Visual material effect evaluation method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data analysis, in particular to a visual material effect evaluation method, which comprises the following steps: controlling a camera shooting unit to shoot a face video when a target user watches a visual material, and determining pupil center coordinates of the target user corresponding to a video frame; extracting micro-expression data of the target user from a video frame of the face video in real time, and synchronously acquiring a coordinate point of a visual material mapped by a pupil center coordinate of the target user corresponding to the video frame according to a preset mapping relation; and synchronously displaying the information of the micro-expression data of the target user and the position of the coordinate point of the pupil center coordinate mapped to the visual material on the visual material on a display interface of the equipment according to a time sequence. According to the method, the content of the visual material can be evaluated in multiple dimensions, and a multi-level visual material effect evaluation result is obtained, so that optimization of the overall and local content of the visual material is better guided.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method for evaluating visual material effects, electronic equipment and a storage medium. Background Art

[0002] Nowadays, facing the fiercely competitive business environment, it has become a common method to promote commodity transactions by designing visual materials that attract users. Visual materials can be understood as advertising pages, product packaging materials, etc. By designing visual materials that consumers are interested in, it can increase consumers' willingness to buy, deepen their impressions and improve their favorability.

[0003] There is an existing method for evaluating the effect of visual materials. By obtaining the facial video of the evaluator during the test, the microscopic movements of the evaluator's face are identified and encoded based on the facial action coding system, and a set of data values ​​of the evaluator arranged in chronological order is obtained. Then, the data values ​​are processed by simple operations such as averaging to obtain the evaluator's objective preference for the visual material, and the evaluation results are used to design the content of the visual material. However, this method only evaluates and analyzes the overall design effect of the visual material through facial micro-expressions, and cannot analyze the content of the visual material by region. Therefore, the evaluation results cannot accurately reflect the user's preference for the local specific content of the visual material, and cannot help merchants clarify the specific optimization direction of the visual material. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method, electronic device and storage medium for evaluating the effects of visual materials, which can evaluate the content of visual materials in multiple dimensions and obtain multi-level visual material effect evaluation results, so as to better guide the optimization of the overall and local content of visual materials.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for evaluating the effect of visual materials, which is applied to a device equipped with a camera unit, wherein the camera unit is used to shoot a facial video of the target user and determine the pupil center coordinates of the target user corresponding to each video frame; the method comprises:

[0006] Controlling the camera unit to capture a facial video of a target user while viewing visual materials, and determining the pupil center coordinates of the target user corresponding to the video frame;

[0007] Extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship;

[0008] Information on the target user's micro-expression data and the position of the coordinate point where the pupil center coordinates are mapped to the visual material are synchronously displayed on the display interface of the device in a time series.

[0009] Optionally, before controlling the camera unit to capture the facial video of the target user in the process of viewing the visual material, the method further includes:

[0010] When the calibration instruction is triggered, controlling the camera unit to capture a facial video of the recognized user as a calibration video;

[0011] Acquire the user's reference facial micro-expression data in the calibration video, and organize the reference facial micro-expression data into a time series result in chronological order;

[0012] When the evaluation instruction is triggered, the user currently identified by the camera unit is determined as the target user;

[0013] and / or,

[0014] When the calibration instruction is triggered, controlling the camera unit to capture a facial video of the recognized user as a calibration video;

[0015] calibrating the preset mapping relationship using the calibration video;

[0016] Acquire the user's reference facial micro-expression data in the calibration video, and organize the reference facial micro-expression data into a time series result in chronological order;

[0017] When the evaluation instruction is triggered, the user currently recognized by the camera unit is determined as the target user.

[0018] Optionally, after extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship, the method further includes:

[0019] According to the acquired coordinate points, an eye movement heat map and a sight track map based on the visual material are displayed on the display interface of the device.

[0020] Optionally, the data types of the reference facial micro-expression data and the micro-expression data respectively include at least first-type data indicating negativity and second-type data indicating pleasure; after the eye movement heat map and sight track map based on the visual material are displayed on the display interface of the device according to the acquired coordinate points, the method further includes:

[0021] Arrange the micro-expression data into time series results in chronological order; the time series results corresponding to the micro-expression data are the first time series results, and the time series results corresponding to the reference facial micro-expression data are the second time series results;

[0022] Determine the real-time impact and real-time pleasure of the target user at each time point according to the first time series result and the second time series result, and mark the corresponding positions in the two-dimensional analysis model according to the pupil center coordinates of the target user at each time point mapped to the coordinate points of the visual material and the sight track sequence number in the sight track diagram, and obtain the evaluation result based on the two-dimensional analysis model;

[0023] Synchronously displaying the eye movement heat map, the gaze trajectory map and the evaluation results on the display interface of the device;

[0024] Among them, the two elements of the two-dimensional analysis model are impact and pleasure.

[0025] Optionally, determining the real-time impact and real-time pleasure of the target user at each time point according to the first time series result and the second time series result includes:

[0026] Calculate the real-time impact force D=Y / X; wherein Y is the data value at a certain time point in the first time series result, and X is the data average value of the second time series result;

[0027] According to a preset conversion rule, the real-time impact force D is converted into a percentage system D*;

[0028] The real-time negative intensity index corresponding to the first category of data and the real-time pleasure intensity index corresponding to the second category of data are calculated, and the real-time pleasure degree is calculated according to the real-time negative intensity index and the real-time pleasure intensity index.

[0029] Optionally, the calculating a real-time negative intensity index corresponding to the first category of data and a real-time pleasure intensity index corresponding to the second category of data, and calculating a real-time pleasure degree according to the real-time negative intensity index and the real-time pleasure intensity index, includes:

[0030] Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to data type;

[0031] Calculate real-time Negative Strength Index

[0032] Among them, α iis the i-th data value in the negative first sub-time series result, i is greater than zero and less than or equal to the number of data in the negative first sub-time series, is the data average of the negative second sub-time series results;

[0033] Calculate real-time pleasure intensity index

[0034] Among them, β i is the i-th data value in the result of the first sub-time series of pleasure, i is greater than zero and less than or equal to the number of data in the first sub-time series of pleasure, is the data average of the results of the second sub-time series of pleasure;

[0035] According to the preset conversion rule, the real-time negative intensity index Q is converted into a percentage system Q*, and the real-time pleasure intensity index P is converted into a percentage system P*;

[0036] The real-time pleasure degree is calculated, where the real-time pleasure degree is a weighted sum of the real-time negative intensity index Q* and the real-time pleasure intensity index P*.

[0037] Optionally, the data types of the reference facial micro-expression data and the micro-expression data respectively include at least a first type of data indicating negativity and a second type of data indicating pleasure; after extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship, the method further comprises:

[0038] Arrange the micro-expression data into time series results in chronological order; the time series results corresponding to the micro-expression data are the first time series results, and the time series results corresponding to the reference facial micro-expression data are the second time series results;

[0039] According to the first time series result and the second time series result, the data values ​​of the two elements of the two-dimensional analysis model are calculated, and corresponding positions of the two-dimensional analysis model are marked;

[0040] Displaying the marked two-dimensional analysis model on a display interface of the device;

[0041] Among them, the two elements of the two-dimensional analysis model are impact and pleasure.

[0042] Optionally, the calculating, according to the first time series result and the second time series result, data values ​​of two elements of the two-dimensional analysis model respectively includes:

[0043] Calculating impact force

[0044] Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average value of the second time series results;

[0045] The negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data are calculated, and the pleasure degree is calculated according to the negative intensity index and the pleasure intensity index.

[0046] A second aspect of the present invention discloses an electronic device, comprising:

[0047] A memory storing executable program code;

[0048] a processor coupled to the memory;

[0049] The processor calls the executable program code stored in the memory to execute the method for evaluating visual material effects disclosed in the first aspect of the present invention.

[0050] The third aspect of the present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for evaluating the effects of visual materials disclosed in the first aspect of the present invention.

[0051] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0052] In an embodiment of the present invention, by controlling the camera unit to shoot the facial video of the target user while watching the visual material, the pupil center coordinates of the target user corresponding to the video frame can be determined; the micro-expression data of the target user is extracted from the video frame of the facial video in real time, and according to a preset mapping relationship, the pupil center coordinates of the target user corresponding to the video frame are synchronously obtained and mapped to the coordinate point of the visual material; thereby, the information of the micro-expression data of the target user and the position of the pupil center coordinates mapped to the coordinate point of the visual material are synchronously displayed on the display interface of the device in a time series. It can be seen that the implementation of the present invention can evaluate the content of the visual material in multiple dimensions and obtain multi-level visual material effect evaluation results, thereby better guiding the optimization of the overall and local content of the visual material; in addition, based on the data results of the dual-modal matching, the key focus areas of sight tracking such as the primary gaze area and the area of ​​interest can be analyzed. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 It is a flow chart of a method for evaluating visual material effects disclosed in an embodiment of the present invention;

[0055] Figure 2 It is a flow chart of another method for visual material effect evaluation disclosed in an embodiment of the present invention;

[0056] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0059] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] The method for evaluating visual material effects of various embodiments of the present invention is applied to a device equipped with a camera unit, where the camera unit is used to shoot a facial video of a target user and determine the pupil center coordinates of the target user corresponding to each video frame.

[0061] Embodiment 1

[0062] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for evaluating visual material effects disclosed in an embodiment of the present invention. Figure 1 As shown, the method may include:

[0063] Step 101: Control a camera unit to capture a facial video of a target user while viewing a visual material, and determine the pupil center coordinates of the target user corresponding to the video frame.

[0064] Step 102: extract the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously obtain the pupil center coordinates of the target user corresponding to the video frame and map them to the coordinate points of the visual material according to a preset mapping relationship.

[0065] Step 103: synchronously display the information of the micro-expression data of the target user and the position of the coordinate point of the pupil center mapped to the visual material on the display interface of the device in a time series.

[0066] In the embodiments of the present disclosure, the determination of the pupil center coordinates of the target user in the video frame and the setting of the mapping relationship between the pupil center coordinates and the coordinate points of the visual material can be achieved through existing technical means.

[0067] Optionally, before controlling the camera unit to capture the facial video of the target user while watching visual materials, the method also includes: when a calibration instruction is triggered, controlling the camera unit to capture the facial video of the identified user as a calibration video; obtaining baseline facial micro-expression data of the user in the calibration video, and arranging the baseline facial micro-expression data into a time series result in chronological order; and when an evaluation instruction is triggered, determining the user currently identified by the camera unit as the target user.

[0068] Here, the calibration instruction or the evaluation instruction is triggered, which can be understood as the user touching a preset position of the corresponding dialog box on the touch screen.

[0069] In this way, a specific method for determining the target user is given, and the facial video of the target user is obtained, and the user's baseline facial micro-expression data is obtained based on the facial video, so as to improve the accuracy of subsequent analysis results.

[0070] Optionally, before controlling the camera unit to shoot the facial video of the target user while watching the visual material, the method further includes: when the calibration instruction is triggered, controlling the camera unit to shoot the facial video of the identified user as the calibration video; using the calibration video to calibrate the preset mapping relationship; obtaining the user's baseline facial micro-expression data in the calibration video, and arranging the baseline facial micro-expression data in chronological order as a time series result; when the evaluation instruction is triggered, determining the user currently identified by the camera unit as the target user. In this way, a specific method for determining the target user is given, and the facial video of the target user obtained is used as the calibration video, and the calibration video is used to calibrate the preset mapping relationship, which can improve the accuracy of subsequent analysis results.

[0071] Optionally, after extracting the micro-expression data of the target user from the video frame of the facial video in real time and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship, the method further includes: displaying an eye movement heat map and a sight track map based on the visual material on the display interface of the device according to the acquired coordinate points. In this way, a sight track map and a heat map of the target user in time series are obtained, and multi-level visual material effect analysis can be performed through the two images.

[0072] Optionally, the data types of the baseline facial micro-expression data and the micro-expression data each include at least a first type of data indicating negativity and a second type of data indicating pleasure; extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously obtaining the pupil center coordinates of the target user corresponding to the video frame according to a preset mapping relationship, and mapping them to the coordinate points of the visual material, the method also includes: arranging the micro-expression data into time series results in chronological order; the time series results corresponding to the micro-expression data are the first time series results, and the time series results corresponding to the baseline facial micro-expression data are the second time series results; based on the first time series results and the second time series results, calculating the data values ​​of the two elements of the two-dimensional analysis model, and marking the corresponding positions of the two-dimensional analysis model; displaying the marked two-dimensional analysis model on the display interface of the device; wherein the two elements of the two-dimensional analysis model are impact and pleasure.

[0073] In the disclosed embodiment, the pleasantness among the elements of the two-dimensional analysis model represents the attractiveness of the visual material. The higher the pleasantness, the higher the liking for the visual material and the lower the repulsion. The impact among the elements of the two-dimensional analysis model represents the influence of the visual material on emotions. The stronger the impact, the stronger the visual material's mobilization of emotions.

[0074] In this way, by designing a two-dimensional analysis model with impact and pleasure as the elements, and marking the data in the two-dimensional analysis model, it is possible to accurately analyze the user's multi-faceted objective feelings about the visual material. In addition, by combining the baseline facial data for processing and calculation, the differences in the individual baseline states of the evaluators can be effectively eliminated.

[0075] Optionally, calculating the data values ​​of two elements of the two-dimensional analysis model according to the first time series result and the second time series result includes:

[0076] Calculating impact force

[0077] Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average of the second time series results;

[0078] The negative intensity index corresponding to the first type of data and the pleasure intensity index corresponding to the second type of data are calculated, and the pleasure degree is calculated based on the negative intensity index and the pleasure intensity index.

[0079] In this way, a specific method for calculating the data values ​​of the two elements of the two-dimensional analysis model based on the first time series results and the second time series results is given.

[0080] Optionally, a negative intensity index corresponding to the first type of data and a pleasure intensity index corresponding to the second type of data are calculated, and the pleasure degree is calculated according to the negative intensity index and the pleasure intensity index, including:

[0081] Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to the data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to the data type;

[0082] Calculating Negative Strength Index

[0083] Where e is the total number of data values ​​in the negative first sub-time series results, α i is the i-th data value in the negative first sub-time series result, is the data average of the negative second sub-time series results;

[0084] Calculating the Pleasure Intensity Index

[0085] Among them, r is the total number of data values ​​in the first sub-time series results of pleasure, β i To obtain the i-th data value in the first sub-time series result, The data average of the results of the second sub-time series of pleasure;

[0086] According to the preset conversion rules, the negative intensity index Q is converted into the percentage system Q*, and the pleasure intensity index P is converted into the percentage system P*;

[0087] Calculate the real-time pleasure, which is the weighted sum of the real-time negative intensity index Q* and the real-time pleasure intensity index P*.

[0088] Preferably, the weight corresponding to the real-time negative intensity index is 0.75, and the weight corresponding to the real-time pleasure intensity index is 0.25.

[0089] Optionally, the weight corresponding to the real-time negative intensity index is 0.5, and the weight corresponding to the real-time pleasant intensity index is 0.5.

[0090] Optionally, the weight corresponding to the real-time negative intensity index is 0.25, and the weight corresponding to the real-time pleasant intensity index is 0.75.

[0091] The preferred and optional weight distribution methods provided by the present invention are only examples. The weight values ​​of the real-time negative intensity index and the real-time pleasure intensity index can be selected according to the actual needs of the tested product, and the present invention does not make specific limitations here.

[0092] Optionally, the preset conversion rule can be:

[0093] If P is less than or equal to 0.05, P* is 0 points;

[0094] If P is greater than 0.05 and less than or equal to 0.5, P* is converted between 0 and 70 points;

[0095] If P is greater than 0.5 and less than or equal to 2, P* is converted between 70-99 points;

[0096] If P is greater than 2, then P* is 100 points;

[0097] If Q is less than or equal to 0.4, P* is 100 points;

[0098] If P is greater than 0.4 and less than or equal to 1, P* is converted between 100-60 points;

[0099] If P is greater than 1 and less than or equal to 2.5, P* is converted between 60 and 0 points;

[0100] If P is greater than 2.5, P* is 0 points.

[0101] In this way, the pleasure intensity index and negative intensity index converted into percentage are obtained, and then the pleasure degree is calculated, which is convenient for subsequent analysis in the model.

[0102] Optionally, mark the corresponding positions of the 2D analysis model, including:

[0103] According to the preset conversion rules, the impact force Z is converted into the percentage system Z*;

[0104] When the impact force Z* is greater than or equal to the first threshold and the pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "very attractive" in the two-dimensional analysis model;

[0105] When the impact force Z* is greater than or equal to the second threshold and less than the first threshold, and the pleasure W is greater than or equal to the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "liking the product" in the two-dimensional analysis model;

[0106] When the impact force Z* is greater than or equal to the first threshold value and the pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "interest in the product" in the two-dimensional analysis model;

[0107] When the impact force Z* is greater than or equal to the second threshold and less than the first threshold, and the pleasure W is greater than or equal to the second threshold and less than the first threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "feeling the product is ordinary" in the two-dimensional analysis model;

[0108] When the impact force Z* is less than the second threshold value and the pleasure W is greater than or equal to the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity and satisfaction with the product" in the two-dimensional analysis model;

[0109] When the impact force Z* is less than the second threshold value and the pleasure W is greater than or equal to the second threshold value and less than the first threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "familiarity with the product" in the two-dimensional analysis model;

[0110] When the impact force Z* is less than the second threshold value and the pleasure W is less than the second threshold value, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "no feeling towards the product" in the two-dimensional analysis model;

[0111] When the impact force Z* is greater than or equal to the second threshold and less than the first threshold, and the pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "dislike for the product" in the two-dimensional analysis model;

[0112] When the impact force Z* is greater than or equal to the first threshold and the pleasure W is less than the second threshold, the coordinate points corresponding to the two elements of the two-dimensional analysis model are displayed in the area representing "strong product stimulation" in the two-dimensional analysis model;

[0113] Here, the first threshold is greater than the second threshold.

[0114] Optionally, according to a preset conversion rule, the specific method of converting the impact force Z into the percentage system Z* may be:

[0115] If Z is less than or equal to 0.1, Z* is 0 points;

[0116] If Z is greater than 0.1 and less than or equal to 0.6, Z* is converted between 0-30 points;

[0117] If Z is greater than 0.6 and less than or equal to 1, Z* is converted between 30 and 70 points;

[0118] If Z is greater than 1 and less than or equal to 2.5, Z* is converted between 70-99 points;

[0119] If Z is greater than 2.5, Z* is 100 points.

[0120] Optionally, the first threshold is 67.

[0121] Optionally, the second threshold is 34.

[0122] By adopting the method for evaluating the effect of visual materials provided by the embodiment of the present disclosure, by controlling the camera unit to shoot the facial video of the target user in the process of watching the visual material, the pupil center coordinates of the target user corresponding to the video frame can be determined; the micro-expression data of the target user is extracted from the video frame of the facial video in real time, and according to the preset mapping relationship, the pupil center coordinates of the target user corresponding to the video frame are synchronously obtained and mapped to the coordinate point of the visual material; thereby, the information of the micro-expression data of the target user and the position of the pupil center coordinates mapped to the coordinate point of the visual material are synchronously displayed on the display interface of the device in a time series. It can be seen that the implementation of the present invention can evaluate the content of visual materials in multiple dimensions and obtain multi-level visual material effect evaluation results, thereby better guiding the optimization of the overall and local content of the visual material.

[0123] Embodiment 2

[0124] See also Figure 2 , Figure 2 is a flow chart of another method for evaluating the effect of visual materials disclosed in an embodiment of the present invention. In this embodiment, the data types of the reference facial micro-expression data and the micro-expression data include at least the first type of data indicating negativity and the second type of data indicating pleasure. Figure 2As shown, the method may include:

[0125] Step 201: When a calibration instruction is triggered, control the camera unit to capture a facial video of the recognized user as a calibration video.

[0126] Step 202: Calibrate the preset mapping relationship using the calibration video.

[0127] Step 203: Obtain the user's baseline facial micro-expression data in the calibration video, and sort the baseline facial micro-expression data into a time series result in chronological order.

[0128] Step 204: When the evaluation instruction is triggered, the user currently recognized by the camera unit is determined as the target user.

[0129] Step 205: Control the camera unit to capture the facial video of the target user while viewing the visual material, and determine the pupil center coordinates of the target user corresponding to the video frame.

[0130] Step 206: extract the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously obtain the pupil center coordinates of the target user corresponding to the video frame and map them to the coordinate points of the visual material according to a preset mapping relationship.

[0131] Step 207: The micro-expression data of the target user and the coordinate point of the pupil center mapped to the visual material are synchronously displayed on the display interface of the device in a time series.

[0132] Step 208: Display an eye movement heat map and a sight track map based on the visual material on the display interface of the device according to the acquired coordinate points.

[0133] Step 209: Arrange the micro-expression data into time series results according to time sequence.

[0134] In this embodiment, the time series result corresponding to the micro-expression data is the first time series result, and the time series result corresponding to the reference facial micro-expression data is the second time series result.

[0135] Step 210: determine the real-time impact and real-time pleasure of the target user at each time point based on the first time series results and the second time series results, and map the pupil center coordinates of the target user at each time point to the coordinate points of the visual material and the sight trajectory sequence number in the sight trajectory diagram, mark the corresponding positions in the two-dimensional analysis model, and obtain the evaluation results based on the two-dimensional analysis model.

[0136] Step 211: synchronously display the eye movement heat map, the gaze trajectory map and the evaluation results on the display interface of the device.

[0137] In the disclosed embodiment, the two elements of the two-dimensional analysis model are impact and pleasure.

[0138] Optionally, the real-time impact and real-time pleasure of the target user at each time point are determined based on the first time series results and the second time series results, including: calculating the real-time impact D=Y / X; wherein Y is the data value at a certain time point in the first time series results, and X is the data average of the second time series results; converting the real-time impact D into a percentage D* according to a preset conversion rule; calculating the real-time negative intensity index corresponding to the first category of data and the real-time pleasure intensity index corresponding to the second category of data, and calculating the real-time pleasure based on the real-time negative intensity index and the real-time pleasure intensity index.

[0139] Optionally, a real-time negative intensity index corresponding to the first type of data and a real-time pleasure intensity index corresponding to the second type of data are calculated, and a real-time pleasure degree is calculated based on the real-time negative intensity index and the real-time pleasure intensity index, including: arranging the first time series results into a negative first sub-time series and a pleasure first sub-time series according to the data type, and arranging the second time series results into a negative second sub-time series and a pleasure second sub-time series according to the data type; calculating the real-time negative intensity index Among them, α i is the i-th data value in the negative first sub-time series result, i is greater than zero and less than or equal to the data value of the negative first sub-time series, The data average of the negative second sub-time series results; calculate the real-time pleasure intensity index Among them, β i is the i-th data value in the result of the first sub-time series of pleasure, i is greater than zero and less than or equal to the data value of the first sub-time series of pleasure, is the data average of the results of the second sub-time series of pleasure; according to the preset conversion rules, the real-time negative intensity index Q is converted into the percentage Q*, and the real-time pleasure intensity index P is converted into the percentage P*; the real-time pleasure degree W is calculated as (3×Q*+P*) / 4. In this way, a specific method for calculating the real-time pleasure degree is given.

[0140] It can be seen that the implementation of the disclosed embodiment can evaluate the content of visual materials in multiple dimensions and obtain multi-level visual material effect evaluation results, thereby better guiding the optimization of the overall and local content of visual materials. In addition, based on the data results of bimodal matching, the key focus areas of sight tracking such as the user's primary gaze area and the area of ​​interest can be analyzed, which is conducive to clarifying the optimization direction of visual materials.

[0141] Embodiment 3

[0142] See also Figure 3 , Figure 3Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Figure 3 As shown, the electronic device may include:

[0143] A memory 301 storing executable program codes;

[0144] a processor 302 coupled to the memory 301;

[0145] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the method for visual material effect evaluation described in the above embodiment of the present invention.

[0146] Embodiment 4

[0147] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for evaluating the effect of visual materials described in the above embodiments.

[0148] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0149] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0150] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0151] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0152] Finally, it should be noted that the method for evaluating the effects of visual materials, the electronic device, and the storage medium disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the effect of visual materials, characterized in that: Applied to a device equipped with a camera unit, the camera unit is used to shoot a facial video of the target user and determine the pupil center coordinates of the target user corresponding to each video frame; the method comprises: Controlling the camera unit to capture a facial video of a target user while viewing visual materials, and determining the pupil center coordinates of the target user corresponding to the video frame; Extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship; Information on the target user's micro-expression data and the position of the coordinate point where the pupil center coordinates are mapped to the visual material are synchronously displayed on the display interface of the device in a time series.

2. The method according to claim 1, characterized in that Before controlling the camera unit to capture the facial video of the target user while viewing the visual material, the method further includes: When the calibration instruction is triggered, controlling the camera unit to capture a facial video of the recognized user as a calibration video; Acquire the user's reference facial micro-expression data in the calibration video, and organize the reference facial micro-expression data into a time series result in chronological order; When the evaluation instruction is triggered, the user currently identified by the camera unit is determined as the target user; and / or, When the calibration instruction is triggered, controlling the camera unit to capture a facial video of the recognized user as a calibration video; calibrating the preset mapping relationship using the calibration video; Acquire the user's reference facial micro-expression data in the calibration video, and organize the reference facial micro-expression data into a time series result in chronological order; When the evaluation instruction is triggered, the user currently recognized by the camera unit is determined as the target user.

3. The method according to claim 2, characterized in that After extracting the micro-expression data of the target user from the video frame of the facial video in real time, and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship, the method further comprises: According to the acquired coordinate points, an eye movement heat map and a sight track map based on the visual material are displayed on the display interface of the device.

4. The method according to claim 3, characterized in that The data types of the reference facial micro-expression data and the micro-expression data respectively include at least first-type data indicating negativity and second-type data indicating pleasure; after the eye movement heat map and sight track map based on the visual material are displayed on the display interface of the device according to the acquired coordinate points, the method further includes: Arrange the micro-expression data into time series results in chronological order; the time series results corresponding to the micro-expression data are the first time series results, and the time series results corresponding to the reference facial micro-expression data are the second time series results; Determine the real-time impact and real-time pleasure of the target user at each time point according to the first time series result and the second time series result, and mark the corresponding positions in the two-dimensional analysis model according to the pupil center coordinates of the target user at each time point mapped to the coordinate points of the visual material and the sight track sequence number in the sight track diagram, and obtain the evaluation result based on the two-dimensional analysis model; Synchronously displaying the eye movement heat map, the gaze trajectory map and the evaluation results on the display interface of the device; Among them, the two elements of the two-dimensional analysis model are impact and pleasure.

5. The method according to claim 4, characterized in that Determining the real-time impact and real-time pleasure of the target user at each time point according to the first time series result and the second time series result includes: Calculate the real-time impact force D=Y / X; wherein Y is the data value at a certain time point in the first time series result, and X is the data average value of the second time series result; According to a preset conversion rule, the real-time impact force D is converted into a percentage system D*; The real-time negative intensity index corresponding to the first category of data and the real-time pleasure intensity index corresponding to the second category of data are calculated, and the real-time pleasure degree is calculated according to the real-time negative intensity index and the real-time pleasure intensity index.

6. The method according to claim 5, characterized in that The calculating the real-time negative intensity index corresponding to the first type of data and the real-time pleasure intensity index corresponding to the second type of data, and calculating the real-time pleasure degree according to the real-time negative intensity index and the real-time pleasure intensity index, comprises: Arrange the first time series results into a negative first sub-time series and a pleasant first sub-time series according to data type, and arrange the second time series results into a negative second sub-time series and a pleasant second sub-time series according to data type; Calculate real-time Negative Strength Index Among them, α i is the i-th data value in the negative first sub-time series result, i is greater than zero and less than or equal to the number of data in the negative first sub-time series, is the data average of the negative second sub-time series results; Calculate real-time pleasure intensity index Among them, β i is the i-th data value in the result of the first sub-time series of pleasure, i is greater than zero and less than or equal to the number of data in the first sub-time series of pleasure, is the data average of the results of the second sub-time series of pleasure; According to the preset conversion rule, the real-time negative intensity index Q is converted into a percentage system Q*, and the real-time pleasure intensity index P is converted into a percentage system P*; The real-time pleasure degree is calculated, where the real-time pleasure degree is a weighted sum of the real-time negative intensity index Q* and the real-time pleasure intensity index P*.

7. The method according to claim 2, characterized in that: The data types of the reference facial micro-expression data and the micro-expression data include at least first-type data indicating negativity and second-type data indicating pleasure; after extracting the micro-expression data of the target user from the video frame of the facial video in real time and synchronously acquiring the pupil center coordinates of the target user corresponding to the video frame and mapping them to the coordinate points of the visual material according to a preset mapping relationship, the method further includes: Arrange the micro-expression data into time series results in chronological order; the time series results corresponding to the micro-expression data are the first time series results, and the time series results corresponding to the reference facial micro-expression data are the second time series results; According to the first time series result and the second time series result, the data values ​​of the two elements of the two-dimensional analysis model are calculated, and corresponding positions of the two-dimensional analysis model are marked; Displaying the marked two-dimensional analysis model on a display interface of the device; Among them, the two elements of the two-dimensional analysis model are impact and pleasure.

8. The method according to claim 7, characterized in that The step of calculating the data values ​​of two elements of the two-dimensional analysis model according to the first time series result and the second time series result includes: Calculating impact force Where t is the total number of data values ​​in the first time series result, x i is the i-th data value in the first time series result, is the data average value of the second time series results; The negative impact force corresponding to the first type of data and the pleasant impact force corresponding to the second type of data are calculated, and the pleasantness is calculated according to the negative intensity index and the pleasant intensity index.

9. An electronic device, characterized in that: The electronic device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for evaluating visual material effects as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the method for evaluating the effect of visual materials as described in any one of claims 1-8.

Images