Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent reminding method and device and medium

An intelligent reminder and time slot technology, applied in the computer field, can solve problems such as difficulty in identifying users, ignoring the needs of users to set reminders, etc., and achieve the effect of improving accuracy

Active Publication Date: 2019-06-28
江苏瑞焕激光科技有限公司
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, there are still many defects in the new setting method, such as: when the user's voice sets the reminder, the voice (sentence structure) input by the user varies greatly, which makes it difficult for the device to recognize the user's intention
For another example, it is possible that the user's intention to set a reminder is hidden in the user's voice, and the device does not correctly obtain the user's intention and ignore the user's need to set a reminder

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
  • Intelligent reminding method and device and medium
  • Intelligent reminding method and device and medium
  • Intelligent reminding method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] An intelligent reminder method, such as figure 1 shown, including the following steps:

[0046] S1: receiving the voice signal input by the user;

[0047] S2: Preprocessing the voice signal to obtain user intention information and time information in the voice signal;

[0048] Among them, such as figure 2 As shown, the preprocessing of the voice signal to obtain user intention information and time information in the voice signal specifically includes:

[0049] S11: Using ASR to identify the voice signal, and convert the voice signal into text information;

[0050] S12: Perform word segmentation processing on the text information to obtain multiple word strings;

[0051] S13: Extract the user intention information and time information from the word string.

[0052] This method converts voice information into text signals, then performs word segmentation, and extracts user intent and reminder time. The user intention information is used to indicate what the user wa...

Embodiment 2

[0060] Embodiment 2 adds a method of defining time slots on the basis of Embodiment 1:

[0061] The if the user intention information is a reminder specifically includes:

[0062] Retrieve whether there is a phrase identical to the user's intention information in the preset intention library;

[0063] If it exists, disambiguate the user intent information according to the context of the user intent information;

[0064] If the disambiguated user intention information points to the intention of ordering a reminder, define the user intention information as a reminder;

[0065] Specifically, the intention library includes a plurality of phrases, such as: remind, book, call, set, fix and so on. The method also judges the user's intention after disambiguating the user's intention information, which improves the accuracy of user's intention judgment. For example: the user enters "book a taxi at 2 o'clock tomorrow afternoon", and after word segmentation, the word "book" is obtaine...

Embodiment 3

[0078] Embodiment 3 On the basis of Embodiment 2, an error reporting function is added.

[0079] For the time slot set in the second embodiment, if an error occurs in the filled time slot, the values ​​of tfy, tpd, uc, and tpt are empty. For example, an example of parameters passed at this time: {'tfy':",'tpd':",'uc':",'tpt':",'error_type':'...'}. error_type is used to identify the type of error.

[0080] For example, the value range of error_type includes:

[0081] ① "tfy_time_undefined", that is, the tfy time is uncertain, for example: the user enters "wake me up every working day", since each working day does not belong to the definite time frequency, so the tfy time is uncertain and an error is reported, the user should input the number of times per day Time, which day of the week, or which day of the month, etc. to determine the frequency of reminders.

[0082] ②"tpt_time_undefined", that is, the tpt time is uncertain, for example: the user enters "remind me to go out ...

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 provides an intelligent reminding method and device and a medium. The method comprises the following steps: receiving a voice signal input by a user; preprocessing the voice signal to obtain user intention information and time information in the voice signal; if the user intention information is reminding, filling a preset time slot with the time information; if an error exists in the filled time slot, emptying the filled time slot, and generating reply information to inquire the user to perform setting again; and setting a reminder according to the filled time slot. The method analyzes voice information input by a user, and obtains user intention information and time information. According to the technical scheme, the time slot is filled with the time information through theslot filling and conversation management technology in natural language processing, when the filled time slot information is correct, reminding is set according to the filled time information in thetime slot, different grammar habits of a user can be adapted, and the accuracy of voice reminding setting is improved.

Description

technical field [0001] The invention belongs to the field of computers, and in particular relates to an intelligent reminder method, device and medium. Background technique [0002] When traditionally using a mobile terminal to set a reminder, the user manually presses a button or toggles a button to set it on the mobile terminal. With the evolution and iteration of technology, existing mobile terminals begin to support users to set reminders in more ways. [0003] However, there are still many defects in the new setting method, such as: when the user voice sets the reminder, the voice (sentence structure) input by the user varies greatly, which brings difficulty for the device to recognize the user's intention. For another example, it is possible that the user's intention to set a reminder is hidden in the user's voice, and the device does not correctly acquire the user's intention and ignores the user's need to set a reminder. Contents of the invention [0004] Aiming ...

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): H04M1/725G10L15/26G06Q10/10H04M1/72451
Inventor 邱楠宋亚楠梁剑华邵浩邓婧文张凯李方圆严汉明邹创华
Owner 江苏瑞焕激光科技有限公司
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
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