CN114973954A - Intelligent advertisement putting platform and method thereof - Google Patents
Intelligent advertisement putting platform and method thereof Download PDFInfo
- Publication number
- CN114973954A CN114973954A CN202210591521.3A CN202210591521A CN114973954A CN 114973954 A CN114973954 A CN 114973954A CN 202210591521 A CN202210591521 A CN 202210591521A CN 114973954 A CN114973954 A CN 114973954A
- Authority
- CN
- China
- Prior art keywords
- information
- crowd
- module
- advertisement
- unit
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F9/00—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements
- G09F9/30—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
- G06V40/176—Dynamic expression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent advertisement putting platform and an intelligent advertisement putting method, and belongs to the technical field of advertisement putting. In order to solve the problems that corresponding advertisements cannot be launched according to different watching crowds, the flexibility is poor, and the watching requirements of different watching crowds cannot be met, the intelligent advertisement launching platform and the intelligent advertisement launching method thereof convert, process, reference and compare the acquired crowd information, determine the crowd identification information, comprehensively evaluate the identification information, find the specified advertisement with a specific identity according to identity confirmation, and intelligently launch the specified advertisement on an advertisement launching screen, can launch the corresponding advertisements according to different watching crowds, are good in flexibility, can meet the watching requirements of different watching crowds, and have wide market prospects.
Description
Technical Field
The invention relates to the technical field of advertisement putting, in particular to an intelligent advertisement putting platform and an intelligent advertisement putting method.
Background
Advertising is of particular interest when present, and it conveys out flat information, branding, images and thus attracts consumer interest.
Chinese patent publication No. CN214751971U discloses an intelligent advertisement delivery system, which comprises an advertisement machine body, a central processing unit for processing signals and data, a storage module electrically connected to the central processing unit, a signal receiving module, a signal sending module, an infrared thermal imaging sensor, a timer, a speaker and a liquid crystal display, the infrared thermal imaging sensor is used for detecting whether there is a human thermal imaging signal in front of the advertisement machine body in real time, the timer is used for timing the time interval when the infrared thermal imaging sensor does not detect the human thermal imaging signal and sending the signal to the central processing unit in real time, and the central processing unit is used for adjusting the brightness of the liquid crystal display and the volume of the speaker according to the data sent by the timer. The utility model discloses a system can automatic control reduce the volume of advertisement machine speaker and liquid crystal display's luminance to the power saving, more intelligent and environmental protection. However, the above patents have the following drawbacks:
the corresponding advertisements can not be put in according to different watching crowds, the flexibility is poor, and the watching requirements of different watching crowds can not be met.
Disclosure of Invention
The invention aims to provide an intelligent advertisement putting platform and an intelligent advertisement putting method, which are used for converting, processing and comparing acquired crowd information by reference, determining crowd identification information, comprehensively evaluating the identification information, finding a specific advertisement with a specific identity according to identity confirmation, putting the advertisement intelligently on an advertisement putting screen, putting corresponding advertisements according to different watching crowds, having good flexibility, meeting the watching requirements of different watching crowds and having wide market prospect, and solving the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
an intelligent advertisement putting platform comprises an outer shell and a face cover, wherein the face cover is arranged on the outer shell, an advertisement putting screen is embedded in the face cover, heat dissipation holes and data transmission interfaces are formed in the side face of the outer shell, and a plurality of data transmission interfaces are regularly arranged above the heat dissipation holes;
the inner side of the outer shell is provided with an acquisition module, an analysis module, a division module, an index module and a storage module, wherein
The output end of the acquisition module is electrically connected with the input end of the analysis module;
the acquisition module is used for acquiring crowd information of watching the delivered advertisements in front of the advertisement delivery screen in real time and feeding back the crowd information acquired in real time to the analysis module;
the output end of the analysis module is electrically connected with the input end of the dividing module;
the analysis module is used for analyzing and processing the crowd information acquired in real time, determining the identification information of the crowd information and feeding the determined identification information back to the division module;
the output end of the dividing module is electrically connected with the input end of the index module;
the dividing module is used for carrying out identity division on the determined identification information, determining the specific identity of the crowd information and feeding back the determined specific identity to the indexing module;
the output end of the index module is electrically connected with the input end of the storage module;
the index module is used for indexing the determined specific identity and searching for and delivering the specified advertisement of the specific identity stored in the storage module;
the storage module is used for storing advertisements corresponding to crowd information with different identities.
Further, the acquisition module comprises a high-definition camera, a smoke sensor and an infrared sensor,
the high-definition camera is used for acquiring figure image information of people watching the delivered advertisements in front of the advertisement delivery screen in real time and storing the figure image information in the memory;
the smoke sensor is used for acquiring whether smoke exists in front of the advertisement putting screen in real time;
the infrared inductor is used for sensing whether crowds exist in front of the advertisement putting screen in real time.
Further, the figure recognition module receives figure image information stored in the memory, extracts and recognizes the figure image information to confirm whether a figure actually exists, and extracts facial features to obtain face specific data when the figure actually exists;
the human eye recognition module is used for receiving the facial feature data, comprehensively analyzing the facial feature data and obtaining the human eye sight direction of the character so as to judge whether the human eyes watch the advertisement putting screen or not, and the facial expression and the facial muscle dragging condition of the character;
the attention collection module is used for collecting attention information of a character when watching the advertisement, and judging the attention of the character when watching the advertisement on the advertisement putting screen by combining facial expression of the character, fixation time in the same direction and limb movement;
and the attention degree grading module is used for grading the attention degree information of the people, marking the advertisement with a large number of people watching in a specific time and high attention degree grading of the people, and transmitting the advertisement content information, the advertisement putting time information and the corresponding crowd information corresponding to the marking information to the analysis module.
Further, the analysis module comprises a transmitting and receiving unit, a conversion processing unit and a reference comparison unit,
the output end of the transmitting and receiving unit is connected with the input end of the conversion processing unit;
the transmitting and receiving unit is used for receiving the crowd information acquired by the acquisition module in real time and feeding back the received crowd information to the conversion processing unit;
the output end of the conversion processing unit is connected with the input end of the reference comparison unit;
the conversion processing unit is used for converting the received crowd information into data information which can be automatically identified by the reference comparison unit;
the reference comparison unit is used for performing reference comparison on the converted data information to determine the identification information of the crowd information;
the reference comparison unit further comprises
After the crowd information is converted, the crowd appearance and the crowd wearing information of the crowd collected in real time are compared according to the stored crowd appearance and the stored crowd wearing information, and therefore the identification information of the crowd is determined;
after the identification information of the crowd is determined, the identification information of the crowd is completely transmitted to the dividing module, so that the dividing module can conveniently divide the identity according to the identification information of the crowd.
Further, the dividing module comprises a comprehensive evaluation unit and an identity confirmation unit,
the output end of the comprehensive evaluation unit is connected with the input end of the identity confirmation unit;
the comprehensive evaluation unit is used for comprehensively evaluating the determined identification information of the crowd, considering multi-party factors and feeding back the comprehensive evaluation result to the identity confirmation unit;
the identity confirmation unit is used for carrying out identity confirmation of specific identities of the crowd after comprehensive evaluation, wherein the identities of the crowd comprise children, teenagers, adolescents, middle-aged people or old people.
Further, the index module comprises a bidirectional guide unit and a call return unit,
the bidirectional guide unit is electrically connected with the call return unit in a bidirectional way;
the bidirectional guiding unit is used for guiding and guiding the crowds after identity confirmation to guide the crowds to advertisements of corresponding specific crowds stored in the storage module;
the calling and returning unit is used for calling out the directed advertisements of the corresponding specific crowds and putting the advertisements through the advertisement putting screen.
Furthermore, the storage module comprises a storage unit, a plurality of storage units are respectively used for storing specific advertisements of different crowds, and the specific advertisements are specially designed and manufactured for the different crowds.
Furthermore, the advertisements are sorted according to a clustering mode, and the sorted advertisements are compressed, fused and stored in a specific storage unit.
Further, the eye recognition module tracks the direction of the eye's gaze by:
acquiring space coordinate data of a pupil center point and space coordinate data of an inner corner of an eye according to character image information;
step two, obtaining the coordinates(s) of the points concerned by the person on the image based on the mapping relation expected to be learned by the pupil-canthus method x ，s y ) The mapping relationship is as follows:
βf(p p ，p e )＝(s x ，s y )
wherein, f (p) p ，p e ) Is a mapping function; p is a radical of p Is the spatial coordinate data of the pupil center, p e The data is inner canthus space coordinate data, beta is a posture coefficient when the head posture changes, and the value of beta is 1 when the head posture is fixed;
step three, calculating the vector (v) of the pupil-eye corner x ，v y )＝p p -p e And fitting a real mapping relation according to a polynomial function to obtain:
wherein, a 0 ...a 11 The learning coefficient is determined by user calibration, and calibration is carried out according to individual characteristics of the user;
and step four, evaluating the coordinate information and the projection range of the launching screen by the coordinate information of the point concerned by the person on the image obtained after mapping, confirming that the eye sight is tracking the advertisement on the launching screen when the coordinate information falls into the expected range of the preset launching screen, and otherwise, evaluating that the eye sight is not tracking the advertisement on the launching screen.
According to another aspect of the present invention, an intelligent advertisement delivery method for an intelligent advertisement delivery platform is provided, which includes the following steps:
s1: the method comprises the steps that a collecting module collects crowd information of advertisements watched and delivered in front of an advertisement delivery screen in real time, and an analyzing module analyzes and processes the crowd information collected in real time to determine identification information of the crowd information;
s2: the dividing module is used for carrying out identity division on the determined identification information, determining the specific identity of the crowd information, indexing the determined specific identity through the indexing module, searching the specified advertisement with the specific identity stored in the storage module, and intelligently delivering the specified advertisement on the advertisement delivery screen.
Compared with the prior art, the invention has the beneficial effects that:
the invention relates to an intelligent advertisement putting platform and a method thereof.A collecting module collects crowd information watching and putting advertisements in front of an advertisement putting screen in real time, an analyzing module converts and compares the crowd information collected in real time, the crowd appearance and the crowd wearing information collected in real time are compared by referring to the stored crowd appearance and the crowd wearing information, thereby determining the identification information of the crowd, a dividing module comprehensively evaluates the determined identification information and confirms the identity of the crowd after considering various factors, an indexing module indexes the determined specific identity, finds the specified advertisement with the specific identity stored in the storing module, calls the directed advertisement of the corresponding specific crowd, intelligently puts the specified advertisement on the advertisement putting screen, and puts the corresponding advertisement according to different watching crowds, the mobile phone has good flexibility, can meet the watching requirements of different watching crowds, and has wide market prospect.
Drawings
FIG. 1 is a schematic diagram of an intelligent advertisement delivery platform of the present invention;
FIG. 2 is a cross-sectional view of an intelligent advertising platform of the present invention;
FIG. 3 is a schematic diagram of an intelligent advertisement delivery platform of the present invention;
FIG. 4 is a block diagram of an intelligent advertisement delivery platform of the present invention;
FIG. 5 is an architecture diagram of an intelligent advertisement delivery platform of the present invention;
fig. 6 is a flowchart of the intelligent advertisement delivery platform of the present invention.
In the figure: 1. an outer housing; 11. heat dissipation holes; 12. a data transmission interface; 2. a face cover; 21. an advertisement delivery screen; 3. an acquisition module; 31. a high-definition camera; 32. a smoke sensor; 33. an infrared sensor; 4. an analysis module; 41. a transmission transceiving unit; 42. a conversion processing unit; 43. a reference comparison unit; 5. a dividing module; 51. a comprehensive evaluation unit; 52. an identity confirmation unit; 6. an indexing module; 61. a bidirectional guide unit; 62. calling a return unit; 7. a storage module; 71. and storing the unit.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1-2, an advertisement intelligent delivery platform comprises an outer shell 1 and a surface cover 2, wherein the surface cover 2 is arranged on the outer shell 1, an advertisement delivery screen 21 is embedded on the surface cover 2, a heat dissipation hole 11 and a data transmission interface 12 are arranged on the side surface of the outer shell 1, and a plurality of data transmission interfaces 12 are arranged above the heat dissipation hole 11 in order.
The designated advertisements of the corresponding crowds are intelligently released on the advertisement releasing screen 21, the corresponding advertisements can be released according to different watching crowds, the flexibility is good, the watching requirements of different watching crowds can be met, and the intelligent advertisement releasing screen has a wide market prospect.
Referring to fig. 3, an acquisition module 3, an analysis module 4, a division module 5, an index module 6 and a storage module 7 are arranged on the inner side of the outer shell 1, wherein the output end of the acquisition module 3 is electrically connected with the input end of the analysis module 4; the acquisition module 3 is used for acquiring the crowd information of the advertisement viewed and delivered in front of the advertisement delivery screen 21 in real time and feeding back the crowd information acquired in real time to the analysis module 4; the output end of the analysis module 4 is electrically connected with the input end of the dividing module 5; the analysis module 4 is used for analyzing and processing the crowd information collected in real time, determining the identification information of the crowd information, and feeding the determined identification information back to the dividing module 5; the output end of the dividing module 5 is electrically connected with the input end of the index module 6; the dividing module 5 is used for carrying out identity division on the determined identification information, determining the specific identity of the crowd information and feeding back the determined specific identity to the indexing module 6; the output end of the index module 6 is electrically connected with the input end of the storage module 7; the indexing module 6 is used for indexing the determined specific identity and searching the specified advertisement of the specific identity stored in the storage module 7 for delivery; the storage module 7 is used for storing advertisements corresponding to crowd information with different identities.
The acquisition module 3 acquires crowd information watching the advertisement in front of the advertisement putting screen 21 in real time, the analysis module 4 converts and compares the crowd information acquired in real time, the crowd appearance and the crowd wearing information acquired in real time are compared with each other according to the stored crowd appearance and the stored crowd wearing information, thereby determining the identification information of the crowd, the dividing module 5 comprehensively evaluates the determined identification information and confirms the identity of the specific identity of the crowd after considering the multi-factors, the index module 6 indexes the determined specific identity, finds the specified advertisement with the specific identity stored in the storage module 7, calls the directed advertisement of the corresponding specific crowd, intelligently puts the specified advertisement on the advertisement putting screen 21, and puts the corresponding advertisement according to different watching crowds, the mobile phone has good flexibility, can meet the watching requirements of different watching crowds, and has wide market prospect.
Referring to fig. 4-5, the acquisition module 3 includes a high-definition camera 31, a smoke sensor 32 and an infrared sensor 33, and the high-definition camera 31 is used for acquiring crowd characteristic information of the advertisement to be watched and delivered in front of the advertisement delivery screen 21 in real time, including crowd appearance and wearing of the crowd; the smoke sensor 32 is used for acquiring whether smoke exists in front of the advertisement putting screen 21 in real time; the infrared sensor 33 is used for sensing whether people are in front of the advertisement putting screen 21 in real time. By means of the high-definition camera 31, the crowd characteristic information can be captured, the image information of people of the crowd, including the appearance and the wearing of the people, is identified and stored in the storage, so that the corresponding specific advertisement can be conveniently put in, and the demands of the crowd are met. The smoke sensor 32 can be used for capturing smoke in front of the advertisement putting screen 21, and the normal operation of the advertisement putting screen 21 is guaranteed. Whether crowd exists in front of the advertisement putting screen 21 or not can be captured by means of the infrared inductor 33, and if the crowd does not exist, the advertisement putting screen 21 suspends advertisement putting, so that electric energy is saved.
Specifically, the person identification module receives the person image information stored in the memory, extracts and identifies the person image information to determine whether the person actually exists, and extracts facial features to obtain the face specific data when the person actually exists;
the human eye recognition module is used for receiving the facial feature data, comprehensively analyzing the facial feature data and obtaining the human eye sight direction of the character so as to judge whether the human eyes watch the advertisement putting screen 21 or not, and the facial expression and the facial muscle dragging condition of the character;
the attention degree acquisition module is used for acquiring attention degree information of a person when watching the advertisement, and judging the attention degree of the person watching the advertisement on the advertisement putting screen 21 by combining facial expression, facial muscle dragging condition, watching time in the same direction and limb movement of the person;
and the attention degree scoring module is used for scoring attention degree information of the people, marking the advertisements which have a large number of people to watch and high attention degree score of the people in a specific time, and transmitting advertisement content information, advertisement putting time information and corresponding crowd information corresponding to the marking information to the analysis module 4.
The principle and the effect of the technical scheme are as follows: since the high definition camera 31 captures the captured environmental information, even if the sensing function of the infrared sensor 33 is combined, the person identification is still a contour identification, and further confirmation is needed, and further extraction of the person characteristics for analysis and confirmation of whether the person really exists, such as the facial contour characteristics, appearance and wearing, age and hair condition, of the person can be realized by the person identification module. On the premise of confirming the existence of the character, the data analysis of the character facial features can acquire basic information of a user, such as facial paleness degree, gender, facial expression condition, hair condition and eye attention direction condition, on one hand, the data analysis of the character facial features can judge whether the character watches the advertisement putting screen 21, and on the other hand, the attention degree of the character watching the advertisement on the advertisement putting screen 21 is judged by combining the facial expression of the character, the facial muscle attention condition, the watching time in the same direction and limb movement through the attention degree acquisition module. Under the premise, the attention degree of the character is graded, and for the advertisement with a large number of people to be watched in a specific time and a high attention degree grade of the character, the advertisement is shown to meet the requirements of the user or meet the favor of the user, and the advertisement is successfully delivered, so that the advertisement is labeled, and the labeled advertisement information, the corresponding character characteristics and other information are transmitted to the analysis module, thereby facilitating the later data statistics and comprehensive screening of the preference of the user.
The eye recognition module tracks the direction of the eye's gaze by:
acquiring space coordinate data of a pupil center point and space coordinate data of an inner corner of an eye according to character image information;
step two, obtaining the coordinates(s) of the points concerned by the person on the image based on the mapping relation expected to be learned by the pupil-canthus method x ，s y ) The mapping relationship is as follows:
βf(p p ，p e )＝(s x ，s y )
wherein, f (p) p ，p e ) Is a mapping function; p is a radical of p Is the spatial coordinate data of the pupil center, p e Is the inner eyeAngular space coordinate data, beta is a posture coefficient when the head posture is changed, and the value of beta is 1 when the head posture is fixed; the mapping function can be selected in various ways according to the situation so as to meet different use environments;
step three, calculating the vector (v) of the pupil-eye corner x ，v y )＝p p -p e And fitting a real mapping relation according to a polynomial function to obtain:
wherein, a 0 ...a 11 The coefficients are determined by user calibration, which is performed according to individual characteristics of the user, and contain some individual differences, so that the user uses the calibration only once and for life.
And step four, evaluating the coordinate information of the point concerned by the person on the image obtained after mapping and the projection range of the launching screen 21, when the coordinate information falls into the expected range of the preset launching screen 21, confirming that the eyes of the person are tracking the advertisement on the launching screen 21, otherwise, evaluating that the eyes of the person are not tracking the advertisement on the launching screen 21.
The technical effect of the technical scheme is as follows: the eye gaze tracking technology is to track the eye movement by measuring the position of the fixation point of the eye or the movement of the eye relative to the head, and aims to monitor the eye movement and the fixation direction of a user when the user watches a specific target.
The analysis module 4 comprises a transmission transceiving unit 41, a conversion processing unit 42 and a reference comparison unit 43, wherein the output end of the transmission transceiving unit 41 is connected with the input end of the conversion processing unit 42; the transmitting and receiving unit 41 is configured to receive the crowd information acquired by the acquisition module 3 in real time, and feed back the received crowd information to the conversion processing unit 42; the output end of the conversion processing unit 42 is connected with the input end of the reference comparison unit 43;
the conversion processing unit 42 is used for converting the received crowd information into data information which can be automatically identified by the reference comparison unit 43; the reference comparison unit 43 is configured to perform reference comparison on the converted data information, and determine the identification information of the crowd information.
The transmitting and receiving unit 41 receives the crowd information acquired by the acquisition module 3 in real time, feeds the received crowd information back to the conversion processing unit 42, converts the received crowd information through the conversion processing unit 42 into data information which can be automatically identified by the reference comparison unit 43, and performs reference comparison on the converted data information through the reference comparison unit 43 to determine the identification information of the crowd information.
The reference alignment unit 43 further comprises
After the crowd information is converted, the crowd appearance and the crowd wearing information of the crowd collected in real time are compared according to the stored crowd appearance and the stored crowd wearing information, and therefore the identification information of the crowd is determined; after the identification information of the crowd is determined, the identification information of the crowd is completely transmitted to the dividing module 5, so that the dividing module 5 can conveniently divide the identity according to the identification information of the crowd. The dividing module 5 comprises a comprehensive evaluation unit 51 and an identity confirmation unit 52, wherein the output end of the comprehensive evaluation unit 51 is connected with the input end of the identity confirmation unit 52; the comprehensive evaluation unit 51 is configured to perform comprehensive evaluation on the determined identification information of the crowd, consider a plurality of factors, and feed back a result of the comprehensive evaluation to the identity confirmation unit 52; the identity confirmation unit 52 is used for performing identity confirmation of specific identities of the population after comprehensive evaluation, including children, teenagers, adolescents, middle-aged people or elderly people. After the comprehensive evaluation unit 51 comprehensively evaluates the identification information of the determined crowd, the comprehensive evaluation result is fed back to the identity confirmation unit 52, the identity confirmation unit 52 confirms the identity of the specific identity of the crowd after comprehensive evaluation, including children, teenagers, young adults, middle-aged adults or old people, corresponding advertisements are put in according to the identity confirmation, the watching requirements of different watching crowds can be met, and the comprehensive evaluation system has a wide market prospect. The index module 6 includes a bidirectional directing unit 61 and a call return unit 62, and the bidirectional directing unit 61 and the call return unit 62 are electrically connected in a bidirectional manner; the bidirectional guiding unit 61 is used for guiding and guiding the identified crowd to advertisements of corresponding specific crowd stored in the storage module 7; the call back unit 62 is used to call out the directed advertisement corresponding to the specific crowd and deliver the advertisement through the advertisement delivery screen 21.
The bidirectional guide unit 61 guides the people after identity confirmation to guide the advertisements of the corresponding specific people stored in the storage module 7, the return unit 62 is called to call the advertisements of the corresponding specific people, and the advertisements are released through the advertisement release screen 21.
And different crowd information collected in real time can be stored in the storage module 7, so that the information can be called in time next time, the advertisement putting speed is increased, and the advertisement putting efficiency is improved.
The storage module 7 includes storage units 71, and the plurality of storage units 71 respectively store specific advertisements of different crowds, and the specific advertisements are specifically designed and manufactured for the different crowds.
The advertisements are sorted according to a clustering mode, and the sorted advertisements are compressed, fused and stored in a specific storage unit 71.
Referring to fig. 6, in order to better show the intelligent advertisement delivery process of the intelligent advertisement delivery platform, the embodiment provides an intelligent advertisement delivery method of the intelligent advertisement delivery platform, which includes the following steps:
s1: the acquisition module 3 acquires the crowd information for watching the delivered advertisements in front of the advertisement delivery screen 21 in real time, and the analysis module 4 analyzes and processes the crowd information acquired in real time to determine the identification information of the crowd information;
s2: the dividing module 5 divides the identity of the determined identification information, determines the specific identity of the crowd information, indexes the determined specific identity through the index module 6, finds the specified advertisement of the specific identity stored in the storage module 7, and intelligently puts the specified advertisement on the advertisement putting screen 21.
To sum up, the intelligent advertisement delivery platform and the method thereof of the present invention, the collection module 3 collects the crowd information watching the delivered advertisement in front of the advertisement delivery screen 21 in real time, the analysis module 4 converts and compares the crowd information collected in real time, the crowd appearance and the crowd wearing information of the crowd collected in real time are compared with the stored crowd appearance and crowd wearing information, thereby determining the identification information of the crowd, the division module 5 performs comprehensive evaluation on the determined identification information and confirms the identity of the specific identity of the crowd after considering the multi-factors, the index module 6 indexes the determined specific identity, finds the specified advertisement of the specific identity stored in the storage module 7, calls the advertisement of the specific crowd correspondingly guided, and intelligently delivers the specified advertisement on the advertisement delivery screen 21, the corresponding advertisements can be released according to different watching crowds, the flexibility is good, the watching requirements of different watching crowds can be met, and the market prospect is wide.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (10)
1. An intelligent advertisement putting platform comprises an outer shell (1) and a face cover (2), and is characterized in that the face cover (2) is arranged on the outer shell (1), an advertisement putting screen (21) is embedded in the face cover (2), heat dissipation holes (11) and data transmission interfaces (12) are formed in the side face of the outer shell (1), and a plurality of data transmission interfaces (12) are regularly arranged above the heat dissipation holes (11);
the inner side of the outer shell (1) is provided with an acquisition module (3), an analysis module (4), a division module (5), an index module (6) and a storage module (7), wherein
The output end of the acquisition module (3) is electrically connected with the input end of the analysis module (4);
the acquisition module (3) is used for acquiring crowd information watching the delivered advertisements in front of the advertisement delivery screen (21) in real time and feeding the crowd information acquired in real time back to the analysis module (4);
the output end of the analysis module (4) is electrically connected with the input end of the dividing module (5);
the analysis module (4) is used for analyzing and processing the crowd information acquired in real time, determining the identification information of the crowd information and feeding the determined identification information back to the dividing module (5);
the output end of the dividing module (5) is electrically connected with the input end of the index module (6);
the dividing module (5) is used for carrying out identity division on the determined identification information, determining a specific identity of the crowd information, and feeding back the determined specific identity to the indexing module (6);
the output end of the index module (6) is electrically connected with the input end of the storage module (7);
the indexing module (6) is used for indexing the determined specific identity and searching for a specific advertisement of the specific identity stored in the storage module (7) for delivery;
the storage module (7) is used for storing advertisements corresponding to crowd information with different identities.
2. The intelligent advertising platform according to claim 1, wherein the acquisition module (3) comprises a high-definition camera (31), a smoke sensor (32) and an infrared sensor (33),
the high-definition camera (31) is used for acquiring the figure image information of people watching the advertisement before the advertisement putting screen (21) in real time and storing the figure image information in the memory;
the smoke sensor (32) is used for collecting whether smoke exists in front of the advertisement putting screen (21) in real time;
the infrared sensor (33) is used for sensing whether people exist in front of the advertisement putting screen (21) in real time.
3. The intelligent advertising delivery platform of claim 2, wherein the acquisition module further comprises:
the figure recognition module receives figure image information stored in the memory, extracts and recognizes the figure image information to confirm whether a figure actually exists or not, and extracts facial features to obtain face specific data when the figure actually exists;
the human eye recognition module receives the facial feature data, comprehensively analyzes the facial feature data, and obtains the human eye sight direction of the person so as to judge whether the human eyes watch the advertisement putting screen (21), the facial expression of the person and the muscle dragging condition of the face;
the attention degree acquisition module is used for acquiring attention degree information of a person when watching the advertisement, and judging the attention degree of the person when watching the advertisement on the advertisement putting screen (21) by combining facial expressions of the person, watching time in the same direction and limb movement;
and the attention degree scoring module is used for scoring attention degree information of the people, labeling advertisements which have a large number of people to watch and high attention degree score of the people in specific time, and transmitting advertisement content information, advertisement putting time information and corresponding crowd information corresponding to the labeling information to the analysis module (4).
4. The intelligent advertising platform according to claim 1, wherein the analysis module (4) comprises a transmission transceiver unit (41), a transformation processing unit (42) and a reference comparison unit (43),
the output end of the transmission transceiving unit (41) is connected with the input end of the conversion processing unit (42);
the transmitting and receiving unit (41) is used for receiving the crowd information acquired by the acquisition module (3) in real time and feeding back the received crowd information to the conversion processing unit (42);
the output end of the conversion processing unit (42) is connected with the input end of the reference comparison unit (43);
the conversion processing unit (42) is used for converting the received crowd information into data information which can be automatically identified by the reference comparison unit (43);
the reference comparison unit (43) is used for performing reference comparison on the data information after the conversion processing to determine the identification information of the crowd information;
the reference comparison unit (43) further comprises
After the crowd information is converted, the crowd appearance and the crowd wearing information of the crowd collected in real time are compared according to the stored crowd appearance and the stored crowd wearing information, and therefore the identification information of the crowd is determined;
after the identification information of the crowd is determined, the identification information of the crowd is completely transmitted to the dividing module (5), and the dividing module (5) is convenient to divide the identity according to the identification information of the crowd.
5. An intelligent advertising platform according to claim 1, wherein the partitioning module (5) comprises a comprehensive evaluation unit (51) and an identity confirmation unit (52),
the output end of the comprehensive evaluation unit (51) is connected with the input end of the identity confirmation unit (52);
the comprehensive evaluation unit (51) is used for comprehensively evaluating the determined identification information of the crowd, considering multi-party factors and feeding back the comprehensive evaluation result to the identity confirmation unit (52);
the identity confirmation unit (52) is used for carrying out identity confirmation of specific identities of the people group after comprehensive evaluation, wherein the identities of the people group comprise children, teenagers, middle-aged people or elderly people.
6. An intelligent advertising platform according to claim 1, wherein the index module (6) comprises a bidirectional direction unit (61) and a call return unit (62),
the bidirectional guide unit (61) is electrically connected with the call return unit (62) in a bidirectional way;
the bidirectional guiding unit (61) is used for guiding and guiding the people after identity confirmation to guide the people to advertisements of corresponding specific people stored in the storage module (7);
the call back unit (62) is used for calling out the directed advertisements corresponding to the specific crowd and delivering the advertisements through the advertisement delivery screen (21).
7. The intelligent advertising platform according to claim 1, wherein the storage module (7) comprises storage units (71), and a plurality of the storage units (71) respectively store specific advertisements of different crowds, and the specific advertisements are specifically designed and manufactured for different crowds.
8. The intelligent advertising platform according to claim 7, wherein the advertisements are sorted in a clustering manner, and the sorted advertisements are compressed and fused and then stored in a specific storage unit (71).
9. The intelligent advertising platform according to claim 3, wherein the eye recognition module tracks the direction of the eye's gaze by:
acquiring space coordinate data of a pupil center point and space coordinate data of an inner corner of an eye according to character image information;
step two, obtaining the coordinates(s) of the points concerned by the person on the image based on the mapping relation expected to be learned by the pupil-canthus method x ，s y ) The mapping relationship is as follows:
βf(p p ，p e )＝(s x ，s y )
wherein, f (p) p ，p e ) Is a mapping function; p is a radical of p Is the spatial coordinate data of the pupil center, p e Is the inner corner of the eye space coordinate data, and beta is the posture when the head posture changesA coefficient, β being a value of 1 when the head pose is fixed;
step three, calculating the vector (v) of the pupil-eye corner x ，v y )＝p p -p e And fitting a real mapping relation according to a polynomial function to obtain:
wherein, a 0 ...a 11 The learning coefficient is determined by user calibration, and calibration is carried out according to individual characteristics of the user;
and step four, evaluating the coordinate information of the point concerned by the person on the image obtained after mapping and the projection range of the projection screen (21), when the coordinate information falls into the expected range of the preset projection screen (21), confirming that the eye sight is used for tracking the advertisement on the projection screen (21), otherwise, evaluating that the eye sight is not used for tracking the advertisement on the projection screen (21).
10. An intelligent advertisement delivery method of the intelligent advertisement delivery platform according to any one of claims 1 to 9, comprising the steps of:
s1: the acquisition module (3) acquires crowd information for watching the delivered advertisements in front of the advertisement delivery screen (21) in real time, and the analysis module (4) analyzes and processes the crowd information acquired in real time to determine the identification information of the crowd information;
s2: the dividing module (5) is used for carrying out identity division on the determined identification information, determining the specific identity of the crowd information, indexing the determined specific identity through the indexing module (6), searching the specified advertisement of the specific identity stored in the storage module (7), and intelligently delivering the specified advertisement on the advertisement delivery screen (21).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591521.3A CN114973954A (en) | 2022-05-28 | 2022-05-28 | Intelligent advertisement putting platform and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591521.3A CN114973954A (en) | 2022-05-28 | 2022-05-28 | Intelligent advertisement putting platform and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114973954A true CN114973954A (en) | 2022-08-30 |
Family
ID=82957050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210591521.3A Withdrawn CN114973954A (en) | 2022-05-28 | 2022-05-28 | Intelligent advertisement putting platform and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114973954A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829655A (en) * | 2022-12-30 | 2023-03-21 | 广州掌购网络科技有限公司 | Advertisement effect intelligent analysis management system and method based on big data analysis |
| CN117408760A (en) * | 2023-12-14 | 2024-01-16 | 成都亚度克升科技有限公司 | Picture display method and system based on artificial intelligence |
-
2022
- 2022-05-28 CN CN202210591521.3A patent/CN114973954A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829655A (en) * | 2022-12-30 | 2023-03-21 | 广州掌购网络科技有限公司 | Advertisement effect intelligent analysis management system and method based on big data analysis |
| CN115829655B (en) * | 2022-12-30 | 2023-09-22 | 广州掌购网络科技有限公司 | Advertisement effect intelligent analysis management system and method based on big data analysis |
| CN117408760A (en) * | 2023-12-14 | 2024-01-16 | 成都亚度克升科技有限公司 | Picture display method and system based on artificial intelligence |
| CN117408760B (en) * | 2023-12-14 | 2024-02-27 | 成都亚度克升科技有限公司 | Picture display method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114973954A (en) | Intelligent advertisement putting platform and method thereof | |
| CN104157107B (en) | A kind of human posture's apparatus for correcting based on Kinect sensor | |
| CN201242756Y (en) | Human face recognition device | |
| CN104598869A (en) | Intelligent advertisement pushing method based on human face recognition device | |
| CN109361865A (en) | A kind of image pickup method and terminal | |
| CN104820495B (en) | A kind of micro- Expression Recognition of exception and based reminding method and device | |
| CN112666705A (en) | Eye movement tracking device and eye movement tracking method | |
| CN107358175A (en) | Method for collecting iris and electronic installation | |
| CN112818722A (en) | Modular dynamically configurable living body face recognition system | |
| CN108401129A (en) | Video call method, device, terminal based on Wearable and storage medium | |
| CN109961039A (en) | A kind of individual's goal video method for catching and system | |
| CN208351494U (en) | Face identification system | |
| CN114255508A (en) | OpenPose-based student posture detection analysis and efficiency evaluation method | |
| CN201233607Y (en) | Human face recognition device | |
| CN111178172A (en) | Laboratory mouse sniffing action recognition method, module and system | |
| CN112733608A (en) | Curling player posture detection and action analysis system | |
| CN201467351U (en) | Television audience rating statistical device based on human face detection | |
| CN204790850U (en) | Unusual little expression discernment and reminding device | |
| CN110321782A (en) | A kind of system detecting characteristics of human body's signal | |
| Yang et al. | vGaze: Implicit saliency-aware calibration for continuous gaze tracking on mobile devices | |
| CN202033766U (en) | Reflection-type finger vein characteristic acquisition device | |
| CN111680608B (en) | Intelligent sports auxiliary training system and training method based on video analysis | |
| CN210721506U (en) | Dynamic face recognition terminal based on 3D camera | |
| CN113066264A (en) | Fatigue state identification method and desk lamp | |
| CN213155816U (en) | Eye movement instrument |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220830 |
|
| WW01 | Invention patent application withdrawn after publication |