Method for identifying voice advice of doctor

A technology of voice recognition and recognition method, which is applied in the field of recognition, can solve problems such as unclear content of wills and heavy workload, and achieve the effects of ensuring clear completion, saving time, and clear doctor's orders

Inactive Publication Date: 2018-12-18
成都赫思维信科技有限责任公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is that the doctor writes the doctor's order by hand, and the workload is heavy, and the content of the will is prone to be unclear. The problem

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] Physician of the present invention uses voice doctor's order recognition method, comprises the following steps:

[0024] S1, collecting the doctor's voice;

[0025] S2. Convert the doctor's voice collected in step S1 into text data, and store the text data;

[0026] S3. Perform error correction on the text data converted in step S2, and check the error correction list that has recorded the association of several original vocabulary-deviation vocabulary. If the deviation vocabulary exists in the text data, error correction is carried out, and the text data after error correction is found to be the preliminary speech recognition result;

[0027] S4. Convert the preliminary speech recognition result obtained in step S3 into speech, and the doctor judges whether the speech converted from the preliminary speech recognition result is the same as the speech entered in step S1; if they are the same, the preliminary speech recognition result is used as the final speech recognit...

Embodiment 2

[0032] Based on embodiment 1, the method for generating the error correction list described in step S2 includes the following steps: collect the original vocabulary, obtain deviation vocabulary similar to the pronunciation of the original vocabulary according to the pronunciation of the original vocabulary, and associate an original vocabulary with all similar pronunciations Deviation vocabulary, all original words and associated deviation vocabulary generate an error correction list.

Embodiment 3

[0034] Based on the above-mentioned embodiment, when the final speech recognition result is output by the patient in step S4, the final speech recognition result is converted into speech and output. When outputting the final voice recognition result to the patient, the output mode of text data or the mode of voice can be adopted.

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 method for identifying the voice advice of a doctor. The method comprises the steps of acquiring a doctor voice; converting the acquired doctor voice into text data and storing the text data; correcting the converted text data, and determining the corrected text data as a preliminary voice recognition result; converting the obtained preliminary voice recognition result into a voice, and enabling a doctor to determine whether the voice converted from the preliminary voice recognition result is the same as the input voice; if so, outputting the preliminary voice recognition result to a patient as a final voice recognition result; if not, enabling the doctor to find a corresponding erroneous word in the text data according to an erroneous word in the voice, to manually modify the erroneous word, and to output the modified text data to the patient as the final voice recognition result. The method inputs the doctor's advice by means of voice, and can ensure the clearness and the completion of the doctor's advice.

Description

technical field [0001] The invention relates to a recognition method, in particular to a doctor's voice medical order recognition method. Background technique [0002] A doctor's order is a doctor's instructions to a patient in terms of diet, medication, and laboratory tests according to the needs of the disease and treatment. A doctor's order refers to a medical order issued by a doctor in medical activities. The content of the doctor's order and the start and stop time should be written by the doctor. The content of the doctor's order should be accurate and clear, and each doctor's order should contain only one content, and the time of issue should be indicated, which should be specific to the minute. It is divided into three categories: long-term doctor's order, temporary doctor's order and backup doctor's order. [0003] Physicians have many patients, and the complexity of each patient's medical order is different. The doctor's handwriting speed is slow, and each pers...

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
IPC IPC(8): G10L15/26G10L15/22G10L15/20G06F17/27
CPCG06F40/232G10L15/20G10L15/22G10L15/26G10L2015/226
Inventor 张浩
Owner 成都赫思维信科技有限责任公司
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