CN112383702A - Panoramic photo obtaining method based on hotel check-in personnel and advertisement pushing method - Google Patents
Panoramic photo obtaining method based on hotel check-in personnel and advertisement pushing method Download PDFInfo
- Publication number
- CN112383702A CN112383702A CN202011121853.2A CN202011121853A CN112383702A CN 112383702 A CN112383702 A CN 112383702A CN 202011121853 A CN202011121853 A CN 202011121853A CN 112383702 A CN112383702 A CN 112383702A
- Authority
- CN
- China
- Prior art keywords
- hotel
- panoramic
- personnel
- photos
- check
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The invention relates to a panoramic photo acquisition method and an advertisement pushing method based on hotel check-in personnel, which are used for acquiring a plurality of personal panoramic photos of hotel check-in personnel from different angles when a person is checked to check in and register; extracting related panoramic photos of hotel resident persons at different angles from the collected personal panoramic photos at different angles; panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel. Obtaining a matched list of the brand information of the advertisement to be played through the user attribute; the method effectively solves the problems that the information obtained by analyzing the existing figure photos from a single angle is one-sided and inaccurate, and the grade and the value of the information are grouped according to the consumption behaviors and the consumption capacities of the customers, so that more characteristic marketing contents can be formulated according to the characteristics of the customers and accurate advertisements can be pushed for the pushing of the customers with high consumption capacity and the customers with low consumption capacity.
Description
Technical Field
The invention belongs to the technical field of hotel image processing, and particularly relates to a panoramic photo obtaining method and an advertisement pushing method based on hotel check-in personnel.
Background
The precise marketing of consumers becomes the next battlefield of the shopping center, and as the competition of the shopping center is increased, more and more shopping malls start to lean on the quality control data for fine management. The so-called 'precise marketing' refers to analyzing the consumption habits of users by means of the development of big data, marking exclusive labels on the consumption behaviors of the users, drawing user figures according to the label contents, and then pushing business information in a targeted manner. That is, the user profile is the key basis for accurate marketing! The user portrait can be roughly divided into information data and behavior data, wherein the information data comprises height, weight, marriage and education degree and the like; behavioral data includes shopping habits, consumption habits, travel, investments, hobbies, and the like;
the essence of precision marketing is to deliver a message to the user. The information that a client needs at present can only exert the maximum effect on the accurate marketing!
The problems existing at present are as follows:
for the hotel checked-in personnel, due to the inconvenience of disclosure of private privacy in all aspects, the information data and behavior data of the checked-in personnel are difficult to obtain so as to form the user portrait, so that the scenic spots around the hotel and the commercial shopping centers, namely merchants of all brands, basically cannot realize the accurate marketing of the hotel checked-in personnel in the prior art. For the hotel attendants, the hotel attendants are basically unfamiliar with surrounding scenic spots and commercial shopping centers, and the situations that the merchant cannot find the articles and the hotel attendants are unfamiliar with the articles occur. In the related art, there is no technical solution to solve the problem.
The accurate pushing can be said to be a large trend of advertisement pushing nowadays, especially the advertisement pushing of a large-scale information flow, and as the contact between the user and the internet is more compact and the technology is continuously updated iteratively, the 'accurate' is more intense, which is the development trend of the advertisement.
Therefore, the creation of the user portrait is very important. The simplest and straightforward way to capture a user representation is by means of a photograph. The attribute labels of the age, the gender, the height, the weight, the brand preference, the consumption ability and the like of the user can be obtained through the photo. However, at present, a 2D character photo can only be acquired through a foreground terminal, and the data value obtained by analyzing the photo is not large due to only one shooting angle, so that the data value is relatively high. Only the panoramic photo of the person can show all things in a certain range in a multi-azimuth and more comprehensive manner, so that the learned information is more direct and comprehensive.
Disclosure of Invention
And analyzing the panoramic photo of the person to obtain some wearing brands of the user and a consumption capacity corresponding to the wearing brands. These attributes are obtained.
The user dresses, and the selection to the brand mostly all can have own custom or hobby, and the brand advertisement that the propelling movement oneself was used commonly, and the effect will be done a lot more.
If the grade and the value are grouped according to the consumption behaviors and the consumption capacity of the customers, more distinctive marketing contents can be formulated according to the characteristics of the customers for pushing some customers with high consumption capacity and customers with low consumption capacity.
However, in the existing person photos obtained from a single angle, the information obtained by analysis is one-sided and inaccurate, the view range is limited, and a complete person photo cannot be obtained possibly, and a partial picture is lacked. The prior patents and prior art have not found any relevant art to solve this problem.
Therefore, the application provides an aspect of providing a method for acquiring a panoramic photo of a person living in a hotel, which comprises the following steps:
4 cameras are arranged in the front, back, left and right of a hotel foreground testimony checking area, and are in the same network with the testimony checking all-in-one machine;
when a hotel check-in person checks check-in registration before the testimony checking integrated machine, collecting a plurality of personal panoramic photos of the hotel check-in person from different angles;
extracting related panoramic photos of the hotel check-in personnel at different angles from the collected personal panoramic photos at different angles according to the acquired face information of the hotel check-in personnel during the testimony verification;
panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel.
Furthermore, a plurality of panoramic photos of hotel accommodations from different angles are extracted from the collected personal panoramic photos from different angles, and the following method is adopted:
acquiring a front photo of a hotel resident by a front camera, and segmenting the hotel resident and a scene by a face recognition and person recognition method;
obtaining a left photo and a right photo from the scene photos of the left camera and the right camera, segmenting people, and removing the interference of the scene;
the front camera and the rear camera are in mirror image positions, when the coordinate position of a person shot by the front camera is obtained, the position of the person appearing in the rear camera is reversely deduced, the person is segmented according to the picture transmitted by the rear camera through an object recognition and color recognition algorithm, scene interference is removed, and the person picture on the back is obtained.
Further, the 4 acquired processed photos are spliced to establish a person 3D model, so that the three-dimensional panoramic photo of the resident is acquired.
Further, the upper body and lower body clothes are identified in style and color according to the divided pictures of the persons living in the hotel, and the acquired person parameter information is obtained.
Further, the figure parameter information comprises face information, clothes style, clothes color, height, three-dimension and estimated weight.
Further, the obtained three-dimensional panoramic photo is processed, a brand list worn by the user and the value corresponding to the brand list are obtained, and the brand preference and consumption level attributes of the user are generated.
Further, the attributes of the age, the gender and the birthday acquired when the person certificate is checked in and registered, the brand preference and the consumption level attribute of the generated user are transmitted to the cloud platform.
Further, when the transactor checks check-in and check-in, panoramic photos of the hotel check-in personnel at different angles are obtained, and the processing mode of the temporarily-unavailable view angle photos is as follows:
and splicing the divided photos of the plurality of visual angles, and temporarily reserving the unrecognized visual angles. And marking the panoramic photo to indicate lack of a visual angle;
transmitting the identifiable figure parameter information and the corresponding attributes to a cloud platform;
when the testimony checking all-in-one machine is in a non-working state, namely no resident is transacted, the system is configured with a dynamic face recognition system, and people in the monitored area of a face recognition monitoring camera of the access system are accurately captured by the face recognition system to obtain a clear face image;
if the resident with the missing visual angle appears in the dynamic face recognition process, the photo of the person with the missing visual angle is obtained through the previous process until the panoramic photo file of the person is built step by step.
The invention also provides an advertisement pushing method, which adopts the method for acquiring the panoramic photos of the hotel attendants; also comprises
Transmitting the panoramic image containing the wearing brand of the hotel resident to the platform and the corresponding user attribute;
the cloud platform carries out picture analysis on the received panoramic image to obtain the information of the brand worn by the hotel resident; according to the obtained attribute of brand preference, consumption level attribute, age, sex and birthday of user
Obtaining a matched list of the brand information of the advertisement to be played;
and pushing the brand information list of the advertisement to be played to the hotel witness verification terminal all-in-one machine, so that when the hotel witness verification terminal all-in-one machine verifies the identity information of the client, the customized brand information list of the advertisement to be played is loaded for playing.
By adopting the technical scheme, the invention has the following beneficial effects:
1. the invention solves the problems that the information obtained by analyzing the existing figure photos obtained from a single angle is one-sided and inaccurate, and extracts related panoramic photos of the hotel presence personnel from a plurality of personal panoramic photos from different angles according to the face information of the hotel presence personnel obtained during the testimony verification; panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel.
2. Corresponding to the limitation of the view finding range, a complete figure photo can not be obtained, and the situation of partial image lack can not be obtained.
3. Adopt this technical scheme can accomplish according to the hotel personnel of living in and dress the brand, the advertisement of propelling movement looks adaptation, and the user is dressed and mostly can have own custom or hobby to the selection of brand, and the brand advertisement that the propelling movement oneself was used commonly used, and the effect will make a result in a lot of more.
4. The grade and the value are grouped according to the consumption behaviors and the consumption capacity of the customers, and more distinctive marketing contents can be formulated according to the characteristics of the customers and accurate advertisements can be pushed for the pushing of some customers with high consumption capacity and customers with low consumption capacity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the camera of the present invention in the same network as the witness check machine;
FIG. 2 is a flow chart of a panoramic photo acquisition method of the present invention;
fig. 3 is a schematic diagram of a specific embodiment of the method for acquiring a panoramic photo according to the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of systems consistent with certain aspects of the invention, as detailed in the appended claims.
As shown in fig. 1, the present embodiment provides a method for obtaining a panoramic photo of a person living in a hotel, including:
4 cameras are arranged in the front, back, left and right of a hotel foreground testimony checking area, and are in the same network with the testimony checking all-in-one machine;
when a hotel check-in person checks check-in registration before the testimony checking integrated machine, collecting a plurality of personal panoramic photos of the hotel check-in person from different angles;
extracting related panoramic photos of the hotel check-in personnel at different angles from the collected personal panoramic photos at different angles according to the acquired face information of the hotel check-in personnel during the testimony verification;
panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel.
As a preferred embodiment, a plurality of panoramic photographs of hotel room-entering personnel at different angles are extracted from a plurality of panoramic photographs of individuals at different angles, and the following method is adopted:
acquiring a front photo of a hotel resident by a front camera, and segmenting the hotel resident and a scene by a face recognition and person recognition method;
obtaining a left photo and a right photo from the scene photos of the left camera and the right camera, segmenting people, and removing the interference of the scene;
the front camera and the rear camera are in mirror image positions, when the coordinate position of a person shot by the front camera 1 is obtained, the position of the person appearing in the rear camera is reversely deduced, the person is segmented according to the pictures transmitted by the rear camera through object recognition and a color recognition algorithm, scene interference is removed, and the person picture on the back is obtained.
In a preferred embodiment, the acquired 4 processed photos are spliced to create a 3D model of a person, so as to acquire a three-dimensional panoramic photo of the resident.
As a preferred embodiment, the upper and lower body clothes pattern recognition and color recognition are performed on the divided picture of the stay person in the hotel, and the acquired character parameter information is obtained. The figure parameter information comprises face information, clothes style, clothes color, height, three-dimension and estimated weight. And processing the obtained three-dimensional panoramic photo, obtaining a brand list worn by the user and the value corresponding to the brand list, and generating the brand preference and consumption level attributes of the user. And transmitting the attributes of the age, the gender and the birthday obtained when the testimony of the person is checked to check in registration, the generated user brand preference and the consumption level attribute to a cloud platform.
In a preferred embodiment, when the transactor checks the check-in registration, a plurality of panoramic photographs of the hotel checked-in personnel at different angles are obtained, and the processing method of the perspective photographs which are not obtained temporarily is as follows:
and splicing the divided photos of the plurality of visual angles, and temporarily reserving the unrecognized visual angles. And marking the panoramic photo to indicate lack of a visual angle;
transmitting the identifiable figure parameter information and the corresponding attributes to a cloud platform;
when the testimony checking all-in-one machine is in a non-working state, namely no resident is transacted, the system is configured with a dynamic face recognition system, and people in the monitored area of a face recognition monitoring camera of the access system are accurately captured by the face recognition system to obtain a clear face image;
if the resident with the missing visual angle appears in the dynamic face recognition process, the photo of the person with the missing visual angle is obtained through the previous process until the panoramic photo file of the person is built step by step.
Please refer to fig. 1 and 3 to provide a specific embodiment:
1. 4 cameras are arranged in the front, back, left and right of the hotel foreground and are in the same network with the human-certificate checking all-in-one machine. The device is used for taking photos of guests in the hotel, such as front photos, left photos, right photos, rear photos and 4 visual angles.
2. Guests transact the check-in program in the hotel foreground, and the witnesses are compared in a mode of swiping the witnesses before the front witness checking integrated machine.
3. The testimony checking machine sends shooting request to the camera (front side), the camera (left side), the camera (right side) and the camera (back side)
4. And (4) shooting by a camera (front side), acquiring a front side photo of the guest, and returning the shot photo content to the testimony checking all-in-one machine.
5. The testimony inspection all-in-one machine is used for obtaining the front photo shot by the camera (front), and then dividing the resident and the scene through algorithms such as face recognition and figure recognition, so that the interference of algorithm recognition is reduced.
6. And the testimony checking integrated machine is used for identifying the patterns of the upper and lower clothes, identifying the color and the like of the processed front photos. And the figure parameter information obtained from the front photo.
7. And the testimony all-in-one machine is used for acquiring face information, clothes styles, colors and the like after processing according to algorithms such as face algorithm, object recognition, color recognition and the like. From the camera (left side), the camera (right side) of the scene picture. And acquiring the left photo and the right photo of the person, segmenting the person, and removing the interference of the scene.
8. The position of the camera (rear side) and the position of the camera (front side) are in mirror image positions, when the coordinate position of a person shot by the camera (front side) is obtained, the position of the person appearing on the camera (rear side) can be reversely deduced, and the person is segmented according to the picture transmitted by the camera (rear side) by an object recognition and color recognition algorithm, so that the scene interference is removed, and the picture of the person on the back is taken.
9. And the testimony checking terminal splices the 4 acquired processed photos. Establishing a 3D model of a person to obtain a panoramic photo of a resident
10. And identifying the acquired scene photos by applying an algorithm, acquiring a brand list worn by the user and the value corresponding to the brand list, and generating the brand preference and the consumption level attribute of the user.
11. Acquiring the height and weight attributes of the user through an algorithm;
12. and (3) obtaining the panoramic photo synthesized by the end user through attributes such as age, gender and birthday obtained by evidence reading and attributes such as brand preference, consumption level, height and weight obtained by an algorithm. And (5) transmitting to the platform.
13. The platform obtains the attribute label of the user, and returns an advertisement list to the human evidence checking all-in-one machine through data analysis.
14. And playing the advertisement list by the testimony examination all-in-one machine.
The above flows are 4 machine positions, and can obtain a complete flow of 4 photos at the front, the left side, the side and the back without shielding, in an actual application scene, the photos at other visual angles can be found on the left side and the right side of a guest and are followed by other interfering people, so that the photos cannot be identified and obtained, and the splitting condition occurs
1. And (4) taking the scene pictures shot at the 4 positions at the witness all-in-one machine for identification. There may be cases where 1 or more viewing angles, such as left, right, back, etc., are not available,
2. at that time, the witness integrated machine can be spliced by using 1 or more identified visual angles, and the visual angles which cannot be identified are temporarily reserved. And identifies the panoramic photograph noting the lack of a viewing angle.
3. And the testimony inspection all-in-one machine acquires the advertisement list from the cloud platform through the recognizable character characteristics and plays the advertisement list.
4. When the testimony checking all-in-one machine is in a non-working state, namely no resident is transacted, the system is a set of system with dynamic face recognition, and people in the monitoring area monitored by the face recognition monitoring camera of the access system are accurately captured by the face recognition monitoring camera to obtain clear face images.
5. If the resident with the missing visual angle appears in the dynamic face recognition process, the photo of the person with the missing visual angle is obtained through the previous process until the panoramic photo file of the person is built step by step.
The invention also provides an advertisement pushing method, which adopts the method for acquiring the panoramic photos of the hotel attendants; also comprises
Transmitting the panoramic image containing the wearing brand of the hotel resident to the platform and the corresponding user attribute;
the cloud platform carries out picture analysis on the received panoramic image to obtain the information of the brand worn by the hotel resident; according to the obtained attribute of brand preference, consumption level attribute, age, sex and birthday of user
Obtaining a matched list of the brand information of the advertisement to be played;
and pushing the brand information list of the advertisement to be played to the hotel witness verification terminal all-in-one machine, so that when the hotel witness verification terminal all-in-one machine verifies the identity information of the client, the customized brand information list of the advertisement to be played is loaded for playing.
By adopting the technical scheme, the problem that the information obtained by analyzing the existing figure photos obtained from a single angle is one-sided and inaccurate is solved, and related panoramic photos of the hotel check-in personnel at different angles are extracted from the collected personal panoramic photos at different angles according to the face information of the hotel check-in personnel obtained during the testimony verification; panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel. Corresponding to the limitation of the view finding range, a complete figure photo can not be obtained, and the situation of partial image lack can not be obtained. Adopt this technical scheme can accomplish according to the hotel personnel of living in and dress the brand, the advertisement of propelling movement looks adaptation, and the user is dressed and mostly can have own custom or hobby to the selection of brand, and the brand advertisement that the propelling movement oneself was used commonly used, and the effect will make a result in a lot of more. The grade and the value are grouped according to the consumption behaviors and the consumption capacity of the customers, and more distinctive marketing contents can be formulated according to the characteristics of the customers and accurate advertisements can be pushed for the pushing of some customers with high consumption capacity and customers with low consumption capacity. Under the hotel scene, based on image recognition, the method puts advertisements of corresponding brands on the wearing brands of the passengers living in, and groups the consumption capacity of the advertisements in grade and value, so as to push customized advertisements.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (9)
1. A panoramic photo obtaining method based on hotel check-in personnel is characterized by comprising the following steps: comprises that
4 cameras are arranged in the front, back, left and right of a hotel foreground testimony checking area, and are in the same network with the testimony checking all-in-one machine;
when a hotel check-in person checks check-in registration before the testimony checking integrated machine, collecting a plurality of personal panoramic photos of the hotel check-in person from different angles;
extracting related panoramic photos of the hotel check-in personnel at different angles from the collected personal panoramic photos at different angles according to the acquired face information of the hotel check-in personnel during the testimony verification;
panoramic pictures of hotel check-in personnel at different angles are synthesized to obtain panoramic images containing brand dressed by the hotel check-in personnel.
2. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 1, wherein: the method comprises the following steps of extracting related panoramic photos of hotel resident persons at different angles from a plurality of collected personal panoramic photos at different angles, and adopting the following method:
acquiring a front photo of a hotel resident by a front camera, and segmenting the hotel resident and a scene by a face recognition and person recognition method;
obtaining a left photo and a right photo from the scene photos of the left camera and the right camera, segmenting people, and removing the interference of the scene;
the front camera and the rear camera are in mirror image positions, when the coordinate position of a person shot by the front camera is obtained, the position of the person appearing in the rear camera is reversely deduced, the person is segmented according to the picture transmitted by the rear camera through an object recognition and color recognition algorithm, scene interference is removed, and the person picture on the back is obtained.
3. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 2, characterized in that: and splicing the obtained 4 processed photos to establish a 3D model of a person, so as to obtain the three-dimensional panoramic photo of the resident.
4. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 3, wherein: and carrying out upper body and lower body clothes pattern recognition and color recognition on the split pictures of the persons living in the hotel, and obtaining the character parameter information.
5. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 4, wherein: the figure parameter information comprises face information, clothes style, clothes color, height, three-dimension and estimated weight.
6. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 3, wherein: and processing the obtained three-dimensional panoramic photo, obtaining a brand list worn by the user and the value corresponding to the brand list, and generating the brand preference and consumption level attributes of the user.
7. The panoramic photo obtaining method based on hotel check-in personnel as claimed in claim 6, wherein: and transmitting the attributes of the age, the gender and the birthday obtained when the testimony of the person is checked to check in registration, the generated user brand preference and the consumption level attribute to a cloud platform.
8. The method for acquiring the panoramic photo based on the hotel attendees according to any one of claims 2 to 7, wherein: when the transactor certificate checks in and registers, panoramic photos of hotel check-in personnel at different angles are obtained, and the processing mode of the temporarily-unavailable view angle photos is as follows:
splicing the divided photos of the plurality of visual angles, temporarily reserving the unrecognized visual angles, and identifying the panoramic photo to indicate the lack of the visual angles;
transmitting the identifiable figure parameter information and the corresponding attributes to a cloud platform;
when the testimony checking all-in-one machine is in a non-working state, namely no resident is transacted, the system is configured with a dynamic face recognition system, and people in the monitored area of a face recognition monitoring camera of the access system are accurately captured by the face recognition system to obtain a clear face image;
if the resident with the missing visual angle appears in the dynamic face recognition process, the photo of the person with the missing visual angle is obtained through the previous process until the panoramic photo file of the person is built step by step.
9. The advertisement pushing method is characterized by comprising the following steps: adopting the panoramic photo acquisition method of the hotel resident according to any one of the claims 1 to 8; also comprises
Transmitting the panoramic image containing the wearing brand of the hotel resident to the platform and the corresponding user attribute;
the cloud platform carries out picture analysis on the received panoramic image to obtain the information of the brand worn by the hotel resident; obtaining a matched list of the brand information of the advertisement to be played according to the obtained user brand preference, consumption level attribute, age, gender and birthday;
and pushing the brand information list of the advertisement to be played to the hotel witness verification terminal all-in-one machine, so that when the hotel witness verification terminal all-in-one machine verifies the identity information of the client, the customized brand information list of the advertisement to be played is loaded for playing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011121853.2A CN112383702A (en) | 2020-10-20 | 2020-10-20 | Panoramic photo obtaining method based on hotel check-in personnel and advertisement pushing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011121853.2A CN112383702A (en) | 2020-10-20 | 2020-10-20 | Panoramic photo obtaining method based on hotel check-in personnel and advertisement pushing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112383702A true CN112383702A (en) | 2021-02-19 |
Family
ID=74580193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011121853.2A Pending CN112383702A (en) | 2020-10-20 | 2020-10-20 | Panoramic photo obtaining method based on hotel check-in personnel and advertisement pushing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112383702A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008257216A (en) * | 2007-03-12 | 2008-10-23 | Akira Tomono | Information presentation device for general public |
| CN102243650A (en) * | 2010-06-01 | 2011-11-16 | 微软公司 | Generating tailored content based on scene image detection |
| CN103080963A (en) * | 2010-08-11 | 2013-05-01 | 瑞典爱立信有限公司 | Face-directional recognition driven display controL |
| CN109461036A (en) * | 2018-12-04 | 2019-03-12 | 深圳阜时科技有限公司 | A kind of advertisement play back device |
| CN111401160A (en) * | 2020-03-03 | 2020-07-10 | 北京三快在线科技有限公司 | Hotel authentication management method, system and platform and hotel PMS system |
-
2020
- 2020-10-20 CN CN202011121853.2A patent/CN112383702A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008257216A (en) * | 2007-03-12 | 2008-10-23 | Akira Tomono | Information presentation device for general public |
| CN102243650A (en) * | 2010-06-01 | 2011-11-16 | 微软公司 | Generating tailored content based on scene image detection |
| CN103080963A (en) * | 2010-08-11 | 2013-05-01 | 瑞典爱立信有限公司 | Face-directional recognition driven display controL |
| CN109461036A (en) * | 2018-12-04 | 2019-03-12 | 深圳阜时科技有限公司 | A kind of advertisement play back device |
| CN111401160A (en) * | 2020-03-03 | 2020-07-10 | 北京三快在线科技有限公司 | Hotel authentication management method, system and platform and hotel PMS system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI700612B (en) | Information display method, device and system | |
| US10698558B2 (en) | Automatic tagging of objects on a multi-view interactive digital media representation of a dynamic entity | |
| JP6850291B2 (en) | Methods and devices for minimizing false positives in face recognition applications | |
| Sundberg et al. | Occlusion boundary detection and figure/ground assignment from optical flow | |
| US20190278434A1 (en) | Automatic tagging of objects on a multi-view interactive digital media representation of a dynamic entity | |
| JP6267861B2 (en) | Usage measurement techniques and systems for interactive advertising | |
| EP4260286A1 (en) | Virtual clothing try-on | |
| AU2016291660A1 (en) | Apparatus and methods for facial recognition and video analytics to identify individuals in contextual video streams | |
| CN105005777A (en) | Face-based audio and video recommendation method and face-based audio and video recommendation system | |
| JP6500374B2 (en) | Image processing apparatus and image processing program | |
| Rhee et al. | Cartoon-like avatar generation using facial component matching | |
| US10212408B1 (en) | Depth-map augmentation techniques | |
| US20190318491A1 (en) | System and method for gathering data related to quality service in a customer service environment | |
| CN108090422A (en) | Hair style recommends method, Intelligent mirror and storage medium | |
| CN111008935A (en) | Face image enhancement method, device, system and storage medium | |
| AU2017231602A1 (en) | Method and system for visitor tracking at a POS area | |
| Jampour et al. | Face inpainting based on high-level facial attributes | |
| US20230111437A1 (en) | System and method for content recognition and data categorization | |
| KR101817773B1 (en) | An Advertisement Providing System By Image Processing of Depth Information | |
| KR102178396B1 (en) | Method and apparatus for manufacturing image output based on augmented reality | |
| Zollhöfer et al. | Interactive model‐based reconstruction of the human head using an RGB‐D sensor | |
| CN110889006A (en) | Recommendation method and device | |
| CN112508595A (en) | Advertisement putting method for putting corresponding advertisement based on wearing brand of hotel stay personnel | |
| JP2008046691A (en) | Face image processor and program for computer | |
| US20180232781A1 (en) | Advertisement system and advertisement method using 3d model |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210219 |
|
| WD01 | Invention patent application deemed withdrawn after publication |