CN108073284B - Shopping system based on brain wave recognition emotion - Google Patents
Shopping system based on brain wave recognition emotion Download PDFInfo
- Publication number
- CN108073284B CN108073284B CN201711348101.8A CN201711348101A CN108073284B CN 108073284 B CN108073284 B CN 108073284B CN 201711348101 A CN201711348101 A CN 201711348101A CN 108073284 B CN108073284 B CN 108073284B
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- item
- brain wave
- module
- 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.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 56
- 230000008451 emotion Effects 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000007418 data mining Methods 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 239000000523 sample Substances 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 210000003710 cerebral cortex Anatomy 0.000 claims description 3
- 230000001939 inductive effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012567 pattern recognition method Methods 0.000 claims 1
- 230000001960 triggered effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000008909 emotion recognition Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000001914 calming effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/377—Electroencephalography [EEG] using evoked responses
- A61B5/378—Visual stimuli
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0641—Shopping interfaces
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Psychiatry (AREA)
- General Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Development Economics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Molecular Biology (AREA)
- Psychology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Educational Technology (AREA)
- Developmental Disabilities (AREA)
- Child & Adolescent Psychology (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a shopping system for recognizing emotion based on brain waves, which comprises a brain wave acquisition module and a shopping recommendation system thereof, wherein a brain wave sensor is worn on the head of a user, the shopping recommendation system is arranged at the background of an e-commerce website, the brain wave sensor is used for detecting the brain waves of the user, analyzing, processing and recognizing emotion, and when specific emotion is recognized, the shopping recommendation system acquires related data and accurately recommends commodities to the user; the invention is triggered when the user browses the commodities, thereby effectively saving time and improving shopping efficiency.
Description
Technical Field
The invention relates to a shopping recommendation system based on brain wave emotion recognition, and belongs to the technical field of intelligence.
Background
With the gradual expansion of the electronic commerce scale, the variety and the number of the online commodities are continuously increased, and the choice of shopping for consumers is greatly expanded. However, consumers often spend a significant amount of time finding a suitable good. This process of browsing a large amount of irrelevant information and goods will undoubtedly bring great inconvenience to the consumer.
Disclosure of Invention
The invention provides a shopping system which is triggered when a user browses commodities, so that a large amount of time is effectively saved, and shopping efficiency is improved.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the shopping recommendation system based on the brain wave emotion recognition comprises a brain wave acquisition module and a shopping recommendation system thereof, wherein a brain wave sensor in the brain wave acquisition module is worn on the head of a user, and the shopping recommendation system is deployed on a background of an e-commerce website. The brain wave sensor is used for detecting brain waves of a user, acquiring brain wave signals to obtain analog voltage signals, dividing the analog voltage signals into two paths, inputting current obtained by the current sensor into the ARM single chip microcomputer, directly inputting the other path of the current into the ARM single chip microcomputer, processing the signals to obtain phase power of beta waves and theta waves, then obtaining an absolute power ratio of the beta waves and the theta waves, establishing an emotion inference rule through a machine learning method, namely a gradient push tree (GBDT), identifying three emotions, namely positive, calm and negative, and starting a shopping recommendation system to provide recommended commodities for the user when specific emotions are identified.
As a further preferred aspect of the present invention, the brain wave acquisition module further comprises a brain wave sensor, a current sensor, and an ARM single chip microcomputer;
as a further preferable mode of the present invention, the brain wave sensor is configured to measure brain wave signals of cerebral cortex, and the brain wave signals include delta wave (1-3 Hz), theta wave (4-7 Hz), alpha wave (8-13 Hz), and beta wave (14-30 Hz), and the measurement employs a dry electrode probe, and obtains analog signals of the beta wave and the theta wave through signal amplification and filtering and then through a ThinkGearAM brain wave processing chip;
as a further preferred embodiment of the present invention, the current sensor uses a hall sensor, and is configured to convert a current value in the line into a voltage value according to a certain linear relationship, so as to input the voltage value into the ARM single chip microcomputer, and further calculate the current value in the line through the ARM single chip microcomputer;
as a further preferred embodiment of the present invention, the ARM single chip microcomputer is configured to process the voltage signal directly transmitted from the brain wave sensor and the voltage signal transmitted from the current sensor, and obtain the absolute power ratio of the β wave to the θ wave after the processing. Establishing an emotion inference rule through a machine learning method, namely a gradient push tree (GBDT), identifying three types of positive, calm and negative emotions, and finally transmitting data to a computer background through serial port communication;
as a further preferred aspect of the present invention, the shopping recommendation system further comprises a database module, a data mining module, a recommendation processing module, and a user scoring module;
as a further preferred aspect of the present invention, the database module is used for recording and storing transaction data, commodity data and user information data of a user, and preparing data for data mining at the next stage;
as a further preferred embodiment of the present invention, the data mining module is configured to integrate the information in the database module and the real-time transaction information into the recommended item. Data mining analyzes data highly automatically by various methods such as statistics, online analysis processing, intelligence retrieval, machine learning, expert systems, pattern recognition and the like, makes inductive reasoning, and excavates potentially useful information from a large amount of data. The module finds the relation between the shopping history of the user and the commodity characteristic data from the data of the database module, and then delivers the result to the recommendation processing module;
as a further preferred aspect of the present invention, the recommendation processing module is configured to execute a hybrid recommendation algorithm, and execute a corresponding algorithm in combination with an emotion to determine the recommended commodity item. The module simultaneously provides a recommendation list including the user and the favorite commodity items;
as a further preferred aspect of the present invention, the user scoring module is configured to score the recommended commodities after the user obtains the commodity recommendation list, and score the recommended commodities once each time the recommendation is completed, where the score is evaluated by recognizing emotion through brain waves detected by the system when the user browses the recommended commodities. In the present system, the recognized emotions are converted into quantitative numerical evaluations, defined as positive score of 2, calm score of 1, and vanishing score of 0. The user scoring matrix may be represented as R (m n), where m represents the number of users, n represents the number of items, and the non-zero element R in the scoring matrixijE.g. R. The user set is denoted as U ═ U1,u2,…,ui}, each item tjThe content of the E-T item set is expressed as a VSM characteristic vector fvj＝(w1j,w2j…wbj…wnj) Wherein w isbjIndicates that the b-th keyword is for item tjThe weight of (a), the weight being calculated in tf/idf mode;
selecting features with higher frequency to form a high-dimensional feature vector space, using a Widrow-Hoff learning algorithm to perform user modeling by using a gradient descent training model, and using a user uiItem s score risThen, the feature vector of the user is expressed as uvis＝(v1is,v2is,…,vbis,…,vnis) Wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiThe importance of the interest; when user uiScoring the s +1 st item ri(s+1)Then, the feature vector of the user is expressed as uvi(s+1)Updating user u at the same timeiFeature weight for j item:
wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiImportance of interest, uvisDenoted as user uiItem s score risThen, the feature vector of the user, fvsVSM feature vector, r, represented as item si(s+1)Denoted as user uiScoring item s +1, wbjExpressed as representing the b-th keyword for item tjThe weight of (c);
and finally, the system feeds the scoring result back to the recommendation processing module.
Advantageous effects
When a user browses commodities, the system analyzes and processes the detected brain waves, identifies the emotion of the user, starts the recommendation system according to the identified emotion, and recommends the commodities which are possibly loved to the user.
Drawings
FIG. 1 is a front view of a preferred embodiment of the present invention;
FIG. 2 is a block diagram of a brain wave acquisition module;
FIG. 3 is a graph of emotion to merchandise matching for a preferred embodiment of the present invention;
FIG. 4 is a system flow diagram of a preferred embodiment of the present invention;
in the figure: 1 is a brain wave sensor, and 2 is a shopping recommendation system applied to a computer.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
As shown in the front view of fig. 1, a shopping system comprises a brain wave acquisition module and a shopping recommendation system thereof, wherein a user wears equipment provided with a brain wave sensor, acquires a brain wave signal, obtains a voltage signal, and then divides the voltage signal into two paths, one path of the voltage signal is input into an ARM single chip microcomputer through the current obtained by the current sensor, the other path of the voltage signal is directly input into the ARM single chip microcomputer to obtain beta wave and theta wave power, the absolute power ratio of the beta wave and the theta wave is obtained through calculation, an emotion inference rule is established through a machine learning method, namely a gradient push tree (GBDT), relevant emotions are recognized, and when specific emotions are recognized, the shopping recommendation system obtains relevant data and provides recommended commodities for the user;
as shown in the structure diagram of the brain wave acquisition module of fig. 2, the brain wave acquisition module comprises a brain wave sensor, a current sensor and an ARM single chip microcomputer;
as a further preferable mode of the present invention, the brain wave sensor is configured to measure brain wave signals of cerebral cortex, and the brain wave signals include delta wave (1-3 Hz), theta wave (4-7 Hz), alpha wave (8-13 Hz), and beta wave (14-30 Hz), and the measurement employs a dry electrode probe, and obtains analog signals of the beta wave and the theta wave through signal amplification and filtering and then through a ThinkGearAM brain wave processing chip;
as a further preferred embodiment of the present invention, the current sensor uses a hall sensor, and is configured to convert a current value in the line into a voltage value according to a certain linear relationship, so as to input the voltage value into the ARM single chip microcomputer, and further calculate the current value in the line through the ARM single chip microcomputer;
as a further preferred embodiment of the present invention, the ARM single chip microcomputer is configured to process the voltage signal directly transmitted from the brain wave sensor and the voltage signal transmitted from the current sensor, and obtain the absolute power ratio of the β wave to the θ wave after the processing. Establishing an emotion inference rule through a machine learning method, namely a gradient push tree (GBDT), identifying three types of positive, calm and negative emotions, and finally transmitting data to a computer background through serial port communication;
as shown in fig. 3, the emotion and article matching map in the recommendation processing module is shown. For three emotions recognized by brain waves: positive, quiet and negative, and different operations are respectively carried out.
The method comprises the following steps: executing a content-based recommendation algorithm: the user set is denoted as U ═ U1,u2,…，ui,…,umAnd the item set is denoted as T ═ T1,t2,…,tj…tn}. Using the tf/idf weighting pattern, the weight of the jth item in the system for user i is obtained by the following equation:
fji＝freqji/maxtfi；
wherein freqjiRepresents an item tjAt user uiNumber of occurrences, maxtfiRepresenting user uiMaximum number of occurrences of all items in idfjRepresents an item tjThe inverse document frequency of (c).
Using Rocchio algorithm to obtain user U
Wherein IrAnd InrRespectively representing known sets of items liked and disliked by user u; while β and γ are weights that conquer feedback, their values are given by the system. Then according to the user
The corresponding goods are searched in the database. Adding similar commodities which are interested by the user into a recommendation list;
calming: performing a hybrid recommendation algorithm that combines a content-based algorithm and a collaborative filtering-based algorithm: and calculating the similarity based on the content between the users by using a CCHR algorithm on the basis of the modeling.User uiWith user ujThe similarity between the two is calculated in the form of
Wherein,
representing user uiThe mean of the weights of each feature in the feature vector. Since the similarity calculation is performed according to the latest feature vector of the user, the feature weight v in the above formulamisAre all abbreviated as vmi. A user scoring matrix R (m is multiplied by n), wherein non-zero elements rij in the scoring matrix are epsilon to R and represent users uiFor item tjThe value of (a). Set R (k) represents user ukSet of unscored items of rkj' representation to user ukUnscored item t of (1)jE, prediction score of R (k), and prediction of any user ukUnscored item t of (1)jScore for ε R (k):
wherein,
representing a target user ukThe mean value of the scores of the scored items,
representing a target user ukOf a neighboring user uiThe mean of the scores of the scored items. And finally adding the commodity items with high prediction scores into a recommendation list.
And (3) negative: at the moment, the user has no purchase desire and no operation on browsed commodities.
As shown in the system flow chart of fig. 4, the brain wave signal is acquired by wearing a brain wave sensor when a user browses commodities, the positive emotion, the calm emotion and the negative emotion are identified by a brain wave acquisition module, and then related data are transmitted to a computer background in a serial port communication mode. A data mining module in the system integrates information in a database in advance, finds the relation between the shopping history of the user and the commodity feature data, and then delivers the result to a recommendation processing module. When the emotion of the user is identified to be positive, the recommendation processing module executes a recommendation algorithm based on the content and adds similar commodities into a recommendation list; when the emotion of the user is identified to be calm, the recommendation processing module executes a mixed recommendation algorithm combining a content-based algorithm and a collaborative filtering-based algorithm, and adds commodities with high prediction scores into a recommendation list; when the emotion of the user is identified as negative, the recommendation processing module is not operated; the system then pushes the recommendation list obtained by the algorithm to the user. When the user obtains the recommendation list, the user scores the recommended commodities at the same time, and the scores are evaluated by recognizing emotion through brain waves detected by the system when the user browses the recommended commodities. And after the system scores, updating the commodity characteristic weight in the database to prepare for next recommendation.
As a further preferred aspect of the present invention, the shopping recommendation system further comprises a database module, a data mining module, a recommendation processing module, and a user scoring module;
as a further preferred aspect of the present invention, the database module is used for recording and storing transaction data, commodity data and user information data of a user, and preparing data for data mining at the next stage;
as a further preferred embodiment of the present invention, the data mining module is configured to integrate the information in the database module and the real-time transaction information into the recommended item. Data mining analyzes data highly automatically by various methods such as statistics, online analysis processing, intelligence retrieval, machine learning, expert systems, pattern recognition and the like, makes inductive reasoning, and excavates potentially useful information from a large amount of data. The module finds the relation between the shopping history of the user and the commodity characteristic data from the data of the database module, and then delivers the result to the recommendation processing module;
as a further preferred aspect of the present invention, the recommendation processing module is configured to execute a hybrid recommendation algorithm, and execute a corresponding algorithm in combination with an emotion to determine the recommended commodity item. The module simultaneously provides a recommendation list including the user and the favorite commodity items;
as a further preferred aspect of the present invention, the user scoring module is configured to score the recommended commodities after the user obtains the commodity recommendation list, and score the recommended commodities once each time the recommendation is completed, where the score is evaluated by recognizing emotion through brain waves detected by the system when the user browses the recommended commodities. In the present system, the recognized emotions are converted into quantitative numerical evaluations, defined as positive score of 2, calm score of 1, and vanishing score of 0. The user scoring matrix may be represented as R (m n), where m represents the number of users, n represents the number of items, and the non-zero element R in the scoring matrixijE.g. R. The user set is denoted as U ═ U1,u2,…,ui}, each item tjThe content of the E-T item set is expressed as a VSM characteristic vector fvj＝(w1j,w2j…wbj…wnj) Wherein w isbjIndicates that the b-th keyword is for item tjThe weight of (a), the weight being calculated in tf/idf mode; wherein wbjIndicates that the b-th keyword is for item tjThe weight of (a), the weight being calculated with the tf/idf model algorithm;
fji＝freqji/maxtfi；
wherein freqjiRepresents an item tjAt user uiNumber of occurrences, maxtfiRepresenting user uiMaximum number of occurrences of all items in idfjRepresents an item tjThe inverse document frequency of (d);
selecting features with higher frequency to form a high-dimensional feature vector space, using a Widrow-Hoff learning algorithm to perform user modeling by using a gradient descent training model, and using a user uiItem s score risThen, the feature vector of the user is expressed as uvis＝(v1is,v2is,…,vbis,…,vnis) Wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiThe importance of the interest; when user uiScoring the s +1 st item ri(s+1)Then, the feature vector of the user is expressed as uvi(s+1)Updating user u at the same timeiFeature weight for j item:
wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiImportance of interest, uvisDenoted as user uiItem s score risThen, the feature vector of the user, fvsVSM feature vector, r, represented as item si(s+1)Denoted as user uiScoring item s +1, wbjExpressed as representing the b-th keyword for item tjThe weight of (c);
and finally, the system feeds the scoring result back to the recommendation processing module.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The meaning of "and/or" as used herein is intended to include both the individual components or both.
The term "connected" as used herein may mean either a direct connection between components or an indirect connection between components via other components.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (3)
1. A shopping system based on brain wave recognition emotion comprises a brain wave acquisition module and a shopping recommendation system thereof, wherein a user wears equipment provided with a brain wave sensor, acquires a voltage signal after acquiring a brain wave signal, and then divides the brain wave signal into two paths, one path of the voltage signal is input into an ARM single chip microcomputer through the current obtained by a current sensor, the other path of the voltage signal is directly input into the ARM single chip microcomputer to obtain beta wave and theta wave power, the absolute power ratio of the beta wave and the theta wave is obtained through calculation, an emotion inference rule is established through a machine learning method, namely a gradient push tree GBDT, so that three types of emotions, namely positive, calm and negative emotions are recognized, and when the three types of emotions are recognized, the shopping recommendation system acquires related data and provides recommended commodities for the user;
the brain wave acquisition module comprises a brain wave sensor, a current sensor and an ARM single chip microcomputer;
the method is characterized in that:
the brain wave sensor is used for measuring brain wave signals when the cerebral cortex browses commodities, and comprises delta waves of 1-3 Hz, theta waves of 4-7 Hz, alpha waves of 8-13 Hz and beta waves of 14-30 Hz respectively, a dry electrode probe is adopted for measurement, and after signal amplification and filtering, the dry electrode probe is processed by a ThinkGearAM brain wave processing chip to obtain voltage signals of the beta waves and the theta waves;
the current sensor uses a Hall sensor and is used for converting a current value in a line into a voltage value according to a certain linear relation, so that the voltage value is input into the ARM single chip microcomputer, and the current value in the line is calculated through the ARM single chip microcomputer;
the ARM single chip microcomputer is used for processing a voltage signal directly transmitted from the brain wave sensor and a current signal transmitted from the current sensor, and obtaining the absolute power ratio of beta waves to theta waves after processing; an emotion inference rule is established through a machine learning method, namely a gradient boosting tree GBDT, three types of emotions, namely positive, calm and negative are identified, and finally data are transmitted to a computer background through serial port communication.
2. The system of claim 1, wherein the shopping recommendation system further comprises a database module, a data mining module, a recommendation processing module, and a user scoring module;
the database module is used for recording and storing brain wave signals of users, transaction data of the users, commodity data and user information data and preparing data for data mining at the next stage;
the data mining module is used for integrating the information in the database module and the real-time transaction information into recommended items; data mining automatically analyzes data through statistics, online analysis and processing, information retrieval, machine learning, an expert system and a pattern recognition method, makes inductive reasoning and excavates potential useful information from the data; the module finds the relation between the shopping history of the user and the commodity characteristic data from the data of the database module, and then delivers the result to the recommendation processing module;
the recommendation processing module is used for executing corresponding algorithms of active, calm and passive emotion operation and judging recommended commodity items; the module simultaneously provides a recommendation list including the user and the favorite commodity items; when the emotion of the user is identified to be positive, the recommendation processing module executes a recommendation algorithm based on the content and adds similar commodities which are interested by the user into a recommendation list; when the emotion of the user is identified to be calm, the recommendation processing module executes a mixed recommendation algorithm combining a content-based algorithm and a collaborative filtering-based algorithm, and adds commodities with high prediction scores into a recommendation list; when the emotion of the user is identified as negative, the recommendation processing module is not operated;
the user scoring module is used for scoring the recommended commodities after the user obtains the commodity recommendation list, scoring is carried out once each time the recommendation is completed, and the scoring is evaluated by recognizing emotion through brain waves detected by the system when the user browses the recommended commodities.
3. The system of claim 1, wherein in the user scoring module, the recognized emotion is translated into a quantitative numerical rating, defining a positive score of 2 full, a calm score of 1, and a vanishing score of 0; the user scoring matrix is represented as R (m × n), m represents the number of users, n represents the number of items, and the non-zero element R in the scoring matrixijE is R; the user set is denoted U ═ U1,u2,…,ui+, each item tjThe content of the E-T item set is expressed as a VSM characteristic vector fvj＝(w1j,w2j…wbj…wnj) Wherein w isbjIndicates that the b-th keyword is for item tjThe weight of (a), the weight being calculated in tf/idf mode;
selecting features with higher frequency to form a high-dimensional feature vector space, using a Widrow-Hoff learning algorithm to perform user modeling by using a gradient descent training model, and using a user uiItem s score risThen, the feature vector of the user is expressed as uvis＝(v1is,v2is,…,vbis,…,vnis) Wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiThe importance of the interest; when user uiScoring the s +1 st item ri(s+1)Then, the feature vector of the user is expressed as uvi(s+1)Updating user u at the same timeiFeature weight for j item:
wherein v isbisRepresents the b-th characteristic keyword pair description user u after the s-th item scoringiImportance of interest, uvisDenoted as user uiItem s score risThen, the feature vector of the user, fvsVSM feature vector, r, represented as item si(s+1)Denoted as user uiScoring item s +1, wbjExpressed as representing the b-th keyword for item tjThe weight of (c);
and finally, the system feeds the scoring result back to the recommendation processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711348101.8A CN108073284B (en) | 2017-12-15 | 2017-12-15 | Shopping system based on brain wave recognition emotion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711348101.8A CN108073284B (en) | 2017-12-15 | 2017-12-15 | Shopping system based on brain wave recognition emotion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108073284A CN108073284A (en) | 2018-05-25 |
| CN108073284B true CN108073284B (en) | 2021-05-04 |
Family
ID=62158820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711348101.8A Active CN108073284B (en) | 2017-12-15 | 2017-12-15 | Shopping system based on brain wave recognition emotion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073284B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002531A (en) * | 2018-07-17 | 2018-12-14 | 泉州装备制造研究所 | A kind of video display recommender system and video display recommended method based on eeg data analysis |
| CN112188597B (en) * | 2018-07-25 | 2023-11-03 | Oppo广东移动通信有限公司 | Method for creating proximity-aware network and related product |
| CN108932511B (en) * | 2018-10-09 | 2022-09-13 | 南京邮电大学 | Shopping decision method based on brain-computer interaction |
| CN109815361B (en) * | 2019-01-29 | 2023-08-08 | 南京信息工程大学 | Intelligent music recommendation system based on brain wave identification |
| CN110472395B (en) * | 2019-08-05 | 2021-04-20 | 武汉联影医疗科技有限公司 | Brain wave data processing method, device, equipment, medium and brain wave data processor |
| CN112435083A (en) * | 2019-08-26 | 2021-03-02 | 珠海格力电器股份有限公司 | Article recommendation method based on brain wave recognition and electronic equipment |
| CN113807904B (en) * | 2020-06-17 | 2024-10-22 | 北京沃东天骏信息技术有限公司 | Item recommendation method, device and system, computer system and storage medium |
| CN113421141A (en) * | 2020-07-29 | 2021-09-21 | 阿里巴巴集团控股有限公司 | Shopping processing method and device based on brain-computer and brain nerve signals and electronic equipment |
| CN112597838B (en) * | 2020-12-14 | 2024-06-07 | 吉林市不凡时空科技有限公司 | Multidimensional emotion semantic recognition system based on brain waves and processing method thereof |
| CN112333215B (en) * | 2021-01-06 | 2021-05-07 | 浙江育英职业技术学院 | Commodity recommendation method based on block chain system, storage medium and electronic equipment |
| CN113409123A (en) * | 2021-07-01 | 2021-09-17 | 北京沃东天骏信息技术有限公司 | Information recommendation method, device, equipment and storage medium |
| CN115064022A (en) * | 2022-03-25 | 2022-09-16 | 深圳尼古拉能源科技有限公司 | Enhanced perception experience platform and use method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101133845B1 (en) * | 2010-10-19 | 2012-04-06 | 성균관대학교산학협력단 | Method for creating brainwave signal database |
| CN105045898A (en) * | 2015-08-03 | 2015-11-11 | 东南大学 | Electroencephalographic earphone based dynamic personalized song recommendation system and method therefor |
| CN107123019A (en) * | 2017-03-28 | 2017-09-01 | 华南理工大学 | A kind of VR shopping commending systems and method based on physiological data and Emotion identification |
| CN107320114A (en) * | 2017-06-29 | 2017-11-07 | 京东方科技集团股份有限公司 | Shooting processing method, system and its equipment detected based on brain wave |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101690659B (en) * | 2009-09-29 | 2012-07-18 | 华东理工大学 | Brain wave analysis method |
| CN103885445B (en) * | 2014-03-20 | 2016-05-11 | 浙江大学 | The brain control method of a kind of brain control animal robot system and animal robot |
-
2017
- 2017-12-15 CN CN201711348101.8A patent/CN108073284B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101133845B1 (en) * | 2010-10-19 | 2012-04-06 | 성균관대학교산학협력단 | Method for creating brainwave signal database |
| CN105045898A (en) * | 2015-08-03 | 2015-11-11 | 东南大学 | Electroencephalographic earphone based dynamic personalized song recommendation system and method therefor |
| CN107123019A (en) * | 2017-03-28 | 2017-09-01 | 华南理工大学 | A kind of VR shopping commending systems and method based on physiological data and Emotion identification |
| CN107320114A (en) * | 2017-06-29 | 2017-11-07 | 京东方科技集团股份有限公司 | Shooting processing method, system and its equipment detected based on brain wave |
Non-Patent Citations (1)
| Title |
|---|
| "脑电信号在情感识别中的应用 ";陈曾，刘光远;《计算机工程》;20100622;第36卷(第9期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108073284A (en) | 2018-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108073284B (en) | Shopping system based on brain wave recognition emotion | |
| CN108665333B (en) | Commodity recommendation method and device, electronic equipment and storage medium | |
| Patel et al. | Sentiment analysis of customer feedback and reviews for airline services using language representation model | |
| CN101661487B (en) | Method and system for searching information items | |
| Shi et al. | Enhanced customer requirement classification for product design using big data and improved Kano model | |
| CN105183727A (en) | Method and system for recommending book | |
| Chemchem et al. | Combining SMOTE sampling and machine learning for forecasting wheat yields in France | |
| Chen et al. | A novel classification method based on ICGOA-KELM for fault diagnosis of rolling bearing | |
| Badriyah et al. | A hybrid recommendation system for E-commerce based on product description and user profile | |
| CN108932511B (en) | Shopping decision method based on brain-computer interaction | |
| KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
| CN107895303A (en) | A kind of method of the personalized recommendation based on OCEAN models | |
| Xia et al. | Fault diagnosis of flexible production line machining center based on PCA and ABC-LVQ | |
| Pourmostaghimi et al. | Designing and implementation of a novel online adaptive control with optimization technique in hard turning | |
| CN110020195B (en) | Article recommendation method and device, storage medium and electronic equipment | |
| Ahmed et al. | Improving prediction of plant disease using k-efficient clustering and classification algorithms | |
| KR101468457B1 (en) | method for smart searching of goods | |
| CN112488355A (en) | Method and device for predicting user rating based on graph neural network | |
| Siswandi et al. | Application of the C 4.5 Algorithm to Classify Customer Characteristics at PT. Bayer Indonesia | |
| Boukrouh et al. | Personalized fashion product recommendations using transfer learning and nearest neighbors models | |
| JP2003122572A (en) | Data analyzer and recording medium | |
| KR20150020490A (en) | Device for calculating of goods price, method for calculating of goods price and method for providing goods information using the same | |
| Feng et al. | The construction of a three-dimensional human body based on semantic-driven parameters to improve virtual fitting | |
| Thuan et al. | Hybrid recommender system with review helpfulness features | |
| Tsao et al. | Intelligent Design Suggestion and Sales Forecasting for New Products in the Apparel Industry |
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 |