Identification method and device for application scenario of mobile terminal

A mobile terminal and application scene technology, applied in the field of data processing, can solve the problems of high recognition cost, low recognition accuracy, complex recognition algorithm, etc., and achieve the effect of simple recognition algorithm, low cost of scene recognition, and high recognition accuracy

Inactive Publication Date: 2018-12-07
南京宽塔信息技术有限公司
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem to be solved by the present invention is to provide a mobile terminal application scene recognition method and device in order to overcome the defects of high cost, complex recognition algorithm and low recognition accuracy of mobile terminal indoor and outdoor scene recognition 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
  • Identification method and device for application scenario of mobile terminal
  • Identification method and device for application scenario of mobile terminal
  • Identification method and device for application scenario of mobile terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] This embodiment provides a method for identifying application scenarios of a mobile terminal, wherein the mobile terminal includes a terminal state detection module, such as figure 1 As shown, the identification methods of mobile terminal application scenarios include:

[0055] Step 101. Obtain the first time-series state data collected by the terminal state detection module in a preset application scenario.

[0056] The terminal state detection module includes at least one of a magnetic sensor, an acceleration sensor, an air pressure sensor, a brightness sensor, a gyroscope sensor, a temperature sensor, a GPS positioning module, a Wi-Fi module, and a base station module.

[0057] The preset application scenarios include indoor and outdoor, and / or, the motion state of the mobile terminal, and the motion state includes at least one of stationary, walking, exercise, and riding a vehicle, and / or, the placement state of the mobile terminal, and the placement state includes ...

Embodiment 2

[0077] This embodiment provides a method for identifying an application scene of a mobile terminal. When the preset application scene includes at least two of indoor and outdoor, the motion state of the mobile terminal, and the placement state of the mobile terminal, the deep neural network model is a multi-task deep neural network model. Network model, the difference between this embodiment and embodiment 1 is that, as Figure 5 As shown, step 103 includes:

[0078] 103'. Set the first time window data with a corresponding scene label according to each corresponding preset application scene.

[0079] Step 104 includes:

[0080] 104'. Taking the first time window data as input and using the corresponding multiple scene labels as output to train a multi-task deep neural network model to obtain a multi-scene scene prediction model output.

[0081]In the training phase, a certain amount of state data needs to be collected through the terminal state detection module. In order to...

Embodiment 3

[0086] This embodiment provides an identification device for an application scene of a mobile terminal. The mobile terminal includes a terminal state detection module, such as Figure 7 As shown, the mobile terminal application scene recognition device includes a sample collection module 201, a first time window module 202, a label setting module 203, a model training module 204, a prediction data collection module 205, a second time window module 206 and a prediction module 207.

[0087] The sample collection module 201 is used to obtain the first time series state data collected by the terminal state detection module in a preset application scenario.

[0088] The terminal state detection module includes at least one of a magnetic sensor, an acceleration sensor, an air pressure sensor, a brightness sensor, a gyroscope sensor, a temperature sensor, a GPS positioning module, a Wi-Fi module, and a base station module.

[0089] The preset application scenarios include indoor and ...

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

No PUM Login to view more

Abstract

The invention discloses an identification method and device for an application scenario of a mobile terminal. The mobile terminal comprises a terminal state detection module, and the identification method comprises the following steps: acquiring first time sequence state data acquired by the terminal state detection module in a preset application scenario; segmenting the first time sequence statedata by taking a preset time period as a unit, and obtaining first time window data; setting a corresponding scenario label for the first time window data according to a corresponding preset application scenario; training a deep neural network and obtaining a scenario prediction model; acquiring second time sequence state data acquired by the terminal state detection module in a to-be-predicted application scenario; segmenting the second time sequence state data by taking the preset time period as the unit, and obtaining second time window data; and inputting the second time window data into the scenario prediction model, and obtaining a scenario label of the to-be-predicted application scenario. The identification method disclosed by the invention has the advantages of simple data processing procedure, simple identification algorithm and high identification accuracy rate.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a method and device for identifying application scenarios of mobile terminals. Background technique [0002] The mining of scene information can provide important environmental information for upper-layer applications. For example, in the communication process, mobile terminal equipment needs to work in a good environment, and different environments may affect the quality of communication. For operators, scene recognition can help their network performance diagnosis. Moreover, the current mobile terminal has become an important platform for environment perception and crowd communication. Effective indoor and outdoor scene recognition methods can provide useful environmental information for terminal equipment applications, thereby effectively improving the communication quality of mobile terminals. For example, based on location services, GPS (Global Positioning System) can...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H04M1/725
CPCH04M1/72454
Inventor 邓红峰
Owner 南京宽塔信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap