Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hospital outpatient flow prediction method based on capsule network

A prediction method and people flow technology, applied in the direction of forecasting, neural learning methods, biological neural network models, etc., can solve the problems of no change in people flow, high implementation cost, and no coverage of people flow, so as to improve medical experience and save money. The effect of investment and optimization of resource allocation

Pending Publication Date: 2021-01-22
NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this technology is that it can only judge the flow of people at that time. There is a certain path from the installation position of the camera to each department and there are diversions and confluences. The real-time data obtained by the camera does not cover the flow of people after a large number of patients arrive at specific departments. It is not possible to predict changes in the flow of people in the future; at the same time, each entrance is equipped with a shooting device, which brings high implementation costs

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
  • Hospital outpatient flow prediction method based on capsule network
  • Hospital outpatient flow prediction method based on capsule network
  • Hospital outpatient flow prediction method based on capsule network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The execution flow of step S200 is as follows figure 2 As shown, including the following sub-steps:

[0058] S201. Summarize the number of registrations and the flow of people in each department according to a certain time step, wherein: the value range of the time step is 1 to 10 minutes; the main source of the change in the flow of people in a department is new registration and the end of diagnosis and treatment, so Extracting registration data and real-time people flow data can retain the main source of power for the future evolution of people flow;

[0059] S202. Generate a two-dimensional matrix representing the relationship between time, departments, number of registrations in departments, and flow of people;

[0060] S203. Normalize the two-dimensional matrix, and output a class of sample matrix, wherein: the dimensions of the class of sample matrix include time and department, and its values ​​are normalized department registration volume and normalized traffi...

Embodiment 2

[0085] Step S4 also includes the following sub-steps, such as Figure 5 Shown:

[0086] S403. Compare the flow of people in each department predicted in the model application stage with the subsequent actual flow of people. When the error MRE range exceeds the specified value, automatically stop the model application, and repeat steps S100 to S400. Model training, tuning and application Each process; the error range interval is 1% to 5%.

Embodiment 3

[0088] S402 The predicted traffic data is sent to the mobile App through the 4G network.

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 a hospital outpatient flow prediction method based on a capsule network, and the method comprises the steps: firstly extracting historical data from a hospital registration system and an outpatient system, then carrying out the data conversion, model training and optimization, and obtaining a capsule network model with an average relative error MRE meeting the requirementsof a specified index; and according to the extracted real-time visitor flow rate of each department at a certain moment, predicting the visitor flow rate of each department in a future period of timeso as to accurately predict the visitor flow rate of each department in the future period of time based on the registration amount and the visitor flow rate provided by the hospital registration system and the outpatient service system, so that the camera investment is save, the user experience is improved, the hospital can reasonably utilize resources, the patient can autonomously determine the medical period, and the medical experience is improved.

Description

technical field [0001] The present invention relates to the technical field of smart medical treatment and flow forecasting, in particular to a method for predicting the flow of people in outpatient clinics based on a capsule network. Background technique [0002] At present, due to the unbalanced allocation of medical resources in our country, the huge flow of people in large hospitals and the limited resources of community hospitals have led to "difficulty in seeing a doctor", continued tension between doctors and patients, and frequent occurrence of "doctor-patient conflicts". At the same time, patients do not understand the flow of people in hospitals, and large Hospitals are often overcrowded with people, and the patient experience is poor. For this reason, efficient people flow forecasting is an effective way to solve the problem: on the one hand, the hospital adjusts internal staffing according to the predicted people flow to rationally use resources; Choose the righ...

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): G06Q10/04G06K9/62G06N3/04G06N3/08G06N20/20
CPCG06Q10/04G06N3/08G06N20/20G06N3/045G06F18/214
Inventor 亓晋许会芬孙莹孙雁飞
Owner NANJING NANYOU INST OF INFORMATION TECHNOVATION CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com