CN117436953B - Advertisement delivery management system and method based on data analysis - Google Patents
Advertisement delivery management system and method based on data analysis Download PDFInfo
- Publication number
- CN117436953B CN117436953B CN202311380436.3A CN202311380436A CN117436953B CN 117436953 B CN117436953 B CN 117436953B CN 202311380436 A CN202311380436 A CN 202311380436A CN 117436953 B CN117436953 B CN 117436953B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- elevator
- personnel
- target
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06V40/172—Classification, e.g. identification
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Accounting & Taxation (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The invention discloses an advertisement putting management system and method based on data analysis, and belongs to the technical field of advertisement putting. The system comprises a data acquisition and preprocessing module, a personnel identification and feature extraction module, a target personnel screening and identification module, a historical advertisement data analysis module, an advertisement putting suggestion generation module and a real-time advertisement effect evaluation and prompting module; the data acquisition and preprocessing module acquires the number of elevators in a target area and acquires image data of personnel in the elevators; the personnel identification and feature extraction module is used for extracting feature vectors; the target person screening and identifying module is used for screening target persons and identifying the target persons; the historical advertisement data analysis module is used for analyzing historical advertisement data; the advertisement putting suggestion generation module generates advertisement putting suggestions applicable to the target area; and the real-time advertisement effect evaluation and prompt module outputs corresponding prompt information according to the evaluation result.
Description
Technical Field
The invention relates to the technical field of advertisement delivery, in particular to an advertisement delivery management system and method based on data analysis.
Background
With the development of society, advertisements are in more and more scenes, and the advertisement exposure rate is greatly improved and the sales rate of promotion products is also improved by playing the advertisements on the elevator display screen, so that the importance of advertisement putting management on the elevator display screen is embodied.
At present, the advertisement putting management of the elevator display screen mainly selects advertisements randomly for putting, lacks pertinence to a certain extent, has certain defects, and is specifically embodied in the following layers: random placement of advertisements may not meet their particular goals and needs for advertisers who typically wish to present advertisements in front of particular times, places, and groups of people in order to better convey information and promote products, which may not provide such accurate and customized advertising; for advertisement companies often need to examine in the field before advertisement is put, know the environment and user group where the elevator is located, which needs to spend manpower resources and increase cost, and the advertisement can not be put by randomly selecting the advertisement, so that the putting resources can not be effectively utilized, and the demands of the advertisement companies and the advertisement companies can not be met.
Disclosure of Invention
The invention aims to provide an advertisement delivery management system and method based on data analysis, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
an advertisement delivery management method based on data analysis, the method comprises the following steps:
S100, acquiring the number of elevators in a target area, and numbering each elevator; then, the cameras of the elevators in the target area are utilized to collect images of the personnel in the elevators;
S200, analyzing images acquired by each elevator in a target area to obtain target personnel;
S300, aiming at historical advertisement data put in a target area, calculating the attention degree of target personnel in the target area to the type of the historical advertisement, and obtaining attention differences of different target areas to advertisements of the same type;
S400, calculating historical advertisement browsing quantity corresponding to a target area according to average times of each elevator in the target area for each target person to enter and exit every day; combining the historical advertisement browsing amount corresponding to the target area and the attention degree of the target personnel to the type of the historical advertisement, and outputting corresponding putting suggestions;
S500, acquiring real-time advertisement data put in a target area, evaluating the effect of target personnel in the target area on the real-time advertisement put in, and outputting corresponding prompt information according to the evaluation result.
Further, step S200 includes:
S201, acquiring image data collected by elevators in each target area in a selected period, respectively carrying out face recognition, and aiming at personnel data identified by each elevator, forming an elevator personnel set A, wherein A= { a 1,a2,...,am }, a 1 represents personnel data of a first elevator, a 2 represents personnel data of a second elevator, a i represents personnel data of an i-th elevator, and i is less than or equal to m;
S202, recording personnel image data of an elevator in a selected period for each element of an elevator personnel set A, and marking the acquisition time for each personnel image data; for each elevator, carrying out face recognition on the personnel image data of all the elevators in the selected period, taking the personnel image data of the first elevator in the selected period as template data, and taking the personnel image data except the first elevator as data to be matched; similarity calculation is carried out on each piece of personnel image data of the template data and the data to be matched, and a specific calculation formula is as follows:
wherein a and b respectively represent two face feature vectors;
When the similarity is within a similarity threshold interval B and the acquisition time is different, classifying the image data into an elevator personnel; when the similarity is beyond the similarity threshold interval B and the image data matched with the similarity threshold interval B cannot be found, classifying the image data into template data, and continuing to calculate the similarity of the next round; until all elevator personnel image data in the selected period are matched, marking, namely an elevator personnel 1 and an elevator personnel 2 in sequence; and b= [ c, d ], c and d are respectively the minimum and maximum values of the similarity threshold interval;
s203, counting the times Q of the entrance and exit of each elevator personnel for each target area, and selecting the elevator personnel with the times Q of the entrance and exit being more than or equal to a threshold value Q as target personnel. The number of times of entering and exiting each elevator person is counted to find out the person who frequently uses the elevator in the target area, and potential persons for watching advertisements in the target area can be determined, so that advertisement delivery can be carried out more specifically.
Further, step S300 includes:
S301, recording the gazing time length of a target person on an elevator display screen and the position data of the target person by using a camera of each elevator according to the historical data; the historical data is that an advertising company puts historical advertisements on elevator display screens of all target areas, and each advertisement is independently and continuously put for the same days;
s302, calculating the watching coefficient of each elevator target person for each historical advertisement type according to the watching duration of the target person for the elevator display screen, wherein the specific formula is as follows:
J represents the number corresponding to the target person of each elevator, and j is an integer from 1 to p; t represents the number of advertisement strips corresponding to each historical advertisement type, and t is an integer from 1 to x; t jt represents the gazing time length of the jth target person on the T historical advertisement; t is the average value of the gazing time length of all elevator personnel in the selected period;
According to the position data of the target personnel, calculating the position coefficient of the target personnel playing each historical advertisement type by each elevator, wherein the specific formula is as follows:
N jt represents the distance between the jth target person and the elevator display screen when the jth historical advertisement is played, and the calculation process of N jt is as follows: firstly, taking the bottom of an elevator as an xoy plane, and respectively projecting the positions of an elevator display screen and a target person onto the xoy plane; taking an elevator projection side where an elevator display screen is projected as a y axis, taking two endpoints of the elevator display screen projection as horizontal lines perpendicular to the y axis, and selecting the elevator projection side closest to the horizontal lines as an x axis, wherein the intersection point of the x axis and the y axis is the origin of coordinates; recording projection coordinates of the jth target person, and obtaining N jt according to a distance formula; and N represents the maximum distance from the origin of coordinates; calculating the distance between the target person and the elevator display screen when the historical advertisement is played, and reflecting the possibility that the target person receives the advertisement, namely, the closer the distance between the target person and the elevator display screen is, the greater the possibility that the target person receives the advertisement is, the greater the influence of receiving the advertisement is, so that the better the advertisement putting effect is;
S303, calculating the attention gamma of all target areas to each historical advertisement type according to the watching coefficient of each elevator target person to each historical advertisement type and the position coefficient of each elevator target person playing each historical advertisement type, wherein the specific formula is as follows: Wherein α i represents the viewing coefficient of the target person of the ith elevator for each history advertisement type, and β i represents the position coefficient of the target person of the ith elevator playing each history advertisement type;
And comparing the attention degree of different target areas to the same historical advertisement types according to the calculation result, thereby obtaining the attention degree difference of different target areas to each historical advertisement type. The difference of the attention degree can be found by comparing the attention degree of the same historical advertisement type between the target areas, so that the areas which are more suitable for putting the advertisement of the specific type can be determined; this helps optimize the advertisement placement strategy, place the advertisement in the target area with the most attractive and interesting degree, and improve the effect and influence of the advertisement.
Further, step S400 includes:
s401, counting the times of entering and exiting of target personnel in a selected period for each elevator in each target area; the number of times of getting in and out of the elevator by the target person is q, the number of days of the selected period is d, and the average number of times of getting in and out of the target person per day is w: w=q/d;
s402, obtaining a historical advertisement browsing amount L corresponding to a target area according to the watching coefficient of target personnel of each elevator to each historical advertisement type and average number of times w of entering and exiting of the target personnel every day, and Wherein w i represents the average number of target person in and out per day for the ith elevator;
S403, obtaining attention degree difference results of different target areas in the step S303 on each historical advertisement type, and dividing the historical advertisement types; when the attention degrees of the same historical advertisement types in different target areas are different, outputting corresponding delivery suggestions, namely dividing the historical advertisement types into target areas with the largest attention degrees; when the attention of the same type of historical advertisement in different target areas is the same, outputting corresponding putting suggestions, namely dividing the same type of historical advertisement into corresponding proportions according to the size of the historical advertisement browsing amount corresponding to the target areas; therefore, advertisement resources can be reasonably distributed according to the attention degree and the browsing amount, and the advertisement can be properly exposed and focused in each target area.
Further, step S500 includes:
S501, according to the advertisement putting scheme of the target area provided in the step S403, putting real-time advertisements, and obtaining real-time advertisement data put in the target area, namely, the watching time length of target personnel on the elevator display screen;
s502, calculating the watching coefficient of target personnel in a target area for each type of advertisement Associating the calculated results with historical advertisement viewing coefficients of the same typeComparing; if it isIf the effect of real-time advertisement delivery is not as expected, outputting a corresponding prompt signal, namely 'the watching coefficient is lower than the historical average level, please further analyze the reason'; if it isThe effect of the real-time advertisement in the target area exceeds the historical advertisement, the putting suggestion can be continuously utilized to obtain a better advertisement effect, and a corresponding prompt signal is output, namely 'good putting effect, please keep continuously'.
The advertisement putting management system based on the data analysis comprises a data acquisition and preprocessing module, a personnel identification and feature extraction module, a target personnel screening and identification module, a historical advertisement data analysis module, an advertisement putting suggestion generation module and a real-time advertisement effect evaluation and prompting module;
The data acquisition and preprocessing module acquires the number of the elevators in the target area and numbers the elevators, and acquires the image data of the personnel in the elevators; the personnel identification and feature extraction module is used for carrying out face recognition on the collected image data and extracting feature vectors of the face; the target person screening and identifying module screens out target persons according to the threshold value Q of the times of entering and exiting and the threshold value interval B of the similarity, and identifies the target persons; the historical advertisement data analysis module puts historical advertisements on elevator display screens in a target area, records the watching time length and position data of target personnel on the advertisements, and calculates the watching coefficient and position coefficient of each elevator on each type of historical advertisements; the advertisement putting suggestion generation module combines the number of times of entering and exiting of the target person and the historical advertisement attention degree to generate an advertisement putting scheme suitable for the target area; the real-time advertisement effect evaluation and prompting module evaluates the watching effect of the target personnel on the advertisement according to the real-time advertisement data, and outputs corresponding prompting information according to the evaluation result.
Further, the data acquisition and preprocessing module comprises an elevator quantity acquisition and numbering unit, a personnel image acquisition unit and a data preprocessing unit;
the elevator number and numbering unit is responsible for acquiring and numbering the elevator number of the target area; the personnel image collecting unit is responsible for collecting image data of personnel in the elevator; the data preprocessing unit preprocesses the collected image data;
the personnel identification and feature extraction module comprises a face identification unit, a feature extraction unit and a face matching unit;
The face recognition unit recognizes the face in the image by using a face recognition technology; the feature extraction unit extracts feature vectors from the identified faces; the face matching unit calculates a similarity based on the feature vector, thereby performing face matching.
Further, the target personnel screening and identifying module comprises a personnel screening unit and a personnel identifying unit;
The personnel screening unit screens out target personnel according to the set threshold value Q; the personnel identification unit carries out identification based on the result of the personnel screening unit;
The historical advertisement data analysis module comprises a viewing time length statistics unit, a position data statistics unit, a viewing coefficient calculation unit and a position coefficient calculation unit;
The watching time length statistics unit is used for counting the watching time length of the target person on the advertisement; the position data statistics unit is used for counting the position data of the target personnel; the watching coefficient calculating unit calculates the watching coefficient of each elevator for each historical advertisement type; the position coefficient calculating unit calculates the position coefficient of the target person playing each historical advertisement type by each elevator.
Further, the advertisement putting proposal generating module comprises an in-out frequency counting unit, an advertisement attention calculating unit and an advertisement putting proposal generating unit;
The time counting unit is used for counting the time of the target person entering the elevator; the advertisement attention calculating unit is used for calculating unit attention of each historical advertisement type under different target areas according to the calculation results of the watching coefficient calculating unit and the position coefficient calculating unit; the advertisement delivery scheme generating unit calculates advertisement browsing amounts of different target areas based on the number of times of entering and exiting counting unit, and generates advertisement delivery schemes of different target areas by combining the advertisement attention calculating unit;
The real-time advertisement effect evaluation and prompting module comprises a real-time advertisement data acquisition unit, an advertisement effect evaluation unit and an advertisement putting prompting unit;
the real-time advertisement data acquisition unit is used for acquiring advertisement data in real time; the advertisement effect evaluation unit evaluates the effect of the advertisement putting unit; and the advertisement putting prompting unit outputs corresponding prompting information according to the result of the advertisement effect evaluation unit.
Compared with the prior art, the invention has the following beneficial effects: the target personnel can be accurately identified through data analysis and personnel identification technology, so that accurate positioning of advertisement delivery is realized; through analysis of historical advertisement delivery data, the attention degree of target personnel to different types of advertisements can be known, and references are provided for formulating a more effective advertisement delivery scheme; combining factors such as the times of entering and exiting of target personnel, historical advertisement attention, and the like, generating advertisement putting suggestions applicable to a target area, thereby improving the efficiency and accuracy of advertisement putting; the intelligent information collection system also plays a role in intelligent information collection, reduces the work of the advertising company for carrying out field investigation on the target area, can automatically obtain the difference of the attention degree of different areas to the same advertising type through the system, and saves the cost of the advertising company; through the advertisement data that gathers in real time, can in time evaluate the effect of target personnel to real-time advertisement delivery to in time output corresponding prompt message, promote advertising effect.
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 an advertisement delivery management method based on data analysis according to 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.
Referring to fig. 1, the present invention provides the following technical solutions:
an advertisement delivery management method based on data analysis, the method comprises the following steps:
S100, acquiring the number of elevators in a target area, and numbering each elevator; then, the cameras of the elevators in the target area are utilized to collect images of the personnel in the elevators;
S200, analyzing images acquired by each elevator in a target area to obtain target personnel;
S201, acquiring image data collected by elevators in each target area in a selected period, respectively carrying out face recognition, and aiming at personnel data identified by each elevator, forming an elevator personnel set A, wherein A= { a 1,a2,...,am }, a 1 represents personnel data of a first elevator, a 2 represents personnel data of a second elevator, a i represents personnel data of an i-th elevator, and i is less than or equal to m;
S202, recording personnel image data of an elevator in a selected period for each element of an elevator personnel set A, and marking the acquisition time for each personnel image data; for each elevator, carrying out face recognition on the personnel image data of all the elevators in the selected period, taking the personnel image data of the first elevator in the selected period as template data, and taking the personnel image data except the first elevator as data to be matched; similarity calculation is carried out on each piece of personnel image data of the template data and the data to be matched, and a specific calculation formula is as follows:
wherein a and b respectively represent two face feature vectors;
When the similarity is within a similarity threshold interval B and the acquisition time is different, classifying the image data into an elevator personnel; when the similarity is beyond the similarity threshold interval B and the image data matched with the similarity threshold interval B cannot be found, classifying the image data into template data, and continuing to calculate the similarity of the next round; until all elevator personnel image data in the selected period are matched, marking, namely an elevator personnel 1 and an elevator personnel 2 in sequence; and b= [ c, d ], c and d are respectively the minimum and maximum values of the similarity threshold interval;
s203, counting the times Q of the entrance and exit of each elevator personnel for each target area, and selecting the elevator personnel with the times Q of the entrance and exit being more than or equal to a threshold value Q as target personnel. The number of times of entering and exiting each elevator person is counted to find out the person who frequently uses the elevator in the target area, and potential persons for watching advertisements in the target area can be determined, so that advertisement delivery can be carried out more specifically.
In the embodiment, it is assumed that a target area exists, image data of 3 elevators are acquired in a selected period, face recognition is performed, and an elevator personnel set A= { a 1,a2,a3 };
For personnel data for each elevator we have:
Personnel data a 1 of the first elevator= [ image data 1, image data 2, image data 3, ]
Personnel data a 2 of the second elevator= [ image data 1, image data 2, image data 3, ]
Personnel data a 3 of the third elevator= [ image data 1, image data 2, image data 3, ]
The image data comprises face feature vectors, acquisition time and other information.
Next, similarity calculation is performed on each of the person image data; for example, image data 1 and image data 2 are selected for similarity calculation;
Setting a similarity threshold interval b= [0.8,1.0] according to the similarity calculation result, wherein the image data with the similarity between 0.8 and 1.0 is considered to be the same person, and if the similarity is in the interval, the image data are marked as the same elevator person; assuming that the similarity between image data 1 and image data 2 is 0.9 in the person data of the first elevator, they are marked as the same elevator person within the threshold interval B.
Finally, counting the times Q of the entrance and exit of each elevator target person in each target area, and selecting the elevator person with the entrance and exit times greater than or equal to a threshold value Q as the target person, so that the person with the elevator frequently used in the target area can be determined, and the person can be used as the target person for potential advertisement watching.
S300, aiming at historical advertisement data put in a target area, calculating the attention degree of target personnel in the target area to the type of the historical advertisement, and obtaining attention differences of different target areas to advertisements of the same type;
S301, recording the gazing time length of a target person on an elevator display screen and the position data of the target person by using a camera of each elevator according to the historical data; the historical data is that an advertising company puts historical advertisements on elevator display screens of all target areas, and each advertisement is independently and continuously put for the same days;
s302, calculating the watching coefficient of each elevator target person for each historical advertisement type according to the watching duration of the target person for the elevator display screen, wherein the specific formula is as follows:
J represents the number corresponding to the target person of each elevator, and j is an integer from 1 to p; t represents the number of advertisement strips corresponding to each historical advertisement type, and t is an integer from 1 to x; t jt represents the gazing time length of the jth target person on the T historical advertisement; t is the average value of the gazing time length of all elevator personnel in the selected period;
According to the position data of the target personnel, calculating the position coefficient of the target personnel playing each historical advertisement type by each elevator, wherein the specific formula is as follows:
N jt represents the distance between the jth target person and the elevator display screen when the jth historical advertisement is played, and the calculation process of N jt is as follows: firstly, taking the bottom of an elevator as an xoy plane, and respectively projecting the positions of an elevator display screen and a target person onto the xoy plane; taking an elevator projection side where an elevator display screen is projected as a y axis, taking two endpoints of the elevator display screen projection as horizontal lines perpendicular to the y axis, and selecting the elevator projection side closest to the horizontal lines as an x axis, wherein the intersection point of the x axis and the y axis is the origin of coordinates; recording projection coordinates of the jth target person, and obtaining N jt according to a distance formula; and N represents the maximum distance from the origin of coordinates; calculating the distance between the target person and the elevator display screen when the historical advertisement is played, and reflecting the possibility that the target person receives the advertisement, namely, the closer the distance between the target person and the elevator display screen is, the greater the possibility that the target person receives the advertisement is, the greater the influence of receiving the advertisement is, so that the better the advertisement putting effect is;
S303, calculating the attention gamma of all target areas to each historical advertisement type according to the watching coefficient of each elevator target person to each historical advertisement type and the position coefficient of each elevator target person playing each historical advertisement type, wherein the specific formula is as follows: Wherein α i represents the viewing coefficient of the target person of the ith elevator for each history advertisement type, and β i represents the position coefficient of the target person of the ith elevator playing each history advertisement type;
And comparing the attention degree of different target areas to the same historical advertisement types according to the calculation result, thereby obtaining the attention degree difference of different target areas to each historical advertisement type. The difference of the attention degree can be found by comparing the attention degree of the same historical advertisement type between the target areas, so that the areas which are more suitable for putting the advertisement of the specific type can be determined; this helps optimize the advertisement placement strategy, place the advertisement in the target area with the most attractive and interesting degree, and improve the effect and influence of the advertisement.
In this embodiment, it is assumed that there are two target areas, namely, an area a and an area B, and there are 4 advertisement types in the history advertisement data, namely, an advertisement type 1, an advertisement type 2, an advertisement type 3, and an advertisement type 4;
The number of elevators in the target area A is 3, and the number of the elevators is A1, A2 and A3; the number of elevators in the target area B is 2, and the number of elevators is B1 and B2;
Assume that target area A has 10 target persons, numbered A001 to A010; assuming that the target area B has 8 target persons, the numbers are B001 to B008;
Number of advertisement bars for each type of advertisement in target area a: assume that there are 1 history advertisement for each advertisement type; preset advertisement standard gazing duration: assume 5 seconds;
Target person gazing time length for elevator A1 of target area a:
advertisement type 1: [3,6,5,4,2,5,7,4,3,6];
advertisement type 2: [4,3,5,6,7,2,4,5,6,3];
Advertisement type 3: [7,3,6,5,4,2,7,4,6,3];
Advertisement type 4: [5,4,6,3,7,2,5,4,6,3].
For elevator A1 of target area a, a viewing coefficient α is calculated:
α1＝[(1/10)*(3+6+5+4+2+5+7+4+3+6)]/5；
α2＝[(1/10)*(4+3+5+6+7+2+4+5+6+3)]/5；
α3＝[(1/10)*(7+3+6+5+4+2+7+4+6+3)]/5；
α4＝[(1/10)*(5+4+6+3+7+2+5+4+6+3)]/5。
Calculating the viewing coefficients of other elevators and advertisement types in the same way; the same applies to the calculation of the position coefficients.
Attention gamma for region a for each historical advertisement type:
γ1＝(α1+α2+α3+α4)+((1-β1)+(1-β2)+(1-β3)+(1-β4))；
And finally, comparing the attention gamma of different target areas to the same historical advertisement type, and obtaining the attention difference of different target areas to each historical advertisement type.
S400, calculating historical advertisement browsing quantity corresponding to a target area according to average times of each elevator in the target area for each target person to enter and exit every day; combining the historical advertisement browsing amount corresponding to the target area and the attention degree of the target personnel to the historical advertisement type to generate an advertisement putting scheme suitable for the target area;
s401, counting the times of entering and exiting of target personnel in a selected period for each elevator in each target area; the number of times of getting in and out of the elevator by the target person is q, the number of days of the selected period is d, and the average number of times of getting in and out of the target person per day is w: w=q/d;
s402, obtaining a historical advertisement browsing amount L corresponding to a target area according to the watching coefficient of target personnel of each elevator to each historical advertisement type and average number of times w of entering and exiting of the target personnel every day, and Wherein w i represents the average number of target person in and out per day for the ith elevator;
S403, obtaining attention degree difference results of different target areas in the step S303 on each historical advertisement type, and dividing the historical advertisement types; when the attention degrees of the same historical advertisement types in different target areas are different, outputting corresponding delivery suggestions, namely dividing the historical advertisement types into target areas with the largest attention degrees; when the attention of the same type of historical advertisement in different target areas is the same, outputting corresponding putting suggestions, namely dividing the same type of historical advertisement into corresponding proportions according to the size of the historical advertisement browsing amount corresponding to the target areas; therefore, advertisement resources can be reasonably distributed according to the attention degree and the browsing amount, and the advertisement can be properly exposed and focused in each target area.
S500, acquiring real-time advertisement data put in a target area, evaluating the effect of target personnel in the target area on real-time advertisement putting, and adjusting and optimizing an advertisement putting scheme according to the evaluation result.
S501, according to the advertisement putting scheme of the target area provided in the step S403, putting real-time advertisements, and obtaining real-time advertisement data put in the target area, namely, the watching time length of target personnel on the elevator display screen;
s502, calculating the watching coefficient of target personnel in a target area for each type of advertisement Associating the calculated results with historical advertisement viewing coefficients of the same typeComparing; if it is If the effect of real-time advertisement delivery is not as expected, outputting a corresponding prompt signal, namely 'the watching coefficient is lower than the historical average level, please further analyze the reason'; if it isThe effect of the real-time advertisement in the target area exceeds the historical advertisement, the putting suggestion can be continuously utilized to obtain a better advertisement effect, and a corresponding prompt signal is output, namely 'good putting effect, please keep continuously'.
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 (7)
1. An advertisement delivery management method based on data analysis is characterized in that: the method comprises the following steps:
S100, acquiring the number of elevators in a target area, and numbering each elevator; then, the cameras of the elevators in the target area are utilized to collect images of the personnel in the elevators;
S200, analyzing images acquired by each elevator in a target area to obtain target personnel;
The step S200 includes:
S201, acquiring elevator numbers of the step S100, wherein the numbers are 1,2, n; acquiring image data collected by elevators in each target area in a selected period, respectively carrying out face recognition, and aiming at personnel data identified by each elevator, forming an elevator personnel set A, wherein A= { a 1,a2,...,am }, a 1 represents personnel data of a first elevator, a 2 represents personnel data of a second elevator, a i represents personnel data of an ith elevator, and i is less than or equal to m;
S202, recording personnel image data of an elevator in a selected period for each element of an elevator personnel set A, and marking the acquisition time for each personnel image data; for each elevator, carrying out face recognition on the personnel image data of all the elevators in the selected period, taking the personnel image data of the first elevator in the selected period as template data, and taking the personnel image data except the first elevator as data to be matched; similarity calculation is carried out on each piece of personnel image data of the template data and the data to be matched, and a specific calculation formula is as follows:
wherein a and b respectively represent two face feature vectors;
When the similarity is within a similarity threshold interval B and the acquisition time is different, classifying the image data into an elevator personnel; when the similarity is beyond the similarity threshold interval B and the image data matched with the similarity threshold interval B cannot be found, classifying the image data into template data, and continuing to calculate the similarity of the next round; until all elevator personnel image data in the selected period are matched, marking, namely an elevator personnel 1 and an elevator personnel 2 in sequence; and b= [ c, d ], c and d are respectively the minimum and maximum values of the similarity threshold interval;
S203, counting the times Q of the entrance and the exit of each elevator personnel for each target area, and selecting the elevator personnel with the times Q of the entrance and the exit being more than or equal to a threshold value Q as target personnel;
S300, aiming at historical advertisement data put in a target area, calculating the attention degree of target personnel in the target area to the type of the historical advertisement, and obtaining attention differences of different target areas to advertisements of the same type;
The step S300 includes:
s301, recording the gazing time length of a target person on an elevator display screen and the position data of the target person by using a camera of each elevator according to the historical data;
s302, calculating the watching coefficient of each elevator target person for each historical advertisement type according to the watching duration of the target person for the elevator display screen, wherein the specific formula is as follows:
J represents the number corresponding to the target person of each elevator, and j is an integer from 1 to p; t represents the number of advertisement strips corresponding to each historical advertisement type, and t is an integer from 1 to x; t jt represents the gazing time length of the jth target person on the T historical advertisement; t is the average value of the gazing time length of all elevator personnel in the selected period;
According to the position data of the target personnel, calculating the position coefficient of the target personnel playing each historical advertisement type by each elevator, wherein the specific formula is as follows:
N jt represents the distance between the jth target person and the elevator display screen when the jth historical advertisement is played, and the calculation process of N jt is as follows: firstly, taking the bottom of an elevator as an xoy plane, and respectively projecting the positions of an elevator display screen and a target person onto the xoy plane; taking an elevator projection side where an elevator display screen is projected as a y axis, taking two endpoints of the elevator display screen projection as horizontal lines perpendicular to the y axis, and selecting the elevator projection side closest to the horizontal lines as an x axis, wherein the intersection point of the x axis and the y axis is the origin of coordinates; recording projection coordinates of the jth target person, and obtaining N jt according to a distance formula; and N represents the maximum distance from the origin of coordinates;
S303, calculating the attention gamma of all target areas to each historical advertisement type according to the watching coefficient of each elevator target person to each historical advertisement type and the position coefficient of each elevator target person playing each historical advertisement type, wherein the specific formula is as follows: Wherein α i represents the viewing coefficient of the target person of the ith elevator for each history advertisement type, and β i represents the position coefficient of the target person of the ith elevator playing each history advertisement type;
According to the calculation result, comparing the attention degree of different target areas to the same historical advertisement type, so as to obtain the attention degree difference of different target areas to each historical advertisement type;
S400, calculating historical advertisement browsing quantity corresponding to a target area according to average times of each elevator in the target area for each target person to enter and exit every day; combining the historical advertisement browsing amount corresponding to the target area and the attention degree of the target personnel to the type of the historical advertisement, and outputting corresponding putting suggestions;
S500, acquiring real-time advertisement data put in a target area, evaluating the effect of target personnel in the target area on the real-time advertisement put in, and outputting corresponding prompt information according to the evaluation result.
2. The advertising management method based on data analysis of claim 1, wherein: the step S400 includes:
s401, counting the times of entering and exiting of target personnel in a selected period for each elevator in each target area; the number of times of getting in and out of the elevator by the target person is q, the number of days of the selected period is d, and the average number of times of getting in and out of the target person per day is w: w=q/d;
s402, obtaining a historical advertisement browsing amount L corresponding to a target area according to the watching coefficient of target personnel of each elevator to each historical advertisement type and average number of times w of entering and exiting of the target personnel every day, and Wherein w i represents the average number of target person in and out per day for the ith elevator;
S403, obtaining attention degree difference results of different target areas in the step S303 on each historical advertisement type, and dividing the historical advertisement types; when the attention degrees of the same historical advertisement types in different target areas are different, outputting corresponding delivery suggestions, namely dividing the historical advertisement types into target areas with the largest attention degrees; when the attention of the same type of historical advertisement in different target areas is the same, outputting corresponding putting suggestions, namely dividing the same type of historical advertisement into corresponding proportions according to the size of the historical advertisement browsing amount corresponding to the target areas.
3. The advertising management method based on data analysis of claim 2, wherein: the step S500 includes:
S501, according to the advertisement putting scheme of the target area provided in the step S403, putting real-time advertisements, and obtaining real-time advertisement data put in the target area, namely, the watching time length of target personnel on the elevator display screen;
s502, calculating the watching coefficient of target personnel in a target area for each type of advertisement Associating the calculated results with historical advertisement viewing coefficients of the same typeComparing; if it isOutputting a corresponding prompt signal, namely 'the watching coefficient is lower than the historical average level, please further analyze the reason'; if it isAnd outputting a corresponding prompt signal, namely 'good throwing effect, please keep continuously'.
4. The advertising management system of an advertising management method based on data analysis as claimed in claim 3, wherein: the system comprises a data acquisition and preprocessing module, a personnel identification and feature extraction module, a target personnel screening and identification module, a historical advertisement data analysis module, an advertisement putting suggestion generation module and a real-time advertisement effect evaluation and prompting module;
The data acquisition and preprocessing module acquires the number of elevators in a target area and numbers the elevators, and acquires image data of personnel in the elevators; the personnel identification and feature extraction module is used for carrying out face recognition on the collected image data and extracting feature vectors of the face; the target person screening and identifying module screens out target persons according to the threshold value Q of the times of entering and exiting and the threshold value interval B of the similarity, and identifies the target persons; the historical advertisement data analysis module is used for putting the historical advertisements on an elevator display screen of a target area, recording the watching duration and position data of target personnel on the advertisements, and calculating the watching coefficient and position coefficient of each elevator on each type of the historical advertisements; the advertisement putting suggestion generation module combines the number of times of entering and exiting of the target person and the historical advertisement attention degree to generate advertisement putting suggestions applicable to the target area; and the real-time advertisement effect evaluation and prompt module evaluates the watching effect of the target personnel on the advertisement according to the real-time advertisement data and outputs corresponding prompt information according to the evaluation result.
5. The advertising management system as recited in claim 4, wherein: the data acquisition and preprocessing module comprises an elevator quantity acquisition and numbering unit, a personnel image acquisition unit and a data preprocessing unit;
The elevator number and numbering unit is responsible for acquiring and numbering the elevator number of the target area; the personnel image collecting unit is responsible for collecting image data of personnel in the elevator; the data preprocessing unit preprocesses the collected image data;
the personnel identification and feature extraction module comprises a face identification unit, a feature extraction unit and a face matching unit;
The face recognition unit recognizes the face in the image by using a face recognition technology; the feature extraction unit extracts feature vectors from the identified faces; the face matching unit calculates similarity based on the feature vector, thereby performing face matching.
6. The advertising management system as recited in claim 4, wherein: the target personnel screening and identifying module comprises a personnel screening unit and a personnel identifying unit;
The personnel screening unit screens out target personnel according to a set threshold value Q; the personnel identification unit performs identification based on the result of the personnel screening unit;
the historical advertisement data analysis module comprises a viewing time length statistics unit, a position data statistics unit, a viewing coefficient calculation unit and a position coefficient calculation unit;
The watching duration statistics unit is used for counting the watching duration of the target person on the advertisement; the position data statistics unit is used for counting the position data of the target personnel; the watching coefficient calculating unit calculates the watching coefficient of each elevator for each historical advertisement type; the position coefficient calculating unit calculates the position coefficient of the target person playing each historical advertisement type by each elevator.
7. The advertising management system as recited in claim 4, wherein: the advertisement putting suggestion generation module comprises an in-out frequency counting unit, an advertisement attention calculating unit and an advertisement putting suggestion generation unit;
The time counting unit is used for counting the time of the target person entering and exiting the elevator; the advertisement attention calculating unit is used for calculating unit attention of each historical advertisement type under different target areas according to the calculation results of the watching coefficient calculating unit and the position coefficient calculating unit; the advertisement putting suggestion generation unit calculates advertisement browsing amounts of different target areas based on the number of times of entering and exiting statistics unit, and generates advertisement putting suggestions of different target areas by combining the advertisement attention calculation unit;
The real-time advertisement effect evaluation and prompting module comprises a real-time advertisement data acquisition unit, an advertisement effect evaluation unit and an advertisement putting prompting unit;
the real-time advertisement data acquisition unit is used for acquiring advertisement data in real time; the advertisement effect evaluation unit evaluates the effect of the advertisement putting unit; and the advertisement putting prompting unit outputs corresponding prompting information according to the result of the advertisement effect evaluation unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380436.3A CN117436953B (en) | 2023-10-24 | 2023-10-24 | Advertisement delivery management system and method based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380436.3A CN117436953B (en) | 2023-10-24 | 2023-10-24 | Advertisement delivery management system and method based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117436953A CN117436953A (en) | 2024-01-23 |
| CN117436953B true CN117436953B (en) | 2024-10-22 |
Family
ID=89554626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311380436.3A Active CN117436953B (en) | 2023-10-24 | 2023-10-24 | Advertisement delivery management system and method based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436953B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118982388B (en) * | 2024-07-26 | 2025-04-01 | 江苏策翼信息科技有限公司 | Intelligent advertisement generation method based on multimedia advertisement promotion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846694A (en) * | 2018-06-06 | 2018-11-20 | 厦门集微科技有限公司 | A kind of elevator card put-on method and device, computer readable storage medium |
| CN113627984A (en) * | 2020-12-10 | 2021-11-09 | 北京交通大学 | An intelligent elevator advertising screen system and advertising delivery method based on scene perception |
| CN115689654A (en) * | 2022-11-16 | 2023-02-03 | 武汉辰鑫禾奕文化传播有限公司 | Advertisement putting intelligent management system and method based on big data |
| CN116887000A (en) * | 2023-06-07 | 2023-10-13 | 广州大事件网络科技有限公司 | Advertisement directional delivery method and system |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682946A (en) * | 2016-12-30 | 2017-05-17 | 北京七鑫易维信息技术有限公司 | Advertisement content analysis method and device |
| CN106971317A (en) * | 2017-03-09 | 2017-07-21 | 杨伊迪 | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique |
| JP7070286B2 (en) * | 2018-09-21 | 2022-05-18 | トヨタ自動車株式会社 | Information processing equipment, information processing methods and programs |
| JP7251104B2 (en) * | 2018-11-02 | 2023-04-04 | 大日本印刷株式会社 | ADVERTISING MANAGEMENT DEVICE, PROGRAM, ADVERTISING DISTRIBUTION SYSTEM AND ADVERTISING MANAGEMENT METHOD |
| CN109670860B (en) * | 2018-11-27 | 2024-04-05 | 平安科技（深圳）有限公司 | Advertisement putting method and device, electronic equipment and computer readable storage medium |
| CN109377288A (en) * | 2018-11-27 | 2019-02-22 | 西安数拓网络科技有限公司 | Analysis method and device are launched in a kind of advertisement |
| CN110097395B (en) * | 2019-03-27 | 2023-05-26 | 平安科技（深圳）有限公司 | Directional advertisement putting method and device and computer readable storage medium |
| CN110111129B (en) * | 2019-03-28 | 2024-01-19 | 中国科学院深圳先进技术研究院 | Data analysis method, advertisement playing device and storage medium |
| CN112215636B (en) * | 2020-01-21 | 2021-11-19 | 华为技术有限公司 | Advertisement attribution method and equipment |
| CN111353461B (en) * | 2020-03-11 | 2024-01-16 | 京东科技控股股份有限公司 | Attention detection method, device and system of advertising screen and storage medium |
| CN111813986B (en) * | 2020-07-10 | 2023-12-22 | 重庆中科云从科技有限公司 | Intelligent advertisement pushing method, device, system, medium and electronic terminal |
| CN113538059B (en) * | 2021-07-23 | 2023-04-07 | 四川大学 | User time sequence behavior visualization method facing online shopping advertisement |
| CN116308528A (en) * | 2023-03-20 | 2023-06-23 | 上海视脉电子科技有限公司 | Animation display method, system, storage medium and intelligent terminal |
| CN116468483A (en) * | 2023-04-17 | 2023-07-21 | 湖南山阅文化传媒有限责任公司 | Elevator advertisement putting system |
-
2023
- 2023-10-24 CN CN202311380436.3A patent/CN117436953B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846694A (en) * | 2018-06-06 | 2018-11-20 | 厦门集微科技有限公司 | A kind of elevator card put-on method and device, computer readable storage medium |
| CN113627984A (en) * | 2020-12-10 | 2021-11-09 | 北京交通大学 | An intelligent elevator advertising screen system and advertising delivery method based on scene perception |
| CN115689654A (en) * | 2022-11-16 | 2023-02-03 | 武汉辰鑫禾奕文化传播有限公司 | Advertisement putting intelligent management system and method based on big data |
| CN116887000A (en) * | 2023-06-07 | 2023-10-13 | 广州大事件网络科技有限公司 | Advertisement directional delivery method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117436953A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8351647B2 (en) | Automatic detection and aggregation of demographics and behavior of people | |
| US9747497B1 (en) | Method and system for rating in-store media elements | |
| JP4794453B2 (en) | Method and system for managing an interactive video display system | |
| CN101847218A (en) | People flow counting system and method thereof | |
| CN106971317A (en) | The advertisement delivery effect evaluation analyzed based on recognition of face and big data and intelligently pushing decision-making technique | |
| US10296936B1 (en) | Method and system for measuring effectiveness of a marketing campaign on digital signage | |
| TW201033908A (en) | System and method for counting people flow | |
| CN117436953B (en) | Advertisement delivery management system and method based on data analysis | |
| US20140249886A1 (en) | Billboard exposure determining system and method | |
| JP4159159B2 (en) | Advertising media evaluation device | |
| CN113213017A (en) | Intelligent garbage classification propaganda and education and delivery supervision system based on visual AI technology | |
| US11367083B1 (en) | Method and system for evaluating content for digital displays by measuring viewer responses by demographic segments | |
| CN108876454A (en) | The device and its statistical method of accurate statistics commercial audience situation | |
| CN113240466B (en) | Mobile media video data processing method and device based on big data depth analysis and storage medium | |
| CN114708018B (en) | Electronic screen advertisement intelligent charging management system based on data analysis | |
| CN109993589A (en) | A machine vision-based advertising machine passenger flow data analysis method | |
| CN108537184A (en) | A kind of stream of people's statistical system being applicable in market survey | |
| CN115689654A (en) | Advertisement putting intelligent management system and method based on big data | |
| JP5272214B2 (en) | Advertisement effect index measuring device, advertisement effect index measuring method and program | |
| CN117172855B (en) | Elevator advertisement playing method and system based on face recognition | |
| CN114757694A (en) | An advertising video information push system | |
| CN111476600B (en) | Statistical analysis method for audience numbers of direct ladder advertisement | |
| CN109492616A (en) | A kind of advertisement screen face identification method based on autonomous learning | |
| CN118246987A (en) | Advertisement placement management system based on placement effect analysis | |
| CN201467351U (en) | Television audience rating statistical device based on human face detection |
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 |