Advertisement evaluation system control method and device, and storage medium

Abstract

The invention discloses a control method and device of an advertisement evaluation system and a storage medium, and belongs to the technical field of advertisement evaluation. The method comprises the steps of obtaining a neural physiological signal when a user receives media content, extracting a target rhythm signal from the neural physiological signal, calculating a difference parameter of the target rhythm signal in a preset brain region, and identifying an emotional state type of the user according to the difference parameter through an emotional analysis model, and aligning the emotional state type with the timestamp of the media content to generate an emotional state curve, and determining the playing effect of the media content according to the emotional state curve. According to the method, the time and degree of generating the specific emotion by the user are analyzed according to the neurophysiological signals when the user watches the media content, so that the playing effect of the media content is determined.

Description

Technical Field

[0001] This application relates to the field of advertising evaluation technology, and in particular to a control method, device and storage medium for an advertising evaluation system. Background Technology

[0002] Accurate evaluation of advertising effectiveness is crucial for optimizing marketing strategies and improving ROI. Among related technologies, advertising evaluation methods rely on user self-reporting, such as questionnaires and focus group interviews, or external behavioral data, such as click-through rates and viewing duration. These methods typically infer the emotional appeal and cognitive effect of advertising by collecting users' subjective feedback after viewing the ad or by statistically analyzing their interactive behavior.

[0003] However, user opinions collected through methods such as questionnaires are easily influenced by factors such as memory bias and social expectations, while behavioral data is mostly statistically derived after the fact, making it difficult to accurately correlate with specific elements of the advertisement, such as a particular scene or line of text. Therefore, evaluations of advertising effectiveness based on this information are unlikely to accurately reflect the key elements that resonate with users.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a control method, device and storage medium for an advertising evaluation system, which aims to solve the technical problem that the evaluation of the effect of advertising playback is difficult to accurately reflect the key elements of the advertisement that move users.

[0006] To achieve the above objectives, this application provides a control method for an advertising evaluation system, the method comprising the following steps: Acquire the neurophysiological signals of the user when receiving media content, and extract the target rhythm signal from the neurophysiological signals; Calculate the differential parameters of the target rhythm signal between preset brain regions; The emotional state type of the user is identified based on the difference parameters using a sentiment analysis model. Align the emotional state type with the timestamp of the media content to generate an emotional state curve; The playback effect of the media content is determined based on the emotional state curve.

[0007] In one embodiment, after the step of determining the playback effect of the media content based on the emotional state curve, the method further includes: Based on the curve characteristics of the emotional state curve, identify the target time period in the media content where the rate of change of the curve characteristics is greater than the rate of change threshold; The media content is correlated with media elements within the target time period to determine the target media elements.

[0008] In one embodiment, the step of determining the playback effect of the media content based on the emotional state curve includes: Acquire the user's target physiological signals, which include eye-tracking signals and / or skin conductance response signals; Based on the time dimension, align the target physiological signals with the emotional state curve; Based on the alignment results, the emotional state type and the target physiological signal are fused and analyzed to generate a comprehensive evaluation report on the media content.

[0009] In one embodiment, the step of determining the playback effect of the media content based on the emotional state curve includes: Based on the emotional state curve, the visual elements in the media content are associated and labeled. Based on the associated annotation results, the playback effect of the media content is determined.

[0010] In one embodiment, the step of determining the playback effect of the media content based on the emotional state curve further includes: The attention rhythm signal is extracted from the neurophysiological signal, and the attention concentration of the attention rhythm signal is calculated. Align the attention concentration parameter with the timestamp of the media content to generate an attention concentration curve; Based on the emotional state curve and the attention concentration curve, identify the collaborative time interval in the media content where the emotional state type is positive and the attention concentration exceeds a preset threshold. The playback effect of the media content is determined based on the coordinated time interval, the emotional state curve, and the attention concentration curve.

[0011] In one embodiment, the step of calculating the differential parameters of the target rhythm signal between preset brain regions includes: Calculate the first average power of the target rhythm signal in the first preset brain region within a preset time window, and the second average power of the target rhythm signal in the second preset brain region within the preset time window; The difference parameter is determined based on the difference between the first average power and the second average power.

[0012] In one embodiment, prior to the step of identifying the user's emotional state type based on the difference parameters using a sentiment analysis model, the method further includes: Acquire historical neurophysiological signal data and the corresponding emotional state labels for the historical neurophysiological signal data; Extract at least one dimension of neural features from the historical neurophysiological signal data, the neural features including the differential parameters; The machine learning model is trained based on the neural features and the emotional state annotations. If the machine learning model is determined to have converged according to the preset convergence criteria, the trained machine learning model is selected as the sentiment analysis model.

[0013] In one embodiment, the step of determining the playback effect of the media content based on the emotional state curve further includes: Extract memory EEG signals from the neurophysiological signals; Align the memory EEG signal with the timestamp of the media content to generate a memory coding strength curve; Identify the feature information of the memory coding intensity curve, and identify the memory coding identifier based on the feature information; The playback effect is determined based on the memory encoding identifier and the emotional state curve.

[0014] In addition, to achieve the above objectives, this application also provides a control device for an advertising evaluation system, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the control method for the advertising evaluation system as described above.

[0015] In addition, to achieve the above objectives, this application also provides a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the control method of the advertising evaluation system as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: This application acquires the neurophysiological signals of users when receiving media content, extracts the target rhythm signals, calculates the difference parameters of the target rhythm signals between preset brain regions, identifies the user's emotional state type based on the difference parameters, and generates an emotional state curve by precisely aligning the identified emotional state type with the timestamp of the media content. This achieves a millisecond-level correlation between the user's internal emotional response and the external content elements of the advertisement, enabling analysts to accurately locate the specific advertising moment that triggers specific emotional fluctuations. This achieves the technical effect of objectively displaying specific segments of the advertising content that resonate with or resist the user's true emotions, providing accurate decision-making basis for the precise diagnosis and optimization of advertising content. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the control method for the advertising evaluation system of this application; Figure 2 This is a flowchart illustrating the second embodiment of the control method for the advertising evaluation system of this application; Figure 3 This is a flowchart illustrating the third embodiment of the control method for the advertising evaluation system of this application; Figure 4 This is a flowchart illustrating the fourth embodiment of the control method for the advertising evaluation system of this application; Figure 5 This is a flowchart illustrating the fifth embodiment of the control method for the advertising evaluation system of this application; Figure 6 This is a schematic diagram of the structure of the control device of the advertising evaluation system in the hardware operating environment involved in the embodiments of this application.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0022] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0023] The main solution of this application embodiment is: to obtain the neurophysiological signals of the user when receiving media content, extract the target rhythm signal from the neurophysiological signals, calculate the difference parameters of the target rhythm signal between preset brain regions, identify the user's emotional state type according to the difference parameters through an emotion analysis model, align the emotional state type with the timestamp of the media content, generate an emotional state curve, and determine the playback effect of the media content based on the emotional state curve.

[0024] Current advertising evaluation methods rely on user self-reporting, such as questionnaires and focus group interviews, or external behavioral data, such as click-through rates and viewing duration. They typically infer the emotional appeal and cognitive effect of an ad indirectly by collecting subjective feedback from users after viewing it or by statistically analyzing their interactions. However, user opinions collected through methods like questionnaires are susceptible to memory bias and social expectations, while behavioral data is mostly post-hoc and difficult to precisely correlate with specific elements within the ad, such as a particular scene or line of text. Therefore, evaluations of ad performance based on this information often fail to accurately reflect the key elements that resonate with users.

[0025] This application acquires the neurophysiological signals of users when receiving media content, extracts the target rhythm signals, calculates the difference parameters of the target rhythm signals between preset brain regions, identifies the user's emotional state type based on the difference parameters, and generates an emotional state curve by precisely aligning the identified emotional state type with the timestamp of the media content. This achieves a millisecond-level correlation between the user's internal emotional response and the external content elements of the advertisement, enabling analysts to accurately locate the specific advertising moment that triggers specific emotional fluctuations. This achieves the technical effect of objectively displaying specific segments of the advertising content that resonate with or resist the user's true emotions, providing accurate decision-making basis for the precise diagnosis and optimization of advertising content.

[0026] To better understand the above technical solutions, exemplary embodiments of this application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0027] It should be noted that the executing entity in this embodiment can be an advertising evaluation system, or a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or control device of an advertising evaluation system capable of the above functions. This embodiment does not specifically limit the specific implementation. The following uses an advertising evaluation system as an example to describe this embodiment and the following embodiments.

[0028] Based on this, embodiments of this application provide a control method for an advertising evaluation system, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the control method for the advertising evaluation system of this application.

[0029] In this embodiment, the control method of the advertising evaluation system includes steps S10 to S50: Step S10: Obtain the neurophysiological signals of the user when receiving media content, and extract the target rhythm signal from the neurophysiological signals; In this embodiment, neural signals are electrical signals that transmit information within a living organism. Their conduction is a complex mechanism combining changes in electrical potential along nerve fibers with the transmission of chemical mediators. When a user views an advertisement, the advertising evaluation system collects their electroencephalogram (EEG) signals using specialized equipment. These signals are then cleaned and decomposed to filter out specific frequency EEG oscillation components. Based on the media content, the system searches for the desired advertising evaluation task and selects specific components from the neurophysiological signals as target rhythm signals.

[0030] Optionally, the target rhythm signal extracts only the alpha band signal from the prefrontal cortex. The advertising evaluation system selects specific electrodes in the left and right prefrontal lobes and calculates the signal power within the 8-13 Hz frequency range, thereby focusing on the neural indicators most directly related to emotional valence assessment and improving computational efficiency and accuracy. Alternatively, the target rhythm signal can simultaneously extract signals such as the alpha rhythm from the prefrontal cortex and the theta rhythm from the central region as rhythm signals. The advertising evaluation system processes multiple rhythm signals from different brain regions in parallel, acquiring basic emotional signals while providing data scalability for subsequent potential attention or cognitive load analysis.

[0031] Step S20: Calculate the differential parameters of the target rhythm signal between preset brain regions; Step S30: Identify the user's emotional state type based on the difference parameters using the sentiment analysis model; In this embodiment, based on the asymmetrical activation of the left and right hemispheres of the brain, the increased activation of the left prefrontal cortex is associated with positive and approaching emotions, such as happiness, excitement, and desire, while the increased activation of the right prefrontal cortex is associated with negative and avoidant emotions, such as disgust, fear, and disappointment. The advertising evaluation system can analyze the user's emotional state by measuring the imbalance of specific neural activities in the left and right hemispheres based on the difference parameters between different brain regions.

[0032] Specifically, the advertising evaluation system calculates the first average power of the target rhythm signal in a first preset brain region within a preset time window, and the second average power of the target rhythm signal in a second preset brain region within the preset time window. Based on the difference between the first and second average powers, a difference parameter is determined. The first and second preset brain regions are the left and right hemispheres, respectively.

[0033] In one implementation, since alpha waves are stronger in a relaxed state and are suppressed (i.e., their power decreases) when brain regions are active, the advertising evaluation system determines the difference parameters of the target rhythm signal in different brain regions by calculating the asymmetry of prefrontal alpha waves. If the alpha power in the right prefrontal cortex is greater than that in the left prefrontal cortex, the advertising evaluation system can determine that the left brain region is more active and infer that the subject is in a positive emotional state. Conversely, it infers a negative emotional state.

[0034] Optionally, the difference parameter is calculated using the logarithmic power difference formula. The system calculates the difference between the natural logarithm of the right-side average power and the natural logarithm of the left-side average power, thereby effectively reducing the influence of individual differences and power distribution skewness. The difference parameter can also be directly calculated as the ratio of the average power of the left and right brain regions. The difference parameter is determined by dividing the right-side power value by the left-side power value.

[0035] For example, the system first determines the electrode sets representing the left and right prefrontal lobes based on the electrode location profile. For each analysis time window, the average power of all target rhythm signals from the electrodes in the left and right brain regions is calculated. The two average power values ​​are then substituted into a preset formula to calculate and output the difference parameters.

[0036] Furthermore, the advertising evaluation system inputs the time series of differential parameters into a pre-trained computational model. The model infers based on its internally learned patterns and outputs a judgment of the user's emotional state at each moment. This sentiment analysis model is a machine learning model that can map neural features to emotional state categories such as positive or negative.

[0037] Optionally, the sentiment analysis model employs a support vector machine. The advertising evaluation system extracts three features for each analysis window: the current dissimilarity parameter, the previous window parameter, and the magnitude of their change, forming a feature vector that is input into the sentiment analysis model. This sentiment analysis model, based on kernel function calculations, generates a user's positivity index and / or negativity index, and determines a "positive" or "negative" category label.

[0038] Optionally, the sentiment analysis model employs a one-dimensional convolutional neural network, receiving a long sequence of raw, differentially expressed parameters as input. The convolutional layers automatically extract local temporal patterns, and these patterns are then comprehensively analyzed by the network layers to output a probability distribution of sentiment categories, thus yielding the corresponding sentiment index parameters.

[0039] Step S40: Align the emotional state type with the timestamp of the media content to generate an emotional state curve; In this embodiment, the advertising evaluation system establishes a precise correspondence between the neural signal timeline and the advertising playback timeline. It transforms the output emotion recognition results into an advertising time coordinate system and organizes all data points chronologically to form a trajectory depicting the changes in emotion as the advertising content changes—that is, an emotion state curve. Here, the timestamp marks the temporal information of each moment in the advertising content. The emotion state curve is a graphical or sequential representation with the advertising playback time as the horizontal axis and the emotion state as the vertical axis.

[0040] Step S50: Determine the playback effect of the media content based on the emotional state curve.

[0041] In this embodiment, the advertising evaluation system performs quantitative analysis on the emotional state curve, extracts key evaluation indicators, and integrates the evaluation indicators according to the preset evaluation logic to draw a conclusion on the effectiveness of the advertisement in evoking positive emotions, i.e., the playback effect.

[0042] As an optional implementation method, the advertising evaluation system uses emotional state curves to associate and annotate the points on the screen in the media content, and determines the playback effect of the media content based on the association and annotation results.

[0043] Optionally, based on the curve characteristics of the emotional state curve, the target time period in the media content where the rate of change of the curve characteristics is greater than the rate of change threshold is identified, and the media elements in the media content during the target time period are analyzed for correlation to determine the target media elements.

[0044] Specifically, the advertising evaluation system can identify key locations where users' emotional states change significantly by analyzing the characteristics of an emotional state curve aligned with the media content on a timeline. This allows the system to determine the key media elements corresponding to these locations, i.e., the target media elements. By combining the target media elements and / or the emotional states corresponding to the emotional state curve at these key locations, the system can analyze the playback effect of the media content.

[0045] For example, the advertising evaluation system also includes an emotion module. This emotion module can present participants with multiple advertising creative concepts, such as text descriptions or simple animations, during the script or storyboard stage, to measure the motivational arousal and positive emotional intensity evoked by different concepts. The goal is to select the advertising creative concept that most effectively stimulates consumer interest and desire, rather than relying on participants' "opinions" on which advertising creative concept is better during group interviews, thereby maximizing high returns at low cost.

[0046] Furthermore, the advertising evaluation system can also provide the playback effect obtained from the media content evaluation, and / or the generated comprehensive evaluation report, to managers or advertising designers, so that they can optimize or design the media content based on the playback effect and / or the comprehensive evaluation report.

[0047] Optionally, the advertising evaluation system can adjust the playback order of media elements or generate advertising design suggestions based on the playback effect and / or the effect of different media elements on playback in the comprehensive evaluation report. For example, the advertising evaluation system uses the quantitative score of playback effect and the diagnostic details in the comprehensive evaluation report as input to execute structured optimization logic. If the report indicates that the first half of the advertisement is emotionally flat while the second half shows a strong synergistic range, the system suggests moving the high-value segments in the second half to a more prominent position to quickly capture the viewer's attention. If the report identifies a specific visual element that is simultaneously associated with positive emotional peaks, high attention concentration, and strong memory encoding, the system will generate design suggestions, such as "increasing the screen area of ​​this element" or "extending its display time." Conversely, for media elements that trigger negative emotions or loss of attention, the system suggests their removal, replacement, or adjustment in presentation.

[0048] This application embodiment acquires the neurophysiological signals of users when receiving media content, extracts the target rhythm signals, calculates the difference parameters of the target rhythm signals between preset brain regions, identifies the user's emotional state type based on the difference parameters, and generates an emotional state curve by accurately aligning the identified emotional state type with the timestamp of the media content. This achieves millisecond-level correlation between the user's internal emotional response and the external content elements of the advertisement, enabling analysts to accurately locate the specific advertising moment that triggers specific emotional fluctuations. This achieves the technical effect of objectively displaying specific segments of the advertising content that resonate with or conflict with the user's real emotions, providing accurate decision-making basis for the precise diagnosis and optimization of advertising content.

[0049] Based on the same inventive concept, this application also provides a second embodiment, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the control method for the advertising evaluation system of this application.

[0050] In this embodiment, after determining the playback effect of the media content based on the emotional state curve as described in step S50, steps S51 to S53 are further included: Step S51: Acquire the user's target physiological signals, including eye-tracking signals and / or skin conductance response signals; Step S52: Align the target physiological signals with the emotional state curves based on the time dimension; Step S53: Based on the alignment results, perform a fusion analysis of emotional state types and target physiological signals to generate a comprehensive evaluation report on the media content.

[0051] In this embodiment, the advertising evaluation system, while identifying emotional states based on electroencephalogram (EEG) signals, can also incorporate users' physiological signals, such as eye-tracking signals and / or conductance of skin signals, as target neural signals. Through time alignment and fusion analysis techniques, a comprehensive evaluation report on the emotional impact of media content is generated. The target physiological signals are physiological measurement data reflecting users' overt behavior and autonomic nervous system responses, in addition to neurophysiological signals. For example, eye-tracking signals record the user's visual attention allocation, and conductance of skin signals reflect the user's physiological arousal level.

[0052] In one implementation, the advertising evaluation system also includes a motivational arousal module. Motivational arousal reflects the user's level of engagement and emotional involvement with the advertising message, and is related to the activation of the brain's reward system and emotional centers. For example, in alpha waves, prefrontal alpha asymmetry is associated with emotional motivation, including approach and avoidance. While electrodermal activity (EDA) is not entirely equivalent to electroencephalography (EEG), it is often measured synchronously with EEG. Increased EDA activity is a direct indicator of physiological arousal and can reflect a user's excitement or tension.

[0053] Specifically, by using source localization algorithms, the association between the advertising evaluation system and the limbic system can infer the activity of deep brain regions closely related to motivation and emotion, such as the amygdala and ventral striatum. Activation in these areas suggests that the advertising content has a strong emotional driving force and may prompt users to make purchases.

[0054] For example, the advertising evaluation system simultaneously activates eye trackers and electrodermal sensors to collect data on eye movement trajectories, fixation point positions, pupil diameter changes, and skin surface conductivity changes while the user views the advertisement. The system synchronously acquires these two signals with EEG signals and achieves precise alignment of multi-source data through a unified timestamp. The system performs multimodal fusion analysis, such as identifying co-occurring time segments where the emotional state is positive, visual fixation is stable on the core element of the advertisement, and electrodermal response is significantly elevated. By analyzing the consistency and inconsistencies of multimodal indicators, the system evaluates the overall performance of the advertising content in terms of emotional arousal, attention attraction, and physiological engagement.

[0055] This application's embodiments overcome the limitations of interpreting single EEG signals by integrating multi-dimensional data on emotion, visual attention, and physiological arousal, achieving a comprehensive and multi-dimensional evaluation of the emotional effectiveness of advertising. Cross-validation of multimodal data enhances the reliability and robustness of the evaluation conclusions, and the generated comprehensive report more accurately reveals the overall performance of advertising content in terms of emotional communication, attention retention, and physiological arousal, providing richer decision-making basis for advertising optimization.

[0056] Since the system described in Embodiment 2 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0057] Based on the same inventive concept, this application also provides a third embodiment, referring to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the control method for the advertising evaluation system of this application.

[0058] In this embodiment, the control method of the advertising evaluation system further includes steps S61-S64: Step S61: Extract attention rhythm signals from neurophysiological signals and calculate the attention concentration of attention rhythm signals; Step S62: Align the attention concentration parameter with the timestamp of the media content to generate an attention concentration curve; Step S63: Based on the emotional state curve and attention concentration curve, identify the collaborative time interval in the media content where the emotional state type is positive and the attention concentration exceeds the preset threshold; Step S64: Determine the playback effect of media content based on the collaborative time interval, emotional state curve, and attention concentration curve.

[0059] In this embodiment, the advertising evaluation system, based on emotion assessment, extracts rhythmic signals reflecting attentional states in parallel from the same neurophysiological signals, calculates attention concentration parameters, generates attention concentration curves, and comprehensively determines the advertising playback effect by identifying the synergistic time intervals between positive emotions and focused attention. Here, the attention rhythmic signal is a specific EEG frequency band signal related to cognitive input and mental concentration, such as Theta waves and Beta waves, while attention concentration is a parameter that quantifies the degree of user attention input.

[0060] Specifically, when processing EEG signals, the advertising evaluation system simultaneously extracts the power changes of theta waves in the prefrontal cortex and beta waves in the parietal / occipital cortex, and transforms these rhythmic activities into a numerical sequence of attention concentration using a specific algorithm. Utilizing the same time synchronization mechanism as the emotional state curve, the system maps the attention concentration sequence onto the advertising timeline, generating an attention concentration curve. The system simultaneously scans the two curves on the timeline, identifying the coordinating time intervals where the emotional state is positive and the attention concentration exceeds a preset threshold. The final playback effect judgment not only considers the overall proportion of positive emotions but also uses these coordinating intervals as the core basis, calculating their total duration and intensity to form a comprehensive evaluation.

[0061] In one embodiment, the advertising evaluation system also includes an attention module. When a person focuses their attention on external stimuli, specific EEG rhythms in the cerebral cortex, particularly the parietal and occipital lobes, change. Specifically, in the prefrontal cortex, increased Theta wave activity is associated with high levels of mental concentration and cognitive load. In the parietal and occipital lobes, desynchronization (reduction of Beta wave activity) is closely related to sensorimotor function and attentional concentration. The advertising evaluation system identifies the user's level of attentional concentration by analyzing relevant EEG rhythm signals.

[0062] Optionally, the neurophysiological signal also includes a P300 component, an event-related potential component that peaks approximately 300 milliseconds after the stimulus. The amplitude of the P300 is directly related to the allocation of attentional resources. If a key image or core tagline in an advertisement can trigger a larger P300 amplitude, it indicates that it has successfully captured the consumer's attention. The advertising evaluation system can track in real time when a consumer's attention peaks and declines while watching a 30-second advertisement, thereby identifying the point of attention loss.

[0063] Optionally, the advertising evaluation system can simultaneously measure consumers' emotions, attention, memory encoding, and motivational arousal related to the advertisement using electroencephalography (EEG), avoiding self-report bias. It can precisely identify which elements in the advertisement, such as visuals, music, and copy, evoke positive / negative responses, supporting creative optimization.

[0064] In one example, to detect which performs better in a video—pre-roll ads or mid-roll ads—or which banner ad placement is most appealing in an article, the ad evaluation system can measure the degree to which consumers’ attention shifts from the main content and their emotional response when ads appear in a simulated media usage flow, quantifying the “intrusion” effect and value of different ad placements.

[0065] In another example, the advertising evaluation system can test new packaging designs in front of virtual or real shelves. It combines EEG and eye-tracking to identify different packaging designs that immediately capture attention and evoke positive emotional responses, thus determining the most responsive packaging designs.

[0066] Since the system described in Embodiment 3 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0067] Based on the same inventive concept, this application also provides a fourth embodiment, referring to... Figure 4 , Figure 4This is a flowchart illustrating the fourth embodiment of the control method for the advertising evaluation system of this application.

[0068] In this embodiment, the control method of the advertising evaluation system further includes steps S71-S74: Step S71: Extract memory EEG signals from neurophysiological signals; Step S72: Align the memory EEG signals with the timestamps of the media content to generate a memory coding strength curve; Step S73: Identify the feature information of the memory coding intensity curve, and identify the memory coding identifier based on the feature information; Step S74: Determine the playback effect based on the memory encoding identifier and the emotional state curve.

[0069] In this embodiment, the advertising evaluation system, based on emotion evaluation, further extracts EEG components related to memory encoding from neurophysiological signals, generates a memory encoding intensity curve, and predicts the potential for advertising content to be remembered in the long term by identifying curve features. Finally, it combines emotional response and memory potential to comprehensively determine the playback effect. Memory EEG signals are specific neural activities related to successful information storage, such as gamma waves and late positive complexes. Memory encoding intensity is a parameter that quantifies the probability of information being successfully encoded by the brain.

[0070] It's important to note that whether a user can remember information is already signaled in the brain the moment the information is presented. Successful memory encoding is related to a specific pattern of electrical activity in the brain. Advertising evaluation systems can compare the EEG signals of successfully remembered and forgotten advertising elements during presentation to identify the advertising elements that users remember most vividly, thereby determining the effectiveness of playback.

[0071] In one embodiment, the advertising evaluation system, while processing EEG signals, analyzes high-frequency Gamma band activity in parallel, particularly Gamma energy changes in the left temporal lobe region, and simultaneously detects late positive complex components in event-related potentials. Signal intensity values ​​reflecting memory encoding potential are time-synchronized and mapped onto the advertising timeline to generate a memory encoding intensity curve. The advertising evaluation system analyzes the curve's peak values, sustained high-value intervals, and other characteristics to identify time points or segments with high memory encoding potential as memory encoding markers. In the final effect evaluation, the system focuses on segments where positive emotions overlap with memory encoding markers, confirming that these segments possess high emotional value and high memory retention potential.

[0072] For example, gamma wave activity in the left temporal lobe is considered a key indicator of successful memory encoding. When a media element, such as a brand logo or product packaging, appears, if it is accompanied by strong gamma wave activity, it indicates that the media element has a high probability of being stored in long-term memory.

[0073] This application extends the evaluation of advertising effectiveness from immediate emotional response to long-term memory retention potential prediction. By analyzing memory-related neural indicators such as Gamma waves and late positive complex waves, it predicts which content is more likely to be remembered by the audience at the time the advertisement is played. Combined with the emotional evaluation results, it identifies the core segments of the advertisement that have both positive emotional impact and high memory retention value.

[0074] Since the system described in Embodiment 4 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0075] Based on the same inventive concept, this application also provides a fifth embodiment, referring to... Figure 5 , Figure 5 This is a flowchart illustrating the fifth embodiment of the control method for the advertising evaluation system of this application.

[0076] In this embodiment, the control method of the advertising evaluation system further includes steps S31 to S34: Step S31: Obtain historical neurophysiological signal data and the corresponding emotional state annotations for the historical neurophysiological signal data; Step S32: Extract at least one dimension of neural features from historical neurophysiological signal data, including differential parameters; Step S33: Train the machine learning model based on neural features and emotional state annotations; Step S34: If the machine learning model converges according to the preset convergence condition, select the trained machine learning model as the sentiment analysis model.

[0077] In this embodiment, the advertising evaluation system constructs a machine learning model for emotion recognition through supervised learning. The model training process includes steps such as acquiring labeled historical neurophysiological data, extracting multi-dimensional neural features, and training the model until convergence. Emotional state labels are real emotion tags obtained through a rigorous process, and neural features are discriminative indicators extracted from the original signal, including differential parameters.

[0078] Furthermore, the system collects a large amount of EEG data and corresponding emotion annotations from users watching various emotional content. Annotation sources include standardized self-reports and expert facial expression coding. For each historical data segment, the system extracts differential parameters such as prefrontal alpha asymmetry and can further extract multi-dimensional features such as power and functional connectivity across all brain frequency bands. The feature vectors and emotion annotations are input into a machine learning algorithm for training. Model parameters are adjusted by monitoring training error and validation set performance until the model reaches the preset convergence condition. Finally, the best-performing model is saved as the emotion analysis model.

[0079] Since the system described in Embodiment 5 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0080] This application provides a control device for an advertising evaluation system, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the control method of the advertising evaluation system in the first embodiment described above.

[0081] The following is for reference. Figure 6 The diagram illustrates a structural schematic of a control device suitable for implementing the advertising evaluation system of the embodiments of this application. The control device for the advertising evaluation system in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The control device of the advertising evaluation system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0082] like Figure 6As shown, the control device of the advertising evaluation system may include a processing unit 1001 (e.g., a core processor, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The random access memory 1004 also stores various programs and data required for the operation of the control device of the advertising evaluation system. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the control device of the advertising evaluation system to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a control device for an advertising evaluation system with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0083] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0084] The control device for the advertising evaluation system provided in this application, employing the control method of the advertising evaluation system in the above embodiments, can solve the technical problem that the evaluation of advertising playback effects is difficult to accurately reflect the key elements in the advertisement that move users. Compared with the prior art, the beneficial effects of the control device for the advertising evaluation system provided in this application are the same as the beneficial effects of the control method for the advertising evaluation system provided in the above embodiments, and other technical features in the control device for the advertising evaluation system are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0085] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0086] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0087] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the control method of the advertising evaluation system in the above embodiments.

[0088] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0089] The aforementioned computer-readable storage medium may be included in the control device of the advertising evaluation system; or it may exist independently and not be assembled into the control device of the advertising evaluation system.

[0090] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the control device of the advertising evaluation system, the control device of the advertising evaluation system causes the following: to acquire the neurophysiological signals of the user when receiving media content, to extract the target rhythm signal from the neurophysiological signals, to calculate the difference parameters of the target rhythm signal between preset brain regions, to identify the user's emotional state type based on the difference parameters through an emotion analysis model, to align the emotional state type with the timestamp of the media content, to generate an emotional state curve, and to determine the playback effect of the media content based on the emotional state curve.

[0091] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0094] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the control method of the aforementioned advertising evaluation system. This addresses the technical problem that evaluations of advertising playback effects are often inaccurate in reflecting the key elements in an advertisement that resonate with users. Compared to existing technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the control method of the advertising evaluation system provided in the above embodiments, and will not be elaborated upon here.

[0095] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A control method of an advertisement evaluation system, characterized by, The method comprises the following steps: Obtaining a neurophysiological signal of a user when receiving media content, and extracting a target rhythm signal from the neurophysiological signal; Calculating a difference parameter of the target rhythm signal between preset brain regions; Identifying an emotional state type of the user according to the difference parameter through an emotional analysis model; Aligning the emotional state type with a timestamp of the media content to generate an emotional state curve; Determining a play effect of the media content according to the emotional state curve.

2. The control method of the advertisement evaluation system according to Claim 1, wherein After the step of determining the play effect of the media content according to the emotional state curve, the method further comprises: According to the curve characteristics of the emotional state curve, identifying a target time period in the media content in which a change rate of the curve characteristics is greater than a change rate threshold; Performing correlation analysis on media elements of the media content in the target time period to determine a target media element.

3. The control method of the advertisement evaluation system according to Claim 2, wherein The step of determining the play effect of the media content according to the emotional state curve comprises: Obtaining a target physiological signal of the user, the target physiological signal comprising an eye tracking signal and / or a galvanic skin response signal; Aligning the target physiological signal with the emotional state curve based on a time dimension; According to the alignment result, performing fusion analysis on the emotional state type and the target physiological signal to generate a comprehensive evaluation report on the media content.

4. The control method of the advertisement evaluation system according to Claim 1, wherein The step of determining the play effect of the media content according to the emotional state curve comprises: According to the emotional state curve, performing correlation labeling on picture points in the media content; According to the correlation labeling result, determining the play effect of the media content.

5. The control method of the advertisement evaluation system according to Claim 1, wherein The step of determining the play effect of the media content according to the emotional state curve further comprises: Extracting an attention rhythm signal from the neurophysiological signal, and calculating an attention concentration degree of the attention rhythm signal; Aligning the attention concentration degree parameter with a timestamp of the media content to generate an attention concentration degree curve; Based on the emotional state curve and the attention concentration degree curve, identifying a synergistic time interval in which the emotional state type is positive and the attention concentration degree exceeds a preset threshold in the media content; According to the synergistic time interval, and the emotional state curve and the attention concentration degree curve, determining the play effect of the media content.

6. The control method of the advertisement evaluation system according to Claim 1, wherein The step of calculating the difference parameter of the target rhythm signal between preset brain regions comprises: Calculating a first average power of the target rhythm signal in a first preset brain region within a preset time window, and a second average power of the target rhythm signal in a second preset brain region within the preset time window; According to a difference value between the first average power and the second average power, determining the difference parameter.

7. The control method of the advertisement evaluation system according to Claim 1, wherein Before the step of identifying the emotional state type of the user according to the difference parameter through the emotional analysis model, the method further comprises: Obtaining historical neurophysiological signal data and emotional state labels corresponding to the historical neurophysiological signal data; extracting at least one dimension of neural features from the historical neuro-physiological signal data, the neural features comprising the difference parameter; training a machine learning model according to the neural features and the emotion state labels; if the machine learning model is determined to converge according to a preset convergence condition, selecting the trained machine learning model as the emotion analysis model.

8. The control method of the advertisement evaluation system according to Claim 1, wherein The step of determining the play effect of the media content according to the emotion state curve further comprises: extracting a memory electroencephalogram signal from the neuro-physiological signal; aligning the memory electroencephalogram signal with a timestamp of the media content to generate a memory encoding intensity curve; identifying feature information of the memory encoding intensity curve and identifying a memory encoding label according to the feature information; determining the play effect according to the memory encoding label and the emotion state curve.

9. A control device of an advertisement evaluation system, characterized by, The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the control method of the advertisement evaluation system according to any one of claims 1 to 8.

10. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the control method of the advertisement evaluation system according to any one of claims 1 to 8.

Images