The solution search system and the operation method of the solution search system

Abstract

The invention provides a solution scheme search system and operation method of solution scheme search system, the solution scheme search system includes an arithmetic server, plural pieces of model servers, giant amount of databases, a database server, a central server and a relational database. The central server according to the recorded user identity in the relational database provides plural pieces of usable prediction models for the user to choose. The central server transfers to the arithmetic server a first question description archives sent by a user and a chosen first prediction model. The arithmetic server according to the first question description archives and the first prediction model produces a first model input archives. A first model sever corresponding to the first prediction model utilizes the first prediction model and the first model input archives to generate a first solution scheme code. The database server according to the first solution scheme code reads at least one first solution scheme through the giant amount of databases.

Description

technical field [0001] The present invention relates to a solution search system, in particular to a solution search system utilizing massive data and data exploration technology. Background technique [0002] The success of a product is not only closely related to the research and development technology, but also requires a large number of tests to ensure the stability of the product, especially for high-tech products that require high stability and reliability, such as industrial instruments, mobile devices, workstations, personal For products such as computers or servers, the standards for quality control testing are more stringent. When a problem is detected in a product, it is necessary to reproduce the problem, collect and analyze relevant data, find out the possible cause of the problem, propose a possible solution, and verify the proposed solution...etc. to ensure that the detected problem can be detected Properly resolved, these processes may not only be very time-...

AI Technical Summary

Problems solved by technology

When a problem is detected in a product, it is necessary to reproduce the problem, collect and analyze relevant data, find out the possible cause of the problem, propose a possible solution, and verify the proposed solution...etc. to ensure that the detected problem can be detected Properly resolved, these processes may not only be very time-consuming, but may even cause the product to miss the opportunity to enter the market, and the implementation must rely on the engineer's personal experience and professionalism; that is, whether the engineer's experience and professionalism are sufficient will greatly affect It affects the time required to propose a solution, and may also affect whether the proposed solution can completely solve the problem, making the quality of the solution difficult to grasp

In addition, since personal experience is not easy to pass on, even if the problem to be solved is the same or similar, different engineers may still have to repeat the above process to come up with a solution. This approach is not only inefficient, but also cannot ensure that engineers can find the most suitable solution. cut solution

[0003] In addition, for the same type of products, the proportion of the same or similar problems is very high. Although the solution was recorded or archived in the past, due to the variety of problems, the amount of information involved is quite large, and The way that each engineer describes the problem may be inconsistent, so it is difficult to store it systematically. As a result, it is still difficult for engineers to find relevant solutions in practice, and it is difficult to achieve the purpose of enabling engineers to share experience

Images