Intelligent Wechat Banking System Based on Natural Language Automatic Scheduling Program and Natural Language Intelligent Scheduling Method for Computer System
A natural language and automatic scheduling technology, applied in the direction of voice input/output, etc., can solve the problem of unfriendly experience and achieve the effect of reducing the link of judgment and selection, novel and human-computer interaction experience, and convenient for customers to use
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] The present invention is an intelligent WeChat banking system based on a natural language automatic scheduler, comprising: a natural language input device 1 for accepting description calling commands or questions, the natural language input device adopts a web question-and-answer client, and the natural language The input is handwriting input or voice input, for example, it may be text converted by voice, for example: query the balance of all my accounts.
[0038] A natural language processing device 2 for performing basic word segmentation and syntactic analysis on commands or questions accepted by the natural language input device, and processing specific vocabulary according to the rules in the rule base 3 . The natural language processing device uses word segmentation technology to perform word segmentation and syntactic analysis on natural language, and processes specific words according to the rules in the rule base. Then, it is passed to the predicate extraction ...
Embodiment 2
[0049] The present invention is a kind of natural language intelligent dispatching method to computer system, comprises the following steps:
[0050] Step A: Accept the natural language describing the call command or question; it can be text converted from voice, for example: query the balance of all my accounts.
[0051] Step B: Perform natural language analysis, and process specific words according to the rules in the rule base;
[0052] Step C: According to the result obtained in step B, generate a first-order predicate description and a description of constraint attributes. It includes the step of extracting first-order predicates for specific or main verbs, expressing the main intention of input commands or questions, and extracting specific or mainly restrictive words to extract constraint data.
[0053] Step D: Annotate the functions and parameters in the function library ontology; through the function ontology annotation module, perform semantic annotations on the fun...
Embodiment 3
[0061] In this embodiment, first apply for a WeChat bank public account (also called a subscription number, represented by "K" in this article), and provide intelligent services based on natural language through this public account. Deploy a WeChat banking background server (for example: www.keydian.com) that provides Internet access. This server runs the WeChat banking system described in this patent, and binds the public account K to this server address. In this way, when a user on WeChat pays attention to WeChat Bank’s public account K and asks a question in natural language to WeChat Bank, the question will be forwarded to the background server, which will process it and go through the steps described above , and finally returns the result, and then replies to the user through the WeChat public account K. This is a complete process. A specific problem is taken as an example to describe the working principle of the present invention.
[0062] When the user inputs "query t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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