CN114841749A - Accurate business information pushing method based on LBS and machine learning - Google Patents
Accurate business information pushing method based on LBS and machine learning Download PDFInfo
- Publication number
- CN114841749A CN114841749A CN202210532351.1A CN202210532351A CN114841749A CN 114841749 A CN114841749 A CN 114841749A CN 202210532351 A CN202210532351 A CN 202210532351A CN 114841749 A CN114841749 A CN 114841749A
- Authority
- CN
- China
- Prior art keywords
- activity
- campus
- aerial vehicle
- unmanned aerial
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000010801 machine learning Methods 0.000 title claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 401
- 230000006399 behavior Effects 0.000 claims abstract description 25
- 238000012417 linear regression Methods 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000007306 turnover Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000001737 promoting effect Effects 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims 2
- 238000004220 aggregation Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 description 3
- 235000015243 ice cream Nutrition 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0243—Comparative campaigns
-
- 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
- G06Q30/0261—Targeted advertisements based on user location
-
- 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
- G06Q30/0264—Targeted advertisements based upon schedule
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an accurate business information pushing method based on LBS and machine learning, which comprises the following steps: the unmanned aerial vehicle acquires the school activity gathering points and judges whether the school activity gathering points are selected as activity propaganda points or not; acquiring image data through an unmanned aerial vehicle to observe campus activities, and identifying activity participation number and purchasing behavior participation degree; the unmanned aerial vehicle acquires campus moving images of different event times and different event handling places, and judges the influence of the event handling places of the event times on the campus traffic; the unmanned aerial vehicle acquires the propaganda effect of the media propaganda campus activity; judging the input-output ratio of the campus activity sponsorship according to the actual sales condition; the method comprises the steps that an unmanned aerial vehicle obtains a campus activity propaganda effect, and the fitness of campus activity types and students in a school is analyzed through the propaganda effect; determining which times and places and which campaign types to advertise may increase sales.
Description
Technical Field
The invention relates to the technical field of information, in particular to an accurate business information pushing method based on LBS and machine learning.
Background
For research and development of campus APP or companies taking students in campuses as marketing subjects, advertisement pushing is often required according to campus activity types. Such as recommending clothing companies or recommending light design companies for organizations that need to hold concerts, recommending sporting goods for sporting events, etc. However, advertising on what campaign is the best investment is a problem that few people know, because even though there is a campaign in the school sometimes, the students who participate in the campaign are different, and a good publicity effect cannot be obtained. The schools are different in types and the preferences of students are different, and some social group organizers who hold the schools are high in enthusiasm and capacity, and some social group organizers are not high in enthusiasm and capacity. A good community this year may be poorly organized throughout the year, so whether a campus activity is doing well is not fixed.
Disclosure of Invention
The invention provides an accurate business information pushing method based on LBS and machine learning, which mainly comprises the following steps: the unmanned aerial vehicle acquires the school activity gathering points and judges whether the school activity gathering points are selected as activity propaganda points or not; acquiring image data through an unmanned aerial vehicle to observe campus activities, and identifying activity participation number and purchasing behavior participation degree; the unmanned aerial vehicle acquires campus moving images of different event times and different event handling places, and judges the influence of the event handling places of the event times on the campus traffic; the unmanned aerial vehicle acquires the propaganda effect of the media propaganda campus activity; judging the input-output ratio of the campus activity sponsorship according to the actual sales condition; the method comprises the steps that an unmanned aerial vehicle obtains a campus activity propaganda effect, and the fitness of campus activity types and students in a school is analyzed through the propaganda effect; the sales amount can be increased by judging which time, place and activity types are advertised;
further optionally, the unmanned aerial vehicle acquires the school activity gathering point, and the determining whether to select the school activity gathering point as an activity propaganda point comprises:
the method comprises the steps of carrying out regional division on a campus according to a campus road network map, judging possible gathering points of activities in the campus according to roads and open areas in the campus to obtain a plurality of divided areas, and carrying out aerial photography in each divided area through an unmanned aerial vehicle to obtain image data in each divided area; the processor acquires image data acquired by the unmanned aerial vehicle, inputs the image data into the trained full convolution neural network and extracts the number of people in each divided area; and calculating the number of the heads in each divided area according to a head detection algorithm YOLO-OFLSTM, and judging possible gathering points of activities in the school to obtain a proper activity propaganda point.
Further optionally, the collecting image data by the unmanned aerial vehicle observes campus activities, and the identifying activity participation number and purchasing behavior participation degree includes:
the unmanned aerial vehicle collects image data of the activity propaganda points, and divides a purchasing area, a watching area and a quick passing area through an area function; extracting the number of people in each area according to a people detection algorithm, wherein the sum of the number of people in the purchasing area and the number of people in the watching area is the number of participating people, and the number of people in the purchasing area is judged as the number of purchasing behavior people; carrying out unsupervised pedestrian re-identification in the purchasing area and the observation area to obtain the conversion rate from the observation area to the purchasing area; the processor takes continuous frame images of students in a purchasing area acquired by the unmanned aerial vehicle as a gallery, samples are in the watching area, whether the samples in the previous period appear in the current purchasing area is judged through pedestrian re-identification, and the purchasing rate of the watching area is obtained; the purchase rate is the ratio of the number of the persons participating in the activity to the number of the persons in the activity area, the conversion rate is the ratio of the persons entering the purchase area to the total number of the persons in the observation area, and the purchase behavior participation rate is the ratio of the conversion rate of the observation area multiplied by the number of the persons in the observation area plus the number of the persons in the purchase area to the total number of the persons in the activity area.
Further optionally, the unmanned aerial vehicle obtains campus moving images of different activity time and different activity holding places, and the influence of the activity time and activity holding places on the campus traffic is judged to include:
the method comprises the steps that an unmanned aerial vehicle is used for collecting image data of different activity areas at different times, and the pedestrian volume of campus moving images of different activity times and different places is obtained through processing of a head detection algorithm YOLO-OFLSTM; inputting the pedestrian flow data into a multivariate linear model based on multivariate linear regression for training, and predicting the pedestrian flow at any time period; judging time and places with much flow of people to obtain time and places suitable for holding campus activities; the method comprises the following steps: the unmanned aerial vehicle acquires the influence of activity time on the flow of people in the campus activity; the unmanned aerial vehicle acquires the influence of an activity holding place on the flow of persons in the campus activities;
unmanned aerial vehicle acquires the influence of activity time on campus activity traffic, specifically includes:
the unmanned aerial vehicle acquires the pedestrian volume change before and after each activity time of the activity area, and predicts the pedestrian volume of the activity time; acquiring the pedestrian flow in the activity area at any moment, drawing a nuclear density curve on an x axis, judging that 'hour, week and month in one day' are variable drawing charts, fitting data with extreme values in the same chart, and acquiring a factor with high relevance of the pedestrian flow in the activity area; determining 'hours of day', 'weeks' and 'months' which can influence the flow of people in the active area; and establishing a linear regression model by using the flow rates of people in different time of the activity area, and inputting variables to predict the flow rate of people in the holding time of the activity area. Unmanned aerial vehicle obtains the influence that the place was held to the activity to campus activity flow of people, specifically includes:
on an individual, the activity of the teacher is random, and the individual is difficult to predict about the current idea; the students and teachers move in schools and school teaching activities are closely related to each other in general, and the school teaching activities influence the gathering and flowing directions of the students at the same time; numbering event places suitable for holding events in a school, and acquiring image data of the pedestrian flow of each event holding place by using an unmanned aerial vehicle; and establishing a linear regression model for the flow of people in each event handling place at the same event time, taking the event region code as a variable, and inputting the variable to predict the flow of people in the event region at the event time.
Further optionally, the obtaining, by the drone, a promotional effect of the media promotion campus campaign includes:
monitoring the pedestrian volume change after the campus activity promotion in real time by using an unmanned aerial vehicle, and determining the influence of the promotion on the pedestrian volume change; the method comprises the steps of acquiring images of activity areas before and after media propaganda through unmanned aerial vehicle remote sensing, inputting head data and propaganda activity modes into a convolutional neural network as characteristics after a head detection algorithm is adopted, acquiring the head number difference before and after activities through characteristic extraction, judging the influence of the activities on the area flow of people, and predicting the popularization suitability of schools; the method comprises the following steps: judging the most suitable propaganda mode of the campus according to the influence of various media propaganda campus activities on the increase rate of the human flow and the actual number of purchasers;
the propaganda campus mode of judging the campus is most suitable through the influence of various media propaganda campus activities to traffic and actual purchasing population increase rate specifically includes:
the propaganda effect is judged by the pedestrian volume in the activity area and the increase rate of the actual number of purchasers; the increase of the flow of people and the sales are in positive correlation, but invalid advertisements with the increase of the flow of people and the increase of the sales are not generated in the actual sales process; the actual purchasing behavior is difficult to judge, a purchasing area can be divided from an activity area frame image shot by the unmanned aerial vehicle, and the purchasing behavior is judged to exist when the unmanned aerial vehicle enters the purchasing area; through the change of the number of people who gets into the purchase region behind the unmanned aerial vehicle real-time supervision media propaganda, obtain the increase rate of purchasing behavior behind the campaign, acquire the actual effect of media campaign propaganda, judge the most suitable propaganda mode in campus.
Further optionally, the determining the campus activity sponsorship input-output ratio according to the actual sales condition includes:
the purpose of the sales promotion is to attract customers and increase sales volume; determining whether the turnover is increased or not by monitoring and selecting proper time and activity places by the unmanned aerial vehicle, and eliminating the turnover change caused by time and product change; judging the activity effect of the campus activity by combining whether the sales volume of the area without activity is increased by the horizontal comparison data and whether the sales volume is increased after the activity is held by the vertical comparison data; the unmanned aerial vehicle renting is taken as a factor which influences the gross profit rate, and if the campus activity output ratio is low, the shooting content of the unmanned aerial vehicle is reduced; calculating the return on investment for the input budget and the output, and judging the input-output ratio; the method comprises the following steps: comparing sales before and after the activity, and judging the activity effect according to the sales rate; reducing the shooting content of the unmanned aerial vehicle for activities with poor input-output ratio; the data comparison is carried out to sales volume around the activity, and the activity effect is judged through the sales volume rate, and the method specifically comprises the following steps:
the promotion activity has a definite target and needs to judge and evaluate the activity effect; carrying out actual evaluation on the activity effect by using a comprehensive comparison method and an input-output ratio method; the comprehensive comparison method needs to be combined with the situation that whether the sales volume of the horizontal comparison data is increased compared with the sales volume of the area without holding the event or not and whether the sales volume is increased after the vertical comparison data holds the event or not; and the input-output ratio method calculates the investment return rate for the input budget and the output and judges whether the input-output ratio is reasonable or not, and the investment return rate is better than the campus activity effect of holding the campus activity.
The activity to input-output ratio difference reduces unmanned aerial vehicle and shoots content, specifically includes:
the unmanned aerial vehicle can monitor and judge the campus activity effect in real time, and can judge the campus activity input-output ratio by combining the turnover; according to monitoring of the campus people flow by the unmanned aerial vehicle, the time and the place with low people flow and poor activity hosting effect are obtained, and the investment of the unmanned aerial vehicle is reduced; and reducing the content shot by the unmanned aerial vehicle for activities with poor input-output ratio.
Further optionally, unmanned aerial vehicle acquires campus activity advertising effect, and campus activity type and student's degree of agreeing with of this school include through advertising effect analysis:
monitoring the change of the pedestrian volume in the activity area after the campus activity promotion by using an unmanned aerial vehicle in real time, and determining the influence of campus activity propaganda on the pedestrian volume; and analyzing the fitness of the campus activity types and the students in the school according to the influence of each campus activity type on the human flow.
An accurate business information pushing method based on LBS and machine learning is characterized in that the system comprises the following steps:
the index for evaluating the sales effect is sales volume which is in direct proportion to the passenger flow and the transaction rate; the factors influencing passenger flow are passenger flow, and the factors influencing transaction rate are activity types; the campus is a closed environment, the pedestrian volume is closely related to school teaching activity arrangement, the image data in the campus are collected in different regions and different time by using the unmanned aerial vehicle, a linear regression equation of the pedestrian volume with respect to time and place is obtained, the time and the place with the maximum pedestrian volume can be predicted through the linear regression equation, the pedestrian volume is in direct proportion to the passenger volume, and the moment with the maximum pedestrian volume is the moment with the maximum passenger volume; the method comprises the following steps that the transaction rate is related to the type of an activity, an unmanned aerial vehicle is used for obtaining image data of an activity scene, the number of persons participating in each activity and the participation degree of purchasing behavior are obtained through processing, and the transaction rate is obtained through calculation; through the passenger flow and the transaction rate, the time and place of the user are judged, and the advertisement propaganda is carried out on the activity types of the user, so that the sales volume is promoted.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
according to the invention, the flow of people in the campus is obtained through the camera shooting analysis of the unmanned aerial vehicle, and campus activities are held at the time and place with much flow of people; when holding the campus activity, the effect of the campus activity of analysis of making a video recording, the influence of feedback campus activity to the regional flow of people of activity combines the sales volume, counteracts in unmanned aerial vehicle's the activity of taking photo by plane, shoots the place according to the shooting time shooting quantity of activity effect adjustment unmanned aerial vehicle, further confirms the time place and the activity kind that are most suitable for the campus to promote, reaches better campus and promotes.
[ description of the drawings ]
Fig. 1 is a flowchart of an accurate business information pushing method based on LBS and machine learning according to the present invention.
Fig. 2 is a schematic diagram of an accurate business information pushing method based on LBS and machine learning according to the present invention.
[ detailed description ] embodiments
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of an accurate business information pushing method based on LBS and machine learning according to the present invention. As shown in fig. 1, the method for pushing accurate business information based on LBS and machine learning in this embodiment may specifically include:
step 101, an unmanned aerial vehicle acquires a school activity gathering point and judges whether the school activity gathering point is selected as an activity propaganda point. The method comprises the steps of carrying out regional division on a campus according to a campus road network map, judging possible gathering points of activities in the campus according to roads and open areas in the campus to obtain a plurality of divided areas, and carrying out aerial photography in each divided area through an unmanned aerial vehicle to obtain image data in each divided area; the processor acquires image data acquired by the unmanned aerial vehicle, inputs the image data into the trained full convolution neural network and extracts the number of people in each divided area; and calculating the number of the heads in each divided area according to a head detection algorithm YOLO-OFLSTM, and judging possible gathering points of activities in the school to obtain a proper activity propaganda point.
And 102, collecting image data through an unmanned aerial vehicle to observe campus activities, and identifying activity participation number and purchasing behavior participation degree. The unmanned aerial vehicle collects image data of the activity propaganda points, and divides a purchasing area, a watching area and a quick passing area through an area function; extracting the number of people in each area according to a people detection algorithm, wherein the sum of the number of people in the purchasing area and the number of people in the watching area is the number of participating people, and the number of people in the purchasing area is judged as the number of purchasing behavior people; carrying out unsupervised pedestrian re-identification in the purchasing area and the observation area to obtain the conversion rate from the observation area to the purchasing area; the processor takes continuous frame images of students in a purchasing area acquired by the unmanned aerial vehicle as a gallery, samples are in the watching area, whether the samples in the previous period appear in the current purchasing area is judged through pedestrian re-identification, and the purchasing rate of the watching area is obtained; the purchase rate is the ratio of the number of the persons participating in the activity to the number of the persons in the activity area, the conversion rate is the ratio of the persons entering the purchase area to the total number of the persons in the observation area, and the purchase behavior participation rate is the ratio of the conversion rate of the observation area multiplied by the number of the persons in the observation area plus the number of the persons in the purchase area to the total number of the persons in the activity area.
And 103, acquiring campus moving images of different event time and different event handling places by the unmanned aerial vehicle, and judging the influence of the event time and event handling places on the campus traffic.
The method comprises the steps that an unmanned aerial vehicle is used for collecting image data of different activity areas at different times, and the pedestrian volume of campus moving images of different activity times and different places is obtained through processing of a head detection algorithm YOLO-OFLSTM; inputting the pedestrian flow data into a multivariate linear model based on multivariate linear regression for training, and predicting the pedestrian flow at any time period; and judging the time and place with much traffic to obtain the time and place suitable for holding the campus activities. The density of campus people streams and the complexity of a scene easily cause the human body target to be shielded, so that the human flow is judged by adopting the characteristic that the human head is not easily shielded; for example: the number of people who acquire the 'dining room area' at twelve o 'clock to fourteen o' clock is three thousand, and the dining room gate has the open space, uses the numerical value as the input characteristic of the graph convolution neural network to carry out data pre-training, and the area is the activity gathering point, and the propaganda effect is better. And the other person obtains that the number of people in the 'teaching building' from seven points to eight points is six thousand, the area of the teaching building is insufficient in open space and poor in propaganda effect, model training is carried out to adjust parameters, the deep learning model is finally trained through the processing method, and when a new area is met, whether the new area is a proper activity propaganda point can be predicted only by inputting the content of the area. The unmanned aerial vehicle obtains the influence of activity time on the campus activity traffic.
The unmanned aerial vehicle acquires the pedestrian volume change before and after each activity time of the activity area, and predicts the pedestrian volume of the activity time; acquiring the pedestrian flow in the activity area at any moment, drawing a nuclear density curve on an x axis, judging that 'hour, week and month in one day' are variable drawing charts, fitting data with extreme values in the same chart, and acquiring a factor with high relevance of the pedestrian flow in the activity area; determining 'hours of day', 'weeks' and 'months' which can influence the flow of people in the active area; establishing a linear regression model according to the flow rates of people in different time of the activity area, and inputting variables to predict the flow rates of people in the holding time of the activity area; for example: obtaining the number of the staying people in a purchasing area as 20, the number of the staying people in a watching area as 40, and the number of the staying people in a quick passing area as 140 in a certain time, wherein the number of the participating people in the activity is 20+40= 60; ten samples in the observation area obtained by pedestrian re-identification enter the purchase area after five minutes, the purchase rate of the observation area is 10/40=25%, and the participation degree of the purchase behavior is (20 + 10)/(140 +40+ 20) = 15%. The unmanned aerial vehicle obtains the influence of the activity holding place on the flow of persons in the campus activities.
On an individual, the activity of the teacher is random, and the individual is difficult to predict about the current idea; the students and teachers move in schools and school teaching activities are closely related to each other in general, and the school teaching activities influence the gathering and flowing directions of the students at the same time; numbering event places suitable for holding events in a school, and acquiring image data of the pedestrian flow of each event holding place by using an unmanned aerial vehicle; establishing a linear regression model for the people flow in each event handling place at the same event time, taking the event region code as a variable, and inputting the variable to predict the people flow in the event region at the event time; for example: acquiring the pedestrian volume of a library area of four thousand in June, seven morning and non-workday, and taking the numerical value as the input characteristic of a multiple linear regression model to perform data pre-training, wherein the campus activities are held in the open space in front of the library at the time, so that the propaganda effect is good; and the people flow rate in a library area, holding time of August, three points in the afternoon and a workday of twenty are obtained, and the numerical values are input into a multiple linear regression model, so that the people flow rate is low, the effect of holding activities is poor, and the library is not suitable for holding activities.
And step 104, the unmanned aerial vehicle acquires the propaganda effect of the media propaganda campus activity. The flow of people who uses unmanned aerial vehicle to promote the campus activity changes and carries out real-time supervision, confirms to promote the influence that changes the flow of people. The method comprises the steps of acquiring images of activity areas before and after media propaganda through unmanned aerial vehicle remote sensing, inputting head data and a propaganda activity mode into a convolutional neural network as features after a head detection algorithm, acquiring head number difference before and after activities through feature extraction, judging influence of the activities on the flow of people in the areas, and predicting popularization suitable for schools. For example: acquiring that the pedestrian volume of a library area in 'June', 'Saturday' and 'eight morning' is seven thousand, and pre-training data by taking a numerical value as an input characteristic of a linear regression model, wherein the pedestrian volume is large at the time, and the holding effect of campus activities is good; and the other one obtains the fact that the flow of people in the library area is fifty in August, Thursday and nine-point in the morning and the propaganda effect of the campus activity is poor, carries out model training and adjusts parameters, obtains a linear regression model through the training method, and can predict the activity time with the maximum flow of people by inputting the activity place. The most suitable propaganda mode of the campus is judged through the influence of various media on the increase rate of the campus activities on the traffic and the actual purchasing number. The propaganda effect is judged by the pedestrian volume in the activity area and the increase rate of the actual number of purchasers; the increase of the flow of people and the sales are in positive correlation, but invalid advertisements with the increase of the flow of people and the increase of the sales are not generated in the actual sales process; the actual purchasing behavior is difficult to judge, a purchasing area can be divided from an activity area frame image shot by the unmanned aerial vehicle, and the purchasing behavior is judged to exist when the unmanned aerial vehicle enters the purchasing area; through the change of the number of people who gets into the purchase region behind the unmanned aerial vehicle real-time supervision media propaganda, obtain the increase rate of purchasing behavior behind the campaign, acquire the actual effect of media campaign propaganda, judge the most suitable propaganda mode in campus. For example: eleven to thirteen points, namely a dining room area, with the flow of people of four thousand, good activity holding effect and suitability for holding activities are obtained; and ten to thirteen points are obtained, namely a 'library area', the flow of people is three hundred, the effect of holding activities is poor, and the activities are not suitable for holding the activities, the numerical values are input into a linear regression model, the linear regression model is obtained through fitting regression by the method, and the activity place with the maximum flow of people can be predicted by inputting the activity time.
And 105, judging the input-output ratio of the campus activity sponsorship according to the actual sales condition. The purpose of the sales promotion is to attract customers and increase sales volume; determining whether the turnover is increased or not by monitoring and selecting proper time and activity places by the unmanned aerial vehicle, and eliminating the turnover change caused by time and product change; judging the activity effect of the campus activity by combining whether the sales volume of the area without activity is increased by the horizontal comparison data and whether the sales volume is increased after the activity is held by the vertical comparison data; the unmanned aerial vehicle renting is taken as a factor which influences the gross profit rate, and if the campus activity output ratio is low, the shooting content of the unmanned aerial vehicle is reduced; and calculating the return on investment for the input budget and the output, and judging the input-output ratio. The campus activities have sealing performance, product promotion and publicity mainly depend on poster publicity, community activities are sponsored, and school platform popularization is completed; the popularization of each college is different, and the effective degree of each popularization is different in the same college; for example: before the poster is posted, the number of people in the activity area is four hundred, after the poster is posted, the number of people in the activity area is five hundred, and the number of people is increased by (500-400)/400 = 25%; and before the community activity sponsorship is obtained, the number of the people in the activity area is two hundred, after the community activity sponsorship, the number of the people in the activity area is four hundred, the number of the people is increased (400-plus-200)/200 =100%, the increase rate of the number of the people of each propaganda mode is cross-compared, and the most suitable propaganda mode of the campus is judged.
And comparing the sales volume before and after the activity, and judging the activity effect according to the sales volume rate.
The promotion activity has a definite target and needs to judge and evaluate the activity effect; carrying out actual evaluation on the activity effect by using a comprehensive comparison method and an input-output ratio method; the comprehensive comparison method needs to be combined with the situation that whether the transverse comparison data is increased compared with the sales of the region without holding the event or not and whether the sales of the longitudinal comparison data after holding the event is increased or not; the input-output ratio method is used for calculating the investment return rate of input budget and output and judging whether the input-output ratio is reasonable or not, and the investment return rate is better than the activity effect of the campus activities holding the campus activities; for example: before the poster is posted, the number of people in the activity area is four hundred, the number of people in the purchase area is fifty, after the poster is posted, the number of people in the activity area is five hundred, the number of people in the purchase area is one hundred, the number of people in the purchase area is increased by (500-400)/400 =25%, and the number of people in the purchase area is increased by (100-50)/50 = 100%; and before sponsoring the community activity, acquiring the number of people in the activity area of two hundred, the number of people in the purchase area of twenty, and after the community activity is sponsored, the number of people in the activity area of four hundred, the number of people in the purchase area of thirty, the number of people in the activity area is increased by (400 + 200)/200 =100%, the number of people in the purchase area is increased by (30-20)/20 =50%, and cross-comparing the actual increase rate of the number of people purchased in each propaganda mode to judge the most suitable propaganda mode in the campus actually. And reducing the shooting content of the unmanned aerial vehicle for activities with poor input-output ratio. The unmanned aerial vehicle can monitor and judge the campus activity effect in real time, and can judge the campus activity input-output ratio by combining the turnover; according to monitoring of the campus people flow by the unmanned aerial vehicle, the time and the place with low people flow and poor activity hosting effect are obtained, and the investment of the unmanned aerial vehicle is reduced; and reducing the shooting content of the unmanned aerial vehicle for activities with poor input-output ratio. For example: the method comprises the steps of obtaining the campus event sales amount of two million in A18 of colleges and universities, and obtaining the unmanned aerial vehicle leasing cost of hundred thousand, wherein the sales amount is three million after the unmanned aerial vehicle carries out data acquisition and judges the appropriate campus event holding place holding time in 19 years; acquiring colleges and universities B, wherein the campus activities are sold in two million in 18 years, unmanned aerial vehicle acquisition is not carried out in 19 years, and the campus activities are sold in two hundred and fifty thousand; acquiring colleges and universities C in the same region, wherein the colleges and universities C do not take campus activities in 18 years, the sales amount is one hundred and fifty thousand, the campus activities are not taken in 19 years, and the sales amount is two million; and calculating the return on investment for the invested budget and the output respectively, and judging the campus activity sponsoring output ratio.
And step 106, the unmanned aerial vehicle acquires the campus activity propaganda effect, and analyzes the type of the campus activity and the fitness of students in the school through the propaganda effect. Monitoring the change of the pedestrian volume in the activity area after the campus activity promotion by using an unmanned aerial vehicle in real time, and determining the influence of campus activity propaganda on the pedestrian volume; and analyzing the degree of fit between the campus activity types and the students in the school according to the influence of each campus activity type on the human flow. For example: acquiring one week before the campus sales promotion activity of colleges and universities A, wherein the sales volume is one hundred thousand, the sales volume of the campus activity in the same week is twenty thousand, the campus activity cost is one thousand, and the fixed cost per week is fifty thousand; acquiring the sales volume of one week before the activity of the campus B of another college as hundred thousand and the sales volume of the current week as thirteen thousand; through a comprehensive comparison method, the campus activities are improved by (20-10- (13-10) -1)/10 =60% of sales; through the input-output ratio method, the investment return rate of colleges and universities A in the current week of the activity is 3.3, the investment return rate of colleges and universities B is 2.6, the investment return rate of colleges and universities A who hold the campus activity is higher than that of colleges and universities B who do not hold the campus activity, and the activity effect of the campus activity is good.
Step 107, determining which times and places and which campaign types to advertise may increase sales.
The index for evaluating the sales effect is sales volume which is in direct proportion to the passenger flow and the transaction rate; the factors influencing passenger flow are passenger flow, and the factors influencing transaction rate are activity types; the campus is a closed environment, the pedestrian volume is closely related to school teaching activity arrangement, the image data in the campus are collected in different regions and different time by using the unmanned aerial vehicle, a linear regression equation of the pedestrian volume with respect to time and place is obtained, the time and the place with the maximum pedestrian volume can be predicted through the linear regression equation, the pedestrian volume is in direct proportion to the passenger volume, and the moment with the maximum pedestrian volume is the moment with the maximum passenger volume; the method comprises the following steps that the transaction rate is related to the type of an activity, an unmanned aerial vehicle is used for obtaining image data of an activity scene, the number of persons participating in each activity and the participation degree of purchasing behavior are obtained through processing, and the transaction rate is obtained through calculation; through the passenger flow, the transaction rate judges which time and place and which activity types are advertised and promoted for sales; the promotion aims at increasing the turnover and the gross profit, the unmanned aerial vehicle has high purchase and lease cost, the campus activity cost is counted, and the gross profit of the campus activity is influenced; a product manufacturer with low gross profit amount is difficult to bear the shooting cost of the unmanned aerial vehicle; for example: the unmanned aerial vehicle has the advantages that the acquired people flow rate in the school is low, the campaign propaganda effect is poor, the input-output ratio is poor, the unmanned aerial vehicle shooting activities in the period are reduced, and the cost is reduced; the method has the advantages that the profit rate of ice cream sales promotion activities in schools is low, the renting cost of the unmanned aerial vehicle is high in marketing cost, the profit amount of the ice cream sales promotion activities is influenced by the unmanned aerial vehicle, the unmanned aerial vehicle shooting in the ice cream sales promotion activities is reduced, the cost is reduced, and the profit amount is increased.
The above description is only an embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are included in the scope of the present invention.
Programs for implementing the information governance of the present invention may be written in computer program code for carrying out operations of the present invention in one or more programming languages, including an object oriented programming language such as Java, python, C + +, or a combination thereof, as well as conventional procedural programming languages, such as the C language or similar programming languages.
The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention.
And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Claims (8)
1. An accurate business information pushing method based on LBS and machine learning, characterized in that the method comprises the following steps: the unmanned aerial vehicle acquires the school activity gathering points and judges whether the school activity gathering points are selected as activity propaganda points or not; acquiring image data through an unmanned aerial vehicle to observe campus activities, and identifying activity participation number and purchasing behavior participation degree; unmanned aerial vehicle obtains the campus motion image of the different activities of different activity time place, judges the influence of activity time activity place to campus traffic, unmanned aerial vehicle obtains the campus motion image of the different activities of different activity time place, judges the influence of activity time activity place to campus traffic, specifically includes: the unmanned aerial vehicle acquires the influence of the activity time on the campus activity traffic, and the unmanned aerial vehicle acquires the influence of the activity holding place on the campus activity traffic; unmanned aerial vehicle acquires the publicity effect of media publicity campus activity, specifically includes: judging the most suitable propaganda mode of the campus according to the influence of various media propaganda campus activities on the increase rate of the human flow and the actual number of purchasers; judging the campus activity sponsoring input-output ratio according to the actual sales condition, and judging the campus activity sponsoring input-output ratio according to the actual sales condition specifically comprises the following steps: carrying out data comparison on sales before and after the activity, judging the activity effect through the sales rate, and reducing the shooting content of the unmanned aerial vehicle for the activity with poor input-output ratio; the method comprises the steps that an unmanned aerial vehicle obtains a campus activity propaganda effect, and the fitness of campus activity types and students in a school is analyzed through the propaganda effect; determining which times and places and which campaign types to advertise may increase sales.
2. The method of claim 1, wherein the UAV obtains campus activity aggregation points and determines whether to select them as activity propaganda points, including dividing the campus according to the campus road network map, determining possible aggregation points of the campus activities according to the campus roads and the air-ground areas to obtain multiple divided areas, and obtaining image data in each divided area by UAV aerial photography; the processor acquires image data acquired by the unmanned aerial vehicle, inputs the image data into the trained full convolution neural network and extracts the number of people in each divided area; and calculating the number of the heads in each divided area according to a head detection algorithm YOLO-OFLSTM, and judging possible gathering points of activities in the school to obtain a proper activity propaganda point.
3. The method of claim 1, wherein the acquiring image data by the unmanned aerial vehicle to observe campus activities and identify activity participation number and purchasing behavior participation degree comprises acquiring image data of activity publicity points by the unmanned aerial vehicle, dividing purchasing areas, watching areas and fast passing areas by area functions; extracting the number of people in each area according to a people detection algorithm, wherein the sum of the number of people in the purchasing area and the number of people in the watching area is the number of participating people, and the number of people in the purchasing area is judged as the number of purchasing behavior people; carrying out unsupervised pedestrian re-identification in the purchasing area and the observation area to obtain the conversion rate from the observation area to the purchasing area; the processor takes continuous frame images of students in a purchasing area acquired by the unmanned aerial vehicle as a gallery, samples are in the watching area, whether the samples in the previous period appear in the current purchasing area is judged through pedestrian re-identification, and the purchasing rate of the watching area is obtained; the purchase rate is the ratio of the number of the persons participating in the activity to the number of the persons in the activity area, the conversion rate is the ratio of the persons entering the purchase area to the total number of the persons in the observation area, and the purchase behavior participation rate is the ratio of the conversion rate of the observation area multiplied by the number of the persons in the observation area plus the number of the persons in the purchase area to the total number of the persons in the activity area.
4. The method as claimed in claim 1, wherein the unmanned aerial vehicle acquires campus moving images of different activity time and different activity holding places and judges the influence of the activity time and activity holding places on campus traffic, and comprises the steps of acquiring image data of different activity areas and different times by using the unmanned aerial vehicle, and obtaining the traffic of the campus moving images of different activity time and different places through a human head detection algorithm YOLO-OFLSTM; inputting the pedestrian flow data into a multivariate linear model based on multivariate linear regression for training, and predicting the pedestrian flow at any time period; judging time and places with much flow of people to obtain time and places suitable for holding campus activities; the method comprises the following steps: the unmanned aerial vehicle acquires the influence of activity time on the flow of people in the campus activity; the unmanned aerial vehicle acquires the influence of an activity holding place on the flow of persons in the campus activities; unmanned aerial vehicle acquires the influence of activity time on campus activity traffic, specifically includes: the unmanned aerial vehicle acquires the pedestrian volume change before and after each activity time of the activity area, and predicts the pedestrian volume of the activity time; acquiring the pedestrian flow in the activity area at any moment, drawing a nuclear density curve on an x axis, judging that 'hour, week and month in one day' are variable drawing charts, fitting data with extreme values in the same chart, and acquiring a factor with high relevance of the pedestrian flow in the activity area; determining 'hours of day', 'weeks' and 'months' which can influence the flow of people in the active area; establishing a linear regression model according to the flow rates of people in different time of the activity area, and inputting variables to predict the flow rates of people in the holding time of the activity area; unmanned aerial vehicle obtains the influence that the place was held to the activity to campus activity traffic of people, specifically includes: on an individual, the activity of the teacher is random, and the individual is difficult to predict about the current idea; the activities of the students and the teacher in the school and the arrangement of school teaching activities are closely related on the whole, and the school teaching arrangement influences the gathering and flowing directions of the students in the same time; numbering event places suitable for holding events in a school, and acquiring image data of the pedestrian flow of each event holding place by using an unmanned aerial vehicle; and establishing a linear regression model for the flow of people in each event handling place at the same event time, taking the event region code as a variable, and inputting the variable to predict the flow of people in the event region at the event time.
5. The method of claim 1, wherein the drone obtains a promotional effect of media promotion of the campus campaign by monitoring in real time the traffic change of the campus campaign with the drone, determining the impact of the promotion on the traffic change; the method comprises the steps of acquiring images of activity areas before and after media propaganda through unmanned aerial vehicle remote sensing, inputting head data and propaganda activity modes into a convolutional neural network as characteristics after a head detection algorithm is adopted, acquiring the head number difference before and after activities through characteristic extraction, judging the influence of the activities on the area flow of people, and predicting the popularization suitability of schools; the method comprises the following steps: judging the most suitable propaganda mode of the campus according to the influence of various media propaganda campus activities on the increase rate of the human flow and the actual number of purchasers; the propaganda campus mode of judging the campus is most suitable through the influence of various media propaganda campus activities to traffic and actual purchasing population increase rate specifically includes: the propaganda effect is judged by the pedestrian volume in the activity area and the increase rate of the actual number of purchasers; the increase of the flow of people and the sales are in positive correlation, but invalid advertisements with the increase of the flow of people and the increase of the sales are not generated in the actual sales process; the actual purchasing behavior is difficult to judge, a purchasing area can be divided from an activity area frame image shot by the unmanned aerial vehicle, and the purchasing behavior is judged to exist when the unmanned aerial vehicle enters the purchasing area; through the change of the number of people who gets into the purchase region behind the unmanned aerial vehicle real-time supervision media propaganda, obtain the increase rate of purchasing behavior behind the campaign, acquire the actual effect of media campaign propaganda, judge the most suitable propaganda mode in campus.
6. The method of claim 1, wherein said determining the campus campaign-sponsored input-output ratio based on actual sales comprises promoting a campaign to attract customers and increase sales; determining whether the turnover is increased or not by monitoring and selecting proper time and activity places by the unmanned aerial vehicle, and eliminating the turnover change caused by time and product change; judging the activity effect of the campus activity by combining whether the sales volume of the area without activity is increased by the horizontal comparison data and whether the sales volume is increased after the activity is held by the vertical comparison data; the unmanned aerial vehicle renting is taken as a factor which influences the gross profit rate, and if the campus activity output ratio is low, the shooting content of the unmanned aerial vehicle is reduced; calculating the return on investment for the input budget and the output, and judging the input-output ratio; the method comprises the following steps: comparing sales before and after the activity, and judging the activity effect according to the sales rate; reducing the shooting content of the unmanned aerial vehicle for activities with poor input-output ratio; the data comparison is carried out to sales volume around the activity, and the activity effect is judged through the sales volume rate, and the method specifically comprises the following steps: the promotion activity has a definite target and needs to judge and evaluate the activity effect; carrying out actual evaluation on the activity effect by using a comprehensive comparison method and an input-output ratio method; the comprehensive comparison method needs to be combined with the situation that whether the sales volume of the horizontal comparison data is increased compared with the sales volume of the area without holding the event or not and whether the sales volume is increased after the vertical comparison data holds the event or not; the input-output ratio method is used for calculating the investment return rate of input budget and output and judging whether the input-output ratio is reasonable or not, and the investment return rate is better than the activity effect of the campus activities holding the campus activities; the activity to input-output ratio difference reduces unmanned aerial vehicle and shoots content, specifically includes: the unmanned aerial vehicle can monitor and judge the campus activity effect in real time, and can judge the campus activity input-output ratio by combining the turnover; according to monitoring of the campus people flow by the unmanned aerial vehicle, the time and the place with low people flow and poor activity hosting effect are obtained, and the investment of the unmanned aerial vehicle is reduced; and reducing the shooting content of the unmanned aerial vehicle for activities with poor input-output ratio.
7. The method of claim 1, wherein the unmanned aerial vehicle obtains campus activity promotion effects, and analyzes the fitness of campus activity types and students in the school through the promotion effects, and comprises the steps of monitoring the change of the flow of people in an activity area after the promotion of the campus activity in real time by using the unmanned aerial vehicle, and determining the influence of the campus activity promotion on the flow of people; and analyzing the fitness of the campus activity types and the students in the school according to the influence of each campus activity type on the human flow.
8. The method of claim 1, wherein said determining which times and places and which campaign categories to advertise may increase sales comprises: the index for evaluating the sales effect is sales volume which is in direct proportion to the passenger flow and the transaction rate; the factors influencing passenger flow are passenger flow, and the factors influencing transaction rate are activity types; the campus is a closed environment, the pedestrian volume is closely related to school teaching activity arrangement, the image data in the campus are collected in different regions and different time by using the unmanned aerial vehicle, a linear regression equation of the pedestrian volume with respect to time and place is obtained, the time and the place with the maximum pedestrian volume can be predicted through the linear regression equation, the pedestrian volume is in direct proportion to the passenger volume, and the moment with the maximum pedestrian volume is the moment with the maximum passenger volume; the method comprises the following steps that the transaction rate is related to the type of an activity, an unmanned aerial vehicle is used for obtaining image data of an activity scene, the number of persons participating in each activity and the participation degree of purchasing behavior are obtained through processing, and the transaction rate is obtained through calculation; through the passenger flow and the transaction rate, the time and place of the user are judged, and the advertisement propaganda is carried out on the activity types of the user, so that the sales volume is promoted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210532351.1A CN114841749B (en) | 2022-05-17 | Accurate business information pushing method based on LBS and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210532351.1A CN114841749B (en) | 2022-05-17 | Accurate business information pushing method based on LBS and machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114841749A true CN114841749A (en) | 2022-08-02 |
| CN114841749B CN114841749B (en) | 2024-05-28 |
Family
ID=
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160125456A1 (en) * | 2014-11-03 | 2016-05-05 | Ds-Iq, Inc. | Advertising campaign targeting using contextual data |
| CN110443634A (en) * | 2019-07-08 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of the dispensing address of vending machine |
| WO2020031315A1 (en) * | 2018-08-09 | 2020-02-13 | 株式会社ウフル | Stadium sales prediction system, method, and program |
| CN110969466A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Method and device for determining advertisement delivery area |
| CN111125288A (en) * | 2019-12-25 | 2020-05-08 | 北京市商汤科技开发有限公司 | Area deployment method, device and storage medium |
| KR20210065563A (en) * | 2019-11-27 | 2021-06-04 | 황희찬 | Method and system for managing work related to advertisement marketing |
| CN113239718A (en) * | 2021-03-05 | 2021-08-10 | 浙江科技学院 | Campus people flow rate statistical method |
| CN113570420A (en) * | 2021-09-23 | 2021-10-29 | 枣庄职业学院 | Big data based automatic selling data adjusting method |
| CN114331522A (en) * | 2021-12-24 | 2022-04-12 | 重庆杰夫与友文化创意有限公司 | Personalized advertisement broadcasting method and system based on user portrait and storage medium |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160125456A1 (en) * | 2014-11-03 | 2016-05-05 | Ds-Iq, Inc. | Advertising campaign targeting using contextual data |
| WO2020031315A1 (en) * | 2018-08-09 | 2020-02-13 | 株式会社ウフル | Stadium sales prediction system, method, and program |
| CN110969466A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Method and device for determining advertisement delivery area |
| CN110443634A (en) * | 2019-07-08 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The determination method, apparatus and server of the dispensing address of vending machine |
| KR20210065563A (en) * | 2019-11-27 | 2021-06-04 | 황희찬 | Method and system for managing work related to advertisement marketing |
| CN111125288A (en) * | 2019-12-25 | 2020-05-08 | 北京市商汤科技开发有限公司 | Area deployment method, device and storage medium |
| CN113239718A (en) * | 2021-03-05 | 2021-08-10 | 浙江科技学院 | Campus people flow rate statistical method |
| CN113570420A (en) * | 2021-09-23 | 2021-10-29 | 枣庄职业学院 | Big data based automatic selling data adjusting method |
| CN114331522A (en) * | 2021-12-24 | 2022-04-12 | 重庆杰夫与友文化创意有限公司 | Personalized advertisement broadcasting method and system based on user portrait and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 沈浩;崔成;王昕;季铁;: "基于人脸云数据数字标牌投放效果的研究", 包装工程, no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Roth | Validating the use of Internet survey techniques in visual landscape assessment—An empirical study from Germany | |
| US8433612B1 (en) | Method and system for measuring packaging effectiveness using video-based analysis of in-store shopper response | |
| de Dios Ortúzar et al. | Valuing reductions in environmental pollution in a residential location context | |
| Willberg et al. | Comparing spatial data sources for cycling studies: A review | |
| Palmer et al. | A deep learning approach to identify unhealthy advertisements in street view images | |
| Lepage et al. | Impact of weather, activities, and service disruptions on transportation demand | |
| Sakas et al. | The influence of websites user engagement on the development of digital competitive advantage and digital brand name in logistics startups | |
| CN114841749B (en) | Accurate business information pushing method based on LBS and machine learning | |
| Nordfält et al. | Utilising eye-tracking data in retailing field research: A practical guide | |
| CN114841749A (en) | Accurate business information pushing method based on LBS and machine learning | |
| Arora et al. | Marketing research | |
| Jou et al. | Route choice behaviour of freeway travellers under real-time traffic information provision–application of the best route and the habitual route choice mechanisms | |
| Simonov et al. | Attention Spillovers from News to Ads: Evidence from an Eye-Tracking Experiment | |
| Balkan et al. | Video analytics in market research | |
| CN110442794B (en) | Construction method of analyst portrait system | |
| US11151584B1 (en) | Method and system for collecting shopper response data tied to marketing and merchandising elements | |
| Smith | The role and changing nature of marketing intelligence | |
| Schouten et al. | Paradata as input to monitoring representativeness and measurement profiles: A case study of the Dutch Labour Force Survey | |
| Addicam et al. | Adaptive advertisement recommender systems for digital signage | |
| Bianco et al. | Automated Detection of Street-Level Tobacco Advertising Displays | |
| KARAMAN | Integration of People Counter Systems to Decision Support Systems in Clothing Retail Industry: A Preliminary Analysis and Possible Applications. | |
| Zhu | Individual Preference Learning with Collaborative Learning Framework | |
| Kholod et al. | Is Video Analytics a Game Changer for Market Research? | |
| Nazmul | Observing and Estimating the Switching Intentions of Existing Consumers towards New Ethnic Indian Restaurant in Helsinki. | |
| Dapperen | The effect of COVID-19 on the behavioural profiles of university website visitors |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 609, No. 3 Yunchuang Street, Huangpu District, Guangzhou City, Guangdong Province, 510000 Applicant after: Xinyang Internet Technology (Guangzhou) Co.,Ltd. Address before: 510000 301-310-075, No. 16, Lingshan East Road, Tianhe District, Guangzhou, Guangdong Province Applicant before: Guangdong Xinyang Internet Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant |