Method and device for improving reaching rate of short message based on classification simulation model

A simulation model and SMS technology, which is applied in the field of improving SMS reach rate based on classification simulation model, can solve the problems of changing the overall semantics, long delay, inability to obtain replaceable characteristic vocabulary and confrontation text in real time, so as to improve usability , avoid delay effects, and efficiently counteract the effect of text generation

Active Publication Date: 2021-09-24
南京山猫齐动信息技术有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Adversarial text generation is based on the existing text to generate similar text that can change the model label, but due to the characteristics of the language itself, the generated adversarial text may change the overall semantics, and there are many uncertainties
At the same time, the real SMS contact recognition device generally has a long delay. If the confrontation text is generated for the real SMS contact recognition device, it needs to be called many times in the process of determining the characteristic vocabulary and generating the confrontation text, and it is impossible to obtain real-time information. Feature words for replacement and adversarial text

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 improving reaching rate of short message based on classification simulation model
  • Method and device for improving reaching rate of short message based on classification simulation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as Figure 1-2 As shown, the embodiment of the present application provides a method for improving the SMS reach rate based on the classification simulation model, including the following steps:

[0048] Step (1): Input the unlabeled SMS sample data into the real SMS contact recognition device M0 to obtain the SMS sample data D=(X, Y) with binary classification labels, and the SMS sample data with binary classification labels The text classification simulation model M1 is obtained through training; specifically:

[0049] It is known that a real text message contact recognition device is denoted as M0, and there are n pieces of unlabeled text message samples. Input the unlabeled SMS sample data into the real SMS contact recognition device M0 to obtain the SMS sample data with binary classification labels: D=(X, Y), X={X 1 , X 2 ,...,X n}, Y={0, 1}, where Y represents the SMS sample label, Y=0 indicates that the SMS can reach the user, Y=1 indicates that the SMS ...

Embodiment 2

[0115] The present application provides a device for improving the reach rate of short messages based on a classification simulation model. The device includes a memory, a processor, and a computer program stored in the memory and operable on the processor. The computer program is controlled by When the processor executes, implement the method described in the first embodiment.

[0116] It should be understood that in this embodiment, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor, and a part of the memory may also include a non-volatile random access memory. For example, the memory may also store device type information.

[0117] The processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices, disc...

Embodiment 3

[0123] The present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the first embodiment is realized.

[0124] Storage media include: U disk, mobile hard disk, read-only memory (English full name: Read-OnlyMemory, English abbreviation: ROM), random access memory (English full name: Random Access Memory, English abbreviation: RAM), magnetic disk or optical disc, etc. Various media that can store program code.

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 and device for improving the reaching rate of a short message based on a classification simulation model, and belongs to the field of artificial intelligence. The method for improving the reaching rate of the short message based on the classification simulation model comprises the following steps of training the classification simulation model M1 by utilizing a dichotomy short message data sample with a label obtained in a real short message reaching identification device M0; before the short message is sent, inputting a short message copywriting into the classification simulation model M1, and if it is predicted that the short message can reach a user, sending the short message directly; and if it is predicted that the short message cannot reach the user, generating an adversarial text for the classification simulation model M1, and when the generated adversarial text is recognized as being capable of reaching the user through the real short message reach recognition device, sending the short message. According to the method, the technical advantages of a text classification model and an adversarial text technology are fully utilized, and the short message reaching rate is increased.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method and device for improving the reach rate of short messages based on a classification simulation model. Background technique [0002] In the process of SMS operation, it is expected that SMS can reach 100% of users to achieve the expected operation effect. However, in the actual SMS operation process, there are always situations where the user cannot be reached. Once the SMS cannot reach the user, how to modify it to generate effective copywriting to ensure the reach of the SMS is a problem that needs to be solved. [0003] In the field of artificial intelligence, machine learning models are good at learning patterns from data. Adversarial text generation is based on the existing text to generate similar text that can change the model label. However, due to the characteristics of the language itself, the generated adversarial text may change the overall semantics, a...

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): G06F16/35G06F40/194G06F40/247G06F40/279G06F40/30G06N20/00
CPCG06F16/355G06F40/194G06F40/247G06F40/279G06F40/30G06N20/00
Inventor 陈帆其他发明人请求不公开姓名
Owner 南京山猫齐动信息技术有限公司
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