Check patentability & draft patents in minutes with Patsnap Eureka AI!

Method and device for verbal skill prediction and storage medium

A technology of speaking and target prediction, applied in the Internet field, can solve the problems of insufficient learning of the prediction model, low prediction accuracy, and inability to obtain sample training for the prediction model. Effect

Pending Publication Date: 2022-04-19
北京有限元科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present disclosure provide a method, device, and storage medium for speech prediction, so as to at least solve the problems existing in the prior art for predicting speech terms when there are few outbound call data or few dialogue nodes. The forecasting model cannot obtain enough samples for training, so that the forecasting model learns insufficiently, resulting in technical problems of low forecasting accuracy

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
  • Method and device for verbal skill prediction and storage medium
  • Method and device for verbal skill prediction and storage medium
  • Method and device for verbal skill prediction and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] According to this embodiment, an embodiment of a method for speech speech prediction is provided. It should be noted that the steps shown in the flow charts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, Although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0024] The method embodiments provided in this embodiment can be executed in mobile terminals, computer terminals, servers or similar computing devices. figure 1 A block diagram of a hardware structure of a computing device for implementing the method for utterance prediction is shown. Such as figure 1 As shown, the computing device may include one or more processors (processors may include but not limited to processing devices such as microprocessors MCUs or programmable logic devices FPGAs), memory for storing data, and me...

Embodiment 2

[0086] Image 6 Shows a device 600 for utterance prediction according to this embodiment, the device 600 corresponds to the method described in the first aspect according to Embodiment 1, and is used to generate a set of utterances composed of multiple utterances Determine the target discourse term that matches the user. refer to Image 6As shown, the apparatus 600 includes: an acquisition module 610, configured to acquire user characteristic information associated with a user; a first determination module 620, configured to use a preset business target value for predicting a term for a specified business target The specified business target prediction model, according to the user characteristic information, determines the business target value of each term in the term set corresponding to the specified business target; and the second determination module 630 is used to determine from the term Determine the target discourse terms that match the user in the set, where differe...

Embodiment 3

[0095] Figure 7 Shows the device 700 for utterance prediction according to this embodiment, the device 700 corresponds to the method according to the first aspect of Embodiment 1, and is used to generate a set of utterances and terms composed of multiple utterances and terms Determine the target discourse term that matches the user. refer to Figure 7 As shown, the device 700 includes: a processor 710; and a memory 720, connected to the processor 710, used to provide the processor 710 with instructions for processing the following processing steps: obtaining user characteristic information associated with the user; using a preset a specified business objective prediction model for predicting a business objective value of a utterance term for a specified business objective, determining a business objective value corresponding to a specified business objective for each utterance term in the utterance term set according to the user characteristic information; and according to t...

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 verbal skill prediction method and device and a storage medium. The method comprises the following steps: acquiring user feature information associated with a user; determining a business target value of each verbal-skill term in the verbal-skill term set corresponding to a specified business target according to the user feature information by using a preset specified business target prediction model for predicting the business target value of the verbal-skill term for the specified business target; according to the service target value, target verbal skill terms matched with the user are determined from a verbal skill term set, different service targets correspond to different service scenes, and the specified service target prediction model is obtained based on training of first sample data and second sample data; the first sample data is sample data generated by other business scenes different from the target business scene corresponding to the specified business target, and the second sample data is sample data generated by the target business scene corresponding to the specified business target.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to a method, device and storage medium for speech prediction. Background technique [0002] Due to the development of artificial intelligence technology, many voice communication systems through robots and people have emerged, especially in voice interaction scenarios such as voice customer service, smart telemarketing, smart collection, and smart speakers. After the robot can communicate with people by voice, how to improve the post-communication effect becomes a difficult point (for example, in intelligent reminder, how to improve the efficiency of robot reminder). In addition to artificially optimizing the robot's speech skills, we also expect to be able to carry out precise marketing of users based on user portraits, so as to achieve the marketing effect of thousands of people. [0003] For example, people who are sensitive to quotas and people who are sensitive ...

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): G06F16/332G06F16/335G06N20/00G06Q30/02
CPCG06F16/3329G06F16/335G06N20/00G06Q30/0252G06Q30/0251
Inventor 罗欢陈实关力王洪斌蒋宁吴海英
Owner 北京有限元科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com