CN113269084A - Movie and television play market prediction method and system based on audience group emotional nerve similarity - Google Patents
Movie and television play market prediction method and system based on audience group emotional nerve similarity Download PDFInfo
- Publication number
- CN113269084A CN113269084A CN202110560889.9A CN202110560889A CN113269084A CN 113269084 A CN113269084 A CN 113269084A CN 202110560889 A CN202110560889 A CN 202110560889A CN 113269084 A CN113269084 A CN 113269084A
- Authority
- CN
- China
- Prior art keywords
- emotional
- similarity
- movie
- audience
- nerve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Abstract
The invention discloses a movie and TV drama market prediction method and system based on audience group emotional nerve similarity, wherein a testee watches movie and TV drama segments induced by different emotions, a multichannel electroencephalogram device is adopted to simultaneously collect the electroencephalogram activities of a plurality of audiences when watching the movie and TV drama, the alpha frequency band energy value of each audience in each second to a certain movie and TV drama segment is obtained based on the preprocessing and wavelet transformation of electroencephalogram signals, the RDM matrix of each audience for the movie and TV drama emotional induction is calculated in real time, the correlation coefficient matrix of the RDM matrix among the audience groups is calculated to quantize the group emotional nerve similarity index, and finally, a movie and TV drama market prediction model is constructed through CNN. The method realizes real-time measurement and analysis of the group audience emotion, can predict the movie and television play market to be shown through the emotional nerve similarity among movie and television play groups, can effectively avoid the problems of post sampling, unclear emotion capture, social allowance deviation and the like in movie and television play audience self-reporting, and has wide market application prospect.
Description
Technical Field
The invention relates to the technical field of audience group emotion calculation of movie and television series, in particular to a movie and television series market prediction method and system based on audience group emotion neural similarity.
Background
In the 21 st century, the technology development promotes the leap forward of the film and television industry, and the competition is more and more intense. The film and television industry has higher requirements for accurately knowing the emotional needs, preferences, experiences and feedback of audiences. Emotion is known as Grammar of human Social life (Grammar of Social life), and recognition and understanding of emotion are one of important functions of human-like intelligent machines. Emotion is an abstract concept, and sensibility exists and is difficult to accurately describe by language. Meanwhile, the method is a complex concept, experiences perception and cannot be simply measured. How to capture the group emotion of the audience of the movie and television play with high precision is very important for predicting the movie and television play market in advance for producers and major teams of the movie and television play, and becomes a difficult problem which needs to be broken through urgently in the field of movie and television theories.
The group emotion of the audience of the movie and television drama refers to the common emotional experience of the group caused by the same movie and television drama segment, and comprises the group emotional nerve similarity degree. At present, the mainstream research technology, method and implementation difficulty are extremely difficult for accurately capturing dynamic nonlinear emotion, and more emotion analysis and identification focused on an individual level are researched in the past, so that the emotion similarity calculation of a population level is neglected. On the other hand, at the present stage, the measurement of group emotion similarity is still mainly carried out in traditional ways such as questionnaires, self-reports, behavioral experiments and the like, and an objective and procedural group emotion similarity calculation method is lacked, so that a method for effectively predicting the movie and television show market based on audience group emotion neural similarity is lacked. Therefore, the movie and television play market prediction system based on the emotional nerve similarity of the audience groups is constructed, so that movie and television play producers can predict in advance, risks are reduced, and cost is reduced.
Disclosure of Invention
The invention provides a movie and television play market prediction method and system based on audience group emotional nerve similarity, which adopts the following technical scheme:
a movie and TV play market prediction method based on audience population emotional nerve similarity comprises the following steps:
s1: recruiting a plurality of movie and television play audiences as experimental testees, and wearing multi-channel electroencephalogram measuring equipment for the testees at the same time;
s2: playing the same movie and TV play segments to a testee to enable the testee to be placed in the same emotion induction environment, and synchronously acquiring original electroencephalograms of a plurality of testees;
s3: carrying out real-time preprocessing and wavelet transformation on original electroencephalogram signals positioned in forehead and frontotemporal channels to obtain energy values of alpha frequency bands per second;
s4: calculating the RDM matrix of each testee for different emotional stimuli in real time according to the energy value;
s5: calculating a correlation coefficient matrix of an RDM matrix among audience groups as a neural similarity index E of group emotion;
s6: and (3) training the constructed convolutional neural network by taking the alpha frequency band energy value of each audience on different movie and television plot feeling segments as an input value and taking the neural similarity index E of group emotion as an output value.
Further, in step S4, the RDM matrix calculation formula for the individual subject for different emotional stimuli is as follows:
Dij＝1-similarity(di，dj)，
wherein D isijCharacterizing the degree of dissimilarity between emotion i and emotion j for a movie fragment, diAlpha-band energy value, d, characterizing emotion i for a movie episodejAn alpha-band energy value characterizing emotion j for the episode of the movie, and e (x) an expected value of the alpha-band energy value characterizing a certain emotion for the episode of the movie.
Further, in step S5, the specific method of calculating the correlation coefficient matrix of the RDM matrix among the audience groups as the neural similarity index E of the group emotion is as follows:
the correlation coefficient matrix of the RDM matrix among the audience groups is calculated by the neuroRA toolkit of python as the neural similarity index E of the group emotion.
Further, when the audience population emotional nerve similarity index E is more than or equal to 0.6, determining that the audience population emotional nerve similarity is strong;
when the audience population emotional nerve similarity index E is more than or equal to 0.4 and less than 0.6, determining that the audience population emotional nerve similarity converges;
and when the audience population emotional nerve similarity index E is less than 0.4, determining that the audience population emotional nerve similarity is insufficient.
Further, in step S3, the forehead and anterior temporal channels are selected as follows: the electrode points are distributed and configured according to the international 10-20 system and related brain regions, and FP1, FPz, FP2, Fz, F3, F4, F7 and F8 electrode points are selected according to the calculation of representing the emotional excitation degree.
Further, in step S1, the multichannel electroencephalogram measuring apparatus employs a 32-lead electrode cap, using saline or gel electrodes, and the impedance of each electrode point is lower than 5k Ω.
Further, repeating the steps S1-S5 to obtain a plurality of groups of training data, and training the constructed convolutional neural network through the plurality of groups of training data, wherein the number of the groups of the training data is more than or equal to 100.
A movie and TV drama market prediction system based on audience population emotional nerve similarity is used for executing the movie and TV drama market prediction method based on the audience population emotional nerve similarity, and is characterized by comprising a movie and TV drama emotion induction device, an electroencephalogram measurement equipment set and an audience population emotional nerve similarity calculation unit which are sequentially connected, wherein the audience population emotional nerve similarity calculation unit comprises a population electroencephalogram signal preprocessing module, a population emotional nerve similarity calculation module and a movie and TV drama market prediction module which are sequentially connected;
the emotion inducing device is used for playing movie and television play fragments;
the electroencephalogram measuring equipment group is used for synchronously acquiring electroencephalogram signals of a plurality of testees and transmitting the electroencephalogram signals to the group electroencephalogram signal preprocessing module;
the group electroencephalogram signal preprocessing module is used for preprocessing the acquired electroencephalogram signals;
the crowd emotion neural similarity calculation module is used for performing wavelet transformation on the preprocessed electroencephalogram signals to obtain an energy value of an alpha frequency band per second, and then calculating a correlation coefficient matrix of an RDM matrix among the crowds in real time to generate an audience crowd emotion neural similarity index E;
after being trained, the movie and television play market prediction module can predict the input energy value of the alpha frequency band per second to obtain the corresponding audience population emotional nerve similarity index E.
Further, the preprocessing of the acquired electroencephalogram signals by the group electroencephalogram signal preprocessing module comprises the steps of amplifying the acquired electroencephalogram signals, intercepting an analysis section, reducing noise, removing artifacts and carrying out band-pass filtering, wherein the removing of the artifacts comprises the removal of electro-oculogram, myoelectricity, electrocardio and power frequency interference.
Furthermore, the film and television plot induction device comprises an image presentation device and an image processing and storing device;
the image presentation device is used for presenting movie and TV play fragments as a visual stimulus source;
the image processing and storing device is used for processing and storing movie and television play fragments.
The movie and television drama market prediction method and system based on the audience population emotional nerve similarity, which are provided by the invention, form a comprehensive calculation strategy from the emotional nerve similarities of different movie and television drama audiences, have the characteristics of real-time monitoring and quantification, and can scientifically and comprehensively analyze the emotional nerve similarities of the audience population. At present, electroencephalogram identification is mostly researched based on amplitude characteristics, and phase synchronization characteristics among multiple brains are ignored. The phase synchronization characteristic detects the correlation between the signal pairs through the instantaneous phase relation between the signals, and represents the emotional excitation degree of the audience to the movie and television drama. The neural similarity of the emotions among the audience groups can be effectively identified by the correlation coefficients of the characteristic dissimilarity matrix. In addition, the invention innovatively provides a method for calculating the emotional nerve similarity index of audience groups by relying on the energy of the brain wave frequency band of a specific brain area, the nerve similarity among the audience groups of the movie and television drama to be mapped can be accurately predicted through the RDM matrix, and the prediction accuracy rate reaches 94.7%. And finally, constructing a film and television play market prediction model based on the emotional nerve similarity of the audience groups through CNN.
2. The system realizes synchronous real-time monitoring and dynamic analysis of multiple persons by means of the characteristic of high time resolution of EEG, can study the similarity of the emotional nerves of the group in a process and full flow, and effectively avoids the problems of post sampling, strong subjectivity, social deviation and the like of the traditional measuring means.
3. The prediction system has the functions of dynamic prediction and visualization, and can help users to intuitively acquire the data of the emotional nerve similarity of audience groups, thereby helping movie and television series producers make scientific decisions. Meanwhile, the method has the characteristics of non-invasiveness, safety, high efficiency and low cost, can be applied to the fields of film clip editing, advertisement effect evaluation, emotion inducing material screening, VR immersion effect evaluation, exhibition hall immersion experience evaluation, audience rating prediction and the like by a popularization merchant, and has wide market application prospect.
Drawings
FIG. 1 is a schematic diagram of a movie and television show market prediction system based on emotional neuro-similarity of audience populations according to the present invention;
fig. 2 is a flowchart of the movie and television show market prediction method based on the emotional nerve similarity of the audience groups according to the invention.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
Emotional experiences are mainly triggered by dramatic segments of film and television, causing changes in brain functional activity, responses in the peripheral autonomic nervous system, and changes in neurochemicals in the body. An electroencephalogram (EEG) is a general reflection of electrophysiological activity of brain nerve cells on the surface of a cerebral cortex or a scalp, contains a large amount of physiological and psychological information related to emotion, has the characteristics of direct objectivity, difficulty in disguising, easiness in quantification, multiple features and the like, and is a cognitive physiological index with a remarkable effect in the field of emotion recognition at present. By monitoring multi-person electroencephalogram signals simultaneously and based on correlation of emotion related nerve activities among brains, the population emotion nerve similarity can be effectively monitored. A movie and television drama market prediction system based on audience group emotion neural similarity simultaneously acquires multi-person EEG data by utilizing an on-line multi-channel EEG device and performs real-time dynamic analysis on group emotion to realize agile data processing and display.
As shown in fig. 1, a system for predicting a market of a movie and television play based on emotional nerve similarity of audience groups comprises:
the video drama emotion inducing device comprises an image presenting device and an image processing and storing device, wherein the image presenting device is used for presenting emotion stimulating materials (video drama fragments), and a screen can be used as a visual stimulus source according to the usual viewing habit. The image processing and storing device is used for processing and storing movie and television play fragments. As an alternative embodiment, a group of subjects simultaneously faces the movie screen, and emotional evokes are performed by playing movie segments.
And the electroencephalogram measuring equipment group is used for synchronously acquiring electroencephalogram signals of a plurality of movie and television series audience testees and transmitting the electroencephalogram signals to the audience group emotional nerve similarity calculating unit. As an alternative embodiment, an EMOTIV EPOC Flex salt brain electrical acquisition system (comprising a control box, a signal receiver, an EPOC Flex Cap, an EPOC Flex salt brine Sensor and the like) can be used, a single ADC is used, the bandwidth is 0.16-43Hz, 32 channels of data are contained, 2 reference electrodes are arranged on ears, and the equipment is used for multi-machine synchronous sequential sampling. Host configuration used by the system: the CPU is configured with Intel Core i7-9700 in equal or higher configuration; the GPU is configured with NVIDIA GeForce GTX 2080Ti in the same or higher configuration; memory: 64GB RAM; 1TB of available disk space.
The group emotion neural similarity calculation unit comprises a group electroencephalogram signal preprocessing module, a group emotion neural similarity calculation module and a movie and television drama market prediction module. The group electroencephalogram signal preprocessing module is used for carrying out preprocessing of amplification, analysis section interception, noise reduction, artifact removal (removal of electro-oculogram, myoelectricity, electrocardio, power frequency interference and the like) and band-pass filtering on the acquired electroencephalogram signals, wherein the artifact removal comprises removal of electro-oculogram, myoelectricity, electrocardio and power frequency interference. The population emotional nerve similarity calculation module is used for performing wavelet transformation on the preprocessed electroencephalogram signals, calculating the energy value of an alpha frequency band per second in real time, and then calculating a nerve representation dissimilarity matrix, namely an RDM matrix, of the audience to be tested for different emotional stimuli in real time. Audience population affective neural similarity indices are calculated by the python-based NeuroRA toolkit. The movie and television drama market prediction module is used for predicting audience group emotional nerve similarity indexes of movie and television drama fragments with different emotions, helping a user grasp group emotional nerve similarity of different movie and television dramas and providing scientific basis for decision making. And the movie and television play market prediction module trains and learns the calculated data through a Convolutional Neural Network (CNN) to obtain a prediction module. In the subsequent operation, the energy value of each second of the alpha frequency range of a film of a subject is directly detected, and the obtained energy value of each second of the alpha frequency range is input into a prediction model to obtain a specific audience population emotional nerve similarity index.
As shown in fig. 2, the movie and television play market prediction method based on the audience population emotional nerve similarity according to the present invention is implemented based on the real-time prediction system, and specifically includes the following steps:
s1: a multi-channel electroencephalogram measuring device is worn by a plurality of testees at the same time, a 32-lead electrode cap is adopted, saline or gel electrodes can be used, the impedance of each electrode point is lower than 5k omega, and a 10-20 system adopting international unified standard is configured at the electrode position.
S2: the testee is placed in the same emotion inducing environment (the same movie and television episode is played), and original electroencephalogram signals of a plurality of testees are synchronously acquired. The human body test method is to reduce head movement or other limb movements of the human body to the greatest extent, avoid language communication among human bodies, and reduce interference of irrelevant visual or auditory stimuli.
S3: and performing real-time preprocessing and wavelet transformation on the original electroencephalogram signals positioned on the forehead and the frontotemporal channel, and calculating the energy value of the alpha frequency band per second in real time. The forehead and anterior temporal channels are selected by: and (3) electrode points are distributed and configured according to the international 10-20 system and related brain areas, and FP1, FPz, FP2, Fz, F3, F4, F7 and F8 electrode points are selected according to calculation representing emotional excitation degrees.
S4: and calculating a characterization dissimilarity matrix, namely an RDM matrix, of each testee in real time according to the energy values under different emotional stimuli obtained in the step S3.
The calculation formula of the RDM matrix is as follows:
Dij＝1-similarity(di，dj)，
wherein D isijCharacterizing the degree of dissimilarity between emotion i and emotion j for a movie fragment, diAlpha-band energy value, d, characterizing emotion i for a movie episodejAn alpha-band energy value characterizing emotion j for the episode of the movie, and e (x) an expected value of the alpha-band energy value characterizing a certain emotion for the episode of the movie.
S5: and calculating a correlation coefficient matrix of the RDM matrixes among the audience groups in real time according to each tested RDM matrix of S4, namely the audience group emotional nerve similarity index E. The python-based NeuroRA kit, which can be used to characterize and analyze multimodal neural data, calculates inter-population correlation (ISC), i.e., neural correlation coefficient, which is used to characterize the neural similarity index E of the population emotion. By inputting data of different testees, the emotional relevance of the testees to the movie and television drama segments is obtained, and the emotional nerve similarity index E of the audience population to the same stimulus is obtained. Criteria for assessing and ranking neural similarity are: when the population emotional nerve similarity index E is more than or equal to 0.6, determining that the population emotional nerve similarity is strong; when E is more than or equal to 0.4 and less than 0.6, determining that the emotional nerve similarity of the population converges; when E is less than 0.4, the emotional nerve similarity of the population is determined to be insufficient.
S6: and according to the neural similarity index of the group emotion, training the neural similarity indexes of the part of audiences by adopting a Convolutional Neural Network (CNN), taking the alpha frequency band energy value of each audience for different movie and television plot emotion fragments as an input value, taking the neural similarity index E of the group emotion as an output value, and training the constructed convolutional neural network CNN. The trained convolutional neural network can predict the neural similarity index E of group emotion under the condition of inputting the energy value of the alpha frequency band per second, and further serves as an important consideration factor for measuring movie and television series.
It can be understood that steps S1 to S5 are repeated to obtain a plurality of sets of training data, and the constructed convolutional neural network is trained by the plurality of sets of training data, where the number of sets of training data is greater than or equal to 100.
The RDM matrix of each testee is used as a training material for deep learning for different emotional stimuli, wherein an energy value of an alpha frequency range per second is used as an input value, a nerve similarity index E of group emotion is used as an output value, and the higher the nerve similarity index E of the group emotion is, the higher the emotional resonance of an audience group to the movie and television series is, the higher the market success rate of the movie and television series is. And predicting the market performance of the film and television series according to a convolutional neural network prediction model trained by the training materials of the small sample group.
The training of the convolutional neural network model is a general convolutional neural network training process, and the training steps of the convolutional neural network are simply introduced as follows:
1. and extracting the energy value of the alpha frequency band per second for each tested electroencephalogram data to be stimulated differently. The input characteristics of the convolutional neural network need to be standardized, so the energy value data of the alpha frequency band per second is subjected to standard normalization processing to a [0, 1] interval.
2. The convolutional layer is used for calculating the alpha frequency band energy value under the stimulation of different movie and television drama fragments, the function of the convolutional layer is to extract the characteristics of input data, the convolutional layer internally comprises a plurality of convolutional kernels, each element forming the convolutional kernels corresponds to a weight coefficient and a deviation value, each neuron in the convolutional layer is connected with a plurality of neurons in an area close to the position in the previous layer, and the size of the area depends on the size of the convolutional kernels. When the convolution kernel works, the convolution kernel regularly sweeps the input characteristics, matrix element multiplication summation is carried out on the input characteristics in the receptive field, and deviation quantity is superposed:
the summation part in the equation is equivalent to solving a cross-correlation (cross-correlation). b is the amount of deviation, ZlAnd Zl+1Represents the convolutional input and output of the L +1 th layer, also called feature map, Ll+1Is Zl+1The feature pattern length and width are assumed to be the same. Z (i, j) corresponds to the pixel of the feature map, w is the weight matrix, K is the channel number of the feature map, f, s0And p is a convolutional layer parameter, corresponding to convolutional kernel size, convolutional step size (stride), and number of padding (padding) layers.
3. After the feature extraction is performed on the convolutional layer, the output feature map is transmitted to the pooling layer for feature selection and information filtering. The pooling layer contains a pre-set pooling function whose function is to replace the result of a single point in the feature map with the feature map statistics of its neighboring regions. The step of selecting the pooling area by the pooling layer is the same as the step of scanning the characteristic diagram by the convolution kernel, and the pooling size, the step length and the filling are controlled.
In the formula, step length s0Pixel (i, j) has the same meaning as the convolution layer, and p is a pre-specified parameter. Pooling is averaged over a pooling area when p is 1, referred to as mean pooling (averaging); when p ∞, the pooling of Lp takes a maximum within a region, called maximal pooling (max pooling).
4. The fully-connected layer is located at the last part of the hidden layer of the convolutional neural network and only signals are transmitted to other fully-connected layers. The feature map loses spatial topology in the fully connected layer, is expanded into vectors and passes through the excitation function.
5. The classifier receives data from the full connection layer to ultimately implement the preference classification.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by using equivalent alternatives or equivalent variations fall within the scope of the present invention.
Claims (10)
1. A movie and TV play market prediction method based on audience population emotional nerve similarity is characterized by comprising the following steps:
s1: recruiting a plurality of movie and television play audiences as experimental testees, and wearing multi-channel electroencephalogram measuring equipment for the testees at the same time;
s2: playing the same movie and TV play segments to a testee to enable the testee to be placed in the same emotion induction environment, and synchronously acquiring original electroencephalograms of a plurality of testees;
s3: carrying out real-time preprocessing and wavelet transformation on original electroencephalogram signals positioned in forehead and frontotemporal channels to obtain energy values of alpha frequency bands per second;
s4: calculating the RDM matrix of each testee for different emotional stimuli in real time according to the energy value;
s5: calculating a correlation coefficient matrix of the RDM matrix among audience groups as a neural similarity index E of group emotion;
s6: and (3) training the constructed convolutional neural network by taking the alpha frequency band energy value of each audience on different movie and television plot feeling segments as an input value and taking the neural similarity index E of the group feeling as an output value.
2. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 1,
in step S4, the RDM matrix calculation formula of the single subject for different emotional stimuli is as follows:
Dij＝1-similarity(di，dj)，
wherein D isijCharacterizing the degree of dissimilarity between emotion i and emotion j for a movie fragment, diAlpha-band energy value, d, characterizing emotion i for a movie episodejAn alpha-band energy value characterizing emotion j for the episode of the movie, and e (x) an expected value of the alpha-band energy value characterizing a certain emotion for the episode of the movie.
3. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 1,
in step S5, the specific method of calculating the correlation coefficient matrix of the RDM matrix among audience groups as the neural similarity index E of group emotion is as follows:
calculating a correlation coefficient matrix of the RDM matrix among audience groups as a neural similarity index E of group emotion through a neuroRA toolkit of python.
4. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 3,
when the audience population emotional nerve similarity index E is more than or equal to 0.6, determining that the audience population emotional nerve similarity is strong;
when the audience population emotional nerve similarity index E is more than or equal to 0.4 and less than 0.6, determining that the audience population emotional nerve similarity converges;
and when the audience population emotional nerve similarity index E is less than 0.4, determining that the audience population emotional nerve similarity is insufficient.
5. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 1,
in step S3, the forehead and anterior temporal channels are selected as follows: the electrode points are distributed and configured according to the international 10-20 system and related brain regions, and FP1, FPz, FP2, Fz, F3, F4, F7 and F8 electrode points are selected according to the calculation of representing the emotional excitation degree.
6. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 1,
in step S1, the multichannel electroencephalogram measuring device adopts a 32-lead electrode cap, and uses saline or gel electrodes, and the impedance of each electrode point is lower than 5k Ω.
7. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 1,
and repeating the steps of S1-S5 to obtain a plurality of groups of training data, and training the constructed convolutional neural network through the plurality of groups of training data, wherein the number of the groups of the training data is more than or equal to 100.
8. A drama market prediction system based on audience population emotional nerve similarity is used for executing the drama market prediction method based on audience population emotional nerve similarity according to any one of claims 1 to 7, and is characterized by comprising a movie drama emotion induction device, an electroencephalogram measuring device group and an audience population emotional nerve similarity calculation unit which are connected in sequence, wherein the audience population emotional nerve similarity calculation unit comprises a population electroencephalogram signal preprocessing module, a population emotional nerve similarity calculation module and a drama market prediction module which are connected in sequence;
the emotion inducing device is used for playing movie and television play fragments;
the electroencephalogram measuring equipment group is used for synchronously collecting electroencephalogram signals of a plurality of testees and transmitting the electroencephalogram signals to the population electroencephalogram signal preprocessing module;
the population electroencephalogram signal preprocessing module is used for preprocessing the acquired electroencephalogram signals;
the crowd emotion neural similarity calculation module is used for performing wavelet transformation on the preprocessed electroencephalogram signals to obtain an energy value of an alpha frequency band per second, and then calculating a correlation coefficient matrix of an RDM matrix among the crowds in real time to generate the audience crowd emotion neural similarity index E;
after being trained, the movie and television play market prediction module can predict the input energy value of the alpha frequency range per second to obtain the corresponding audience population emotional nerve similarity index E.
9. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 8,
the preprocessing of the acquired electroencephalogram signals by the group electroencephalogram signal preprocessing module comprises the steps of amplifying the acquired electroencephalogram signals, intercepting an analysis section, reducing noise, removing artifacts and carrying out band-pass filtering, wherein the removing of the artifacts comprises the removal of electro-oculogram, myoelectricity, electrocardio and power frequency interference.
10. The method of predicting the market of movies based on the emotional neuro-similarity of audience groups as claimed in claim 8,
the movie and television plot induction device comprises an image presentation device and an image processing and storing device;
the image presentation device is used for presenting movie and TV play fragments as a visual stimulus source;
the image processing and storing device is used for processing and storing movie and television play fragments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560889.9A CN113269084B (en) | 2021-05-19 | 2021-05-19 | Movie and television play market prediction method and system based on audience group emotional nerve similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560889.9A CN113269084B (en) | 2021-05-19 | 2021-05-19 | Movie and television play market prediction method and system based on audience group emotional nerve similarity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113269084A true CN113269084A (en) | 2021-08-17 |
| CN113269084B CN113269084B (en) | 2022-11-01 |
Family
ID=77232553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110560889.9A Active CN113269084B (en) | 2021-05-19 | 2021-05-19 | Movie and television play market prediction method and system based on audience group emotional nerve similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113269084B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116509417A (en) * | 2023-04-25 | 2023-08-01 | 上海外国语大学 | Consumer preference consistency prediction method based on nerve similarity |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035563A (en) * | 2014-06-19 | 2014-09-10 | 北京工业大学 | W-PCA (wavelet transform-principal component analysis) and non-supervision GHSOM (growing hierarchical self-organizing map) based electrocardiographic signal identification method |
| CN104361356A (en) * | 2014-12-08 | 2015-02-18 | 清华大学 | Movie audience experience assessing method based on human-computer interaction |
| CN107610707A (en) * | 2016-12-15 | 2018-01-19 | 平安科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN107995588A (en) * | 2017-11-09 | 2018-05-04 | 天津大学 | Co-positioned node selecting method based on EFI |
| CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
| CN109165615A (en) * | 2018-08-31 | 2019-01-08 | 中国人民解放军军事科学院军事医学研究院 | A kind of parameter training algorithm under multi-categorizer single channel mode towards EEG signals |
| CN110687999A (en) * | 2018-07-04 | 2020-01-14 | 刘彬 | Method and device for semantic processing of electroencephalogram signals |
| CN111157988A (en) * | 2020-02-27 | 2020-05-15 | 中南大学 | Gesture radar signal processing method based on RDTM and ATM fusion |
| CN112232861A (en) * | 2020-10-10 | 2021-01-15 | 上海外国语大学 | Plane advertisement evaluation method and system based on neural similarity analysis |
| CN112545519A (en) * | 2021-02-22 | 2021-03-26 | 之江实验室 | Real-time assessment method and system for group emotion homogeneity |
-
2021
- 2021-05-19 CN CN202110560889.9A patent/CN113269084B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035563A (en) * | 2014-06-19 | 2014-09-10 | 北京工业大学 | W-PCA (wavelet transform-principal component analysis) and non-supervision GHSOM (growing hierarchical self-organizing map) based electrocardiographic signal identification method |
| CN104361356A (en) * | 2014-12-08 | 2015-02-18 | 清华大学 | Movie audience experience assessing method based on human-computer interaction |
| CN107610707A (en) * | 2016-12-15 | 2018-01-19 | 平安科技（深圳）有限公司 | A kind of method for recognizing sound-groove and device |
| CN107995588A (en) * | 2017-11-09 | 2018-05-04 | 天津大学 | Co-positioned node selecting method based on EFI |
| CN110687999A (en) * | 2018-07-04 | 2020-01-14 | 刘彬 | Method and device for semantic processing of electroencephalogram signals |
| CN108881985A (en) * | 2018-07-18 | 2018-11-23 | 南京邮电大学 | Program points-scoring system based on brain electricity Emotion identification |
| CN109165615A (en) * | 2018-08-31 | 2019-01-08 | 中国人民解放军军事科学院军事医学研究院 | A kind of parameter training algorithm under multi-categorizer single channel mode towards EEG signals |
| CN111157988A (en) * | 2020-02-27 | 2020-05-15 | 中南大学 | Gesture radar signal processing method based on RDTM and ATM fusion |
| CN112232861A (en) * | 2020-10-10 | 2021-01-15 | 上海外国语大学 | Plane advertisement evaluation method and system based on neural similarity analysis |
| CN112545519A (en) * | 2021-02-22 | 2021-03-26 | 之江实验室 | Real-time assessment method and system for group emotion homogeneity |
Non-Patent Citations (1)
| Title |
|---|
| 诸廉 等: ""论影视创作中人工智能预测技术的应用"", 《中州学刊》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116509417A (en) * | 2023-04-25 | 2023-08-01 | 上海外国语大学 | Consumer preference consistency prediction method based on nerve similarity |
| CN116509417B (en) * | 2023-04-25 | 2024-03-12 | 上海外国语大学 | Consumer preference consistency prediction method based on nerve similarity |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113269084B (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110765920B (en) | Motor imagery classification method based on convolutional neural network | |
| CN110916631B (en) | Student classroom learning state evaluation system based on wearable physiological signal monitoring | |
| Yang et al. | Automatic ocular artifacts removal in EEG using deep learning | |
| Hamad et al. | Feature extraction of epilepsy EEG using discrete wavelet transform | |
| CN112932502B (en) | Electroencephalogram emotion recognition method combining mutual information channel selection and hybrid neural network | |
| CN112545519B (en) | Real-time assessment method and system for group emotion homogeneity | |
| CN111651060B (en) | Real-time evaluation method and evaluation system for VR immersion effect | |
| CN110353702A (en) | A kind of emotion identification method and system based on shallow-layer convolutional neural networks | |
| CN111544015B (en) | Cognitive power-based control work efficiency analysis method, device and system | |
| Gruszczyńska et al. | Epilepsy identification based on EEG signal using RQA method | |
| CN111598451B (en) | Control work efficiency analysis method, device and system based on task execution capacity | |
| JP7373555B2 (en) | Quantification of motor function using EEG signals | |
| CN108324292B (en) | Indoor visual environment satisfaction degree analysis method based on electroencephalogram signals | |
| CN111184509A (en) | Emotion-induced electroencephalogram signal classification method based on transfer entropy | |
| CN111466931A (en) | Emotion recognition method based on EEG and food picture data set | |
| Anwar et al. | Use of portable EEG sensors to detect meditation | |
| CN113269084B (en) | Movie and television play market prediction method and system based on audience group emotional nerve similarity | |
| CN113143296B (en) | Intelligent assessment method and system for communication disorder | |
| Bablani et al. | Deceit identification test on EEG data using deep belief network | |
| Khushaba et al. | A neuroscientific approach to choice modeling: Electroencephalogram (EEG) and user preferences | |
| CN115686208A (en) | Music induced emotion recognition method and system based on EEG | |
| CN115659207A (en) | Electroencephalogram emotion recognition method and system | |
| Ab Rahman et al. | Classification of EEG signal for body earthing application | |
| Dubey et al. | Digital analysis of EEG brain signal | |
| Yun et al. | A Study on Training Data Selection Method for EEG Emotion Analysis Using Artificial Neural Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |