CN116862588A - Advertisement image evaluation method and device - Google Patents
Advertisement image evaluation method and device Download PDFInfo
- Publication number
- CN116862588A CN116862588A CN202310834892.4A CN202310834892A CN116862588A CN 116862588 A CN116862588 A CN 116862588A CN 202310834892 A CN202310834892 A CN 202310834892A CN 116862588 A CN116862588 A CN 116862588A
- Authority
- CN
- China
- Prior art keywords
- advertisement image
- user
- obtaining
- color value
- score
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 44
- 230000004424 eye movement Effects 0.000 claims abstract description 39
- 230000014509 gene expression Effects 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 21
- 230000001815 facial effect Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007935 neutral effect Effects 0.000 description 4
- 230000008921 facial expression Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06Q30/0245—Surveys
-
- 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
Abstract
The invention provides an advertisement image evaluation method and device, which can be used in the financial field or other technical fields. The method comprises the following steps: obtaining a user visibility score based on user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; and obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score. The device is used for executing the method. The method and the device for evaluating the advertisement image improve the reliability of the evaluation of the advertisement image.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an advertisement image evaluation method and device.
Background
Advertisements are typically presented on media such as televisions, broadcasters, newspapers, magazines, the internet, etc. Advertisements may convey information in a variety of forms, such as text, images, audio, and video, for the purpose of attracting consumers' attention to encourage them to purchase or take particular action.
Advertisement effectiveness evaluation refers to the quantitative or qualitative evaluation and analysis of the effectiveness of an advertisement campaign. The purpose of evaluating the effectiveness of an advertisement is to understand the impact and response of the advertisement on the consumer. In the prior art, the advertisement effect can be evaluated by the evaluation indexes such as advertisement exposure rate, advertisement click rate, advertisement conversion rate, sales data change and the like. The above is mainly to evaluate advertisement by advertisement marketing effect, and how to evaluate advertisement effect more comprehensively becomes an important topic to be solved in the field.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides an advertisement image evaluation method and device, which can at least partially solve the problems in the prior art.
In a first aspect, the present invention provides a method for evaluating advertisement images, including:
obtaining a user visibility score based on user eye movement data corresponding to the advertisement image;
obtaining an ideographic definition score based on user face data corresponding to the advertisement image;
obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance;
And obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
In a second aspect, the present invention provides an evaluation apparatus for advertisement images, comprising:
the first obtaining module is used for obtaining the user visibility score based on the user eye movement data corresponding to the advertisement image;
the second obtaining module is used for obtaining an ideographic definition score based on the user face data corresponding to the advertisement image;
the third obtaining module is used for obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance;
and the evaluation module is used for obtaining the evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method for evaluating advertisement images according to any of the above embodiments when executing the program.
In a fourth aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method for evaluating advertising images according to any of the embodiments described above.
In a fifth aspect, the present invention provides a computer program product comprising a computer program which, when executed by a processor, implements the method for evaluating advertisement images according to any of the embodiments described above.
The method and the device for evaluating the advertisement image can obtain the user visibility score based on the user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; based on the user visibility score, the ideographic definition score and the contrast score, an evaluation result of the advertisement image is obtained, the advertisement image can be evaluated from different dimensions, and the reliability of the advertisement image evaluation is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a flowchart of a method for evaluating advertisement images according to a first embodiment of the present application.
Fig. 2 is a flowchart of a method for evaluating advertisement images according to a second embodiment of the present application.
Fig. 3 is a flowchart of a method for evaluating advertisement images according to a third embodiment of the present application.
Fig. 4 is a flowchart of a method for evaluating advertisement images according to a fourth embodiment of the present application.
Fig. 5 is a flowchart of a method for evaluating advertisement images according to a fifth embodiment of the present application.
Fig. 6 is a schematic structural view of an apparatus for evaluating advertisement images according to a sixth embodiment of the present application.
Fig. 7 is a schematic structural view of an apparatus for evaluating advertisement images according to a seventh embodiment of the present application.
Fig. 8 is a schematic structural view of an apparatus for evaluating advertisement images according to an eighth embodiment of the present application.
Fig. 9 is a schematic structural view of an apparatus for evaluating advertisement images according to a ninth embodiment of the present application.
Fig. 10 is a schematic structural view of an apparatus for evaluating advertisement images according to a tenth embodiment of the present application.
Fig. 11 is a schematic entity structure of an electronic device according to an eleventh embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be arbitrarily combined with each other. In the technical scheme of the application, the acquisition, storage, use, processing and the like of the data all accord with the relevant regulations of laws and regulations. The user information in the embodiment of the application is obtained through legal compliance approaches, and the user information is obtained, stored, used, processed and the like through the approval of the client.
In order to facilitate understanding of the technical scheme provided by the application, the following description will explain relevant contents of the technical scheme of the application.
According to the method for evaluating the advertisement image, provided by the embodiment of the application, the attraction of the advertisement image to the user is evaluated through the user visibility score, and the purpose is to judge whether the advertisement image is easily and rapidly noticed by the user; evaluating the cognition of the user on the advertisement image through the ideographic definition score, so as to judge whether the advertisement image is easy to understand by the user; and the barrier-free reading support degree of the advertisement image is evaluated through the contrast value, so that whether the advertisement image is easy to identify is judged, the advertisement image is evaluated from three different dimensions, and the reliability of the advertisement image evaluation is improved.
The following describes a specific implementation procedure of the method for evaluating advertisement images provided by the embodiment of the present application, with a server as an execution body. It can be understood that the execution subject of the method for evaluating advertisement images provided by the embodiment of the present application is not limited to a server.
Fig. 1 is a flowchart of an advertisement image evaluation method according to a first embodiment of the present application, where, as shown in fig. 1, the advertisement image evaluation method according to the embodiment of the present application includes:
S101, obtaining a user visibility score based on user eye movement data corresponding to advertisement images;
specifically, the server may acquire user eye movement data corresponding to the advertisement image, where the user eye movement data corresponding to the advertisement image is eye movement focus data of the user when watching the advertisement image, the user eye movement focus data being acquired by the eye movement instrument in a set duration. The user eye movement data corresponding to the advertisement image comprises a first gazing point and gazing time length of each user watching the advertisement image in a set time length, a second gazing point and gazing time length, a third gazing point and gazing time length, and the like until the last gazing point and gazing time length. The server can obtain a user visibility score according to the user eye movement data corresponding to the advertisement image, wherein the user visibility score is used for evaluating whether the advertisement image is easily noticed by a user. A higher user visibility score indicates that the advertisement image is more noticeable to the user.
In order to collect user eye movement data corresponding to the advertisement image, the advertisement image needs to be marked with a coordinate section. And selecting an element to be detected for image information perceptibility measurement in the advertisement image by a tester, and recording a coordinate interval covered by the element to be detected. When the coordinate interval is recorded, a two-dimensional coordinate system can be established by taking the point at the leftmost lower part of the advertisement image as the origin, and the vertex coordinates of the element to be detected selected by the tester are recorded in sequence to form the coordinate interval. When the user is viewing the advertisement image, if the point of regard of the user falls within the coordinate interval of the element to be detected of the advertisement image, the point of regard is recorded by the eye tracker.
S102, obtaining an ideographic definition score based on user face data corresponding to the advertisement image;
specifically, the user may record face data of the user while viewing the advertisement image. The server can acquire the user face data corresponding to the advertisement image, and user expression recognition is carried out through the user face data, so that the ideographic definition score is obtained. The ideographic sharpness score is used to determine whether the advertising image is easily understood by the user. The higher the ideographic sharpness score, the more easily the advertisement image is understood by the user.
S103, obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance;
specifically, the server may obtain the reference text color value and the reference background color value of the advertisement image, and obtain the contrast score through the reference text color value and the reference background color value of the advertisement image. The contrast score is used to determine whether the advertising image is easily identifiable. The higher the contrast score, the more easily the advertising image is identified.
S104, based on the user visibility score, the ideographic definition score and the contrast score, an evaluation result of the advertisement image is obtained.
Specifically, the server evaluates the advertisement image according to the user visibility score, the ideographic definition score and the contrast score, so that an evaluation result of the advertisement image can be obtained.
For example, if the user visibility score is smaller than a first threshold, the ideographic definition score is smaller than a second threshold or the contrast score is smaller than a third threshold, a prompt message indicating that the advertisement image is unqualified may be output, which indicates that the advertisement effect is bad, and the advertisement image needs to be modified.
For example, if the user visibility score is equal to or greater than a first threshold, the ideographic clarity score is equal to or greater than a second threshold, and the contrast score is equal to or greater than a third threshold, a prompt for the eligibility of the advertisement image may be output.
The evaluation method of the advertisement image provided by the embodiment of the invention can obtain the user visibility score based on the user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; based on the user visibility score, the ideographic definition score and the contrast score, an evaluation result of the advertisement image is obtained, the advertisement image can be evaluated from different dimensions, and the reliability of the advertisement image evaluation is improved.
Fig. 2 is a flow chart of an evaluation method of advertisement images according to a second embodiment of the present invention, as shown in fig. 2, further, based on the user eye movement data corresponding to the advertisement images, obtaining a user attention score includes:
s201, acquiring corresponding user eye movement data of the advertisement image, wherein the user eye movement data comprises each sequential gazing point of each user on the advertisement image and each corresponding gazing time length;
specifically, the server obtains corresponding user eye movement data of the advertisement image, wherein the user eye movement data comprises each sequential gazing point of each user on the advertisement image and each corresponding gazing time length. Each sequential gaze point of each user for the advertisement image refers to a first gaze point, a second gaze point, and a third gaze point … … of the advertisement image viewed by the user within a set period of time, until the last gaze point, each sequential gaze point has a corresponding gaze period, i.e., a length of time the user remains at each sequential gaze point. The set time length is set according to actual needs, and the embodiment of the invention is not limited.
It will be appreciated that the number of sequential gaze points may be different for different users, such as 3 gaze points for user a viewing an advertising image and 5 gaze points for user b viewing an advertising image.
S202, obtaining the average gazing time length of the advertisement image according to each sequential gazing point of each user on the advertisement image and the gazing time length corresponding to each sequential gazing point;
specifically, the server may obtain, according to each sequential gazing point and each corresponding gazing time length of each user on the advertisement image, the number of users corresponding to each sequential gazing point and the average gazing time length corresponding to each sequential gazing point, and then calculate an average value of the average gazing time lengths corresponding to each sequential gazing point as the average gazing time length of the advertisement image.
S203, obtaining the effective gazing point of each user on the advertisement image according to the gazing time length corresponding to each sequential gazing point of each user on the advertisement image and the average gazing time length of the advertisement image;
specifically, for each user, the server compares the gazing time length corresponding to each sequential gazing point of the advertisement image by the user with the average gazing time length of the advertisement image, and if the gazing time length corresponding to the sequential gazing point is smaller than the average gazing time length of the advertisement image, the sequential gazing point is taken as the effective gazing point of the advertisement image by the user; and if the gazing time length corresponding to the sequential gazing point is greater than or equal to the average gazing time length of the advertisement image, the sequential gazing point is not used as the effective gazing point of the user on the advertisement image. The server may obtain an effective gaze point for each user for the advertising image.
For example, user A has three points of gaze for the advertisement image: a first gaze point, a second gaze point, and a third gaze point. The gazing time length corresponding to the first gazing point is smaller than the average gazing time length of the advertisement image, the gazing time length corresponding to the second gazing point is smaller than the average gazing time length of the advertisement image, the gazing time length corresponding to the third gazing point is larger than the average gazing time length of the advertisement image, and then the first gazing point and the second gazing point serve as effective gazing points of users for the advertisement image.
S204, obtaining the effective number of people of each sequential gazing point corresponding to the advertisement image according to the effective gazing point of each user to the advertisement image; according to the sequential gazing points of each user on the advertisement image, the total number of people at each sequential gazing point corresponding to the advertisement image is obtained;
specifically, the server can count and obtain the effective number of people of each sequential gazing point corresponding to the advertisement image according to the effective gazing point of each user on the advertisement image, wherein the effective number of people of the ith gazing point corresponding to the advertisement image is equal to the total number of users including the ith gazing point in the effective gazing points of each user on the advertisement image.
And the server can count the total number of people who obtain each sequential gaze point corresponding to the advertisement image according to each sequential gaze point of each user for the advertisement image. The total number of the ith gazing point corresponding to the advertisement image is equal to the total number of users including the ith gazing point in each sequence gazing point of the advertisement image.
For example, the effective gaze point of the user a is the first gaze point and the second gaze point, the effective gaze point of the user b is the first gaze point and the second gaze point is the second gaze point and the third gaze point, and when the effective number of people of the first gaze point corresponding to the advertisement image is counted, the user a is counted, but the user b is not counted; counting the number of effective people of a second fixation point corresponding to the advertisement image, wherein the user A and the user B are both counted; when counting the number of effective people at the third gaze point corresponding to the advertising image, user b will be counted, but user a will not be counted.
S205, obtaining the user' S gaze score according to the effective number and the total number of each sequential gaze point corresponding to the advertisement image.
Specifically, the server may obtain the user's gaze score according to the number of available people and the total number of people at each sequential gaze point corresponding to the advertisement image.
For example, according to the formulaCalculating a user visibility score V for an advertising image σ Wherein alpha is j Represents the weight adjustment coefficient corresponding to the jth gaze point, M j Representing the effective number of people, N, of the j-th gaze point corresponding to the advertisement image i Indicating the total number of the ith gazing point corresponding to the advertisement image, wherein the sum of the weight adjustment coefficients is equal to 1, i and j are positive integers, i is less than or equal to n, j is less than or equal to n, n indicates the number of the gazing points, and alpha j The embodiment of the invention is not limited by setting according to actual needs.
Fig. 3 is a flowchart of a method for evaluating advertisement images according to a third embodiment of the present invention, as shown in fig. 3, further, based on the foregoing embodiments, the obtaining, according to each sequential gazing point of each user on the advertisement image and each corresponding gazing time period, an average gazing time period of the advertisement image includes:
s301, obtaining the average gazing time length of each sequential gazing point corresponding to the advertisement image according to the gazing time length of each user corresponding to each sequential gazing point of the advertisement image;
Specifically, the server may calculate, according to gaze durations corresponding to the same sequential gaze points of the advertisement images by each user, average gaze durations of the same sequential gaze points corresponding to the advertisement images. And calculating the average gazing time length of all the sequential gazing points, and obtaining the average gazing time length of each sequential gazing point corresponding to the advertisement image.
For example, an average value of gaze durations of respective users corresponding to the first gaze point of the advertisement image is calculated, and the average gaze duration of the first gaze point corresponding to the advertisement image may be obtained. And calculating the average value of the gazing time lengths corresponding to the second gazing point of the advertisement image by each user, and obtaining the average gazing time length of the second gazing point corresponding to the advertisement image. And calculating the average value of the gazing time lengths corresponding to the third gazing point of the advertisement image by each user, and obtaining the average gazing time length of the third gazing point corresponding to the advertisement image. And so on until the average gazing time length of the last gazing point corresponding to the advertisement image is obtained by calculation.
S302, obtaining the total number of people at each sequential fixation point corresponding to the advertisement image according to each sequential fixation point of each user to the advertisement image;
Specifically, the server may count the total number of people who obtain each sequential gaze point corresponding to the advertisement image according to each sequential gaze point of each user for the advertisement image. The total number of the ith gazing point corresponding to the advertisement image is equal to the total number of users including the ith gazing point in each sequence gazing point of the advertisement image.
For example, the respective sequential gaze points of the advertisement image by user A are: a first gaze point, a second gaze point, and a third gaze point; the user B focuses on each sequence of the advertisement images as follows: a first gaze point, a second gaze point, a third gaze point, and a fourth gaze point; the user C focuses on each sequence of the advertisement images as follows: a first gaze point and a second gaze point. Counting the total number of the first fixation point corresponding to the advertisement image, and counting the first user, the second user and the third user; counting the total number of the second fixation point corresponding to the advertisement image, wherein the first user, the second user and the third user are counted; counting the total number of the third fixation point corresponding to the advertisement image, wherein the first user and the second user are counted; and counting the user B when counting the total number of people at the fourth fixation point corresponding to the advertisement image.
S303, obtaining the average gazing time length of the advertisement image according to the average gazing time length and the total number of people of each sequential gazing point corresponding to the advertisement image.
Specifically, the server may obtain the average gazing time length of the advertisement image according to the average gazing time length of each sequential gazing point corresponding to the advertisement image and the total number of people of each sequential gazing point corresponding to the advertisement image.
For example, the formula can be based onCalculating the average gazing time length T of the obtained advertisement image avg Wherein T is i Represents the average gazing time length, N, of the ith gazing point corresponding to the advertisement image i The total number of the ith fixation point corresponding to the advertisement image is represented, i is a positive integer, and is less than or equal to n, wherein n represents the number of the fixation points.
Fig. 4 is a flowchart of a method for evaluating advertisement images according to a fourth embodiment of the present invention, as shown in fig. 4, further, based on the foregoing embodiments, the obtaining an ideographic sharpness score based on the user face data corresponding to the advertisement images includes:
s401, acquiring user face data corresponding to the advertisement image, wherein the user face data comprises multi-frame face pictures of each user;
Specifically, the server may acquire user face data corresponding to the advertisement image, where the user face data includes multiple frames of face pictures of each user. The user face data corresponding to the advertisement image can be synchronously acquired when the user eye movement data are acquired.
S402, carrying out expression recognition on multi-frame facial pictures of each user to obtain an expression type corresponding to each user;
specifically, for each user, the server performs expression recognition on multiple frames of facial pictures of the user through a facial expression recognition model, so that the expression type corresponding to the user can be obtained. When each frame of facial image can identify and acquire one expression, the multi-frame facial image can identify and acquire a plurality of expressions, the plurality of expressions can be used for carrying out expression classification, and the expression types corresponding to the user can comprise one expression type, two expression types or more than two expression types. The facial expression recognition model can be obtained through pre-training, or can be an expression recognition model existing in the prior art.
For example, the expression type is set to three types of positive expression, neutral expression, and negative expression. The smile of expression may be classified as a positive expression, the suspicion of expression or suspicion of expression may be classified as a negative expression, and the lack of expression may be classified as a neutral expression. Each expression specifically comprises which expressions, and the setting is carried out according to actual needs, and the embodiment of the invention is not limited.
S403, counting and obtaining the total number corresponding to each type of expression type according to the expression type corresponding to each user;
specifically, the server performs user statistics corresponding to each type of expression type according to the expression type corresponding to each user, so that the total number corresponding to each type of expression type can be obtained.
For example, the expression type corresponding to the user a is a positive expression, the expression type corresponding to the user b is set to be a neutral expression, and the expression type corresponding to the user c is a negative expression. When the forward expression is counted, counting the user A; when negative expressions are counted, counting the user C; and when the neutral expression is counted, counting the user B.
S404, obtaining the ideographic definition score by the total number corresponding to each expression type and the weight adjustment coefficient corresponding to each expression type.
Specifically, the server may obtain the ideographic definition score according to the total number of people corresponding to each expression type and the weight adjustment coefficient corresponding to each expression type. The weight adjustment coefficient is set according to actual needs, and the embodiment of the invention is not limited.
For example, according to the formulaCalculating to obtain ideographic definition score V of advertisement image β ，β k Weight adjustment coefficient corresponding to the expression type k, W k Representing the total number of people corresponding to the kth expression type, wherein k is a positive integer and is less than or equal to m, m represents the number of expression types, and beta k The embodiment of the invention is not limited by setting according to actual needs.
Fig. 5 is a flowchart of an evaluation method of an advertisement image according to a fifth embodiment of the present invention, as shown in fig. 5, further, based on the above embodiments, obtaining a reference text color value and a reference background color value of the advertisement image includes:
s501, obtaining a color value and a first appearance area of each character in the advertisement image, and obtaining a background color value and a second appearance area corresponding to each character in the advertisement image;
specifically, each text and the rectangular area where each text is located in the advertisement image may be identified by OCR technology. For each character, carrying out pixel-level color recognition on the character and a rectangular area where the character is located, obtaining the color value of the character, and carrying out statistics on the area occupied by the color value of the character to obtain a first appearance area. A color value and a first appearance area of each text within the advertising image may be obtained.
For each character, the background color value of each character can be identified, and the area occupied by the background color value corresponding to the character is counted to obtain the second appearance area. And obtaining a background color value corresponding to each text in the advertisement image and a second appearance area. The background color value and the area occupied by the background color value are identified as the prior art, and are not described herein.
S502, comparing the first appearance areas of the characters, and taking the color value of the character corresponding to the largest first appearance area as the reference character color value of the advertisement image; and comparing the second appearance areas corresponding to the characters, and taking the background color value corresponding to the largest second appearance area as the reference background color value of the advertisement image.
Specifically, comparing the first appearance areas of the characters to obtain the largest first appearance area, and taking the color value of the character corresponding to the largest first appearance area as the reference character color value of the advertisement image. And comparing the mechanical energy of the second appearance area corresponding to each character to obtain the largest second appearance area, and taking the background color value corresponding to the largest second appearance area as the reference background color value of the advertisement image.
On the basis of the foregoing embodiments, further, the obtaining the contrast score based on the reference text color value and the reference background color value of the advertisement image includes:
and calculating the ratio of the reference text color value of the advertisement image to the reference background color value of the advertisement image as the contrast score.
Specifically, the server calculates a ratio of a reference text color value of the advertisement image to a reference background color value of the advertisement image as the contrast score. By comparing the text color value with the background color value, whether the advertisement image is easy to identify can be judged.
On the basis of the foregoing embodiments, further, the obtaining the evaluation result of the advertisement image based on the user visibility score, the ideographic sharpness score, and the contrast score includes:
and if the user watching degree score is judged to be smaller than the first threshold value, the ideographic definition score is smaller than the second threshold value or the contrast score is smaller than the third threshold value, outputting prompt information of disqualification of the advertisement image.
Specifically, the server compares the user visibility score with a first threshold, compares an ideographic definition score with a second threshold, compares the contrast score with a third threshold, and if the user visibility score is smaller than the first threshold, the ideographic definition score is smaller than the second threshold or the contrast score is smaller than the third threshold, that is, any one of the user visibility score, the ideographic definition score and the contrast score is smaller than the corresponding threshold, the server outputs a prompt message that the advertisement image is unqualified to prompt related personnel to improve the advertisement image. The first threshold, the second threshold and the third threshold are set according to actual needs, and the embodiment of the invention is not limited.
The method for evaluating the advertisement image can be pushed to part of users for evaluation before the advertisement is formally put in, and can purposefully perfect the advertisement image when the advertisement image is unqualified in prompting information, so that poor advertisement effect caused by direct putting is avoided. The method for evaluating the advertisement image provided by the embodiment of the invention can be applied to the advertisement which is put in, so that the advertisement image can be evaluated more reliably.
Fig. 6 is a schematic structural diagram of an apparatus for evaluating an advertisement image according to a sixth embodiment of the present invention, as shown in fig. 6, the apparatus for evaluating an advertisement image according to an embodiment of the present invention includes a first obtaining module 601, a second obtaining module 602, a third obtaining module 603, and an evaluating module 604, where:
the first obtaining module 601 is configured to obtain a user visibility score based on user eye movement data corresponding to the advertisement image; the second obtaining module 602 is configured to obtain an ideographic sharpness score based on user face data corresponding to the advertisement image; the third obtaining module 603 is configured to obtain a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; the evaluation module 604 is configured to obtain an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score, and the contrast score.
Specifically, the first obtaining module 601 may obtain user eye movement data corresponding to an advertisement image, where the user eye movement data corresponding to the advertisement image is eye movement focus data of a user when watching the advertisement image, the eye movement focus data being collected by an eye movement instrument in a set period of time. The user eye movement data corresponding to the advertisement image comprises a first gazing point and gazing time length of each user watching the advertisement image in a set time length, a second gazing point and gazing time length, a third gazing point and gazing time length, and the like until the last gazing point and gazing time length. The server can obtain a user visibility score according to the user eye movement data corresponding to the advertisement image, wherein the user visibility score is used for evaluating whether the advertisement image is easily noticed by a user. A higher user visibility score indicates that the advertisement image is more noticeable to the user.
The user may record facial data of the user while viewing the advertising image. The second obtaining module 602 may obtain user facial data corresponding to the advertisement image, and perform user expression recognition through the user facial data, thereby obtaining an ideographic definition score. The ideographic sharpness score is used to determine whether the advertising image is easily understood by the user. The higher the ideographic sharpness score, the more easily the advertisement image is understood by the user.
The third obtaining module 603 may obtain a reference text color value and a reference background color value of the advertisement image, and obtain a contrast score through the reference text color value and the reference background color value of the advertisement image. The contrast score is used to determine whether the advertising image is easily identifiable. The higher the contrast score, the more easily the advertising image is identified.
The evaluation module 604 evaluates the advertisement image according to the user's visibility score, the ideographic definition score and the contrast score, so as to obtain an evaluation result of the advertisement image.
The evaluation device of the advertisement image provided by the embodiment of the invention can obtain the user visibility score based on the user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; based on the user visibility score, the ideographic definition score and the contrast score, an evaluation result of the advertisement image is obtained, the advertisement image can be evaluated from different dimensions, and the reliability of the advertisement image evaluation is improved.
Fig. 7 is a schematic structural diagram of an apparatus for evaluating an advertisement image provided in a seventh embodiment of the present invention, as shown in fig. 7, further, on the basis of the above-described embodiments, a first obtaining module 601 includes a first obtaining unit 6011, a first obtaining unit 6012, a second obtaining unit 6013, a third obtaining unit 6014, and a fourth obtaining unit 6015, wherein:
the first acquiring unit 6011 is configured to acquire corresponding user eye movement data of the advertisement image, where the user eye movement data includes each sequential gazing point of each user on the advertisement image and each corresponding gazing time period; the first obtaining unit 6012 is configured to obtain an average gazing time length of the advertisement image according to each sequential gazing point and each corresponding gazing time length of each user on the advertisement image; the second obtaining unit 6013 is configured to obtain an effective gaze point of each user on the advertisement image according to a gaze duration of each user corresponding to each sequential gaze point of the advertisement image and an average gaze duration of the advertisement image; the third obtaining unit 6014 is configured to obtain, according to the effective gaze points of each user on the advertisement image, an effective number of people at each sequential gaze point corresponding to the advertisement image; according to the sequential gazing points of each user on the advertisement image, the total number of people at each sequential gazing point corresponding to the advertisement image is obtained; the fourth obtaining unit 6015 is configured to obtain a user's gaze score according to the effective number and the total number of each sequential gaze point corresponding to the advertisement image.
Fig. 8 is a schematic structural view of an apparatus for evaluating advertisement images according to an eighth embodiment of the present invention, as shown in fig. 8, further, based on the above embodiments, a first obtaining unit 6012 includes a first obtaining subunit 60111, a second obtaining subunit 60122, and a third obtaining subunit 60123, wherein:
the first obtaining subunit 60121 is configured to obtain, according to gaze durations corresponding to respective sequential gaze points of the advertisement image by respective users, an average gaze duration of each sequential gaze point corresponding to the advertisement image; the second obtaining subunit 60122 is configured to obtain, according to each sequential gaze point of each user on the advertisement image, a total number of people at each sequential gaze point corresponding to the advertisement image; the third obtaining subunit 60123 is configured to obtain the average gazing duration of the advertisement image according to the average gazing duration and the total number of people of each sequential gazing point corresponding to the advertisement image.
Fig. 9 is a schematic structural diagram of an apparatus for evaluating advertisement images according to a ninth embodiment of the present invention, as shown in fig. 9, further, based on the above embodiments, the second obtaining module 602 includes a second obtaining unit 6021, a fifth obtaining unit 6022, a statistical unit 6023, and a sixth obtaining unit 6024, wherein:
The second acquiring unit 6021 is configured to acquire user face data corresponding to the advertisement image, where the user face data includes multiple frames of face pictures of each user; the fifth obtaining unit 6022 is configured to perform expression recognition on multiple frames of facial pictures of each user, so as to obtain an expression type corresponding to each user; the statistics unit 6023 is configured to obtain, according to the expression types corresponding to each user, statistics of total people corresponding to each type of expression type; the sixth obtaining unit 6024 is configured to obtain the ideographic definition score according to the total number of people corresponding to each expression type and the weight adjustment coefficient corresponding to each expression type.
Fig. 10 is a schematic structural diagram of an apparatus for evaluating advertisement images according to a tenth embodiment of the present invention, as shown in fig. 10, further, based on the above embodiments, the third obtaining module 603 includes a third obtaining unit 6031 and a comparing unit 6032, wherein:
the third obtaining unit 6031 is configured to obtain a color value and a first appearance area of each text in the advertisement image, and obtain a background color value and a second appearance area corresponding to each text in the advertisement image; the comparing unit 6032 is configured to compare the first appearance areas of the respective characters, and take the color value of the character corresponding to the largest first appearance area as the reference character color value of the advertisement image; and comparing the second appearance areas corresponding to the characters, and taking the background color value corresponding to the largest second appearance area as the reference background color value of the advertisement image.
Further, based on the above embodiments, the third obtaining module 603 is specifically configured to:
and calculating the ratio of the reference text color value of the advertisement image to the reference background color value of the advertisement image as the contrast score.
Further, based on the above embodiments, the evaluation module 604 is specifically configured to
And if the user watching degree score is judged to be smaller than the first threshold value, the ideographic definition score is smaller than the second threshold value or the contrast score is smaller than the third threshold value, outputting prompt information of disqualification of the advertisement image.
The embodiment of the apparatus provided in the embodiment of the present invention may be specifically used to execute the processing flow of each method embodiment, and the functions thereof are not described herein again, and may refer to the detailed description of the method embodiments.
It should be noted that, the method and the device for evaluating the advertisement image provided by the embodiment of the invention can be used in the financial field and also can be used in any technical field except the financial field, and the application field of the method and the device for evaluating the advertisement image is not limited.
Fig. 11 is a schematic physical structure of an electronic device according to an embodiment of the present invention, as shown in fig. 11, the electronic device may include: a processor 1101, a communication interface (Communications Interface) 1102, a memory 1103 and a communication bus 1104, wherein the processor 1101, the communication interface 1102 and the memory 1103 communicate with each other via the communication bus 1104. The processor 1101 may call logic instructions in the memory 1103 to perform the following method: obtaining a user visibility score based on user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; and obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
Further, the logic instructions in the memory 1103 described above may be implemented in the form of software functional units and sold or used as a separate product, and may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the methods provided by the above-described method embodiments, for example comprising: obtaining a user visibility score based on user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; and obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
The present embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided by the above-described method embodiments, for example, including: obtaining a user visibility score based on user eye movement data corresponding to the advertisement image; obtaining an ideographic definition score based on user face data corresponding to the advertisement image; obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance; and obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present specification, reference to the terms "one embodiment," "one particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (11)
1. A method of evaluating an advertisement image, comprising:
obtaining a user visibility score based on user eye movement data corresponding to the advertisement image;
obtaining an ideographic definition score based on user face data corresponding to the advertisement image;
obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance;
and obtaining an evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
2. The method of claim 1, wherein obtaining a user gaze score based on user eye movement data corresponding to the advertisement image comprises:
acquiring corresponding user eye movement data of the advertisement image, wherein the user eye movement data comprises each sequential gazing point of each user on the advertisement image and each corresponding gazing time length;
according to each sequential gazing point of each user on the advertisement image and each corresponding gazing time length, obtaining the average gazing time length of the advertisement image;
according to the gazing time length corresponding to each sequential gazing point of each user on the advertisement image and the average gazing time length of the advertisement image, obtaining the effective gazing point of each user on the advertisement image;
According to the effective fixation points of each user to the advertisement image, obtaining the effective number of people of each sequential fixation point corresponding to the advertisement image; according to the sequential gazing points of each user on the advertisement image, the total number of people at each sequential gazing point corresponding to the advertisement image is obtained;
and obtaining the user watching degree score according to the effective number and the total number of each sequential watching point corresponding to the advertisement image.
3. The method of claim 2, wherein the obtaining the average gazing time length of the advertisement image according to each sequential gazing point and each corresponding gazing time length of the advertisement image by each user comprises:
according to the gazing time length corresponding to each sequential gazing point of the advertisement image by each user, obtaining the average gazing time length of each sequential gazing point corresponding to the advertisement image;
according to each sequential fixation point of each user to the advertisement image, obtaining the total number of each sequential fixation point corresponding to the advertisement image;
and obtaining the average gazing time length of the advertisement images according to the average gazing time length and the total number of people of each sequential gazing point corresponding to the advertisement images.
4. The method of claim 1, wherein the obtaining an ideographic sharpness score based on user face data corresponding to the advertisement image comprises:
acquiring user face data corresponding to the advertisement image, wherein the user face data comprises multi-frame face pictures of each user;
carrying out expression recognition on multi-frame facial pictures of each user to obtain the expression type corresponding to each user;
counting and obtaining the total number corresponding to each type of expression type according to the expression type corresponding to each user;
and obtaining the ideographic definition score by the total number corresponding to each expression type and the weight adjustment coefficient corresponding to each expression type.
5. The method of claim 1, wherein obtaining a reference text color value and a reference background color value of the advertising image comprises:
acquiring a color value and a first appearance area of each character in the advertisement image, and acquiring a background color value and a second appearance area corresponding to each character in the advertisement image;
comparing the first appearance areas of the characters, and taking the color value of the character corresponding to the largest first appearance area as the reference character color value of the advertisement image; and comparing the second appearance areas corresponding to the characters, and taking the background color value corresponding to the largest second appearance area as the reference background color value of the advertisement image.
6. The method of claim 1, wherein the obtaining a contrast score based on the reference text color value and the reference background color value of the advertising image comprises:
and calculating the ratio of the reference text color value of the advertisement image to the reference background color value of the advertisement image as the contrast score.
7. The method of any one of claims 1 to 6, wherein the obtaining an evaluation result of the advertisement image based on the user visibility score, ideographic sharpness score, and contrast score comprises:
and if the user watching degree score is judged to be smaller than the first threshold value, the ideographic definition score is smaller than the second threshold value or the contrast score is smaller than the third threshold value, outputting prompt information of disqualification of the advertisement image.
8. An advertisement image evaluation device, comprising:
the first obtaining module is used for obtaining the user visibility score based on the user eye movement data corresponding to the advertisement image;
the second obtaining module is used for obtaining an ideographic definition score based on the user face data corresponding to the advertisement image;
the third obtaining module is used for obtaining a contrast score based on the reference text color value and the reference background color value of the advertisement image; wherein, the reference text color value and the reference background color value of the advertisement image are obtained in advance;
And the evaluation module is used for obtaining the evaluation result of the advertisement image based on the user visibility score, the ideographic definition score and the contrast score.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310834892.4A CN116862588A (en) | 2023-07-07 | 2023-07-07 | Advertisement image evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310834892.4A CN116862588A (en) | 2023-07-07 | 2023-07-07 | Advertisement image evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116862588A true CN116862588A (en) | 2023-10-10 |
Family
ID=88221160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310834892.4A Pending CN116862588A (en) | 2023-07-07 | 2023-07-07 | Advertisement image evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116862588A (en) |
-
2023
- 2023-07-07 CN CN202310834892.4A patent/CN116862588A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pieters et al. | Ad gist: Ad communication in a single eye fixation | |
| Kulkarni et al. | A typology of viral ad sharers using sentiment analysis | |
| Hancock et al. | Putting your best face forward: The accuracy of online dating photographs | |
| Spielmann et al. | How captive is your audience? Defining overall advertising involvement | |
| JP2018206085A (en) | Event evaluation support system, event evaluation support device, and event evaluation support program | |
| Wan et al. | Defensive reactions to slim female images in advertising: The moderating role of mode of exposure | |
| CN109615408B (en) | Advertisement putting method and device based on big data, storage medium and electronic equipment | |
| US20140089067A1 (en) | User rewards from advertisers for content provided by users of a social networking service | |
| US20200175543A1 (en) | Methodology for ensuring viewability of advertisements in a flip-based environment | |
| CN102609862A (en) | Method and device for acquiring advertisement delivery parameters | |
| CN104967690B (en) | A kind of information-pushing method and device | |
| JP7421149B2 (en) | Advertisement viewing information output method, advertisement viewing information output program, and information processing device | |
| Augereau et al. | Estimation of english skill with a mobile eye tracker | |
| Cher et al. | The Factors Affecting the Effectiveness of Online Video Advertising: A Study on Malaysian Consumers' Perspective towards Ads on Youtube. | |
| CN116862588A (en) | Advertisement image evaluation method and device | |
| US20180075460A1 (en) | Comment analysis system, comment analysis method, and program for comment analysis | |
| CN115829657A (en) | Data acquisition method and device applied to data statistics and storage medium | |
| CN113918548A (en) | Questionnaire survey method and device based on private domain flow and storage medium | |
| JP7164508B2 (en) | Program, Apparatus and Method for Selecting Items Based on Corrected Effect, and Item Effect Estimation Program | |
| CN111932315A (en) | Data display method and device, electronic equipment and computer readable storage medium | |
| JP7003883B2 (en) | A system for assessing the degree of similarity in psychological states between audiences | |
| Ismail et al. | Selection of Islamic credit cards: An empirical investigation | |
| Valletti et al. | Attention, recall and purchase: Experimental evidence on online news and advertising | |
| Gunarathne et al. | Racial discrimination in social media customer service: evidence from a popular microblogging platform | |
| CN110910015B (en) | Network information analysis method and device |
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 |