CN114764730A - Advertisement accurate delivery method based on vehicle information identification - Google Patents
Advertisement accurate delivery method based on vehicle information identification Download PDFInfo
- Publication number
- CN114764730A CN114764730A CN202111648300.7A CN202111648300A CN114764730A CN 114764730 A CN114764730 A CN 114764730A CN 202111648300 A CN202111648300 A CN 202111648300A CN 114764730 A CN114764730 A CN 114764730A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- playing
- advertisement
- data
- camera
- 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
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
- G06Q30/0265—Vehicular advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an advertisement accurate delivery method based on vehicle information identification, which comprises the following steps: when the vehicle passes through the shooting area of the camera, the camera carries out front-end recognition to recognize vehicle information, which specifically comprises but not limited to information such as the number plate, the type of the vehicle, the color, the brand model, the value, the personalized characteristics of the vehicle, the behavior of a driver and the like; the camera transmits the identified information to the control communication mainboard, the control communication mainboard interacts with the cloud, and advertisements most suitable for the user are matched through a data matching algorithm; after the cloud end inquires the playing requirement, a playing instruction is issued to the control communication mainboard; after the communication mainboard is controlled to obtain a playing instruction, the playing instruction is played by a display terminal; after the playing is finished, the camera is continuously in a standby state to wait for the vehicle to enter the shooting area again. The invention improves the accuracy of advertisement playing, different advertisements represent different commodities and are suitable for different crowds, and the scheme aims to realize that the advertisements are played before specific crowds and relatively accurate playing of offline advertisements is realized.
Description
Technical Field
The invention relates to the technical field of advertisement putting, in particular to an advertisement accurate putting method based on vehicle information identification.
Background
The current outdoor advertisement playing equipment aiming at vehicles is mainly characterized in that a static plane picture or a lamp box is used as a display mode, such as a bus, outdoor large-amplitude advertisement pictures or outdoor large screens are played in a carousel mode, playing is performed in a rolling mode every day after the playing sequence is arranged, playing contents are different according to different time selected by an advertiser, the playing mode aims at different vehicle individuals, the same contents are played or played in a carousel mode, the playing effect cannot be guaranteed, determined contents cannot be played aiming at proper vehicles, after the playing is finished, effect data cannot be given, the playing mode causes resource waste, the effect and the influence of advertisements are reduced, and the influence of an advertisement system on the vehicles outdoors is reduced.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an advertisement accurate delivery method based on vehicle information identification, which utilizes an intelligent algorithm to accurately identify a vehicle, improves the accuracy of advertisement playing, and different advertisements represent different commodities and are suitable for different crowds.
In order to achieve the purpose, the invention provides the following technical scheme: the method for accurately putting the advertisement based on the vehicle information identification is provided, and comprises the following steps:
(1) when the vehicle passes through the shooting area of the camera, the camera carries out front-end recognition to recognize vehicle information such as the number plate, the number plate type, the vehicle type, the color, the brand model, the value, the vehicle personalized feature, the behavior of a driver and the like of the vehicle; the gender of the owner, whether a person is in business or not and the like can be judged according to the color of the vehicle, the vehicle value and the consumption tendency of the owner can be distinguished according to the type of the vehicle, if the SUV is hard to be dispatched to represent that the owner likes off-road, advertisements around the off-road can be pushed; the user label can be oriented by identifying the big data of the owner selected for the brand through the brand examination of the vehicle; in addition, the regional characteristics of the vehicle owner can be identified through the number plate number and the number plate type to carry out targeted advertisement pushing, and whether the vehicle is facing the advertising board or not is judged through identifying the vehicle direction, so that wrong advertisement information pushing is reduced;
(2) the camera transmits the identified information to the control communication mainboard, the control communication mainboard interacts with the cloud end, and advertisements which best meet the user are matched through a data matching algorithm;
(3) After the cloud end inquires the playing requirement, a playing instruction is issued to the control communication mainboard;
(4) after the communication mainboard is controlled to obtain a playing instruction, whether playing content is downloaded or not is inquired; if the download is finished, the display end directly plays the downloaded data, and if the download is not finished, the display end plays the downloaded data;
(5) synchronously detecting passing vehicles during playing, and recording by the control communication mainboard; the vehicle is played by the display terminal when passing next time;
(6) after the playing is finished, the camera is continuously in a standby state to wait for the vehicle to enter the shooting area again.
According to the further limited technical scheme, in the advertisement accurate delivery method based on vehicle information identification, the camera carries out front-end identification on a vehicle detection and tracking algorithm based on the direction gradient histogram and the support vector machine.
In the advertisement accurate delivery method based on vehicle information identification, the camera performing front-end identification includes the following steps:
(1) extracting HOG characteristics from the labeled training set;
(2) training a classifier in a data set with or without a vehicle in the image;
(3) performing window sliding under each frame of video image to obtain a subregion of the image;
(4) Applying the trained classifier in each sub-region;
(5) and creating a heat point diagram, and carrying out vehicle detection and tracking frame by frame.
In the accurate advertisement delivery method based on vehicle information identification, the Sunday algorithm is adopted as the data matching algorithm, the characteristics of the users are not required to be compared in a positive sequence or a negative sequence in the matching process, and when mismatching is found, the algorithm can skip as many characteristics as possible to perform matching in the next step, so that the matching efficiency is improved; and matching the advertisement which is most suitable for the user by the user with most feature labels in a short time.
Further, in the accurate advertisement putting method based on vehicle information identification, the playing instruction is used for storing static data by an HDFS, the calculation logic is distributed to each data node for data calculation based on a MapReduce programming paradigm, two types of nodes including a main node and a working node exist in a cluster, the main node divides input data, divides an original problem into a plurality of similar sub-problems, then sends the divided data and tasks to the working node for calculation, enables a user to see the advertisement playing audience condition in real time, and analyzes and provides each advertisement in long-time playing.
The invention has the beneficial effects that: the advertisement playing of the invention is remotely controlled by the cloud server and the control communication mainboard, and the functions of playing, changing the magazines, turning on and off the machine and detecting the error of hardware can be issued by one key at the port in the software background, thereby saving the manual changing of the magazines and the time cost. In same magazine position, can appear many advertisements and wait to broadcast, the car owner through the advertisement position also has different advertisement preferences simultaneously, so broadcast the advertisement for the people that corresponds the label, will improve the infiltration and the benefit output ratio of advertisement brand power. The specific operation steps are as follows: the traffic flow passes through the identification module, and the graphic data of the vehicle is processed into label data by the control communication mainboard and uploaded to the cloud, and the label data is matched with the advertisement label and then output to play a decision, and finally the corresponding advertisement is put on the curtain. The outdoor manual examination and verification mode of traditional advertisement guarantees the correctness of the publication, however, the real picture of the advertisement in the garage scene is shot in real time through the monitoring and broadcasting module and uploaded to the cloud server, the shot picture can be checked in real time, and the broadcasting effect is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and the embodiments in the drawings do not constitute any limitation to the present invention, and for those skilled in the art, other drawings may be obtained based on these drawings without creative efforts.
FIG. 1 is a diagram of hardware connections according to an embodiment of the present invention.
FIG. 2 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the accompanying drawings and embodiments, which are preferred embodiments of the present invention. It is to be understood that the described embodiments are merely a subset of the embodiments of the invention, and not all embodiments; it should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The main idea of the technical scheme of the embodiment of the invention is as follows: the problem of idle broadcasting of the advertisements is solved, and the advertisements are still played under the condition that no vehicle exists, so that the waste of advertisement resources is caused. The accuracy of advertisement broadcast is improved, different advertisements represent different commodities, adapt to different crowds, and what this scheme need solve lets the advertisement broadcast before specific crowd, accomplishes the relatively accurate broadcast of off-line advertisement. And relatively accurate data of advertisement playing is provided, and the playing effect of the advertisement can be presented through the system in real time.
In order to better understand the technical scheme, the technical scheme is described in detail in the following with reference to the attached drawings and specific embodiments.
The embodiment provides an advertisement accurate delivery method based on vehicle information identification, which comprises the following steps:
(1) when the vehicle passes through the shooting area of the camera, the camera carries out front-end recognition to recognize information of the vehicle, wherein the information specifically comprises but is not limited to vehicle information such as a number plate, a number plate type, a vehicle type, a color, a brand model, a value, vehicle personalized characteristics, behavior of a driver and the like of the vehicle; the vehicle information specifically includes, but is not limited to, the color of the number plate (black, white, yellow, blue, green, yellow-green, gradient color), the type of the number plate (27 kinds of vehicles such as a large car, a small car, an embassy car, a pilothouse car, an offsite car, a general motorcycle, a scooter, an embassy motorcycle, a pilothouse motorcycle, a overseas motorcycle, an outsid motorcycle, a low-speed vehicle, a tractor number plate, a trailer, a coach car, a coach motorcycle, a temporary entry vehicle, a temporary traveling vehicle, a police car, a harbor/Australian entry vehicle, a military number plate, a armed police number plate, a large new energy vehicle, a small new energy vehicle, etc.), the type of the vehicle (a large bus, a medium bus, a small bus, a mini truck, a heavy and medium truck, a light type, a tricycle, a motorcycle, a trailer, an electric bicycle, etc.), the type of the vehicle (a large bus, a medium bus, a small bus, a mini-sized truck, a heavy and medium-sized truck, Car, SUV, MPV, minibus, van, tank truck, barrier truck, flatbed truck, storage van, common truck, etc.) color (black and white back to yellow, green, blue, purple, pink, brown 10 kinds), brand model (20000 kinds), value, vehicle individuation characteristics (9 kinds such as window stickers, ornaments, hangers, luggage rack, vehicle body scratch, vehicle body colored drawing, etc.), and vehicle information such as driver behavior (passenger face, main driver call-in, main driver cell phone, main driver safety belt fastening, main driver smoke exhaust, main driver sun visor laying down, auxiliary driver safety belt not fastening, auxiliary driver sun visor laying down, motorcycle driver and passenger do not wear helmet);
The gender of the owner, whether business people exist or not can be judged through the color of the vehicle, the grade of the vehicle and the consumption tendency of the owner can be distinguished through the type of the vehicle, if the SUV is assigned hard to represent that the owner likes off-road, and the related off-road surrounding advertisements can be pushed; the user tag can be oriented by identifying the big data of the owner for the brand selection through the vehicle brand examination; in addition, the regional characteristics of the vehicle owner can be identified through the number plate number and the number plate type to carry out targeted advertisement pushing, and whether the vehicle is over against the advertising board or not is judged through identifying the vehicle direction, so that wrong advertisement information pushing is reduced;
(2) the camera transmits the identified information to the control communication mainboard, the control communication mainboard interacts with the cloud end, and advertisements most suitable for the user are matched through a data matching algorithm;
(3) after the cloud end inquires the playing requirement, a playing instruction is issued to the control communication mainboard;
(4) after the communication mainboard is controlled to obtain a playing instruction, whether the playing content is downloaded or not is inquired; if the download is finished, the display end directly plays the downloaded data, and if the download is not finished, the display end plays the downloaded data;
(5) synchronously detecting passing vehicles during playing, and recording by the control communication mainboard; the vehicle is played by the display terminal when passing next time;
(6) After the playing is finished, the camera is continuously in a standby state to wait for the vehicle to enter the shooting area again.
The camera of the embodiment performs front-end recognition based on a direction gradient histogram and a vehicle detection and tracking algorithm of a support vector machine. The camera carries out front end identification and comprises the following steps:
(1) extracting HOG characteristics from the labeled training set;
(2) training a classifier in a data set with or without a vehicle in the image;
(3) performing window sliding under each frame of video image to obtain a sub-area of the image;
(4) applying the trained classifier in each sub-region;
(5) and creating a heat point diagram, and carrying out vehicle detection and tracking frame by frame.
The client side obtains image information of a vehicle in front of the current equipment in real time through the shooting equipment, processes the image information through an algorithm, identifies the vehicle information according to the algorithm and sends an advertisement pushing request, and the server pushes the advertisement according to the vehicle characteristic information after receiving the pushing request. The method comprises the steps that a recognition camera is arranged in front of a projector by an effective distance, when a vehicle head enters an effective shooting range of the recognition camera, a controller sends a signal to the projector to start the projector to enter a to-be-played mode, when a camera head algorithm recognizes information such as vehicle model, license plate information, vehicle traveling direction and vehicle color, cloud service is requested, the cloud service calculates vehicle characteristic information according to the vehicle information uploaded by a client, the vehicle characteristic information is transmitted to an advertisement recommendation system to generate an advertisement playing list aiming at the vehicle characteristic information, and finally the advertisement playing list is returned to the client to be played, and the recommended advertisement is played by the projector.
The client can calculate the traffic information of the current point position in real time through a camera head end traffic flow detection algorithm, automatically start different types of advertisement playing modes according to the traffic flow, trigger an advertisement carousel playing mode in a traffic flow peak time period, and trigger an advertisement triggering mode aiming at the vehicle type, the vehicle grade or the license plate in a traffic flow valley period; in addition, the traffic flow of each time period of each point of each advertisement playing can be predicted through a large-scale time sequence prediction algorithm, so that a corresponding advertisement playing mode is started. The method comprises the steps that a vehicle flow statistical algorithm based on a vehicle tracking technology at a camera head end is used for collecting vehicle flow de-weight information of each point location in each time period, information such as the geographic position, surrounding business circles, consumption level, current weather conditions, current date and whether the point location is a holiday is obtained, a prediction algorithm model is trained, a server end obtains characteristic information of the prediction algorithm according to the current time period, the current date, point location information and the weather conditions, current traffic flow information of the point location is calculated through the prediction model, and therefore an advertisement playing mode is determined.
In addition, the client pushes the acquired vehicle flow information and the advertisement playing result information to the cloud service terminal in real time, and the service terminal analyzes data in real time and provides a multi-dimensional advertisement playing effect report. Specifically, the client associates the advertisement playing result with the traffic flow and the information such as the vehicle type, the license plate and the color of the audience vehicle currently detected/identified by the camera algorithm, and uploads the information to the cloud service, and the cloud service performs statistical analysis on the playing record to provide an advertisement playing effect report according to different dimensions.
The vehicle information identification algorithm of the embodiment is implemented by a Yolo v3 algorithm, and a Yolo series algorithm integrates target positioning and classification, and belongs to an end-to-end mode, and a One-Stage algorithm performs One-time detection and uniformly outputs all required results:
1. preparation of training set
The training set is trained under the scene of the user at present, the self-developed general positioning algorithm is adopted for processing, most data can be successfully positioned under the method, and pictures which are not successfully positioned are mainly corrected in a manual mode.
2. Network framework of recognition algorithm
In the whole process, the image is predicted through 3 different stages, namely, prediction one, prediction two and prediction three, the prediction groups of the number of Anchor can be predicted for each element in the feature map in the three stages, and each prediction group comprises a group of prediction data, including information such as the position of a vehicle, the brand classification of the vehicle, the color of the vehicle, the orientation of the vehicle and the like.
3. Calculation of a loss function
In the calculation process of the loss function, the target positioning offset loss, the target confidence loss and the target classification loss are involved, wherein the weight parameter of each part and the total loss are also included:
L(O，o，C，c，l，g)＝λ1Lconf(o，c)+λ2Lcla(O，C)+λ3Lloc(l，g)
The loss function includes three aspects of loss:
lconf shows the confidence loss, the current frame selection is the loss of the real target, and the front is the corresponding weight coefficient;
lcla indicates classification loss, indicates the loss of the current frame selection classification, and is preceded by a corresponding weight coefficient;
lloc indicates a loss of position, indicating a loss between the current box and the corresponding real target, preceded by the corresponding weighting factor.
3.1 target confidence Classification loss
The target classification loss currently adopts cross entropy loss:
lconf represents confidence loss, wherein cross entropy is adopted, oi represents a tag value, the same 1-oi represents another tag value, ci represents a predicted value, a probability value ci is generated after a Sigmod function, and the confidence loss is calculated mainly in a cross entropy mode;
3.2 loss of target location
Lloc (l, g) represents the overall target positioning loss, li ^ m represents the position information predicted by the ith positive sample, gi ^ m represents the real position information corresponding to the ith positive sample, the position information comprises x, y, w, h and other related information, the loss is calculated in a square difference mode, the loss of each positive sample is accumulated to obtain an overall loss value, but in the calculation process, the loss is not directly calculated in an x, y, w and h mode, but is solved by calculating the relation between the coordinate of the center point of the rectangle and the width and height of the rectangle and Anchor, and then is calculated in a log value mode just as the calculation mode of the corresponding real value represented by the li ^ x, li ^ w, li ^ y, lih and g.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units 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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention 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, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the same element.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. The advertisement accurate delivery method based on vehicle information identification is characterized by comprising the following steps:
(1) when the vehicle passes through a camera shooting area, the camera carries out front-end identification, and identification objects include but are not limited to a number plate, a number plate type, a vehicle type, a color, a brand model, a value, vehicle personalized characteristics and driver behavior vehicle information of the vehicle;
(2) the camera transmits the identified information to the control communication mainboard, the control communication mainboard interacts with the cloud, and advertisements most suitable for the user are matched through a data matching algorithm;
(3) after the cloud end inquires the playing requirement, a playing instruction is issued to the control communication mainboard;
(4) After the communication mainboard is controlled to obtain a playing instruction, whether playing content is downloaded or not is inquired; if the download is finished, the display end directly plays the downloaded data, and if the download is not finished, the display end plays the downloaded data;
(5) synchronously detecting vehicles passing through during playing, and recording by the control communication mainboard; the vehicle is played by the display terminal when passing next time;
(6) after the playing is finished, the camera is continuously in a standby state to wait for the vehicle to enter the shooting area again.
2. The advertisement accurate delivery method based on vehicle information identification according to claim 1, characterized in that: the camera carries out front-end recognition and vehicle detection and tracking algorithm based on the direction gradient histogram and the support vector machine.
3. The method for accurately delivering the advertisement based on the vehicle information identification as claimed in claim 2, wherein: the camera carries out front end identification and comprises the following steps:
(1) extracting HOG characteristics from the labeled training set;
(2) training a classifier in a data set with or without a vehicle in the image;
(3) performing window sliding under each frame of video image to obtain a sub-area of the image;
(4) applying the trained classifier in each sub-area;
(5) And creating a heat point diagram, and carrying out vehicle detection and tracking frame by frame.
4. The method for accurately delivering the advertisement based on the vehicle information identification as claimed in claim 1, wherein: the data matching algorithm adopts a Sunday algorithm, the characteristics of the users are not required to be compared in a positive sequence or a negative sequence in the matching process, and when mismatching is found, the algorithm can skip as many characteristics as possible to carry out the next matching, so that the matching efficiency is improved; and matching the advertisements which best meet the user by the user with most feature tags in a short time.
5. The method for accurately delivering the advertisement based on the vehicle information identification as claimed in claim 1, wherein: the HDFS is used for storing static data, computing logic is distributed to each data node for data computing based on a MapReduce programming paradigm, two types of nodes including a main node and a working node exist in a cluster, the main node divides input data, divides an original problem into a plurality of similar sub-problems, then sends the divided data and tasks to the working node for computing, enables a user to see the advertisement playing audience condition in real time, and analyzes and provides each advertisement in long-time playing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111648300.7A CN114764730A (en) | 2021-12-29 | 2021-12-29 | Advertisement accurate delivery method based on vehicle information identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111648300.7A CN114764730A (en) | 2021-12-29 | 2021-12-29 | Advertisement accurate delivery method based on vehicle information identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114764730A true CN114764730A (en) | 2022-07-19 |
Family
ID=82365029
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111648300.7A Pending CN114764730A (en) | 2021-12-29 | 2021-12-29 | Advertisement accurate delivery method based on vehicle information identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114764730A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100450A (en) * | 2022-08-26 | 2022-09-23 | 北京海上升科技有限公司 | Intelligent traffic brand automobile big data detection method and system based on artificial intelligence |
| CN116091138A (en) * | 2023-04-03 | 2023-05-09 | 北京永泰万德信息工程技术有限公司 | Advertisement putting method, system, medium and equipment based on vehicle information identification |
-
2021
- 2021-12-29 CN CN202111648300.7A patent/CN114764730A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100450A (en) * | 2022-08-26 | 2022-09-23 | 北京海上升科技有限公司 | Intelligent traffic brand automobile big data detection method and system based on artificial intelligence |
| CN115100450B (en) * | 2022-08-26 | 2023-01-06 | 中咨数据有限公司 | Intelligent traffic brand automobile big data detection method and system based on artificial intelligence |
| CN116091138A (en) * | 2023-04-03 | 2023-05-09 | 北京永泰万德信息工程技术有限公司 | Advertisement putting method, system, medium and equipment based on vehicle information identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108388888B (en) | Vehicle identification method and device and storage medium | |
| Wang et al. | Traffic light recognition with high dynamic range imaging and deep learning | |
| WO2017080341A1 (en) | Smart parking control method and system integrating toll collection and advertisement pushing | |
| CN114764730A (en) | Advertisement accurate delivery method based on vehicle information identification | |
| CN106384532A (en) | Video data analysis method and apparatus thereof, and parking space monitoring system | |
| CN109993138A (en) | A kind of car plate detection and recognition methods and device | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN103365848A (en) | Method, device and system for inquiring videos | |
| CN114418895A (en) | Driving assistance method and device, vehicle-mounted device and storage medium | |
| WO2019144416A1 (en) | Information processing method and system, cloud processing device and computer program product | |
| CN103577412A (en) | High-definition video based traffic incident frame tagging method and system | |
| CN109657599B (en) | Picture identification method of distance-adaptive vehicle appearance part | |
| CN112434566A (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| CN111723705A (en) | Raspberry pie-based van transportation management control method | |
| CN115424217A (en) | AI vision-based intelligent vehicle identification method and device and electronic equipment | |
| CN112289037B (en) | Motor vehicle illegal parking detection method and system based on high visual angle under complex environment | |
| CN109325755A (en) | Electronics charge system based on automotive hub | |
| CN113486885A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN112818826A (en) | Target identification method and device, electronic equipment and storage medium | |
| WO2023246720A1 (en) | Roadside parking detection method, roadside parking system, and electronic device | |
| CN103761345A (en) | Video retrieval method based on OCR character recognition technology | |
| CN113158852B (en) | Traffic gate monitoring system based on face and non-motor vehicle cooperative identification | |
| CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
| CN113593256B (en) | Unmanned aerial vehicle intelligent driving-away control method and system based on city management and cloud platform | |
| CN112668411B (en) | SGAN-based video stream marking method, SGAN-based video stream marking device, SGAN-based video stream marking system and 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 |