CN108269128B - Advertisement putting method, device, equipment and storage medium - Google Patents
Advertisement putting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN108269128B CN108269128B CN201810058305.6A CN201810058305A CN108269128B CN 108269128 B CN108269128 B CN 108269128B CN 201810058305 A CN201810058305 A CN 201810058305A CN 108269128 B CN108269128 B CN 108269128B
- Authority
- CN
- China
- Prior art keywords
- user
- users
- advertisement
- point
- image information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The disclosure relates to a method, a device, equipment and a storage medium for delivering advertisements, wherein the method comprises the following steps: acquiring image information of a plurality of first users; analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period; establishing a corresponding relation between the user portrait and the attention point; and pushing target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation and the first user portrait, wherein the target advertisement content comprises a focus corresponding to the first user portrait. The method and the device can improve the hit rate of the advertisement.
Description
Technical Field
The present disclosure relates to the field of electronic devices, and in particular, to a method, an apparatus, a device, and a storage medium for advertisement delivery.
Background
Advertising is a means of publicizing and widely delivering information to the public through a certain form of media for a specific need. Through the advertisement, the user can know and generate interest for the product, and then the product transaction and other behaviors occur.
In the related art, in both indoor and outdoor advertisement systems, the advertisement platform generally downloads the advertisement from the central server automatically for playing, and may also play the advertisement according to the geographical location or according to the content specified by the user, so as to achieve the purpose of watching by the user.
Disclosure of Invention
To overcome the problems in the related art, the present disclosure provides a method, an apparatus, a device, and a storage medium for advertisement delivery.
According to a first aspect of the embodiments of the present disclosure, there is provided an advertisement delivery method, including:
acquiring image information of a plurality of first users;
analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
establishing a corresponding relation between the user portrait and the attention point;
and pushing target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation and the first user portrait, wherein the target advertisement content comprises a focus corresponding to the first user portrait.
Optionally, the pushing, to an advertisement platform, the target advertisement content matched with the first user portrait according to the correspondence and the first user portrait includes:
determining the focus point of the first user portrait according to the corresponding relation between the user portrait and the focus point;
determining target advertisement content corresponding to the attention point of the first user portrait according to the corresponding relation between the attention point and the advertisement content;
and sending target advertisement content corresponding to the attention point of the first user portrait to the advertisement platform.
Optionally, the analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period includes:
analyzing the image information of the plurality of first users to obtain user figures of the first users;
clustering the user figures of the first users by adopting a clustering algorithm to obtain a plurality of first user figure categories;
determining a second user representation category based on the number of user representations in each of the first user representation categories, the second user representation category being the first user representation category containing the greatest number of user representations;
a user representation in the second user representation category is determined to be the first user representation.
Optionally, the establishing a correspondence between the user representation and the attention point includes:
acquiring voice information of a plurality of second users and image information corresponding to the second users;
extracting key words in the voice information, and determining the attention points of the second users according to the key words;
analyzing the image information of each second user to obtain a user portrait of each second user;
and training the attention points of the second users and the corresponding user figures of the second users to establish the corresponding relation between the user figures and the attention points.
Optionally, the establishing a correspondence between the user representation and the attention point includes:
receiving a plurality of advertisement images and corresponding user images sent by a camera; the user image is an image of a third user who stays and watches the advertisement image for a time exceeding a preset threshold value;
according to each advertisement image, determining the attention point of each third user;
analyzing the image information of each third user to obtain the user portrait of each third user;
and training the attention points of the third users and the corresponding user figures of the third users to establish the corresponding relation between the user figures and the attention points.
Optionally, the acquiring image information of a plurality of first users includes:
receiving video information sent by a camera; the video information comprises image information of a plurality of first users;
and analyzing the video information to obtain the image information of the plurality of first users.
According to a second aspect of the embodiments of the present disclosure, there is provided an advertisement delivery device, including:
an acquisition module configured to acquire image information of a plurality of first users;
the analysis module is configured to analyze the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
the establishing module is configured to establish a corresponding relation between the user portrait and the attention point;
and the pushing module is configured to push target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation and the first user portrait, wherein the target advertisement content comprises a focus point corresponding to the first user portrait. .
Optionally, the pushing module includes:
a first determination submodule configured to determine a point of interest of the first user representation according to a preset correspondence between the user representation and the point of interest;
a second determining sub-module configured to determine a target advertisement content corresponding to the point of interest of the first user representation according to a corresponding relationship between the point of interest and the advertisement content;
a sending sub-module configured to send targeted advertising content corresponding to a point of interest of the first user representation to the advertising platform.
Optionally, the analysis module comprises:
the analysis submodule is configured to analyze the image information of the plurality of first users to obtain user portraits of the first users;
the processing submodule is configured to perform clustering processing on the user figures of the first users by adopting a clustering algorithm to obtain a plurality of first user figure categories;
a third determination submodule configured to determine a second user representation category based on the number of user representations in each of the first user representation categories, the second user representation category being the first user representation category containing the greatest number of user representations;
a fourth determination submodule configured to determine a user representation in the second user representation category as the first user representation.
Optionally, the establishing module includes:
a first obtaining sub-module configured to obtain voice information of a plurality of second users and image information corresponding to each of the second users;
the extraction sub-module is configured to extract key words in the voice information;
a fifth determining submodule configured to determine a point of interest of each of the second users according to the keyword;
a first analysis sub-module configured to analyze the image information of each of the second users to obtain a user portrait of each of the second users;
and the first establishing sub-module is configured to train the attention points of the second users and the corresponding user figures of the second users so as to establish the corresponding relation between the user figures and the attention points.
Optionally, the establishing module includes:
the first receiving submodule is configured to receive a plurality of advertisement images and corresponding user images sent by the camera; the user image is an image of a third user who stays and watches the advertisement image for a time exceeding a preset threshold value;
a sixth determining sub-module configured to determine, from each of the advertisement images, a point of interest of each of the third users;
the second analysis submodule is configured to analyze the image information of each third user to obtain a user portrait of each third user;
and the second establishing submodule is configured to train the attention points of the third users and the corresponding user figures of the third users so as to establish the corresponding relation between the user figures and the attention points.
Optionally, the obtaining module includes:
the second receiving submodule is configured to receive video information sent by the camera; the video information comprises image information of a plurality of users;
and the third analysis sub-module is configured to analyze the video information to obtain image information of the plurality of first users.
According to a third aspect of the embodiments of the present disclosure, there is provided a server, including:
a processor;
a memory configured to store processor-executable instructions;
wherein the processor is configured to:
acquiring image information of a plurality of first users;
analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
establishing a corresponding relation between the user portrait and the attention point;
and pushing target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation and the first user portrait, wherein the target advertisement content comprises a focus corresponding to the first user portrait.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of the first aspect.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
the method comprises the steps of obtaining image information of a plurality of first users, analyzing the image information of the first users, obtaining a first user portrait in a preset area within a preset time period, then establishing a corresponding relation between the user portrait and a focus point, and pushing target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation between the user portrait and the focus point and the first user portrait, wherein the advertisement content comprises the focus point corresponding to the target user portrait. The server analyzes the image information of the first user in the preset area within the preset time period, and after the first user portrait is obtained, the server puts advertisements aiming at the first user portrait according to the established corresponding relation between the user portrait and the attention point, so that the hit rate of the advertisements can be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a method of placement of an advertisement in accordance with an exemplary embodiment;
FIG. 2 is a flow chart illustrating a method of placement of an advertisement according to another exemplary embodiment;
FIG. 3 is a flow chart illustrating a method of placement of an advertisement according to yet another exemplary embodiment;
FIG. 4 is a flow chart illustrating a method of placement of an advertisement according to yet another exemplary embodiment;
FIG. 5 is a flow chart illustrating a method of placement of an advertisement according to yet another exemplary embodiment;
FIG. 6 is a block diagram illustrating an apparatus for placement of an advertisement in accordance with an exemplary embodiment;
FIG. 7 is a block diagram illustrating an apparatus for placement of an advertisement according to another exemplary embodiment;
FIG. 8 is a block diagram illustrating an apparatus for placement of an advertisement according to yet another exemplary embodiment;
FIG. 9 is a block diagram illustrating an apparatus for placement of an advertisement according to yet another exemplary embodiment;
FIG. 10 is a block diagram illustrating an apparatus for placement of an advertisement according to yet another exemplary embodiment;
FIG. 11 is a block diagram illustrating an apparatus for placement of an advertisement according to yet another exemplary embodiment;
FIG. 12 is a block diagram illustrating an entity of a server in accordance with an illustrative embodiment;
fig. 13 is a block diagram illustrating a placement device for advertisements, according to an example embodiment.
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 apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
In the existing advertisement system, usually, an advertisement platform automatically downloads advertisements from a central server for playing, and the advertisements can also be played according to geographical positions or contents specified by users, so that the purpose of watching by the users is achieved. However, in the related art, a fixed advertisement is usually played within a preset time period, so that the hit rate of the advertisement is low.
Therefore, the advertisement delivery method provided by the embodiments of the present disclosure is intended to solve the above technical problem, and specific implementation manners are referred to the following embodiments.
The following describes in detail a method for delivering an advertisement according to an embodiment of the present disclosure with reference to the accompanying drawings.
Fig. 1 is a flowchart illustrating a method for delivering an advertisement according to an exemplary embodiment, where the method for delivering an advertisement according to the present embodiment is used in a server, as shown in fig. 1. The advertisement putting method comprises the following steps:
in step S11, image information of a plurality of first users is acquired.
In the embodiment of the disclosure, after the camera shoots the video information, the shot video information is sent to the server, and the server analyzes the video information to obtain the image information of the plurality of first users. The video information may be video information obtained by shooting in a preset area within a preset time period by a camera, and therefore, the image information of the plurality of first users obtained by the server will include all the image information of the users appearing in the video information.
In addition, the server may be a dedicated advertisement server, or may be a large website server having an advertisement server function, and the specific type of the server is not limited in the present disclosure.
In step S12, the image information of the plurality of first users is analyzed to obtain a first user profile within a preset area within a preset time period.
In the embodiment of the present disclosure, after acquiring the image information of the plurality of first users, the server analyzes the image information of each first user through an image recognition technology in the related art to obtain the user portrait of each first user within a preset time period and in a preset area. Wherein the user representation includes age and gender information of the first user. It should be noted that the age included in the user representation may be an age group, such as between 20-25 years, or between 20-30 years.
In addition, the preset time period may be set according to the amount of the human flow or the actual situation, and may be set to 3 minutes or 5 minutes, for example. The preset area may be a certain shop floor or a preset range around a certain advertisement, and particularly, when the preset area is a certain shop floor, the server may simultaneously analyze the user portraits of the first user in different time periods of different shop floors. The specific values of the preset time period and the preset area are not limited in this embodiment.
In step S13, a correspondence between the user figure and the point of interest is established.
In the embodiment of the present disclosure, after determining the user representation of each first user, the server analyzes the big data to determine the attention point of each first user, so as to establish the corresponding relationship between the user representation and the attention point. Specifically, the attention point of a first user can be determined through voice information when the first user and a worker carry out conversation, so that the corresponding relation between the user portrait and the attention point is established; or according to the time when the first user stays to watch the advertisement, the attention point of each first user is determined, so that the corresponding relation between the user portrait and the attention point is established.
In step S14, a target advertisement content matching the first user profile is pushed to the advertisement platform according to the corresponding relationship and the first user profile, wherein the target advertisement content includes a focus point corresponding to the first user profile.
In the embodiment of the disclosure, a plurality of advertisement contents are stored in advance in a server, after the server obtains a first user portrait, a target advertisement content matched with the first user portrait is searched from the plurality of advertisement contents according to the established corresponding relationship between the user portrait and a focus point and the first user portrait, wherein the target advertisement content comprises the focus point corresponding to the first user portrait, and after the target advertisement content is searched, the target advertisement content is pushed to an advertisement platform so that the advertisement platform plays the received target advertisement content.
The advertisement delivery method provided by the embodiment of the disclosure obtains the first user portrait in the preset area within the preset time period by obtaining the image information of the first users and analyzing the image information of the first users, then establishes the corresponding relationship between the user portrait and the attention point, and pushes the target advertisement content matched with the first user portrait to the advertisement platform according to the corresponding relationship between the user portrait and the attention point and the first user portrait, wherein the advertisement content includes the attention point corresponding to the target user portrait. The server analyzes the image information of the first user in the preset area within the preset time period, and after the first user portrait is obtained, the server puts advertisements aiming at the first user portrait according to the established corresponding relation between the user portrait and the attention point, so that the hit rate of the advertisements can be improved.
Fig. 2 is a flowchart illustrating a method for delivering an advertisement according to another exemplary embodiment, where the method is used in a server, and this embodiment describes, in detail, a specific implementation manner of the step of "pushing targeted advertisement content matching a first user representation to an advertisement platform according to a corresponding relationship and the first user representation" in step S14 on the basis of the embodiment illustrated in fig. 1, and as illustrated in fig. 2, the method for delivering an advertisement includes the following steps:
in step S21, a point of interest of the first user representation is determined based on a correspondence between the user representation and the point of interest.
In the embodiment of the present disclosure, the server may establish a corresponding relationship between a plurality of user figures and the attention points, for example: for mobile phone advertisement, for female age 20-30, the focus corresponding to the group is appearance and photographing performance of the mobile phone, the user image is male age 30-40, the focus corresponding to the group is performance of the mobile phone and cruising ability of the battery, the user image is female age 40-50, the focus corresponding to the group is price of the mobile phone, and the like. After the server obtains the first user representation, the focus point of the first user representation is determined according to the established corresponding relation between the user representation and the focus point. For example: if the obtained first user image is a female with age of 40-50, the server will obtain the price of the mobile phone as the focus of the first user image.
In step S22, a target advertisement content corresponding to the point of interest of the first user representation is determined based on the correspondence between the point of interest of the user and the advertisement content.
In the embodiment of the present disclosure, generally, each advertisement has a tag information, where the tag information is used to indicate a content of the advertisement that is emphasized, that is, the tag information may be used to represent a focus point corresponding to a user image, that is, a server stores a correspondence between the focus point and an advertisement content in advance, for example, "XX mobile phone, ultra-low price," the advertisement corresponds to a focus point "price," XX mobile phone, ultra-long talk time, "and the advertisement corresponds to a focus point" duration. After the server determines the attention point of the first user portrait, the server determines the target advertisement content corresponding to the attention point of the first user portrait according to the corresponding relation between the attention point and the advertisement content stored in the server in advance. For example, if the focus of the first user image is determined to be "price", the advertisement "XX cell phone, ultra-low price" is determined as the target advertisement content corresponding to "price".
In step S23, targeted advertising content corresponding to the point of interest of the first user representation is sent to the advertising platform.
In the embodiment of the disclosure, after determining the target advertisement content corresponding to the attention point of the first user figure, the server pushes the determined target advertisement content to the advertisement platform, so that the advertisement platform plays the target advertisement content.
According to the advertisement putting method provided by the embodiment of the disclosure, the focus point of the first user portrait is determined according to the corresponding relation between the user portrait and the focus point, the target advertisement content corresponding to the focus point of the first user portrait is determined according to the corresponding relation between the focus point and the advertisement content, and finally the target advertisement content corresponding to the focus point of the first user portrait is sent to the advertisement platform. Because the attention point corresponding to the first user portrait is determined according to the determination of the first user portrait, the target advertisement content corresponding to the attention point is delivered to the advertisement platform, so that the hit rate and the conversion rate of the advertisement can be improved, and the operation support data of a merchant can be improved.
Fig. 3 is a flowchart illustrating a method for delivering an advertisement according to still another exemplary embodiment, where the method is used in a server, and this embodiment describes, in detail, a specific implementation manner of the step "analyzing image information of a plurality of first users to obtain first user images within a preset area within a preset time period" in step S12 on the basis of the embodiments illustrated in fig. 1 and fig. 2, and as shown in fig. 3, the method for delivering an advertisement includes the following steps:
in step S31, the image information of the plurality of first users is analyzed to obtain a user image of each first user.
In this embodiment, after acquiring the image information of the plurality of first users, the server analyzes the image information of each first user through an image recognition technology in the related art to obtain a user portrait of each first user within a preset time period and a preset area. Wherein the user representation includes age and gender information of the first user. It should be noted that the age included in the user representation may be an age group, such as between 20-25 years, or between 20-30 years.
In step S32, a clustering algorithm is used to cluster the user profiles of the first users to obtain a plurality of first user profile categories.
In the embodiment of the disclosure, after acquiring the user images of the first users in the preset area within the preset time period, the server performs clustering processing on the user images of the first users according to a clustering algorithm to classify the user images of the first users with the same attribute into one, for example, in the user images of the first users, females with ages of 20-30 are classified into one, males with ages of 20-30 are classified into one, and females with ages of 31-40 are classified into one … …, so that the first user image categories can be obtained.
In step S33, a second user representation category is determined based on the number of user representations in each first user representation category, the second user representation category being the first user representation category containing the greatest number of user representations.
Specifically, after clustering the user portraits of the first users to obtain a plurality of first user portraits categories, it is necessary to count the number of user portraits included in each first user portraits category. For example: after the clustering process is performed, 3 first user portrait categories, namely, a female aged 20-30, a male aged 31-40, and a female aged 41-50, are obtained, and the server counts the number of user portraits included in the 3 categories, that is, the number of included users, respectively, such as a female aged 20-30, a male aged 31-40, and a female aged 41-50, where the category includes 3 user portraits, 2 user portraits, and 1 user portraits, respectively, and at this time, the first user portrait category including the largest number of user portraits, that is, the category of a female aged 20-30, may be determined as the second user category.
In step S34, a user representation in the second user representation category is determined to be the first user representation.
In the embodiment of the disclosure, after determining the second user portrait type, the server may determine all user portraits included in the second user portrait type as the first user portrait, so that the server may deliver advertisement contents corresponding to the points of interest of the first user portraits to the advertisement platform, thereby improving the hit rate of advertisements.
The advertisement delivery method of the embodiment obtains user figures of each first user by analyzing image information of a plurality of first users, and obtains a plurality of first user figure categories by clustering user figures of the plurality of first users by adopting a clustering algorithm; a user representation in the second user representation category is determined to be the first user representation. Because the number of the user images contained in the second user image category is the largest, the content of the advertisement can be adjusted in real time according to the distribution of the user, the manual participation is reduced, and the hit rate of the advertisement is improved.
Fig. 4 is a flowchart illustrating a method for delivering an advertisement, which is used in a server according to still another exemplary embodiment, and this embodiment describes in detail an embodiment of "establishing a correspondence between a user representation and a point of interest" in step S13 on the basis of the embodiment illustrated in fig. 2, and as illustrated in fig. 4, the method for delivering an advertisement includes the following steps:
in step S41, the voice information of the plurality of second users and the image information corresponding to each second user are acquired.
In the embodiment of the present disclosure, the second user may be the same as or different from the first user. After the terminal collects the video information, the video information is reported to the server, wherein the video information comprises voice information, and the server can obtain the voice information of a plurality of second users and the image information corresponding to each second user by analyzing the video information.
In step S42, a keyword in each piece of speech information is extracted, and the point of interest of each second user is determined based on the keyword.
In the embodiment of the present disclosure, for the voice information of each second user, the server extracts the keyword in the voice information, and determines the attention point of the second user according to the extracted keyword. For example: if the server obtains that the voice information of a certain user is 'how good the performance of the mobile phone is', the server extracts that the keyword in the voice information is 'performance', and therefore the attention point of the user can be determined to be the performance of the mobile phone.
In step S43, the image information of each second user is analyzed to obtain a user image of each second user.
In the embodiment of the present disclosure, after acquiring the image information of each second user, the server analyzes the image information of each second user through an image recognition method in the related art to obtain a user portrait of each second user, where the user portrait includes information such as age and gender.
In addition, in the present embodiment, the execution sequence of step S42 and step S43 is not limited, and step S42 may be executed first, and step S43 may be executed second, step S43 may be executed first, and step S42 may be executed second, and step S42 and step S43 may be executed simultaneously.
In step S44, the points of interest of each second user and the corresponding user images of each second user are trained to establish a correspondence between the user images and the points of interest.
In the embodiment of the disclosure, after obtaining the user portrait of each second user and the attention point of each second user, the server trains the attention point of each second user and the user portrait of each second user by using a deep learning neural network algorithm, so as to establish a corresponding relationship between the user portrait and the attention point. For example: the focus of attention for women aged 20-30 is "appearance", the focus of attention for men aged 31-40 is "performance", and the focus of attention for women aged 41-50 is "price".
In the advertisement delivery method of this embodiment, the voice information of the plurality of second users and the image information corresponding to each second user are obtained, the keywords in each voice information are extracted, the attention points of each second user are determined according to the keywords, the image information of each second user is analyzed to obtain the user images of each second user, and the attention points of each second user and the user images of each second user are trained to establish the corresponding relationship between the user images and the attention points. The server can determine the attention point of each second user by extracting the key word in the voice information, and accordingly, the corresponding relation between the user portrait and the attention point is established, so that the corresponding relation between the user portrait and the attention point can be dynamically updated in real time, and the corresponding relation between the user portrait and the attention point is more accurate.
Fig. 5 is a flowchart illustrating a method for delivering an advertisement, which is used in a server according to still another exemplary embodiment, and this embodiment describes in detail an embodiment of "establishing a correspondence between a user representation and a point of interest" in step S13 on the basis of the embodiment illustrated in fig. 2, and as illustrated in fig. 5, the method for delivering an advertisement includes the following steps:
in step S51, a plurality of advertisement images and corresponding user images sent by the camera are received, where the user images are images of a third user who resides and watches the advertisement images for a time exceeding a preset threshold.
In the embodiment of the present disclosure, the third user may be the same as or different from the first user. The camera collects images, finds that the residence time of a certain user in front of the same advertisement exceeds a preset threshold value, indicates that the user is interested in the advertisement, and collects the user image of the user and the advertisement image of the advertisement which the user resides and watches.
In step S52, the attention point of each third user is determined from each advertisement image.
In the embodiment of the present disclosure, for each advertisement, the server stores tag information corresponding to the advertisement, that is, the content of the advertisement with emphasis, that is, the attention point in which the user is interested, where if a certain advertisement is "XX mobile phone, and the price is ultra-low", it is indicated that the content of the advertisement with emphasis is "price". Therefore, after receiving the advertisement image sent by the camera, the server can determine the attention point of the third user according to the label information corresponding to the advertisement image.
In step S53, the image information of each third user is analyzed to obtain a user image of each third user.
In the embodiment of the present disclosure, after acquiring the image information of each third user, the server analyzes the image information of each third user through an image recognition method in the related art to obtain a user portrait of each third user, where the user portrait includes information such as age and gender.
In addition, in the present embodiment, the execution sequence of step S52 and step S53 is not limited, and step S52 may be executed first, and step S53 may be executed second, step S53 may be executed first, and step S52 may be executed second, and step S52 and step S53 may be executed simultaneously.
In step S54, the attention points of the respective third users and the corresponding user images of the respective third users are trained to establish a correspondence between the user images and the attention points.
In the embodiment of the disclosure, after obtaining the user portraits of the third users and the corresponding points of interest of the third users, the server trains the points of interest of the third users and the user portraits of the third users by using a deep learning neural network algorithm, so as to establish the corresponding relationship between the user portraits and the points of interest. For example: the focus of attention for women aged 20-30 is "shot", the focus of attention for men aged 31-40 is "performance", and the focus of attention for women aged 41-50 is "price".
In the advertisement delivery method of this embodiment, a plurality of advertisement images and corresponding user images sent by a camera are received, where a user image is an image of a third user who stays and watches an advertisement image for a time exceeding a preset threshold, a focus of each third user is determined according to each advertisement image, image information of each third user is analyzed to obtain a user portrait of each third user, and the focus of each third user and the user portrait of each corresponding third user are trained to establish a corresponding relationship between the user portrait and the focus. The server receives a plurality of advertisement images and corresponding user images sent by the camera, so that the attention points of the third users can be determined, and the corresponding relation between the user portrait and the attention points is established, so that the corresponding relation between the user portrait and the attention points can be dynamically updated in real time, and the corresponding relation between the user portrait and the attention points is more accurate.
Optionally, on the basis of the foregoing embodiments, when a user networks a mobile phone by scanning wireless-fidelity (WIFI), the WIFI probe of the mobile phone acquires a Media Access Control (MAC) address in the mobile phone of the user, and since the MAC address in each mobile phone is unique, after the WIFI probe of the mobile phone sends the MAC address to the server, the server marks the user by using the MAC address. In addition, the user's point of interest can be identified by the voice information of the user, and thus the user can be associated with his point of interest.
The above describes the implementation process of the advertisement delivery method, which can be implemented by an advertisement delivery device, and the internal functions and structure of the device will be explained below.
Fig. 6 is a block diagram illustrating an apparatus for placement of an advertisement, according to an example embodiment. As shown in fig. 6, the advertisement delivery device includes an obtaining module 11, an analyzing module 12, a creating module 13 and a pushing module 14.
The acquisition module 11 is configured to acquire image information of a plurality of first users;
the analysis module 12 is configured to analyze the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
the establishing module 13 is configured to establish a correspondence between the user representation and the point of interest;
the pushing module 14 is configured to push targeted advertisement content matched with the first user representation to an advertisement platform according to the corresponding relationship and the first user representation, where the targeted advertisement content includes a point of interest corresponding to the first user representation.
In the advertisement delivery device of this embodiment, the obtaining module 11 obtains image information of a plurality of first users, the analyzing module 12 analyzes the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period, the establishing module 13 establishes a corresponding relationship between the user portrait and a focus point, and the pushing module 14 pushes a target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relationship between the user portrait and the focus point and the first user portrait, where the advertisement content includes the focus point corresponding to the target user portrait. The server analyzes the image information of the first user in the preset area within the preset time period, and after the first user portrait is obtained, the server puts advertisements aiming at the first user portrait according to the established corresponding relation between the user portrait and the attention point, so that the hit rate of the advertisements can be improved.
As shown in fig. 7, fig. 7 is a block diagram of an advertisement delivery device according to another exemplary embodiment, and on the basis of the embodiment shown in fig. 6, the pushing module 14 includes: a first determination submodule 141, a second determination submodule 142 and a sending submodule 143.
The first determination submodule 141 is configured to determine a point of interest of the first user representation on the basis of a correspondence between user representations and points of interest;
the second determining submodule 142 is configured to determine a target advertisement content corresponding to the point of interest of the first user representation according to a corresponding relationship between the point of interest of the user and the advertisement content;
the transmit sub-module 143 is configured to transmit targeted advertising content corresponding to points of interest of the first user representation to the advertising platform.
As shown in fig. 8, fig. 8 is a block diagram of an advertisement delivery device according to another exemplary embodiment, and on the basis of the embodiment shown in fig. 6, the analysis module 12 includes: an analysis sub-module 121, a processing sub-module 122, a third determination sub-module 123 and a fourth determination sub-module 124.
The analysis sub-module 121 is configured to analyze the image information of the plurality of first users to obtain a user representation of each of the first users;
the processing sub-module 122 is configured to perform clustering processing on the user portraits of the first users by using a clustering algorithm, so as to obtain a plurality of first user portraits categories;
a third determination submodule 123 is arranged to determine a second user representation category from the number of user representations in each said first user representation category, said second user representation category being the first user representation category containing the greatest number of user representations;
a fourth determination submodule 124 is configured to determine user representations in the second user representation category as the first user representation.
As shown in fig. 9, fig. 9 is a block diagram of an advertisement delivery apparatus according to another exemplary embodiment, and on the basis of the embodiment shown in fig. 7, the establishing module 13 includes: a first acquisition sub-module 131, an extraction sub-module 132, a fifth determination sub-module 133, a first analysis sub-module 134, and a first establishment sub-module 135.
The first obtaining sub-module 131 is configured to obtain voice information of a plurality of second users and image information corresponding to each of the second users;
the extracting sub-module 132 is configured to extract keywords from each of the voice messages;
the fifth determining submodule 133 is configured to determine a point of interest of each of the second users according to the keyword;
the first analysis sub-module 134 is configured to analyze the image information of each of the second users to obtain a user representation of each of the second users;
the first establishing sub-module 135 is configured to train the attention points of the second users and the corresponding user figures of the second users to establish the corresponding relationship between the user figures and the attention points.
As shown in fig. 10, fig. 10 is a block diagram of an advertisement delivery apparatus according to another exemplary embodiment, and on the basis of the embodiment shown in fig. 7, the establishing module 13 includes: a first receiving sub-module 136, a sixth determining sub-module 137, a second analyzing sub-module 138 and a second establishing sub-module 139.
The first receiving sub-module 136 is configured to receive a plurality of advertisement images and corresponding user images sent by the camera; the user image is an image of a third user who stays and watches the advertisement image for a time exceeding a preset threshold value;
the sixth determining sub-module 137 is configured to determine a point of interest of each of the third users from each of the advertisement images;
the second analysis submodule 138 is configured to analyze the image information of each of the third users to obtain a user representation of each of the third users;
the second establishing sub-module 139 is configured to train the attention points of the third users and the corresponding user figures of the third users to establish the corresponding relationship between the user figures and the attention points.
As shown in fig. 11, fig. 11 is a block diagram of an advertisement delivery device according to another exemplary embodiment, and on the basis of the embodiment shown in fig. 6, the obtaining module 11 includes: a second receiving sub-module 111 and a third analyzing sub-module 112.
The second receiving submodule 111 is configured to receive video information sent by the camera; the video information comprises image information of a plurality of users;
the third analyzing sub-module 112 is configured to analyze the video information to obtain image information of the plurality of first users.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Having described the internal functional modules and structural schematic of the server, fig. 12 is a block diagram illustrating an entity of a server according to an exemplary embodiment, and referring to fig. 12, the server may be embodied as:
a processor;
a memory configured to store processor-executable instructions;
wherein the processor is configured to:
acquiring image information of a plurality of first users;
analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
establishing a corresponding relation between the user portrait and the attention point;
and pushing target advertisement content matched with the first user portrait to an advertisement platform according to the corresponding relation and the first user portrait, wherein the target advertisement content comprises a focus corresponding to the first user portrait.
Fig. 13 is a block diagram illustrating a delivery device 1900 for an advertisement according to an exemplary embodiment. For example, the apparatus 1900 may be provided as a server. Referring to FIG. 13, the device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by the processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the method of placement of advertisements described above.
The device 1900 may also include a power component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input/output (I/O) interface 1958. The device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (12)
1. An advertisement delivery method, comprising:
acquiring image information of a plurality of first users;
analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
establishing a corresponding relation between the user portrait and the attention point;
determining a target focus point of the first user portrait according to the corresponding relation;
determining target advertisement content corresponding to the target attention point according to the corresponding relation between the user attention point and the advertisement content; the advertisement content comprises label information, and the label information is a characteristic point of a commodity corresponding to the advertisement content; the label information is used for representing the attention point corresponding to the first user portrait; the target advertisement content comprises a focus point corresponding to the first user portrait;
and sending the target advertisement content corresponding to the target attention point to the advertisement platform.
2. The method of claim 1, wherein analyzing the image information of the plurality of first users to obtain a first user representation in a predetermined area within a predetermined time period comprises:
analyzing the image information of the plurality of first users to obtain user figures of the first users;
clustering the user figures of the first users by adopting a clustering algorithm to obtain a plurality of first user figure categories;
determining a second user representation category based on the number of user representations in each of the first user representation categories, the second user representation category being the first user representation category containing the greatest number of user representations;
a user representation in the second user representation category is determined to be the first user representation.
3. The method of claim 1, wherein establishing a correspondence between a user representation and a point of interest comprises:
acquiring voice information of a plurality of second users and image information corresponding to the second users;
extracting key words in the voice information, and determining the attention points of the second users according to the key words;
analyzing the image information of each second user to obtain a user portrait of each second user;
and training the attention points of the second users and the corresponding user figures of the second users to establish the corresponding relation between the user figures and the attention points.
4. The method of claim 1, wherein establishing a correspondence between a user representation and a point of interest comprises:
receiving a plurality of advertisement images and corresponding user images sent by a camera; the user image is an image of a third user who stays and watches the advertisement image for a time exceeding a preset threshold value;
according to each advertisement image, determining the attention point of each third user;
analyzing the image information of each third user to obtain the user portrait of each third user;
and training the attention points of the third users and the corresponding user figures of the third users to establish the corresponding relation between the user figures and the attention points.
5. The method of claim 1, wherein the obtaining image information of a plurality of first users comprises:
receiving video information sent by a camera; the video information comprises image information of a plurality of first users;
and analyzing the video information to obtain the image information of the plurality of first users.
6. An advertisement delivery device, comprising:
an acquisition module configured to acquire image information of a plurality of first users;
the analysis module is configured to analyze the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
the establishing module is configured to establish a corresponding relation between the user portrait and the attention point;
a push module comprising: the device comprises a first determining submodule, a second determining submodule and a sending submodule;
a first determining submodule configured to determine a target point of interest of the first user representation according to the correspondence;
the second determination submodule is configured to determine target advertisement content corresponding to the target attention point according to the corresponding relation between the user attention point and the advertisement content; the advertisement content comprises label information, and the label information is a characteristic point of a commodity corresponding to the advertisement content; the label information is used for representing the attention point corresponding to the first user portrait; the target advertisement content comprises a focus point corresponding to the first user portrait;
a sending sub-module configured to send targeted advertising content corresponding to a point of interest of the first user representation to the advertising platform.
7. The apparatus of claim 6, wherein the analysis module comprises:
the analysis submodule is configured to analyze the image information of the plurality of first users to obtain user portraits of the first users;
the processing submodule is configured to perform clustering processing on the user figures of the first users by adopting a clustering algorithm to obtain a plurality of first user figure categories;
a third determination submodule configured to determine a second user representation category based on the number of user representations in each of the first user representation categories, the second user representation category being the first user representation category containing the greatest number of user representations;
a fourth determination submodule configured to determine a user representation in the second user representation category as the first user representation.
8. The apparatus of claim 6, wherein the establishing module comprises:
a first obtaining sub-module configured to obtain voice information of a plurality of second users and image information corresponding to each of the second users;
the extraction sub-module is configured to extract key words in the voice information;
a fifth determining submodule configured to determine a point of interest of each of the second users according to the keyword;
a first analysis sub-module configured to analyze the image information of each of the second users to obtain a user portrait of each of the second users;
and the first establishing sub-module is configured to train the attention points of the second users and the corresponding user figures of the second users so as to establish the corresponding relation between the user figures and the attention points.
9. The apparatus of claim 6, wherein the establishing module comprises:
the first receiving submodule is configured to receive a plurality of advertisement images and corresponding user images sent by the camera; the user image is an image of a third user who stays and watches the advertisement image for a time exceeding a preset threshold value;
a sixth determining sub-module configured to determine, from each of the advertisement images, a point of interest of each of the third users;
the second analysis submodule is configured to analyze the image information of each third user to obtain a user portrait of each third user;
and the second establishing submodule is configured to train the attention points of the third users and the corresponding user figures of the third users so as to establish the corresponding relation between the user figures and the attention points.
10. The apparatus of claim 6, wherein the obtaining module comprises:
the second receiving submodule is configured to receive video information sent by the camera; the video information comprises image information of a plurality of first users;
and the third analysis sub-module is configured to analyze the video information to obtain image information of the plurality of first users.
11. A server, comprising:
a processor;
a memory configured to store processor-executable instructions;
wherein the processor is configured to:
acquiring image information of a plurality of first users;
analyzing the image information of the plurality of first users to obtain a first user portrait in a preset area within a preset time period;
establishing a corresponding relation between the user portrait and the attention point;
determining a target focus point of the first user portrait according to the corresponding relation;
determining target advertisement content corresponding to the target attention point according to the corresponding relation between the user attention point and the advertisement content; the advertisement content comprises label information, and the label information is a characteristic point of a commodity corresponding to the advertisement content; the label information is used for representing the attention point corresponding to the first user portrait; the target advertisement content comprises a focus point corresponding to the first user portrait;
and sending the target advertisement content corresponding to the target attention point to the advertisement platform.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810058305.6A CN108269128B (en) | 2018-01-22 | 2018-01-22 | Advertisement putting method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810058305.6A CN108269128B (en) | 2018-01-22 | 2018-01-22 | Advertisement putting method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108269128A CN108269128A (en) | 2018-07-10 |
| CN108269128B true CN108269128B (en) | 2022-03-08 |
Family
ID=62776304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810058305.6A Active CN108269128B (en) | 2018-01-22 | 2018-01-22 | Advertisement putting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108269128B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242537A (en) * | 2018-08-14 | 2019-01-18 | 平安普惠企业管理有限公司 | Advertisement placement method, device, computer equipment and storage medium |
| CN109272345A (en) * | 2018-08-16 | 2019-01-25 | 西安万像电子科技有限公司 | Advertisement broadcast method and device |
| CN109242555B (en) * | 2018-08-24 | 2021-07-02 | 苏州市明日企业形象策划传播有限公司 | Voice-based advertisement playing method and related product |
| CN109345953A (en) * | 2018-08-28 | 2019-02-15 | 信利光电股份有限公司 | Advertisement pushing method and system, storage medium and mobile terminal based on advertisement machine |
| CN109598537B (en) | 2018-11-06 | 2020-07-31 | 阿里巴巴集团控股有限公司 | Outdoor advertisement putting method and device |
| CN111260385B (en) * | 2018-12-03 | 2023-06-27 | 中国移动通信集团北京有限公司 | Advertisement putting method, device, terminal equipment and medium |
| CN111275467A (en) * | 2018-12-04 | 2020-06-12 | 山东快发网络科技有限公司 | Method and device for delivering advertisement |
| CN111401932A (en) * | 2019-01-02 | 2020-07-10 | 中国移动通信有限公司研究院 | Advertisement putting method and device, electronic equipment and storage medium |
| CN111028006B (en) * | 2019-12-02 | 2023-07-14 | 支付宝(杭州)信息技术有限公司 | Service delivery auxiliary method, service delivery method and related device |
| CN111144932A (en) * | 2019-12-11 | 2020-05-12 | 西安万像电子科技有限公司 | Advertisement putting method, device and system |
| CN111127091A (en) * | 2019-12-20 | 2020-05-08 | 西安万像电子科技有限公司 | Advertisement putting method, device and system |
| CN111460319A (en) * | 2020-03-31 | 2020-07-28 | 深圳前海微众银行股份有限公司 | Message playing optimization method, device, equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236860A (en) * | 2011-07-01 | 2011-11-09 | Tcl集团股份有限公司 | Automatic advisement releasing system and method |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN106874435A (en) * | 2017-01-25 | 2017-06-20 | 北京航空航天大学 | User portrait construction method and device |
| CN106937172A (en) * | 2017-03-23 | 2017-07-07 | 百度在线网络技术（北京）有限公司 | Interactive approach and device during video playback based on artificial intelligence |
-
2018
- 2018-01-22 CN CN201810058305.6A patent/CN108269128B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102236860A (en) * | 2011-07-01 | 2011-11-09 | Tcl集团股份有限公司 | Automatic advisement releasing system and method |
| CN106503015A (en) * | 2015-09-07 | 2017-03-15 | 国家计算机网络与信息安全管理中心 | A kind of method for building user's portrait |
| CN106874435A (en) * | 2017-01-25 | 2017-06-20 | 北京航空航天大学 | User portrait construction method and device |
| CN106937172A (en) * | 2017-03-23 | 2017-07-07 | 百度在线网络技术（北京）有限公司 | Interactive approach and device during video playback based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108269128A (en) | 2018-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108269128B (en) | Advertisement putting method, device, equipment and storage medium | |
| CN108234591B (en) | Content data recommendation method and device based on identity authentication device and storage medium | |
| CN107278374B (en) | Interactive advertisement display method, terminal and smart city interactive system | |
| CN109218390B (en) | User screening method and device | |
| CN105450778B (en) | Information transmission system | |
| CN110366043A (en) | Method for processing video frequency, device, electronic equipment and readable medium | |
| CN112307240B (en) | Page display method and device, storage medium and electronic equipment | |
| CN102592116A (en) | Cloud computing application method, system and terminal equipment, and cloud computing platform | |
| CN104021398A (en) | Wearable intelligent device and method for assisting identity recognition | |
| CN108492140A (en) | A kind of advertisement placement method and system | |
| CN111026969B (en) | Content recommendation method and device, storage medium and server | |
| CN110415023B (en) | Elevator advertisement recommendation method, device, equipment and storage medium | |
| CN115907868A (en) | Advertisement delivery analysis method and device | |
| CN109558542B (en) | Information quality evaluation method, information pushing method and device | |
| CN104185041A (en) | Video interaction advertisement automatic generation method and system | |
| US20170278130A1 (en) | Method and Electronic Device for Matching Advertisement Data | |
| CN111724199A (en) | Intelligent community advertisement accurate delivery method and device based on pedestrian active perception | |
| CN116383480A (en) | Method and device for recommending media in call scene, electronic equipment and storage medium | |
| CN109451334B (en) | User portrait generation processing method and device and electronic equipment | |
| CN113034221B (en) | Information processing method, device, client and server | |
| CN111954017A (en) | Live broadcast room searching method and device, server and storage medium | |
| CN112672202A (en) | Bullet screen processing method, equipment and storage medium | |
| CN108573056B (en) | Content data processing method and device, electronic equipment and storage medium | |
| CN112115354A (en) | Information processing method, information processing apparatus, server, and storage medium | |
| CN105323143A (en) | Network information pushing method, apparatus and system based on instant message |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |