CN116757745A - Advertisement data directional pushing system and method based on Internet - Google Patents
Advertisement data directional pushing system and method based on Internet Download PDFInfo
- Publication number
- CN116757745A CN116757745A CN202311062640.0A CN202311062640A CN116757745A CN 116757745 A CN116757745 A CN 116757745A CN 202311062640 A CN202311062640 A CN 202311062640A CN 116757745 A CN116757745 A CN 116757745A
- Authority
- CN
- China
- Prior art keywords
- user
- advertisement
- vehicle
- target vehicle
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 239000013598 vector Substances 0.000 claims description 55
- 238000004458 analytical method Methods 0.000 claims description 39
- 238000005516 engineering process Methods 0.000 claims description 29
- 238000012544 monitoring process Methods 0.000 claims description 26
- 210000000323 shoulder joint Anatomy 0.000 claims description 26
- 210000005252 bulbus oculi Anatomy 0.000 claims description 24
- 210000000744 eyelid Anatomy 0.000 claims description 24
- 238000013523 data management Methods 0.000 claims description 18
- 210000001508 eye Anatomy 0.000 claims description 15
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 9
- 210000001738 temporomandibular joint Anatomy 0.000 claims description 9
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000001815 facial effect Effects 0.000 claims description 3
- 230000008685 targeting Effects 0.000 claims 1
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008921 facial expression Effects 0.000 description 2
- 230000005057 finger movement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06Q30/0277—Online advertisement
-
- 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
- G06Q30/0266—Vehicular advertisement based on the position of the vehicle
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
- H04L67/306—User profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an advertisement data directional pushing system and method based on the Internet, which belong to the field of advertisement pushing. The invention collects images through the safety cameras in the vehicle, judges the riding state of the user, analyzes the influence of other vehicles on the target vehicle by combining with the urban electronic map, determines the advertisement information focused by the user, analyzes the advertisement type focused by the user, and carries out complete directional pushing on the user through the Internet.
Description
Technical Field
The invention relates to the field of advertisement pushing, in particular to an advertisement data directional pushing system and method based on the Internet.
Background
Advertising is a propaganda means for publicly and widely delivering information to the public through a certain traveling medium and consuming a certain fee for a certain specific need. The internet, also known as the internet or transliterated internet, is a vast network of networks connected in series with each other by a set of common protocols to form a logically single vast international network. Various forms of advertisements are released through the Internet platform, the advertisement can be accurately released aiming at specific audiences, and the advertisement platform has the characteristics of wide coverage, real-time updating and strong interactivity, and can more effectively transmit information, guide consumption, shape brand images and promote sales. Meanwhile, the internet advertisement has the characteristics of being capable of being monitored, tracked and analyzed, and an advertiser can better know the advertisement effect and user feedback, so that adjustment and optimization are performed.
However, in the running process of the user, the advertisement of the user outside the observed vehicle often appears, but the user has already run when not seen, the user turns back again to watch the advertisement, so that the travel progress is very influenced, and the watching experience of the user is influenced when the user does not see the advertisement of interest; meanwhile, advertisement content pushed in a vehicle is difficult for a user to ensure that the user is interested in, and invalid pushing exists.
Therefore, how to ensure that the user can watch the observed advertisements completely in the driving process, and how to push the advertisements of interest to the user is necessary after the user is interested in the advertisements which are not watched completely. Therefore, there is a need for an internet-based advertisement data targeted pushing system and method.
Disclosure of Invention
The invention aims to provide an advertisement data directional pushing system and method based on the Internet, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an advertisement data directional pushing method based on the Internet comprises the following steps:
s1, acquiring an urban electronic map, pre-inputting urban advertisement positions, and numbering the urban advertisement positions;
s2, when the vehicle is in a working state, acquiring the running position of the vehicle in real time, monitoring the behavior of a user in the vehicle, analyzing the riding state of the user, and analyzing the influence of other vehicles on the road on the target vehicle by combining with the urban electronic map;
s3, according to the vehicle influence conditions analyzed in the step S2, when the user is in an observation state, analyzing target advertisement information focused by the user, recording focused advertisement contents of the user at different moments in the driving process, and analyzing focused advertisement content types of the user;
And S4, carrying out directional pushing on the user through the display equipment in the vehicle according to the advertisement content information analyzed in the step S3, and carrying out advertisement pushing on the user through the payment display interface when the user is in the payment interface.
In the running process, the urban advertisement is linked with the in-vehicle push advertisement; when the journey is finished, linking the in-vehicle push advertisement with the push advertisement of the mobile terminal of the user; the Internet is utilized to form three-in-vehicle pushing advertisement-mobile pushing advertisement three-in-one integrated linkage pushing, advertisement data is pushed directionally to users, users can watch interested advertisements completely, and advertising efficiency is improved.
Further, in step S1, the electronic map of the city is consistent with the map used for vehicle navigation, and a rectangular planar coordinate system is constructed, and the coordinate system is preset by a related technician, so that the position and the relation of each point in the city can be accurately described, the space information of the city can be more accurately reflected, and the i-th advertisement position in the city is recorded as (xi, yi).
Further, in step S2, the following steps are included:
s201, when a user enters a target vehicle and starts the vehicle, judging that the target vehicle is in a working state, presetting a time interval as t, presetting the time interval by a related technician, and acquiring the running positions of the target vehicle in real time through positioning equipment to form a set a= { (a 1, b 1), (a 2, b 2),., (am, bm) }, wherein m is the number of acquired target vehicle positions, and (am, bm) is the m-th acquired target vehicle position coordinate;
S202, starting a safety camera in a target vehicle, acquiring a user image in the target vehicle, constructing a three-dimensional coordinate system in the vehicle, presetting the coordinate system by a related technician, determining a position point coordinate by utilizing an image ranging technology, wherein the image ranging technology is a technology for obtaining a depth value by searching the same characteristic points in two images by utilizing an image processing technology, and the image ranging technology is a technology for obtaining object distance information by utilizing a camera and an image processing technology, and the principle of the technology is that the distance is calculated based on the focal length of the camera and the size of an object in the images; acquiring two shoulder joint position points of a user in a target vehicle in real time through an openpost technology, wherein the midpoint position coordinates of the two shoulder joint position point connecting lines form a set P= { (P1, q1, r 1), (P2, q2, r 2), (pm, qm, rm) }, wherein (pm, qm, rm) is expressed as the midpoint position coordinates of the mth shoulder joint position point connecting line, the openpost is a human body gesture recognition item, the openpost is a bottom-up algorithm, gesture estimation of human body actions, facial expressions, finger movements and the like can be realized, all joint points of a human body in an image can be detected, and the detected joint points are distributed to each corresponding person; by the image contour extraction technique, which is an image processing technique, features of an object are extracted by analyzing edges and contours in an image. The outline information of the object can be extracted by detecting the edge of the object in the image, so that the shape and the size of the object can be described. The method is commonly used in the fields of image recognition, target tracking, robot vision and the like; obtaining facial image information of a user, obtaining nasal tip position points of the user, and forming a set U= { (U1, v1, w 1), (U2, v2, w 2), (um, vm, wm) }, wherein (um, vm, wm) is expressed as m-th nasal tip position point coordinates of the user, and then the user shoulder joint position points and the nasal tip position points form a vector set PU= { PU1, PU2, & gt, PUm }, wherein PUm is expressed as a vector formed by a midpoint position of a connecting line of the user shoulder joint position points and the nasal tip position points at m-th target vehicle position, PUm = (um-pm, vm-qm, wm-rm); the position coordinates of the safety camera in the target vehicle are input in advance as (x, y, z);
At the j-th acquired target vehicle position, j e [1, m ], the midpoint position of the user shoulder joint position point connecting line and the nose tip position point form a vector puj= (uj-pj, vj-qj, wj-rj), the midpoint position of the user shoulder joint position point connecting line and the safety camera position form a vector PZj = (x-pj, y-qj, z-rj), and the attention angle alpha of the user is calculated by the following formula:
α=arccos （PUj·PZj）/（|PUj||PZj|）；
where i PUj is represented as a modulus of vector PUj and PZj is represented as a modulus of vector PZj;
s203, the window reference point position coordinates closest to the seat in the target vehicle are recorded in advance, the window reference point positions are preset by related technicians, and when a user is seated, the window reference point position coordinates (e c ，f c ，g c ) The midpoint position of the user shoulder joint position point connecting line and the window reference point position form a vector pe= (e) c -pj，f c -qj，g c Rj), then reference angle α=arccoss (Pe PZj)/(Pe PZj);
when alpha is less than alpha, the advertisement in the vehicle is normally pushed, and the normal pushing of the advertisement in the vehicle refers to the existing pushing mode of the advertisement in the vehicle;
when alpha is more than or equal to alpha, measuring the eye distance of a user through an image ranging technology, determining the two-dimensional key point position of the eye through an OpenPose technology, wherein an inner canthus is a key point H1, an intersection point which is close to the inner canthus in two intersection points of an eyeball and an upper eyelid is a key point H2, an intersection point which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid is a key point H3, an outer canthus is a key point H4, an intersection point which is far from the inner canthus in two intersection points of the eyeball and a lower eyelid is a key point H5, an intersection point which is close to the inner canthus in two intersection points of the eyeball and the lower eyelid is a key point H6, and calculating the aspect ratio H of the human eyes of passengers through the following formula:
H=（||h2-h6||+||h3-h5||）/2||h1-h4||；
Wherein, the I h2-h 6I represents the distance from an intersection point key point h2 which is close to an inner canthus in two intersection points of an eyeball and an upper eyelid to an intersection point key point h6 which is close to the inner canthus in two intersection points of the eyeball and a lower eyelid, the I h3-h 5I represents the distance from an intersection point key point h3 which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid to an intersection point key point h5 which is far from the inner canthus in two intersection points of the eyeball and the lower eyelid, and the I h1-h 4I represents the distance from the inner canthus key point h1 to an outer canthus key point h 4;
when h=0, indicating that the user's eyes are closed, the actual duration is monitored as t Real world Setting the duration threshold to t Threshold value When t Real world ＞t Threshold value When the user is in a closed eye rest state, stopping advertisement pushing; when H is not equal to 0, the user is in observation state, and the monitoring duration is t Holding device Setting the duration threshold to t' Threshold value When t Holding device ＞t’ Threshold value When the user is in the observation state, the process proceeds to step S204;
s204, acquiring a user sitting position through a safety camera in the vehicle, performing image monitoring on other vehicles on the road, marking the vehicle speed of the kth vehicle on the road as vk, marking the distance between the kth vehicle on the road and the target vehicle as dk, and marking the vehicle height as Lk; the preset influence radius is R, and the influence radius is preset by related technicians, so that the influence range is as follows: (x-aj) 2 +（y-bj） 2 =R 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein (aj, bj) is represented as the j-th acquired target vehicle position coordinates, and x and y are represented as variables; according to the sitting position of the user and the advancing direction of the vehicle, the influence range is selected, the selection mode is preset by related technicians, the time Tk of the rest vehicle positions of the road in the influence range is monitored, and the threshold value is set as T Threshold value When Tk is less than T Threshold value When Tk is more than or equal to T, the method has no influence on the target vehicle Threshold value When the following formula is used, the influence on the vehicle is achievedThe index β is calculated:
β=（Lk） 2 （Tk）/（dk+e vk ）；
wherein e is expressed as natural logarithm; setting the threshold value to be beta Threshold value When beta > beta Threshold value When the influence of the kth vehicle on the target vehicle is large, and the sight of the user is blocked, the advertisement in the vehicle is normally pushed; when beta > beta Threshold value When the influence of the kth vehicle on the target vehicle is small, the step S3 is entered;
calculating the vehicle influence indexes of all other vehicles on the road which can be shot by the safety cameras in the target vehicle;
s205, repeating the steps S201-S204 for the target vehicle position acquired in real time, and acquiring the real-time state of the user and the vehicle influence index of the user in the observation state.
Further, in step S3, the following steps are included:
S301, when the user is in an observation state, the driving positions of the target vehicles form a set a ' = { (a 1', b1 '), (a 2', b2 '), (aγ, bγ) }, where γ represents the number of collected target vehicle positions when the user is in the observation state, γe [1, m ], (aγ, bγ) represents the γ target vehicle positions collected when the user is in the observation state, and at the same time, the time corresponding to the collected driving positions is obtained;
s302, for the lambda-th collected target vehicle position, lambda E [1, gamma ]]The midpoint position coordinate of the connecting line of the temporomandibular joint position points of the user is M (p * λ，q * λ，r * Lambda), the coordinates of the nose tip position point are N (ulambda, vlambda, wlambda) to form a vector P * Uλ=（uλ-p * λ，vλ-q * λ，wλ-r * λ），
For the lambda+1th acquired target vehicle position, the midpoint position coordinate of the user temporomandibular joint position point line is M' (p) * （λ+1），q * （λ+1），r * (lambda+1)), the nose tip position point coordinates are N' (u (lambda+1), v (lambda+1), w (lambda+1)), forming vector P * U（λ+1）=（u（λ+1）-p * （λ+1），v（λ+1）-q * （λ+1），w（λ+1）-r * (lambda+1)); the specific indication positions of the shoulder joint position points and the temporomandibular joint position points are preset by relevant technicians;
s303, calculating the coordinate of the focus intersection point delta of the user through the following formula:
δ=M+[|（M’-M）×P * U（λ+1）|/|P * Uλ×P * U（λ+1）|]P * Uλ；
Wherein x is expressed as a vector cross symbol, | (M' -M) ×p * U (lambda+1) | is expressed as a vector and a vector P formed between points M and M * U (lambda+1) is subjected to a vector cross multiplication operation, and P is the modulus * Uλ×P * U (λ+1) | is denoted as vector P * U lambda and vector P * U (lambda+1) is subjected to a module after vector cross multiplication operation;
the method comprises the steps of calculating focus intersection points of all vehicle driving positions of targets acquired by a user in an observation state, and determining advertisement positions focused by the user through cluster analysis, wherein the cluster analysis refers to an analysis process of grouping a set of data objects into a plurality of classes consisting of similar objects, is a technology for searching an internal structure among data, and organizes all data instances into a plurality of similar groups, and the similar groups are called clusters. Data instances in the same cluster are identical to each other, and instances in different clusters are different from each other; acquiring the time of the last driving position acquired when the user is in an observation state, calling the advertisement content played by the time of the last driving position of the determined advertisement position through the Internet, and continuously playing the called advertisement content to the user through display equipment in the vehicle;
s304, marking advertisement types, and counting advertisement types focused by a user in the driving process to obtain a group of sets Q= { (eta) 1 ，μ 1 ），（η 2 ，μ 2 ），...，（η o ，μ o ) O is represented as the number of advertisement types of interest to the user, η o Expressed as the o-th advertisement type, (eta) o ，μ o ) Represented as advertisement type eta o Advertising of mu o Next, the user's preference G for the type of advertisement of the τ th type is calculated by the following formula τ And (3) performing calculation:
G τ =μ τ /∑oξ=1μ ξ ；
wherein τ.epsilon.1, o]，μ τ Denoted as user attention advertisement type eta τ Advertisement quantity of (3);
calculating the preference degree of all advertisement types concerned by the user, sorting according to the size, summarizing the advertisement type concerned by the user, and when the advertisement in the vehicle is normally pushed, namely the user is not in an observation state or is influenced by other vehicles on the road to a large extent, calling the advertisement consistent with the advertisement type with the highest preference degree of the user to carry out directional pushing.
Further, in step S4, advertisement data is pushed directionally to the user through the display device in the vehicle, more interesting advertisement content is provided for the user, accurate pushing of advertisement content is achieved, invalid pushing of advertisements is reduced, user experience is improved, pushing of a large number of advertisement content which is not interesting to the user is avoided, the user is guaranteed to observe the whole watching of the interesting advertisement content in the vehicle during driving, user experience is improved, when the user is in a journey end state, the user is pushed completely to the advertisement in the vehicle through the mobile phone, the user is facilitated to watch the advertisement completely, the situation that the user cannot see the advertisement completely after the user gets off the vehicle is avoided, and advertisement throwing efficiency is improved.
An internet-based advertisement data targeted pushing system, the advertisement data targeted pushing system comprising: the system comprises a driving monitoring module and an advertisement analysis module;
the output end of the driving monitoring module is connected with the input end of the advertisement analysis module;
the running monitoring module is used for intelligently monitoring advertisement data on the way of traveling of a user and comprises an image acquisition unit, a vehicle positioning unit and a basic input unit, wherein the image acquisition unit is used for acquiring images of data in the running process of the vehicle through a safety camera in the target vehicle, the vehicle positioning unit is used for acquiring the position of the target vehicle in real time through positioning equipment, and the basic input unit is used for inputting urban electronic map data, advertisement position data, operation parameters and the like in advance;
the advertisement analysis module is used for intelligently analyzing advertisement push data in the running process of the user and comprises a state analysis unit and an advertisement determination unit, wherein the state analysis unit is used for analyzing the riding state of the user, analyzing the influence of other vehicles on the target vehicle by combining with the urban electronic map, and the advertisement determination unit is used for analyzing the target advertisement information focused by the user when the user is in an observation state, recording focused advertisement contents of the user at different moments in the running process and analyzing focused advertisement content types of the user.
Further, the advertisement data directional pushing system further comprises: a data management module;
the input end of the data management module is connected with the output end of the driving monitoring module, the output end of the data management module is connected with the input end of the advertisement analysis module, and the output end of the advertisement analysis module is connected with the input end of the data management module;
the data management module is used for carrying out distributed management on collected data and analyzed advertisement data and carrying out data cleaning, and the data management module comprises a safety management unit and a data cleaning unit, wherein the safety management unit is used for carrying out safety storage on the collected data and analysis results through a distributed storage structure, and the distributed storage system is used for storing the data on a plurality of independent devices in a scattered mode. The traditional network storage system adopts a centralized storage server to store all data, and the storage server becomes a bottleneck of system performance, is also a focus of reliability and safety, and cannot meet the requirements of large-scale storage application. The distributed network storage system adopts an expandable system structure, utilizes a plurality of storage servers to share storage load, utilizes the position servers to position storage information, improves the reliability, availability and access efficiency of the system, is easy to expand, and the data cleaning unit is used for automatically deleting data after a user finishes a journey, so that data redundancy is avoided, and the speed and the efficiency of operation and analysis are ensured.
Further, the advertisement data directional pushing system further comprises: a directional pushing module;
the input end of the directional pushing module is connected with the output end of the advertisement analysis module;
the directional pushing module is used for pushing advertisements to users in a directional manner according to analysis results, and comprises a vehicle-mounted pushing unit and a payment pushing unit, wherein the vehicle-mounted pushing unit is used for pushing advertisements of advertisement content and interesting types observed by the users in the driving process according to the analysis results, the vehicle-mounted display equipment is used for pushing advertisements in a directional manner, the use experience of the users is improved, the users are guaranteed to observe the whole watching of the advertisement content of the interests of the vehicles in the driving process, the situation that the users leave without watching the advertisements completely is avoided, the use experience of the users is improved, the advertisement content which is not interesting for pushing a large amount of users is avoided, the payment pushing unit is used for pushing advertisements in the vehicles completely through a mobile phone when the users are in a stroke end state, the users can watch the advertisements completely, the situation that the users cannot see the advertisements completely after the users get off the vehicles is avoided, and the advertising efficiency of the advertisements is improved.
Compared with the prior art, the invention has the following beneficial effects:
the invention collects images through the safety cameras in the vehicle, the image acquisition means is quick and convenient, other camera equipment is not required to be installed, and the influence of other vehicles on the road on the target vehicle is analyzed by analyzing the riding state of a user and combining with the pre-recorded urban electronic map, so as to judge whether the other vehicles shield the target vehicle; when a user is in an observation state and the influence of other vehicles on a road on a target vehicle is small, advertisement information focused by the user is determined through analysis, advertisement content watched by the user is acquired through Internet, the user is completely and directionally pushed through display equipment in a vehicle, the user is guaranteed to watch the advertisement content interested in the vehicle completely, the accurate and directional pushing of the advertisement is realized, when the user is not in the observation state or the influence of other vehicles on the target vehicle is large, namely, the user does not observe the advertisement outside the vehicle or the other vehicles shelter from the target vehicle, the advertisement type focused by the user in the driving process is analyzed, the advertisement type content interested in the user is directionally pushed to the user through Internet, the data are automatically deleted after the user finishes a journey, the data redundancy is avoided, the operation and analysis speed and efficiency are ensured, the user is conveniently and completely pushed through a mobile phone, the user can not completely watch the advertisement after the vehicle is taken off, and the urban advertisement is linked with the advertisement pushed in the driving process; when the journey is finished, linking the in-vehicle push advertisement with the push advertisement of the mobile terminal of the user; the Internet is utilized to form three-in-vehicle pushing advertisement-mobile pushing advertisement three-in-one integrated linkage pushing, advertisement data is pushed directionally to users, users can watch interested advertisements completely, and advertising efficiency is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of steps of an Internet-based advertisement data targeted pushing method of the present invention;
FIG. 2 is a schematic diagram of the module composition of an Internet-based advertisement data targeted pushing system of the present invention;
FIG. 3 is an exemplary illustration of a range of influence selection for a target vehicle in the present invention;
FIG. 4 is a schematic view of a user focus intersection in the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides the technical scheme that: fig. 1 is a flowchart of steps of an advertisement data directional pushing method based on internet, and the invention takes a taxi as an example, and comprises the following steps:
S1, acquiring an urban electronic map, pre-inputting urban advertisement positions, and numbering the urban advertisement positions;
in step S1, the electronic map of the city is consistent with the map used for vehicle navigation, and a rectangular plane coordinate system is constructed, and the coordinate system is preset by a relevant technician, for example, the coordinate system is constructed by taking the city landmark as the origin, or the national coordinate system is used, so that the position and the relation of each point in the city can be accurately described, the space information of the city can be more accurately reflected, the ith advertisement position in the city is marked as (xi, yi), and the advertisement comprises a dynamic advertisement board of a market, a advertisement board of a bus station and the like.
S2, when the vehicle is in a working state, acquiring the running position of the vehicle in real time, monitoring the behavior of a user in the vehicle, analyzing the riding state of the user, and analyzing the influence of other vehicles on the road on the target vehicle by combining with the urban electronic map;
in step S2, the following steps are included:
s201, when a user enters a target vehicle and starts the vehicle, judging that the target vehicle is in a working state, namely, a passenger sits on a taxi, presetting a time interval as t, presetting the time interval by a related technician, and acquiring a running position forming set a= { (a 1, b 1), (a 2, b 2) of the target vehicle in real time through positioning equipment comprising GPS positioning, beidou navigation and the like, wherein m is the number of acquired target vehicle positions, and (am, bm) is the m-th acquired target vehicle position coordinate;
S202, starting a safety camera in a target vehicle, acquiring a user image in the target vehicle, constructing a three-dimensional coordinate system in the vehicle, presetting the coordinate system by a related technician, for example, taking the safety camera as an origin, establishing a coordinate system, determining a position point coordinate by utilizing an image ranging technology, wherein the image ranging technology is a technology for obtaining a depth value by searching the same characteristic points in two images by utilizing an image processing technology, and the image ranging technology is a technology for obtaining object distance information by utilizing a camera and an image processing technology, and the principle of the image ranging technology is that the distance is calculated based on the focal length of the camera and the size of an object in the images; acquiring two shoulder joint position points of a user in a target vehicle in real time through an openpost technology, wherein the midpoint position coordinates of the two shoulder joint position point connecting lines form a set P= { (P1, q1, r 1), (P2, q2, r 2), (pm, qm, rm) }, wherein (pm, qm, rm) is expressed as the midpoint position coordinates of the mth shoulder joint position point connecting line, the openpost is a human body gesture recognition item, the openpost is a bottom-up algorithm, gesture estimation of human body actions, facial expressions, finger movements and the like can be realized, all joint points of a human body in an image can be detected, and the detected joint points are distributed to each corresponding person; by the image contour extraction technique, which is an image processing technique, features of an object are extracted by analyzing edges and contours in an image. The outline information of the object can be extracted by detecting the edge of the object in the image, so that the shape and the size of the object can be described. The method is commonly used in the fields of image recognition, target tracking, robot vision and the like; obtaining facial image information of a user, obtaining nasal tip position points of the user, and forming a set U= { (U1, v1, w 1), (U2, v2, w 2), (um, vm, wm) }, wherein (um, vm, wm) is expressed as m-th nasal tip position point coordinates of the user, and then the user shoulder joint position points and the nasal tip position points form a vector set PU= { PU1, PU2, & gt, PUm }, wherein PUm is expressed as a vector formed by a midpoint position of a connecting line of the user shoulder joint position points and the nasal tip position points at m-th target vehicle position, PUm = (um-pm, vm-qm, wm-rm); the position coordinates of the safety camera in the target vehicle are input in advance as (x, y, z);
At the j-th acquired target vehicle position, j e [1, m ], the midpoint position of the user shoulder joint position point connecting line and the nose tip position point form a vector puj= (uj-pj, vj-qj, wj-rj), the midpoint position of the user shoulder joint position point connecting line and the safety camera position form a vector PZj = (x-pj, y-qj, z-rj), and the attention angle alpha of the user is calculated by the following formula:
α=arccos （PUj·PZj）/（|PUj||PZj|）；
where i PUj is represented as a modulus of vector PUj and PZj is represented as a modulus of vector PZj;
s203, the window reference point position coordinates closest to the seat in the target vehicle are input in advance, the window reference point position is preset by a related technician, for example, the front windshield of the passenger seat takes the upper top angle of the front windshield of the vehicle right in front of the seat as the window reference point position, the seat behind the driver seat takes the upper top angle closest to the seat and closest to the front wheel in the advancing direction as the window reference point position, and after the user is seated, the window reference point position coordinates (e c ，f c ，g c ) The midpoint position of the user shoulder joint position point connecting line and the window reference point position form a vector pe= (e) c -pj，f c -qj，g c Rj), then reference angle α=arccoss (Pe PZj)/(Pe PZj);
When alpha is less than alpha, the advertisement in the vehicle is normally pushed, and the normal pushing of the advertisement in the vehicle refers to the existing pushing mode of the advertisement in the vehicle, such as random pushing of sponsored advertisements and the like;
when alpha is more than or equal to alpha, measuring the eye distance of a user through an image ranging technology, determining the two-dimensional key point position of the eye through an OpenPose technology, wherein an inner canthus is a key point H1, an intersection point which is close to the inner canthus in two intersection points of an eyeball and an upper eyelid is a key point H2, an intersection point which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid is a key point H3, an outer canthus is a key point H4, an intersection point which is far from the inner canthus in two intersection points of the eyeball and a lower eyelid is a key point H5, an intersection point which is close to the inner canthus in two intersection points of the eyeball and the lower eyelid is a key point H6, and calculating the aspect ratio H of the human eyes of passengers through the following formula:
H=（||h2-h6||+||h3-h5||）/2||h1-h4||；
wherein, the I h2-h 6I represents the distance from an intersection point key point h2 which is close to an inner canthus in two intersection points of an eyeball and an upper eyelid to an intersection point key point h6 which is close to the inner canthus in two intersection points of the eyeball and a lower eyelid, the I h3-h 5I represents the distance from an intersection point key point h3 which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid to an intersection point key point h5 which is far from the inner canthus in two intersection points of the eyeball and the lower eyelid, and the I h1-h 4I represents the distance from the inner canthus key point h1 to an outer canthus key point h 4;
When h=0, indicating that the user's eyes are closed, the actual duration is monitored as t Real world Setting the duration threshold to t Threshold value When t Real world ＞t Threshold value When the user is in a closed eye rest state, stopping advertisement pushing; when H is not equal to 0, the user is in observation state, and the monitoring duration is t Holding device Setting the duration threshold to t' Threshold value When t Holding device ＞t’ Threshold value When the user is in the observation state, the process proceeds to step S204;
s204, acquiring a user sitting position through a safety camera in the vehicle, performing image monitoring on other vehicles on the road, marking the vehicle speed of the kth vehicle on the road as vk, marking the distance between the kth vehicle on the road and the target vehicle as dk, and marking the vehicle height as Lk; the preset influence radius is R, and the influence radius is preset by related technicians, so that the influence range is as follows: (x-aj) 2 +（y-bj） 2 =R 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein (aj, bj) is represented as the j-th acquired target vehicle position coordinates, and x and y are represented as variables; the influence range is selected according to the seating position of the user and the advancing direction of the vehicle, the selection mode is preset by related technicians, fig. 3 is an exemplary diagram of the influence range selection, the time Tk of the rest vehicle positions of the road in the influence range is monitored, and the threshold is set as T Threshold value When Tk is less than T Threshold value When Tk is more than or equal to T, the method has no influence on the target vehicle Threshold value The vehicle influence index β is calculated by the following formula:
β=（Lk） 2 （Tk）/（dk+e vk ）；
wherein e is expressed as natural logarithm; setting the threshold value to be beta Threshold value When beta > beta Threshold value When the influence of the kth vehicle on the target vehicle is large, and the sight of the user is blocked, the advertisement in the vehicle is normally pushed; when beta > beta Threshold value When the influence of the kth vehicle on the target vehicle is small, the step S3 is entered;
calculating the vehicle influence indexes of all other vehicles on the road which can be shot by the safety cameras in the target vehicle;
s205, repeating the steps S201-S204 for the target vehicle position acquired in real time, and acquiring the real-time state of the user and the vehicle influence index of the user in the observation state.
S3, according to the vehicle influence conditions analyzed in the step S2, when the user is in an observation state, analyzing target advertisement information focused by the user, recording focused advertisement contents of the user at different moments in the driving process, and analyzing focused advertisement content types of the user;
in step S3, the following steps are included:
s301, when the user is in an observation state, the driving positions of the target vehicles form a set a ' = { (a 1', b1 '), (a 2', b2 '), (aγ, bγ) }, where γ represents the number of collected target vehicle positions when the user is in the observation state, γe [1, m ], (aγ, bγ) represents the γ target vehicle positions collected when the user is in the observation state, and at the same time, the time corresponding to the collected driving positions is obtained;
S302, for the lambda-th collected target vehicle position, lambda E [1, gamma ]]The midpoint position coordinate of the connecting line of the temporomandibular joint position points of the user is M (p * λ，q * λ，r * Lambda), the coordinates of the nose tip position point are N (ulambda, vlambda, wlambda) to form a vector P * Uλ=（uλ-p * λ，vλ-q * λ，wλ-r * λ），
For the lambda+1th acquired target vehicle position, the midpoint position coordinate of the user temporomandibular joint position point line is M' (p) * （λ+1），q * （λ+1），r * (lambda+1)), the nose tip position point coordinates are N' (u (lambda+1), v (lambda+1), w (lambda+1)), forming vector P * U（λ+1）=（u（λ+1）-p * （λ+1），v（λ+1）-q * （λ+1），w（λ+1）-r * (lambda+1)); the shoulder joint position point and temporomandibular joint position pointThe specific indication positions of the joint position points are preset by relevant technicians;
s303, calculating the coordinate of the focus intersection point delta of the user through the following formula:
δ=M+[|（M’-M）×P * U（λ+1）|/|P * Uλ×P * U（λ+1）|]P * Uλ；
wherein x is expressed as a vector cross symbol, | (M' -M) ×p * U (lambda+1) | is expressed as a vector and a vector P formed between points M and M * U (lambda+1) is subjected to a vector cross multiplication operation, and P is the modulus * Uλ×P * U (λ+1) | is denoted as vector P * U lambda and vector P * U (lambda+1) is subjected to a module after vector cross multiplication operation; FIG. 4 is a schematic view of a user focus intersection;
the method comprises the steps of calculating focus intersection points of all vehicle driving positions of targets acquired by a user in an observation state, and determining advertisement positions focused by the user through cluster analysis, wherein the cluster analysis refers to an analysis process of grouping a set of data objects into a plurality of classes consisting of similar objects, is a technology for searching an internal structure among data, and organizes all data instances into a plurality of similar groups, and the similar groups are called clusters. Data instances in the same cluster are identical to each other, and instances in different clusters are different from each other; acquiring the time of the last driving position acquired when a user is in an observation state, calling the advertisement content played by the time of the last driving position of the determined advertisement position through the Internet, and continuously playing the called advertisement content to the user through display equipment in the vehicle, such as a vehicle-mounted display and the like;
S304, marking advertisement types, and counting advertisement types focused by a user in the driving process to obtain a group of sets Q= { (eta) 1 ，μ 1 ），（η 2 ，μ 2 ），...，（η o ，μ o ) O is represented as the number of advertisement types of interest to the user, η o Expressed as the o-th advertisement type, (eta) o ，μ o ) Represented as advertisement type eta o Advertising of mu o And, by the following formulaUser's type tau advertisement favorability G τ And (3) performing calculation:
G τ =μ τ /∑oξ=1μ ξ ；
wherein τ.epsilon.1, o]，μ τ Denoted as user attention advertisement type eta τ Advertisement quantity of (3);
calculating the preference degree of all advertisement types concerned by the user, sorting according to the size, summarizing the advertisement type concerned by the user, and when the advertisement in the vehicle is normally pushed, namely the user is not in an observation state or is influenced by other vehicles on the road to a large extent, calling the advertisement consistent with the advertisement type with the highest preference degree of the user to carry out directional pushing.
And S4, carrying out directional pushing on the user through the display equipment in the vehicle according to the advertisement content information analyzed in the step S3, and carrying out advertisement pushing on the user through the payment display interface when the user is in the payment interface.
In step S4, advertisement data is pushed in a targeted manner to a user through a display device in the vehicle, such as a vehicle-mounted display or a vehicle central control display screen, so that advertisement content which is more interesting to the user is provided for the user, accurate pushing of the advertisement content is realized, invalid pushing of advertisements is reduced, user experience is improved, pushing of a large amount of advertisement content which is not interesting to the user is avoided, the user is ensured to observe that the advertisement content which is interesting to the vehicle is completely watched during driving, user experience is improved, when the user is in a journey end state, the user carries out in-vehicle advertisement complete pushing through a mobile phone, the journey end comprises stopping use of the vehicle, payment operation and the like, the user can conveniently carry out complete watching of advertisements, the situation that the user cannot completely see the advertisements after the user gets off the vehicle is avoided, and advertisement efficiency is improved.
Fig. 2 is a schematic diagram of module composition of an advertisement data directional pushing system based on internet, and the advertisement data directional pushing system includes: the system comprises a driving monitoring module and an advertisement analysis module;
the output end of the driving monitoring module is connected with the input end of the advertisement analysis module;
the system comprises a travel monitoring module, a vehicle positioning module and a basic input unit, wherein the travel monitoring module is used for intelligently monitoring advertisement data on the way of traveling of a user and comprises an image acquisition unit, a vehicle positioning unit and a basic input unit, the image acquisition unit is used for acquiring images of data in the process of traveling of a vehicle through a safety camera in the interior of the target vehicle, the vehicle positioning unit is used for acquiring the position of the target vehicle in real time through positioning equipment, such as GPS positioning and Beidou navigation equipment, and the like, the basic input unit is used for inputting urban electronic map data, advertisement position data, operation parameters and the like in advance, and advertisements comprise dynamic billboards of a market, billboards of a bus station and the like;
the advertisement analysis module is used for intelligently analyzing advertisement push data in the running process of the user and comprises a state analysis unit and an advertisement determination unit, wherein the state analysis unit is used for analyzing the riding state of the user, analyzing the influence of other vehicles on the target vehicle by combining with the urban electronic map, and the advertisement determination unit is used for analyzing the target advertisement information focused by the user when the user is in an observation state, recording focused advertisement contents of the user at different moments in the running process and analyzing focused advertisement content types of the user.
The advertisement data directional pushing system further comprises: a data management module;
the input end of the data management module is connected with the output end of the driving monitoring module, the output end of the data management module is connected with the input end of the advertisement analysis module, and the output end of the advertisement analysis module is connected with the input end of the data management module;
the data management module is used for carrying out distributed management on collected data and analyzed advertisement data and carrying out data cleaning, and the data management module comprises a safety management unit and a data cleaning unit, wherein the safety management unit is used for carrying out safety storage on the collected data and analysis results through a distributed storage structure, and the distributed storage system is used for storing the data on a plurality of independent devices in a scattered mode. The traditional network storage system adopts a centralized storage server to store all data, and the storage server becomes a bottleneck of system performance, is also a focus of reliability and safety, and cannot meet the requirements of large-scale storage application. The distributed network storage system adopts an expandable system structure, utilizes a plurality of storage servers to share storage load, utilizes the position servers to position storage information, improves the reliability, availability and access efficiency of the system, is easy to expand, and the data cleaning unit is used for automatically deleting data after a user finishes a journey, wherein the journey comprises stopping the use of a vehicle, carrying out payment operation and the like, avoids data redundancy, and ensures the speed and the efficiency of operation analysis.
The advertisement data directional pushing system further comprises: a directional pushing module;
the input end of the directional pushing module is connected with the output end of the advertisement analysis module;
the directional pushing module is used for carrying out advertisement directional pushing on a user according to an analysis result, and comprises a vehicle-mounted pushing unit and a payment pushing unit, wherein the vehicle-mounted pushing unit is used for carrying out directional pushing on advertisement content and advertisements of interest types observed by the user in the driving process according to the analysis result, for example, a vehicle-mounted display device or a vehicle central control display screen and the like, so that the use experience of the user is improved, the user is guaranteed to observe the whole watching of the advertisement content of the vehicle-induced interest in the driving process, the situation that the user leaves without watching the whole through the advertisement position is avoided, the use experience of the user is improved, the pushing of a large number of advertisement contents which are not interested by the user is avoided, the payment pushing unit is used for carrying out complete pushing on advertisements in the user through a mobile phone when the user is in a stroke end state, the stroke end operation comprises stopping use of the vehicle and carrying out payment operation and the like, the user is convenient to carry out complete watching on the advertisements, the situation that the user fails to complete watching the advertisements after the user gets off the vehicle is avoided, and the advertisement throwing efficiency is improved.
Example 1:
for the lambda-th acquired target vehicle position, lambda ε [1, gamma]The midpoint position coordinate of the connecting line of the temporomandibular joint position points of the user is M (p * λ，q * λ，r * Lambda), the coordinates of the nose tip position point are N (ulambda, vlambda, wlambda)Form vector P * Uλ=（uλ-p * λ，vλ-q * λ，wλ-r * λ），
For the lambda+1th acquired target vehicle position, the midpoint position coordinate of the user temporomandibular joint position point line is M' (p) * （λ+1），q * （λ+1），r * (lambda+1)), the nose tip position point coordinates are N' (u (lambda+1), v (lambda+1), w (lambda+1)), forming vector P * U（λ+1）=（u（λ+1）-p * （λ+1），v（λ+1）-q * （λ+1），w（λ+1）-r * （λ+1））；
Uniformly representing the points and the vectors, namely uniformly representing the coordinates;
the translation of the points is represented by vector addition, resulting in the intersection of interest delta=m+epsilonps * U lambda; wherein ε is represented as a scalar;
multiplying a scalar by a vector fork; focusing on the intersection point δ and the point M ' to form a vector δm ', δm ' x P * U (λ+1) =0; wherein 0 is represented as a zero vector; then
（M’-δ）×P * U（λ+1）=0；
[M’-（M+εP * Uλ）]×P * U（λ+1）=0；
（M’-M）×P * U（λ+1）-εP * Uλ×P * U（λ+1）=0；
（M’-M）×P * U（λ+1）=εP * Uλ×P * U（λ+1）；
ε=|（M’-M）×P * U（λ+1）|/|P * Uλ×P * U（λ+1）|；
Then attention is paid to the intersection point δ=m+ [ | (M' -M) ×p) * U（λ+1）|/|P * Uλ×P * U（λ+1）|]P * Uλ；
It is noted that relational terms such as first and second, and the like are 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. Moreover, 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.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. An advertisement data directional pushing method based on the Internet is characterized in that: comprises the following steps:
s1, acquiring an urban electronic map, pre-inputting urban advertisement positions, and numbering the urban advertisement positions;
s2, when the vehicle is in a working state, acquiring the running position of the vehicle in real time, monitoring the behavior of a user in the vehicle, analyzing the riding state of the user, and analyzing the influence of other vehicles on the road on the target vehicle by combining with the urban electronic map;
s3, according to the vehicle influence conditions analyzed in the step S2, when the user is in an observation state, analyzing target advertisement information focused by the user, recording focused advertisement contents of the user at different moments in the driving process, and analyzing focused advertisement content types of the user;
And S4, carrying out directional pushing on the user through the display equipment in the vehicle according to the advertisement content information analyzed in the step S3, and carrying out advertisement pushing on the user through the payment display interface when the user is in the payment interface.
2. The internet-based advertisement data directional pushing method according to claim 1, wherein the method comprises the following steps: in step S1, the city electronic map is consistent with the map for vehicle navigation, a rectangular planar coordinate system is constructed, and the i-th advertisement position in the city is designated as (xi, yi).
3. The internet-based advertisement data directional pushing method according to claim 2, wherein the method comprises the following steps: in step S2, the following steps are included:
s201, when a user enters a target vehicle and starts the vehicle, judging that the target vehicle is in a working state, presetting a time interval as t, and acquiring a running position of the target vehicle in real time through positioning equipment to form a set a= { (a 1, b 1), (a 2, b 2), (am, bm) }, wherein m is the number of acquired target vehicle positions, and (am, bm) is the m-th acquired target vehicle position coordinate;
s202, starting a safety camera in a target vehicle, acquiring a user image in the target vehicle, constructing a three-dimensional coordinate system in the vehicle, determining position point coordinates by utilizing an image ranging technology, acquiring two shoulder joint position points of the user in the target vehicle in real time by utilizing an openpost technology, wherein the midpoint position coordinates of the two shoulder joint position point connecting lines form a set P= { (P1, q1, r 1), (P2, q2, r 2), (pm, qm, rm) }, wherein (pm, qm, rm) is expressed as the midpoint position coordinates of the m-th shoulder joint position point connecting line; obtaining facial image information of a user through an image contour extraction technology to obtain a user nose tip position point, and forming a set U= { (U1, v1, w 1), (U2, v2, w 2), (um, vm, wm) }, wherein (um, vm, wm) is expressed as m-th user nose tip position point coordinates, and then the user shoulder joint position point and the nose tip position point form a vector set PU= { PU1, PU2, & gt, PUm }, wherein PUm is expressed as a vector formed by a midpoint position of a user shoulder joint position point connecting line and the nose tip position point at m-th target vehicle position, PUm = (um-pm, vm-qm, wm-rm); the position coordinates of the safety camera in the target vehicle are input in advance as (x, y, z);
At the j-th acquired target vehicle position, the midpoint position of the user shoulder joint position point connecting line and the nose tip position point form a vector puj= (uj-pj, vj-qj, wj-rj), the midpoint position of the user shoulder joint position point connecting line and the safety camera position form a vector PZj = (x-pj, y-qj, z-rj), and the attention angle alpha of the user is calculated by the following formula:
α=arccos （PUj·PZj）/（|PUj||PZj|）；
where i PUj is represented as a modulus of vector PUj and PZj is represented as a modulus of vector PZj;
s203, the window reference point position coordinates closest to the seat in the target vehicle are recorded in advance, and when a user sits down, the window reference point position coordinates (e c ，f c ，g c ) The midpoint position of the user shoulder joint position point connecting line and the window reference point position form a vector pe= (e) c -pj，f c -qj，g c Rj), then reference angle α=arccoss (Pe PZj)/(Pe PZj);
when alpha is less than alpha, the advertisement in the vehicle is normally pushed;
when alpha is more than or equal to alpha, measuring the eye distance of a user through an image ranging technology, determining the two-dimensional key point position of the eye through an OpenPose technology, wherein an inner canthus is a key point H1, an intersection point which is close to the inner canthus in two intersection points of an eyeball and an upper eyelid is a key point H2, an intersection point which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid is a key point H3, an outer canthus is a key point H4, an intersection point which is far from the inner canthus in two intersection points of the eyeball and a lower eyelid is a key point H5, an intersection point which is close to the inner canthus in two intersection points of the eyeball and the lower eyelid is a key point H6, and calculating the aspect ratio H of the human eyes of passengers through the following formula:
H=（||h2-h6||+||h3-h5||）/2||h1-h4||；
Wherein, the I h2-h 6I represents the distance from an intersection point key point h2 which is close to an inner canthus in two intersection points of an eyeball and an upper eyelid to an intersection point key point h6 which is close to the inner canthus in two intersection points of the eyeball and a lower eyelid, the I h3-h 5I represents the distance from an intersection point key point h3 which is far from the inner canthus in two intersection points of the eyeball and the upper eyelid to an intersection point key point h5 which is far from the inner canthus in two intersection points of the eyeball and the lower eyelid, and the I h1-h 4I represents the distance from the inner canthus key point h1 to an outer canthus key point h 4;
when h=0, indicating that the user's eyes are closed, the actual duration is monitored as t Real world Setting the duration threshold to t Threshold value When t Real world ＞t Threshold value When the user is in a closed eye rest state, stopping advertisement pushing; when H is not equal to 0, the user is in observation state, and the monitoring duration is t Holding device Setting the duration threshold to t' Threshold value When t Holding device ＞t’ Threshold value When the user is in the observation state, the process proceeds to step S204;
s204, acquiring a user sitting position through a safety camera in the vehicle, performing image monitoring on other vehicles on the road, marking the vehicle speed of the kth vehicle on the road as vk, marking the distance between the kth vehicle on the road and the target vehicle as dk, and marking the vehicle height as Lk; the preset influence radius is R, and the influence range is: (x-aj) 2 +（y-bj） 2 =R 2 The method comprises the steps of carrying out a first treatment on the surface of the Wherein (aj, bj) is represented as the j-th acquired target vehicle position coordinates, and x and y are represented as variables; selecting an influence range according to the seating position of a user and the advancing direction of the vehicle, monitoring the time Tk when the positions of other vehicles on the road are in the influence range, and setting a threshold value as T Threshold value When Tk is less than T Threshold value When Tk is more than or equal to T, the method has no influence on the target vehicle Threshold value The vehicle influence index β is calculated by the following formula:
β=（Lk） 2 （Tk）/（dk+e vk ）；
wherein e is expressed as natural logarithm; setting the threshold value to be beta Threshold value When beta > beta Threshold value When the advertisement is pushed, the advertisement in the vehicle is pushed normally; when beta > beta Threshold value If yes, enter step S3;
calculating the vehicle influence indexes of all other vehicles on the road which can be shot by the safety cameras in the target vehicle;
s205, repeating the steps S201-S204 for the target vehicle position acquired in real time, and acquiring the real-time state of the user and the vehicle influence index of the user in the observation state.
4. The internet-based advertisement data directional pushing method according to claim 3, wherein: in step S3, the following steps are included:
s301, when the user is in an observation state, the driving positions of the target vehicles form a set a ' = { (a 1', b1 '), (a 2', b2 '), (aγ, bγ) }, where γ represents the number of collected target vehicle positions when the user is in the observation state, and (aγ, bγ) represents the γ -th target vehicle position collected when the user is in the observation state, and at the same time, the time corresponding to the collected driving positions is obtained;
S302, for the lambda-acquired target vehicle position, the midpoint position coordinate of the temporal and mandibular joint position point connecting line of the user is M (p * λ，q * λ，r * Lambda), the coordinates of the nose tip position point are N (ulambda, vlambda, wlambda) to form a vector P * Uλ=（uλ-p * λ，vλ-q * λ，wλ-r * λ），
For the lambda+1th acquired target vehicle position, the midpoint position coordinate of the user temporomandibular joint position point line is M' (p) * （λ+1），q * （λ+1），r * (lambda+1)), the nose tip position point coordinates are N' (u (lambda+1), v (lambda+1), w (lambda+1)), forming vector P * U（λ+1）=（u（λ+1）-p * （λ+1），v（λ+1）-q * （λ+1），w（λ+1）-r * （λ+1））；
S303, calculating the coordinate of the focus intersection point delta of the user through the following formula:
δ=M+[|（M’-M）×P * U（λ+1）|/|P * Uλ×P * U（λ+1）|]P * Uλ；
wherein x is expressed as a vector cross symbol, | (M' -M) ×p * U (lambda+1) | is expressed as a vector and a vector P formed between points M and M * U (lambda+1) is subjected to a vector cross multiplication operation, and P is the modulus * Uλ×P * U (λ+1) | is denoted as vector P * U lambda and vector P * U (lambda+1) is subjected to a module after vector cross multiplication operation;
calculating the focused intersection points of all the vehicle driving positions of the targets acquired by the user in the observation state, and determining the focused advertisement positions of the user through cluster analysis; acquiring the time of the last driving position acquired when the user is in an observation state, calling the advertisement content played by the time of the last driving position of the determined advertisement position through the Internet, and continuously playing the called advertisement content to the user through display equipment in the vehicle;
S304, marking advertisement types, and counting advertisement types focused by a user in the driving process to obtain a group of sets Q= { (eta) 1 ，μ 1 ），（η 2 ，μ 2 ），...，（η o ，μ o ) O is represented as the number of advertisement types of interest to the user, η o Expressed as the o-th advertisement type, (eta) o ，μ o ) Represented as advertisement type eta o Advertising of mu o Next, the user's preference G for the type of advertisement of the τ th type is calculated by the following formula τ And (3) performing calculation:
G τ =μ τ /∑oξ=1μ ξ ；
wherein τ.epsilon.1, o]，μ τ Denoted as user attention advertisement type eta τ Advertisement quantity of (3);
calculating the preference degree of all advertisement types concerned by the user, sorting according to the size, summarizing the advertisement type concerned by the user, and calling the advertisement consistent with the advertisement type with the highest preference degree of the user to push in a targeting manner when the advertisement in the vehicle is normally pushed.
5. The internet-based advertisement data directional pushing method according to claim 4, wherein the method comprises the following steps: in step S4, advertisement data is pushed in a targeted manner to a user through display equipment in the vehicle, advertisement content which is more interesting to the user is provided for the user, and when the user is in a journey end state, in-vehicle advertisement is pushed completely to the user through a mobile phone.
6. An advertisement data directional pushing system based on the internet is characterized in that: the advertisement data directional pushing system comprises: the system comprises a driving monitoring module and an advertisement analysis module;
the output end of the driving monitoring module is connected with the input end of the advertisement analysis module;
the running monitoring module is used for intelligently monitoring advertisement data on the way of traveling of a user and comprises an image acquisition unit, a vehicle positioning unit and a basic input unit, wherein the image acquisition unit is used for acquiring images of data in the running process of the vehicle through a safety camera in the target vehicle, the vehicle positioning unit is used for acquiring the position of the target vehicle in real time through positioning equipment, and the basic input unit is used for inputting urban electronic map data, advertisement position data, operation parameters and the like in advance;
the advertisement analysis module is used for intelligently analyzing advertisement push data in the running process of the user and comprises a state analysis unit and an advertisement determination unit, wherein the state analysis unit is used for analyzing the riding state of the user, analyzing the influence of other vehicles on the target vehicle by combining with the urban electronic map, and the advertisement determination unit is used for analyzing the target advertisement information focused by the user when the user is in an observation state, recording focused advertisement contents of the user at different moments in the running process and analyzing focused advertisement content types of the user.
7. The internet-based advertisement data targeted pushing system of claim 6, wherein: the advertisement data directional pushing system further comprises: a data management module;
the input end of the data management module is connected with the output end of the driving monitoring module, the output end of the data management module is connected with the input end of the advertisement analysis module, and the output end of the advertisement analysis module is connected with the input end of the data management module;
the data management module is used for carrying out distributed management on the collected data and the analyzed advertisement data and carrying out data cleaning, and the data management module comprises a safety management unit and a data cleaning unit, wherein the safety management unit is used for carrying out safety storage on the collected data and the analysis result through a distributed storage structure, and the data cleaning unit is used for automatically deleting the data after a user finishes a journey.
8. The internet-based advertisement data targeted pushing system of claim 6, wherein: the advertisement data directional pushing system further comprises: a directional pushing module;
the input end of the directional pushing module is connected with the output end of the advertisement analysis module;
the directional pushing module is used for carrying out advertisement directional pushing on a user according to an analysis result and comprises a vehicle-mounted pushing unit and a payment pushing unit, the vehicle-mounted pushing unit is used for carrying out directional pushing on advertisement content and advertisements of interesting types observed in the running process of the user according to the analysis result, and the payment pushing unit is used for carrying out complete pushing on advertisements in the user through a mobile phone when the user is in a travel end state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311062640.0A CN116757745B (en) | 2023-08-23 | 2023-08-23 | Advertisement data directional pushing system and method based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311062640.0A CN116757745B (en) | 2023-08-23 | 2023-08-23 | Advertisement data directional pushing system and method based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116757745A true CN116757745A (en) | 2023-09-15 |
| CN116757745B CN116757745B (en) | 2023-10-24 |
Family
ID=87953826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311062640.0A Active CN116757745B (en) | 2023-08-23 | 2023-08-23 | Advertisement data directional pushing system and method based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116757745B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103384260A (en) * | 2012-05-04 | 2013-11-06 | 亿赞普(北京)科技有限公司 | Advertisement scheduling method and advertisement server |
| CN105046513A (en) * | 2015-06-19 | 2015-11-11 | 长沙待霁电子科技有限公司 | Vehicle-mounted regionalization intelligence positioning advertisement method |
| CN105046512A (en) * | 2015-06-19 | 2015-11-11 | 长沙待霁电子科技有限公司 | Intelligent positioning advertisement method |
| CN108765018A (en) * | 2018-05-31 | 2018-11-06 | 重庆市城投金卡信息产业股份有限公司 | Based on the associated adaptive advertisement pushing method and system of people's vehicle |
| US20190172095A1 (en) * | 2017-12-05 | 2019-06-06 | Diesel Media Group, LLC | Process and system for location based advertising |
| CN110390554A (en) * | 2018-05-28 | 2019-10-29 | 马鞍山观点信息科技有限公司 | A kind of advertising method for road driving |
-
2023
- 2023-08-23 CN CN202311062640.0A patent/CN116757745B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103384260A (en) * | 2012-05-04 | 2013-11-06 | 亿赞普(北京)科技有限公司 | Advertisement scheduling method and advertisement server |
| CN105046513A (en) * | 2015-06-19 | 2015-11-11 | 长沙待霁电子科技有限公司 | Vehicle-mounted regionalization intelligence positioning advertisement method |
| CN105046512A (en) * | 2015-06-19 | 2015-11-11 | 长沙待霁电子科技有限公司 | Intelligent positioning advertisement method |
| US20190172095A1 (en) * | 2017-12-05 | 2019-06-06 | Diesel Media Group, LLC | Process and system for location based advertising |
| CN110390554A (en) * | 2018-05-28 | 2019-10-29 | 马鞍山观点信息科技有限公司 | A kind of advertising method for road driving |
| CN108765018A (en) * | 2018-05-31 | 2018-11-06 | 重庆市城投金卡信息产业股份有限公司 | Based on the associated adaptive advertisement pushing method and system of people's vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116757745B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200364554A1 (en) | Systems and methods for deep localization and segmentation with a 3d semantic map | |
| Lookingbill et al. | Reverse optical flow for self-supervised adaptive autonomous robot navigation | |
| Cao et al. | Rapid detection of blind roads and crosswalks by using a lightweight semantic segmentation network | |
| US12073575B2 (en) | Object-centric three-dimensional auto labeling of point cloud data | |
| US20210166450A1 (en) | Motion trajectory drawing method and apparatus, and device and storage medium | |
| CN113643329B (en) | Twin attention network-based online update target tracking method and system | |
| CN103598870A (en) | Optometry method based on depth-image gesture recognition | |
| CN106446002A (en) | Moving target-based video retrieval method for track in map | |
| CN110533720A (en) | Semantic SLAM system and method based on joint constraint | |
| US11256915B2 (en) | Object tracking across multiple images | |
| CN114299464A (en) | Lane positioning method, device and equipment | |
| Cui et al. | Dense depth-map estimation based on fusion of event camera and sparse LiDAR | |
| CN117274388B (en) | Unsupervised three-dimensional visual positioning method and system based on visual text relation alignment | |
| CN110110663A (en) | A kind of age recognition methods and system based on face character | |
| CN113901931B (en) | Behavior recognition method of infrared and visible light video based on knowledge distillation model | |
| CN112699834A (en) | Traffic identification detection method and device, computer equipment and storage medium | |
| CN117274515A (en) | Visual SLAM method and system based on ORB and NeRF mapping | |
| CN113177432B (en) | Head posture estimation method, system, equipment and medium based on multi-scale lightweight network | |
| CN116310799A (en) | Dynamic feature point eliminating method combining semantic information and geometric constraint | |
| CN116757745B (en) | Advertisement data directional pushing system and method based on Internet | |
| CN110263836A (en) | A kind of bad steering state identification method based on multiple features convolutional neural networks | |
| CN117710356A (en) | Image target positioning and counting model and implementation method thereof | |
| CN113794872B (en) | Image recognition system based on AR intelligent glasses | |
| CN115619873A (en) | Track tracing-based radar vision automatic calibration method | |
| Li et al. | Simulation of tennis serve behavior based on video image processing and wireless sensor technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |