Lightweight server-free computing method based on message
A Serverless, Computational Approach Technology Applied to Computing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0091] as attached figure 1 As shown, a message-based lightweight serverless computing method, including:
[0092] Step 100: receive customer message, determine message content and message type;
[0093] The customer information received by the present invention includes three types of description information, behavior information and association information.
[0094] Descriptive information is mainly used to understand the basic attributes of customers, such as: contact information, geographic information and demographic information of individual customers, socioeconomic statistical information of corporate customers, etc. This type of information mainly comes from customer registration information. And the basic customer information collected through the enterprise's operation management system.
[0095] Behavioral information generally includes: customer purchase records of services or products, customer service or product consumption records, customer contact records wit...
Embodiment 2
[0110] As an embodiment of the present invention, said receiving a client message, determining message content and message type includes:
[0111] Based on the synonymous semantic division rule, the customer message is divided into a variety of different message sequences according to the sentence; the synonymous semantic division rule is based on the content meaning of the customer content, and the customer information with the same meaning is divided into one category, each One class is a sequence of messages, and then forms a variety of different message sequences.
[0112] Carry out correlation calculation on different sentences in the same message sequence, and determine the first correlation parameter between different sentences in the same message sequence; in the same message sequence, there will be at least one sentence with the same semantic meaning, then the first correlation parameter is 1; When there are two or more sentences with the same semantics in the same me...
Embodiment 3
[0119] As an embodiment of the present invention, the determination of the required message algorithm and algorithm capture method according to the message content includes:
[0120] Obtain message content, determine feature parameters and feature types; type features include timeliness features, depth features, capacity features, etc., and perform calculation formulas to determine message features according to specific message calculation features.
[0121] According to the feature type, determine the algorithm parameters and demand parameters of the message content corresponding to each feature type; the algorithm parameter is the parameter that can be directly obtained from the message content required for calculation, such as: the capacity of the customer message, that is, the occupied Memory space, parameters of the semantic features of the client message, that is, the expressive meaning of the client message. The demand parameter is a demand parameter that starts from the ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


