Unlock instant, AI-driven research and patent intelligence for your innovation.
A method and device for identifying geographic information based on deep learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of deep learning and geographic information, applied in the field of geographic information identification, can solve the problem of low accuracy of geographic information identification, achieve the effect of solving low identification accuracy, precise geographic information identification, and improving efficiency and accuracy
Inactive Publication Date: 2021-01-01
WUHAN UNIV
View PDF4 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] In view of this, the present invention provides a method and device for identifying geographic information based on deep learning to solve or at least partially solve the technical problem of low accuracy in identifying geographic information in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0051] This embodiment provides a method for identifying geographic information based on deep learning, please refer to figure 1 , the method includes:
[0052] First, step S1 is executed: obtaining raw data including geographic information.
[0053] Specifically, raw data can be obtained through existing tools or from existing databases. For example, get it from the network through a crawler.
[0054] Then execute step S2: preprocessing the original data.
[0055] Specifically, due to duplication or errors in the acquired raw data, in order to ensure the quality of the annotation, these data need to be preprocessed, such as data screening, cleaning, etc.
[0056] Next, step S3 is executed: labeling the preprocessed data to form a corpus.
[0057] Specifically, the way of labeling can be manual labeling, automatic labeling or a combination of both. Among them, the automatic labeling method can adopt an active learning strategy, that is, according to the preset selection r...
Embodiment 2
[0156] This embodiment provides a recognition device based on deep learning geographic information, please refer to Figure 9 , the device consists of:
[0157] An acquisition module 601, configured to acquire raw data containing geographical information;
[0158] A preprocessing module 602, configured to preprocess the raw data;
[0159] Annotation module 603, configured to annotate the preprocessed data to form a corpus;
[0160] The training module 604 is used to input the corpus into the deep learning model to train the deep learning model, wherein the deep learning model is BiLSTM+CRF+AGG, including a feature embedding layer, a bidirectional LSTM layer, a BiLSTM output layer, a CRF layer, and a quasi-output layer Layer, aggregation layer and final output layer, AGG is the added aggregation layer;
[0161] The recognition module 605 is configured to input the data containing geographic information to be processed into the trained deep learning model, and aggregate adjac...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The present invention provides a method and device for identifying geographic information based on deep learning. Based on the BiLSTM+CRF deep neural network model, an aggregation layer suitable for fine-grained labeling strategies is added to form a unique geographic information analysis model (BiLSTM+CRF +AGG), and after careful improvement and optimization, the system has a strong fault-tolerant ability, and realizes more accurate geographic location information recognition on irregular, incomplete and typos in the text information; and developed several complete and The auxiliary systems are independent of each other, and also realize the components with stable performance and complete functions, seamlessly apply the deep learning model developed by python to the windows development platform, and friendly support the secondary development of mainstream languages such as C++, C#, java, etc. , realizing the implementation from research to application. The technical effect of improving the accuracy of recognition is achieved.
Description
technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and device for identifying geographic information based on deep learning. Background technique [0002] With the increasing improvement of the national economy, especially the vigorous development of the e-commerce industry, whether it is for social security considerations, or for business optimization management, cost reduction and efficiency improvement considerations, the user's geographical location information is accurately and quickly Analytics is getting more and more attention. [0003] However, due to the rapid growth of user data and the ever-changing changes in geographic information, especially the channels for collecting data are diverse and random due to historical reasons and work scenarios and other factors, resulting in user information There are many problems, mainly in the two aspects of "lack of standardization of geographic i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More