CN111709792A - Advertisement matching method, device, server and storage medium - Google Patents
Advertisement matching method, device, server and storage medium Download PDFInfo
- Publication number
- CN111709792A CN111709792A CN202010582653.0A CN202010582653A CN111709792A CN 111709792 A CN111709792 A CN 111709792A CN 202010582653 A CN202010582653 A CN 202010582653A CN 111709792 A CN111709792 A CN 111709792A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- attention
- advertisements
- played
- target area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
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
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0245—Surveys
Abstract
The invention relates to the technical field of Internet, and discloses an advertisement matching method, an advertisement matching device, a server and a storage medium, wherein the method comprises the following steps: determining the attention degree of each advertisement in a plurality of advertisements played in a target area; determining an advertisement category to which each advertisement belongs; and matching the advertisement category corresponding to the advertisement with the attention degree higher than the preset attention degree in the plurality of advertisements to the target area. The advertisement matching method, the device, the server and the storage medium provided by the invention can match advertisement categories with high attention for users, improve the conversion rate of the delivered advertisements and realize intelligent delivery of the advertisements.
Description
Technical Field
The invention relates to the technical field of internet, in particular to an advertisement matching method, an advertisement matching device, a server and a storage medium.
Background
Advertising is a means for distributing goods or services to consumers or users through advertising media by paying fees, and the cost required for advertisement delivery is relatively high, so that it is expected by each advertiser how to deliver advertisements efficiently and to obtain the greatest advertising benefit.
Currently, for advertisement placement, selective placement is mostly performed based on personal experience, such as presuming that an advertisement is likely to be more focused in some areas through experience perception, and then placing the advertisement in the areas likely to be more focused.
However, the delivery of advertisements by means of experience perception often lacks sufficient data support, and people are prone to fatigue on the same category of advertisements due to long-term attention, so that the attention rate of the delivered advertisements is low, and further the advertisement conversion rate is low.
Disclosure of Invention
In order to solve the problem of low advertisement conversion rate in the prior art, the invention aims to provide an advertisement matching method, an advertisement matching device, a server and a storage medium, wherein the advertisement matching method, the advertisement matching device, the server and the storage medium can dynamically match advertisements according to the attention degree of a user.
In a first aspect, the present invention provides an advertisement matching method, including:
the server determines the attention degree of each advertisement in a plurality of advertisements played in a target area;
the server determines the advertisement category to which each advertisement belongs;
and matching the advertisement category corresponding to the advertisement with the attention degree higher than the preset attention degree in the plurality of advertisements to the target area by the server.
Based on the invention content, the attention degree of each advertisement played in the target area and the advertisement category to which each advertisement belongs are determined, and the advertisement category corresponding to the advertisement with the attention degree higher than the preset attention degree is matched to the target area. Through the design, the advertisement type with high attention can be matched with the target area, so that the advertisement with high attention can be delivered to the target area, the attention of the user to the delivered advertisement is improved, the conversion rate of the delivered advertisement is improved, and the intelligent delivery of the advertisement is realized.
In one possible design, the server determines a degree of interest for each of a plurality of advertisements played within the target area, including:
the server acquires the concerned time length of each advertisement which is concerned when being played within the preset time length;
and the server determines the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
Based on the invention, the user attention of a plurality of advertisements can be accurately obtained according to the attention time and the playing time of the user to the advertisements, and the follow-up accurate matching of the advertisements is ensured.
In one possible design, the server matches, to the target area, an advertisement category corresponding to an advertisement with a higher attention than a preset attention among the advertisements, including:
the server determines the theoretical audience number corresponding to the target area;
the server determines the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of each advertisement;
and the server matches advertisement categories corresponding to the advertisements with the average attention degree higher than the preset average attention degree among the advertisements to the target area.
In one possible arrangement, the server determines an advertisement category to which the plurality of advertisements belong, including:
the server extracts the advertisement characteristics of all the advertisements to be played, wherein the advertisements are contained in the advertisements to be played;
and the server performs cluster analysis on the advertisement characteristics to determine the advertisement categories, so as to determine the category of each advertisement according to the advertisement categories.
In one possible arrangement, the server extracts advertisement characteristics of all advertisements to be played, including:
the server extracts the characteristics of the text introduction information of each advertisement to be played in the advertisements to be played to obtain a first characteristic corresponding to each advertisement to be played;
the server extracts the characteristics of the image information of each advertisement to be played to obtain second characteristics corresponding to each advertisement to be played;
the server extracts the characteristics of the audio information of each advertisement to be played to obtain a third characteristic corresponding to each advertisement to be played;
and the server fuses the first characteristic, the second characteristic and the third characteristic to obtain the advertisement characteristic corresponding to each advertisement to be played.
Based on the invention content, the advertisement characteristics corresponding to each advertisement to be played can be obtained by extracting and fusing the characteristics of the advertisement text introduction information, the image information and the audio information of the advertisement to be played, and the advertisement to be played can be conveniently and accurately classified.
In a second aspect, the present invention provides an advertisement matching apparatus, including:
a first determination unit, configured to determine a degree of attention of each of a plurality of advertisements played in a target area;
a second determining unit, configured to determine an advertisement category to which each advertisement belongs;
and the matching unit is used for matching the advertisement categories corresponding to the advertisements with the attention degrees higher than the preset attention degrees in the plurality of advertisements to the target area.
In one possible design, when the first determining unit is configured to determine the attention degree of each of the plurality of advertisements played in the target area, specifically:
acquiring the concerned time length of each advertisement which is concerned when being played within a preset time length; and
and determining the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
In one possible design, when the matching unit is configured to match, to the target area, an advertisement category corresponding to an advertisement of which a degree of attention is higher than a preset degree of attention among the plurality of advertisements, the matching unit is specifically configured to:
determining the theoretical audience number corresponding to the target area;
determining the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of each advertisement; and
and matching the advertisement categories corresponding to the advertisements with the average human attention degree higher than the preset average human attention degree among the advertisements to the target area.
In a possible design, when the second determining unit is configured to determine the advertisement category to which each advertisement belongs, specifically:
extracting advertisement characteristics of all advertisements to be played, wherein the advertisements are contained in the advertisements to be played;
performing cluster analysis on the advertisement characteristics to determine advertisement categories; and
and determining the category of each advertisement according to the advertisement category.
In one possible design, when the second determination unit is configured to extract the advertisement features of all the advertisements to be played, it is configured to:
extracting the characteristics of the text introduction information of each advertisement to be played in the advertisements to be played to obtain a first characteristic corresponding to each advertisement to be played;
extracting the characteristics of the image information of each advertisement to be played to obtain second characteristics corresponding to each advertisement to be played;
extracting the characteristics of the audio information of each advertisement to be played to obtain a third characteristic corresponding to each advertisement to be played; and
and fusing the first characteristic, the second characteristic and the third characteristic to obtain the advertisement characteristic corresponding to each advertisement to be played.
In a third aspect, the present invention provides a server, including a memory, a processor and a transceiver, which are connected in communication in sequence, where the memory is used for storing a computer program, the transceiver is used for sending and receiving a message, and the processor is used for reading the computer program and executing the advertisement matching method according to the above aspect or any one of the first aspects.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon instructions which, when executed on a computer, perform the advertisement matching method of any of the above aspects.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of advertisement matching as described in any of the above aspects.
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 an application environment of the advertisement matching method, apparatus and storage medium provided by the present invention.
FIG. 2 is a flow chart of an advertisement matching method provided by the present invention.
Fig. 3 is a schematic structural diagram of an advertisement matching device provided by the present invention.
Fig. 4 is a block diagram of a server provided by the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Specific structural and functional details disclosed herein are merely illustrative of example embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It will be understood that when an element is referred to herein as being "connected," "connected," or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Conversely, if a unit is referred to herein as being "directly connected" or "directly coupled" to another unit, it is intended that no intervening units are present. In addition, other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between … …" versus "directly between … …", "adjacent" versus "directly adjacent", etc.).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
Examples
In order to put advertisements more scientifically and reasonably, the embodiment of the application provides an advertisement matching method, an advertisement matching device and a storage medium, wherein the advertisement matching method, the advertisement matching device and the storage medium can match the advertisement categories with high attention degrees for a target area according to the attention degrees so as to put the advertisements with high attention degrees to the target area, improve the attention degrees of users to the put advertisements and improve the conversion rate of the put advertisements.
First, in order to more intuitively understand the scheme provided by the embodiment of the present application, a system architecture of the advertisement matching scheme provided by the embodiment of the present application is described below with reference to fig. 1.
Fig. 1 is a schematic application environment diagram of an advertisement matching method, an advertisement matching apparatus, and a storage medium according to one or more embodiments of the present application. As shown in fig. 1, the server is communicatively connected to one or more multimedia terminals via a network for data communication or exchange. The server may be, but is not limited to, a web server, a database server, and the like. The multimedia terminal may be, but is not limited to, a liquid crystal display, a plasma display, etc. for playing advertisements. The multimedia terminal is provided with an image acquisition device and is used for acquiring image information of an area where the multimedia terminal is located. In a specific implementation process, when the multimedia terminal is not provided with an image acquisition device, the image acquisition device connected with the multimedia terminal can also be used for image acquisition, and the image acquisition device can be a network camera, a miniature camera, an Artificial Intelligence (AI) camera and the like.
The advertisement matching method provided by the embodiment of the present application will be described in detail below.
Specifically, the flow of the advertisement matching method is shown in fig. 2, and may include the following steps:
step S201, the attention degree of each advertisement in a plurality of advertisements played in the target area is determined.
In this embodiment of the present application, the target area may refer to an area where a multimedia terminal that needs to place an advertisement is located, such as a cell, a certain building, or an elevator entrance, and this embodiment of the present application is not specifically limited. In addition, the advertisement described in the embodiment of the present application mainly refers to an electronic advertisement played on a multimedia terminal, such as a ladder media advertisement, a vehicle-mounted advertisement, or a cinema advertisement.
In the embodiment of the present application, the implementation process of step S201 specifically includes the following steps:
acquiring the concerned time length of each advertisement which is concerned when being played within a preset time length;
and determining the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
The predetermined time period may be set according to actual needs, for example, a day, a week or a month, and is not illustrated here.
In this embodiment of the present application, a time length of attention of a user to an advertisement of interest may be calculated by a multimedia terminal according to a timestamp of attention of the user to the advertisement of interest and sent to a server, or the time length of attention of the user to the advertisement of interest may be calculated by the multimedia terminal sending the timestamp of attention of the user to the server and sent by the server, or the multimedia terminal sending image information acquired by an acquired video stream to the server, and the server determining the timestamp and calculating according to the timestamp, which is not specifically limited in this embodiment of the present application. The playing time of the concerned advertisement may be sent to the server by the multimedia terminal, or the playing time of the concerned advertisement may be recorded in advance at the server, which is not specifically limited in the embodiment of the present application. The following description will take an example in which the focused duration is calculated by the server and the multimedia terminal sends the acquired image information to the server.
After receiving the image information sent by the multimedia terminal, the server identifies the faces of the collected video streams and identifies the number of audiences in the area where the multimedia terminal is located. For example, when performing face recognition, 2 face images are recognized in the video stream, and the number of audiences in the area where the multimedia terminal is located is determined to be 2.
When the face recognition is performed on the collected video stream, users (audiences) corresponding to the face can be further recognized, and identity labels are marked on all the recognized users, so that the problem that the repeated statistics of the users affects the accuracy of the statistics of the attention is avoided.
If the video stream has the face, identifying whether the user corresponding to the face pays attention to the currently played advertisement or not through behavior identification, and if the user corresponding to the face pays attention to the currently played advertisement, determining the attention duration of each user paying attention to the concerned advertisement according to the time stamp of each user paying attention to the concerned advertisement by the multimedia terminal.
When the user is identified whether to watch the currently played advertisement through the behavior, the advertisement can be identified through various modes. For example, whether the user pays attention to the currently played advertisement may be determined by determining a deflection angle of the face with respect to a vertical plane and a pitch angle with respect to a horizontal plane, or the visual direction of the user may be determined according to the position of the pupil of the user in the eye socket to determine whether the user pays attention to the currently played advertisement, which is not specifically limited in the embodiment of the present application.
In the process of focusing on the advertisement, the multimedia terminal records a time stamp when each user starts to focus on the advertisement, and when the advertisement stops being focused, the multimedia terminal records a time stamp when each user stops focusing on the advertisement. The length of time for which each user pays attention to the advertisement of interest can be obtained from the time stamp of when the user starts paying attention to the advertisement of interest and the time stamp of when the user stops paying attention to the advertisement of interest.
In the embodiment of the application, if the user has a process of paying attention to the advertisement for multiple times in the advertisement playing period, multiple attention sub-durations of each user to the attention advertisement in the advertisement playing period can be obtained according to the timestamp of paying attention to the attention advertisement every time and the timestamp of stopping paying attention to the attention advertisement every time.
For example, for a particular advertisement played, a user has 3 times the process of focusing on the advertisement during the advertisement playing, wherein, the time corresponding to the timestamp of the advertisement concerned for the first time (namely, the signature time in the timestamp) is 16 hours, 10 minutes and 0 seconds, the time corresponding to the timestamp of the advertisement concerned for the first time is 16 hours, 10 minutes and 5 seconds, the time corresponding to the timestamp of the advertisement concerned for the second time is 16 hours, 10 minutes and 10 seconds, the time corresponding to the timestamp of the advertisement concerned for the second time is 16 hours, 10 minutes and 13 seconds, the time corresponding to the timestamp of the advertisement concerned for the third time is 16 hours, 10 minutes and 15 seconds, the time corresponding to the timestamp of the advertisement concerned for the third time is 16 hours, 10 minutes and 17 seconds, the three focusing sub-periods of the user focusing on the advertisement three times can be divided into 5 seconds, 3 seconds and 2 seconds according to the time stamp of focusing on the advertisement concerned each time and the time stamp of stopping focusing on the advertisement concerned each time.
After the attention duration of each user to the attention advertisement is determined, the multimedia terminal sends the attention duration of the attention advertisement of each user to the server. It can be understood that, if there is a process of paying attention to the advertisement for a plurality of times in the advertisement playing period of the user, when the attention duration is sent to the server, the multimedia terminal sends a plurality of attention sub-durations of the advertisement paid attention to each user to the server.
The attention length of each advertisement which is concerned when playing within the preset length of time is obtained, so that the attention degree of each advertisement can be determined. In particular implementations, the manner of determining the attention of each advertisement includes, but is not limited to, the following two ways, which are described in detail below.
In a first mode
Taking one of the advertisements as an example:
calculating the attention time length of each user in the attention users of the advertisement to the advertisement within a preset time length;
calculating the attention degree of each user to the advertisement according to the attention time length of each user to the advertisement within the preset time length and the advertisement playing time length;
and summing the attention of each user to the advertisement to obtain the attention of the advertisement.
For example, taking a certain time period as one day as an example, for the ad a, 3 users have attention to the ad a, and the time lengths of the 3 users paying attention to the ad a are all _ watch time1, all _ watch time2, and all _ watch time3, respectively, the attention of all users to the ad a can be expressed as
attention＝all_watchtime1/video_time+all_watchtime2/video_time+all_watchtime3/video_time。
Mode two
Taking one of the advertisements as an example:
calculating the sum of the attention time lengths of all users to the advertisement in each advertisement user within a preset time length;
and obtaining the attention degree of each advertisement according to the sum of the attention duration of each advertisement and the playing duration of each advertisement. For example, taking a certain time period as one day as an example, for the ad a, 3 users have attention to the ad a, and the time periods in which the 3 users pay attention to the ad a are all _ watch time1, all _ watch time2, and all _ watch time3, respectively, the attention of all users to the ad a may be expressed as (all _ watch time1+ all _ watch time2+ all _ watch time3)/video _ time.
It is understood that in one or more embodiments, the attention degree corresponding to a plurality of advertisements may be calculated in other manners as long as the attention degree of the user to the advertisements can be accurately reflected.
After step S201 is executed, step S202 is executed: an advertisement category to which each advertisement belongs is determined.
In the embodiment of the application, the advertisement category to which each advertisement belongs in a plurality of advertisements can be obtained by performing feature extraction and clustering analysis on all the advertisements to be played, wherein the plurality of advertisements are included in the advertisements to be played.
The content of the advertisement generally includes advertisement text introduction information, image information, audio information, and the like. In one or more embodiments of the present application, the server may respectively extract features of advertisement text introduction information, image information, and audio information of an advertisement to be played, and then fuse the extracted features to obtain advertisement features corresponding to the advertisement to be played.
Specifically, the server extracts features of advertisement text introduction information of each advertisement to be played in the advertisements to be played to obtain a plurality of first features corresponding to each advertisement to be played, extracts features of image information of each advertisement to be played in the advertisements to be played to obtain a plurality of second features corresponding to each advertisement to be played, extracts features of audio information of each advertisement to be played in the advertisements to be played to obtain a plurality of third features corresponding to each advertisement to be played, and the first features, the second features and the third features are all multi-dimensional vectors. And then the server fuses (splices) the first characteristic, the second characteristic and the third characteristic corresponding to each advertisement to be played to obtain the advertisement characteristic corresponding to each advertisement to be played.
For example, the advertisement text introduction information of the advertisement a is subjected to feature extraction, the obtained first feature is the vector a1(a11, a12, a13), the obtained second feature is the vector a2(a221, a22, a23), the audio information of the advertisement a is subjected to feature extraction, the obtained third feature is the vector a3(a31, a32, a33, a34), and the vector a1, the vector a2 and the vector a3 are spliced to obtain the advertisement feature corresponding to the advertisement a, that is, the advertisement feature corresponding to the advertisement a may be (a11, a12, a13, a221, a22, a23, a31, a32, a33, a 34).
It can be understood that, when the server performs feature extraction on the advertisement, the server may also perform feature extraction on one or two of advertisement text introduction information, image information and audio information of the advertisement, which is not specifically limited in this embodiment of the application.
In the embodiment of the present application, the feature extraction of the advertisement text introduction information of the advertisement may be performed by, but is not limited to, a transform model or a word _ embedding model. Feature extraction of image information of an advertisement may employ a Convolutional Neural Networks (CNN) model. The feature extraction of the audio information of the advertisement can adopt, but is not limited to, a Bi-directional Long Short-Term Memory (Bi-LSTM) model or a Long Short-Term Memory (LSTM) model.
The corresponding advertisement characteristics of the advertisements of the same type are similar, when the advertisement category to which the advertisements belong is determined, the server can cluster the advertisements to be played according to the advertisement characteristics corresponding to the advertisements to be played to obtain at least one advertisement cluster, and the advertisements clustered in the same advertisement cluster belong to the same advertisement category, so that the category to which each advertisement belongs can be determined.
In the embodiment of the present application, the clustering of the advertisements to be played may be, but is not limited to, hierarchical clustering or k-means clustering.
In the embodiment of the present application, all the advertisements to be played may also be classified in advance, and the advertisement categories of all the advertisements to be played are stored in the service. In this way, in the specific implementation process, the feature information of each advertisement is extracted, and then the extracted feature information of each advertisement is matched with the features of each advertisement category, so as to determine the category to which each advertisement belongs.
After step S202 is executed, step S203 is executed: and matching advertisement categories corresponding to the advertisements with the attention degrees higher than the preset attention degrees in the plurality of advertisements to the target area.
In the embodiment of the application, the attention degree of each advertisement played in the target area and the advertisement category to which each advertisement belongs are determined, and the advertisement category corresponding to the advertisement with the attention degree higher than the preset attention degree is matched to the target area. So, can match the advertisement classification that the attention degree is high for the target area to put the advertisement that the attention degree is high to the target area, thereby improve the user to the attention degree of putting the advertisement, avoid audience user's aversion, promote the conversion rate of putting the advertisement, the advertisement of putting simultaneously can be according to the timely dynamic adjustment of user's attention degree, avoided because the user that leads to is paid attention to same classification's advertisement for a long time tired, realize the intelligent of advertisement and put.
In the embodiment of the present application, the specific implementation process of step S203 includes the following steps:
determining the theoretical audience number corresponding to the target area;
determining the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of the advertisements;
and matching the advertisement categories corresponding to the advertisements with the average human attention degree higher than the preset average human attention degree among the advertisements to the target area.
In the embodiment of the application, the attention degree of the advertisement is determined according to the attention duration of the audience to the attention advertisement and the playing duration of the attention advertisement, that is, the more the audience in the target area is, the higher the attention degree of the audience to the attention advertisement is. In consideration of the influence of the number of people on the attention degree, the number of people of the theoretical audience in the target area and the attention degree of the concerned advertisement are combined for matching when the advertisement is matched with the target area.
Specifically, when the multimedia terminal performs face recognition on the collected video stream, the user corresponding to the face can be recognized and the identity label is marked, so that the server can perform duplication removal on the user according to the identity label to obtain the number of theoretical audiences corresponding to the target area. Then, according to the number of theoretical audiences and the attention of the multiple advertisements, the per-person attention of each advertisement is determined, and then the advertisement categories corresponding to the advertisements with the per-person attention higher than the preset per-person attention in the multiple advertisements are matched to the target area, namely, the advertisements in the advertisement categories corresponding to the advertisements with the per-person attention higher than the preset per-person attention are preferentially delivered to the target area.
As described in step S201, if the calculated attention of all users to the advertisement a is attention, and the theoretical audience number obtained by performing deduplication on all identified identity tags is person _ num, the per-person attention per _ attention of the advertisement a may be a value obtained by directly dividing the attention of all users to the advertisement a by the theoretical audience number person _ num, that is, per _ attention/person _ num.
Referring to fig. 3, an embodiment of the present application provides an advertisement matching apparatus, including:
a first determination unit, configured to determine a degree of attention of each of a plurality of advertisements played in a target area;
a second determining unit, configured to determine an advertisement category to which each advertisement belongs;
and the matching unit is used for matching the advertisement categories corresponding to the advertisements with the attention degrees higher than the preset attention degrees in the plurality of advertisements to the target area.
In this embodiment of the application, when the first determining unit is configured to determine the attention degree of each of the multiple advertisements played in the target area, specifically, the first determining unit is configured to:
acquiring the concerned time length of each advertisement which is concerned when being played within a preset time length; and
and determining the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
In this embodiment of the application, when the matching unit is configured to match, to the target area, an advertisement category corresponding to an advertisement of which a degree of attention is higher than a preset degree of attention among the multiple advertisements, the matching unit is specifically configured to:
determining the theoretical audience number corresponding to the target area;
determining the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of each advertisement; and
and matching the advertisement categories corresponding to the advertisements with the average human attention degree higher than the preset average human attention degree among the advertisements to the target area.
In this embodiment of the application, when the second determining unit is configured to determine the advertisement category to which each advertisement belongs, the second determining unit is specifically configured to:
extracting advertisement characteristics of all advertisements to be played, wherein the advertisements are contained in the advertisements to be played;
performing cluster analysis on the advertisement characteristics to determine advertisement categories; and
and determining the category of each advertisement according to the advertisement category.
In the embodiment of the present application, when the second determining unit is used to extract the advertisement features of all the advertisements to be played, the second determining unit is configured to:
extracting the characteristics of the text introduction information of each advertisement to be played in the advertisements to be played to obtain a first characteristic corresponding to each advertisement to be played;
extracting the characteristics of the image information of each advertisement to be played to obtain second characteristics corresponding to each advertisement to be played;
extracting the characteristics of the audio information of each advertisement to be played to obtain a third characteristic corresponding to each advertisement to be played; and
and fusing the first characteristic, the second characteristic and the third characteristic to obtain the advertisement characteristic corresponding to each advertisement to be played.
For the working process, the working details and the technical effects of the hardware apparatus provided in this embodiment, reference may be made to the contents of the foregoing method embodiments, which are not described herein again.
Referring to fig. 4, an embodiment of the present application provides a server for advertisement matching, where the server includes a memory, a processor, and a transceiver, which are sequentially connected in communication, where the memory is used to store a computer program, the transceiver is used to transmit and receive a message, and the processor is used to read the computer program and execute an advertisement method according to the above embodiment.
By way of specific example, the Memory may include, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Flash Memory (Flash Memory), a first-in-first-out Memory (FIFO), a first-in-last-out Memory (FILO), and/or the like; the processor may not be limited to a microprocessor of model STM32F105 series, an ARM (Advanced riscmarchitecture), an X86 architecture processor, or a processor of an integrated NPU (neutral-network processing unit); the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (ieee 802.15.4 standard-based low power local area network protocol), a 3G transceiver, a 4G transceiver, and/or a 5G transceiver, etc. In addition, the server may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, the working details and the technical effects of the server provided in this embodiment, reference may be made to the contents of the above method embodiment, which is not described herein again.
The embodiment of the present application further provides a computer-readable storage medium for an advertisement matching method, that is, the computer-readable storage medium has instructions stored thereon, and when the instructions are run on a computer, the advertisement matching method as described above is performed. The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, floppy disks, optical disks, hard disks, flash memories, flash disks and/or Memory sticks (Memory sticks), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details and the technical effects of the computer-readable storage medium provided in this embodiment, reference may be made to the above method embodiment, which is not described herein again.
Embodiments of the present application also provide a computer program product containing instructions which, when run on a computer, cause the computer to perform the advertisement matching method as described above, wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
The embodiments described above are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device to perform the methods described in the embodiments or some portions of the embodiments.
The invention is not limited to the above alternative embodiments, and any other various forms of products can be obtained by anyone in the light of the present invention, but any changes in shape or structure thereof, which fall within the scope of the present invention as defined in the claims, fall within the scope of the present invention.
Claims (10)
1. An advertisement matching method, comprising:
determining the attention degree of each advertisement in a plurality of advertisements played in a target area;
determining an advertisement category to which each advertisement belongs;
and matching advertisement categories corresponding to the advertisements with the attention degrees higher than the preset attention degrees in the plurality of advertisements to the target area.
2. The method of claim 1, wherein determining a degree of interest for each of a plurality of advertisements played within a target area comprises:
acquiring the concerned time length of each advertisement which is concerned when being played within a preset time length;
and determining the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
3. The method of claim 2, wherein matching the target area with an advertisement category corresponding to an advertisement of the plurality of advertisements having a higher attention than a preset attention comprises:
determining the theoretical audience number corresponding to the target area;
determining the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of each advertisement;
and matching the advertisement categories corresponding to the advertisements with the average human attention degree higher than the preset average human attention degree among the advertisements to the target area.
4. The method of claim 1, wherein determining the advertisement categories to which the plurality of advertisements belong comprises:
extracting advertisement characteristics of all advertisements to be played, wherein the advertisements are contained in the advertisements to be played;
performing cluster analysis on the advertisement characteristics to determine advertisement categories;
and determining the category of each advertisement according to the advertisement category.
5. The method of claim 4, wherein extracting the advertisement characteristics of all advertisements to be played comprises:
extracting the characteristics of the text introduction information of each advertisement to be played in the advertisements to be played to obtain a first characteristic corresponding to each advertisement to be played;
extracting the characteristics of the image information of each advertisement to be played to obtain second characteristics corresponding to each advertisement to be played;
extracting the characteristics of the audio information of each advertisement to be played to obtain a third characteristic corresponding to each advertisement to be played;
and fusing the first characteristic, the second characteristic and the third characteristic to obtain the advertisement characteristic corresponding to each advertisement to be played.
6. An advertisement matching device, characterized in that: the method comprises the following steps:
a first determination unit, configured to determine a degree of attention of each of a plurality of advertisements played in a target area;
a second determining unit, configured to determine an advertisement category to which each advertisement belongs;
and the matching unit is used for matching the advertisement categories corresponding to the advertisements with the attention degrees higher than the preset attention degrees in the plurality of advertisements to the target area.
7. The apparatus according to claim 6, wherein when the first determining unit is configured to determine the attention degree of each of the plurality of advertisements played in the target area, it is specifically configured to:
acquiring the concerned time length of each advertisement which is concerned when being played within a preset time length;
and determining the attention degree of each advertisement according to the attention duration of each advertisement and the playing duration of each advertisement during single playing.
8. The apparatus of claim 7, wherein when the matching unit is configured to match, to the target area, an advertisement category corresponding to an advertisement with a higher attention degree than a preset attention degree among the plurality of advertisements, the matching unit is specifically configured to:
determining the theoretical audience number corresponding to the target area;
determining the per-person attention of each advertisement according to the number of the theoretical audiences and the attention of each advertisement;
and matching the advertisement categories corresponding to the advertisements with the average human attention degree higher than the preset average human attention degree among the advertisements to the target area.
9. A server, comprising: the advertisement matching method comprises a memory, a processor and a transceiver which are sequentially connected in a communication mode, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving messages, and the processor is used for reading the computer program and executing the advertisement matching method according to any one of claims 1-5.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored thereon instructions that, when executed on a computer, perform the advertisement matching method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010582653.0A CN111709792A (en) | 2020-06-23 | 2020-06-23 | Advertisement matching method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010582653.0A CN111709792A (en) | 2020-06-23 | 2020-06-23 | Advertisement matching method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111709792A true CN111709792A (en) | 2020-09-25 |
Family
ID=72542590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010582653.0A Pending CN111709792A (en) | 2020-06-23 | 2020-06-23 | Advertisement matching method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709792A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046515A (en) * | 2015-06-26 | 2015-11-11 | 深圳市腾讯计算机系统有限公司 | Advertisement ordering method and device |
| US20160364746A1 (en) * | 2008-10-02 | 2016-12-15 | Turn Inc. | Segment optimization for targeted advertising |
| CN108985845A (en) * | 2018-07-18 | 2018-12-11 | 北京旷视科技有限公司 | Broadcast monitoring method, apparatus and system |
| CN109509028A (en) * | 2018-11-15 | 2019-03-22 | 北京奇虎科技有限公司 | A kind of advertisement placement method and device, storage medium, computer equipment |
| CN109840810A (en) * | 2019-03-19 | 2019-06-04 | 深圳创维－Rgb电子有限公司 | Data analyze method for pushing, device, background server and readable storage medium storing program for executing |
| CN110019882A (en) * | 2019-03-18 | 2019-07-16 | 星潮闪耀移动网络科技（中国）有限公司 | A kind of advertising creative classification method and system |
| CN110378752A (en) * | 2019-07-26 | 2019-10-25 | 京东方科技集团股份有限公司 | Advertisement recommended method, device, electronic equipment and storage medium |
-
2020
- 2020-06-23 CN CN202010582653.0A patent/CN111709792A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160364746A1 (en) * | 2008-10-02 | 2016-12-15 | Turn Inc. | Segment optimization for targeted advertising |
| CN105046515A (en) * | 2015-06-26 | 2015-11-11 | 深圳市腾讯计算机系统有限公司 | Advertisement ordering method and device |
| CN108985845A (en) * | 2018-07-18 | 2018-12-11 | 北京旷视科技有限公司 | Broadcast monitoring method, apparatus and system |
| CN109509028A (en) * | 2018-11-15 | 2019-03-22 | 北京奇虎科技有限公司 | A kind of advertisement placement method and device, storage medium, computer equipment |
| CN110019882A (en) * | 2019-03-18 | 2019-07-16 | 星潮闪耀移动网络科技（中国）有限公司 | A kind of advertising creative classification method and system |
| CN109840810A (en) * | 2019-03-19 | 2019-06-04 | 深圳创维－Rgb电子有限公司 | Data analyze method for pushing, device, background server and readable storage medium storing program for executing |
| CN110378752A (en) * | 2019-07-26 | 2019-10-25 | 京东方科技集团股份有限公司 | Advertisement recommended method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107819827B (en) | Advertisement putting method, device and system | |
| CN105450778B (en) | Information transmission system | |
| CN108596690B (en) | Advertisement processing method and device | |
| CN108495153B (en) | Multimedia content pushing method, device and system | |
| CN110689367A (en) | Data acquisition method and device, computer device and storage medium | |
| CN105160549A (en) | Passenger flow statistical analysis system | |
| JP2007018218A (en) | Advertising effect evaluation supporting method and device | |
| CN108197994A (en) | Advertisement placement method, system, terminal and computer readable storage medium | |
| US20170134806A1 (en) | Selecting content based on media detected in environment | |
| CN113497977A (en) | Video processing method, model training method, device, equipment and storage medium | |
| CN111523920B (en) | Information pushing method and device and terminal equipment | |
| CN109168043B (en) | Method, equipment and system for displaying recommendation information | |
| CN112396461A (en) | Vehicle-mounted video advertisement management system based on big data | |
| CN113542801A (en) | Method, device, equipment, storage medium and program product for generating anchor identification | |
| CN111709792A (en) | Advertisement matching method, device, server and storage medium | |
| CN108074127A (en) | Data analysing method, device and the electronic equipment of business object | |
| CN116614652A (en) | Advertisement video clip replacement method, device and storage medium in live broadcast scene | |
| CN112561589B (en) | Advertisement delivery method, device and storage medium | |
| CN109858900A (en) | A kind of payment information method for pushing, device and terminal device | |
| CN109255665A (en) | A method of advertisement is launched based on user feature analysis advertisement machine | |
| CN114626881A (en) | Advertisement putting control method, device, equipment, storage medium and program product | |
| CN107798112A (en) | A kind of public feelings information processing method and processing device | |
| UA114587C2 (en) | THE SYSTEM (OPTIONS) OF SELECTION, OPENING AND ROTATION OF PHOTO AND / OR VIDEO CONTENT, AND ALSO MONITORING THE QUANTITY OF THE GOODS AND THE METHOD (OPTIONS) FOR ITS | |
| CN113065883A (en) | Method and device for delivering advertisements | |
| CN111681057A (en) | Method and device for processing media resource for information delivery |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200925 |
|
| RJ01 | Rejection of invention patent application after publication |