple object detection system
CN114782901B (en) Sand table projection method, device, equipment and medium based on visual change analysis
CN112801062B (en) Live video identification method, device, equipment and medium
CN113345083A (en) Product display method and device based on virtual reality, electronic equipment and medium
CN114639152A (en) Multi-modal voice interaction method, device, equipment and medium based on face recognition
CN112686232B (en) Teaching evaluation method and device based on micro expression recognition, electronic equipment and medium
CN112861750B (en) Video extraction method, device, equipment and medium based on inflection point detection
CN112651782B (en) Behavior prediction method, device, equipment and medium based on dot product attention scaling
CN112101191A (en) Expression recognition method, device, equipment and medium based on frame attention network
CN111598600A (en) Multimedia information pushing method and system and terminal equipment
WO2021104388A1 (en) System and method for interactive perception and content presentation
CN111950707B (en) Behavior prediction method, device, equipment and medium based on behavior co-occurrence network
US20210004573A1 (en) Sentiment analysis
CN109801394B (en) Staff attendance checking method and device, electronic equipment and readable storage medium
CN115222778A (en) Moving object detection method and device based on optical flow, electronic device and medium
CN114882420A (en) Reception people counting method and device, electronic equipment and readable storage medium
CN113435975A (en) Wheelchair leasing processing method and device and related equipment

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