System for screening tourism geographic information based on electroencephalogram signals

Abstract

The invention discloses a tourism geographic information screening system based on electroencephalogram signals. The tourism geographic information screening system comprises a data acquisition module, a machine vision module, a microprocessor, a mobile device, a geographic information module and a data feedback module. Wherein the data acquisition module, the machine vision module, the geographic information module and the machine identification module are respectively connected with the microprocessor; according to the method, interests and responses of individuals are monitored in real time, and geographic information analysis is combined, so that intelligence and individuation of a travel destination selection process are realized. The technology has a wide application prospect in the field of tourist industry and personalized recommendation.

Description

Technical Field

[0001] The present invention relates to the technical field of electroencephalogram signals, and in particular to a tourism geographic information system based on electroencephalogram signals for screening. Background Art

[0002] In today's society, as people's material living standards improve, their pursuit of spirituality becomes more and more significant. In this era, the tourism industry is booming and the demand for personalized tourism is increasing. Although travel agencies, various travel apps and platforms provide convenience for consumers and save time and money, the reality is not perfect. Excessive commercialization leads to distorted packaging of scenic spots, and problems such as uneven service quality still exist, which ultimately leads to the failure of tourism services to truly meet the needs of consumers. For example, big data uses a variety of information sources to recommend tourist destinations, including analyzing search records, social media activities and geographic location information. By analyzing users' past travel booking records, similar tourist destinations and itineraries are recommended to them to provide more personalized travel suggestions. But at present, first, this method cannot effectively protect consumers' privacy. Second, the way big data recommends tourist destinations defaults to consumers' consumption habits and travel habits. Its recommended content not only changes slowly but is often the same, wrapping consumers in an information cocoon. Consumers cannot get a fresh travel experience, which makes it impossible to immerse themselves in the deep spiritual enjoyment brought by travel. Summary of the invention

[0003] Purpose of the invention: The purpose of the present invention is to provide a tourism geographic information system based on EEG signals to solve the problems existing in the background technology.

[0004] Technical solution: The tourism geographic information system based on EEG signal screening described in the present invention includes: a data acquisition module, a machine vision module, a microprocessor, a mobile device, a geographic information module and a data feedback module; wherein the data acquisition module, the machine vision module, the geographic information module and the machine recognition module are respectively connected to the microprocessor.

[0005] Furthermore, the machine vision module is used to receive and analyze the pre-processed EEG data transmitted by the microprocessor, and retrieve the destination through the geographic information system; it includes: an image segmentation module and a convolutional neural module.

[0006] Furthermore, the image segmentation module is used to extract image information from the preprocessed EEG data through an image segmentation algorithm; the convolutional neural module calculates the proportion of each category in the entire image by counting the number of pixels or area of ​​each category, and is used to sort the final scores of the landform types from high to low to obtain the landform data that best matches the user's interests.

[0007] Furthermore, the data acquisition module is used to collect the original data of delta waves, theta waves, alpha waves, beta waves, and gamma waves and send them to the microprocessor; it includes an EEG sensor and a brain-computer interface; wherein the EEG interface is used to extract the amplitude and frequency of the EEG signal; and the EEG sensor is used to collect the EEG signal.

[0008] Furthermore, the cloud processing module is used to process the extracted EEG data to remove noise, filtering and artifacts; it includes a Butterworth filter module, a baseline correction module, a wavelet transform module, and an independent component analysis ICA module.

[0009] Furthermore, Butterworth filter is used to filter the extracted EEG data; baseline correction is used to solve the problem of baseline drift; wavelet transform is used for noise filtering; independent component analysis ICA is used to remove EEG artifacts Furthermore, the geographic information system is used to utilize the digital elevation model DEM or the digital terrain model DTM; and is used to determine the specific location of the destination using the GPS or Beidou high-definition navigation system.

[0010] Furthermore, the specific process of the image segmentation algorithm is as follows: (S1) Initialization: Select K initial cluster center points. K samples in the data set can be randomly selected as the initial center points.

[0011] (S2) Assign samples: For each sample in the data set, calculate its distance from the K center points and assign the sample to the category represented by the nearest center point.

[0012] (S3) Update the center point: For each category, calculate the mean of all samples in that category and use the mean as the new center point.

[0013] (S4) Repeat step S2 and step S3: Repeat sample allocation and center point update until a stop condition is met (for example, the maximum number of iterations is reached or the center point no longer changes).

[0014] Output result: Finally, we get K categories and the category information to which each sample belongs.

[0015] Furthermore, the specific process of using the convolutional neural network algorithm is as follows: (S5) Data Collection: First, collect image datasets containing landform elements such as forests, deserts, lakes, mountains, etc. These images should be labeled with corresponding categories so that they can be used for training and testing models.

[0016] (S6) Data preprocessing: Preprocess the image data, including resizing, normalization, cropping, etc.

[0017] (S7) Construct a CNN model: Construct a CNN model, including convolutional layers, pooling layers, and fully connected layers.

[0018] (S8) Model training: The CNN model is trained using the collected image dataset. During the training process, the model will learn to extract the features of different landform elements in the image.

[0019] (S9) Model evaluation: The trained model is evaluated using another independent image dataset to assess its performance in identifying geomorphic elements.

[0020] (S10) Model application: After model training and evaluation are completed, it is applied to new images to identify geomorphic elements in the images.

[0021] Furthermore, the microprocessor is used to receive information from the geographic information module and the machine identification module; to receive information from the data acquisition module; to transmit and receive information from the cloud processing module; and to transmit the destination of interest to the mobile device.

[0022] Beneficial effects: Compared with the existing technology, the present invention has the following significant advantages: by real-time monitoring of individual interest responses and combining geographic information analysis, the process of selecting tourist destinations can be made intelligent and personalized. This technology has broad application prospects in the tourism industry and personalized recommendation fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a structural schematic diagram of the present invention; Figure 2 It is a schematic diagram of the implementation of the present invention; Figure 3 This is a sample of the measured EEG data of the present invention; Figure 4 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is further described below in conjunction with the accompanying drawings.

[0025] like Figure 1-4As shown, an embodiment of the present invention provides a tourism geographic information system based on EEG signal screening, including: a data acquisition module, a machine vision module, a microprocessor, a mobile device, a geographic information module and a data feedback module; wherein the data acquisition module, the machine vision module, the geographic information module and the machine recognition module are respectively connected to the microprocessor; the machine vision module is used to receive and analyze the pre-processed EEG data transmitted by the microprocessor, and retrieve the destination through the geographic information system; including: an image segmentation module and a convolutional neural module; the image segmentation module is used to extract image information from the pre-processed EEG data through an image segmentation algorithm; the convolutional neural module calculates the proportion of each category in the entire image by counting the number of pixels or area of ​​each category, and is used to sort the final scores of the landform types from high to low to obtain the landform data that best matches the user's interests; The specific process of the image segmentation algorithm is as follows: (S1) Initialization: Select K initial cluster center points. K samples in the data set can be randomly selected as the initial center points.

[0026] (S2) Assign samples: For each sample in the data set, calculate its distance from the K center points and assign the sample to the category represented by the nearest center point.

[0027] (S3) Update the center point: For each category, calculate the mean of all samples in that category and use the mean as the new center point.

[0028] (S4) Repeat step S2 and step S3: Repeat sample allocation and center point update until a stop condition is met (for example, the maximum number of iterations is reached or the center point no longer changes).

[0029] Output result: Finally, we get K categories and the category information to which each sample belongs.

[0030] The specific process of using the convolutional neural network algorithm is as follows: (S5) Data Collection: First, collect image datasets containing landform elements such as forests, deserts, lakes, mountains, etc. These images should be labeled with corresponding categories so that they can be used for training and testing models.

[0031] (S6) Data preprocessing: Preprocess the image data, including resizing, normalization, cropping, etc.

[0032] (S7) Construct a CNN model: Construct a CNN model, including convolutional layers, pooling layers, and fully connected layers.

[0033] (S8) Model training: The CNN model is trained using the collected image dataset. During the training process, the model will learn to extract the features of different landform elements in the image.

[0034] (S9) Model evaluation: The trained model is evaluated using another independent image dataset to assess its performance in identifying geomorphic elements.

[0035] (S10) Model application: After model training and evaluation are completed, it is applied to new images to identify geomorphic elements in the images.

[0036] The data acquisition module is used to collect the original data of delta wave, theta wave, alpha wave, beta wave and gamma wave and send them to the microprocessor; it includes an electroencephalogram sensor and a brain-computer interface; the electroencephalogram interface is used to extract the amplitude and frequency of the electroencephalogram signal; the electroencephalogram sensor is used to collect the electroencephalogram signal.

[0037] The cloud processing module is used to process the extracted EEG data, remove noise, filter and artifacts; it includes Butterworth filter module, baseline correction module, wavelet transform module and independent component analysis ICA module. Butterworth filter is used to filter the extracted EEG data; baseline correction is used to solve the problem of baseline drift; wavelet transform is used for noise filtering; independent component analysis ICA is used to remove EEG artifacts The geographic information system is used to utilize the digital elevation model DEM or the digital terrain model DTM; it is used to determine the specific location of the destination using the GPS or Beidou high-definition navigation system.

[0038] The microprocessor is used to receive information from the geographic information module and the machine identification module; to receive information from the data acquisition module; to transmit and receive information from the cloud processing module; and to transmit the destination of interest to the mobile device.

Claims

1. A tourism geographic information system based on electroencephalogram signals, characterized in that: It includes: a data acquisition module, a machine vision module, a microprocessor, a mobile device, a geographic information module and a data feedback module; wherein the data acquisition module, the machine vision module, the geographic information module and the machine recognition module are respectively connected to the microprocessor.

2. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The machine vision module is used for receiving and analyzing the pre-processed EEG data transmitted by the microprocessor, and retrieving the destination through the geographic information system; it includes: an image segmentation module and a convolutional neural module.

3. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The image segmentation module is used to extract image information from the pictures seen by the user through the image segmentation algorithm; the convolutional neural module calculates the proportion of each category in the entire image by counting the number of pixels or area of ​​each category, and is used to sort the final scores of the landform types from high to low to obtain the landform data that best matches the user's interests.

4. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The data acquisition module is used to collect the original data of delta wave, theta wave, alpha wave, beta wave and gamma wave and send them to the microprocessor; it includes an electroencephalogram sensor and a brain-computer interface; the electroencephalogram interface is used to extract the amplitude and frequency of the electroencephalogram signal; the electroencephalogram sensor is used to collect the electroencephalogram signal.

5. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The cloud processing module is used to process the extracted EEG data to remove noise, filtering and artifacts; it includes a Butterworth filter module, a baseline correction module, a wavelet transform module, and an independent component analysis (ICA) module.

6. The tourism geographic information system based on electroencephalogram signal screening according to claim 3 is characterized in that: Butterworth filter is used to filter the extracted EEG data; baseline correction is used to solve the problem of baseline drift; wavelet transform is used for noise filtering; independent component analysis ICA is used to remove EEG artifacts.

7. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The geographic information system is used to use the digital elevation model DEM or digital terrain model DTM to finally determine and locate the destination; it is used to use GPS or Beidou high-definition navigation system to determine the specific location of the destination.

8. The tourism geographic information system based on electroencephalogram signal screening according to claim 3 is characterized in that: The specific process of the image segmentation algorithm is as follows: (S1) Initialization: Select K initial cluster center points. K samples in the data set can be randomly selected as the initial center points. (S2) Assign samples: For each sample in the data set, calculate its distance from the K center points and assign the sample to the category represented by the nearest center point; (S3) Update the center point: For each category, calculate the mean of all samples in that category and use the mean as the new center point; (S4) Repeat steps S2 and S3: repeat sample allocation and center point update until the stop condition is met; output result: finally obtain K categories and the category information to which each sample belongs.

9. The tourism geographic information system based on electroencephalogram signal screening according to claim 3 is characterized in that: The specific process of using the convolutional neural network algorithm is as follows: (S5) Data collection: First, collect image datasets containing landform elements such as forests, deserts, lakes, mountains, etc. These images should be labeled with corresponding categories so that they can be used for training and testing models; (S6) Data preprocessing: preprocessing the image data, including resizing, normalization, cropping, etc.; (S7) Constructing a CNN model: constructing a CNN model, including convolutional layers, pooling layers, and fully connected layers; (S8) Model training: Use the collected image dataset to train the CNN model. During the training process, the model will learn to extract the features of different landform elements in the image; (S9) Model evaluation: The trained model is evaluated using another independent image dataset to assess its performance in identifying geomorphic elements; (S10) Model application: After model training and evaluation are completed, it is applied to new images to identify geomorphic elements in the images.

10. The tourism geographic information system based on electroencephalogram signal screening according to claim 1 is characterized in that: The microprocessor is used to receive information from the geographic information module and the machine identification module; Used to receive information from the data acquisition module; Used to transmit and receive information from the cloud processing module; used to transmit the destination of interest to the mobile device.

Images