Method for solving similar mathematical problems based on equations and questions

Abstract

The invention discloses a method for solving similar mathematical problems based on equations and questions, which comprises the following steps: (1) analyzing a corresponding relationship between numbers in the equations and numbers in the questions to form a universal equation of a single question; (2) marking question types, querying general equations of other single questions under the questions of the same type, and performing intersection calculation to form the general equations of the questions of the same type; and (3) inputting mathematical problems of the same kind, matching a universal equation, and solving a result. According to the invention, the general equation used by the question of the sentence pattern is determined by analyzing the relationship between the equation and the numbers in the question, and the question of the same kind of sentence pattern is solved by utilizing the general equation, so that a large amount of data is not required to be used as a training sample for training, and a general equation can be generated only by a small number of training samples; solving of similar questions is achieved, the data training amount is reduced while excessive computing resources are not consumed, the speed is high, efficiency is high, and implementation is easy.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method for solving similar mathematical problems based on formulas and problems. Background technique [0002] At present, in the field of computer-based problem-solving, the performance of various artificial intelligence systems is that science-based problem-solving is generally weaker than liberal arts-based problem-solving. The reason is that machine learning emphasizes more on the storage and application of memory, calculation, and other related content. The module of logical understanding and reasoning has not been well solved, and mathematical problem-solving, as a part of the science exam, is a test of the computer's understanding and reasoning ability. The research results on mathematical problem-solving are very likely to define the computer. A new level of intelligence. In view of this, mathematical problem solving is also becoming an important puzzle of artificial ...

AI Technical Summary

Problems solved by technology

When existing computers solve mathematical problems, the technical means generally used are LSTM (Long short-term memory, long-term short-term memory) and Transformer model. Both LSTM and Transformer architectures include an encoder and a decoder. Above, LSTM encodes the problem into a series of specific positions represented by keys and values, and the decoder predicts and maps the next character. LSTM can also pre-process some objects that need to be completed logically, such as calculating 8 / (1 + 3), it will calculate (1 + 3) first, and then perform the division operation. This step is already a bit close to the reasoning steps when humans perform calculations, but according to reports, the accuracy of a current intelligent model after training It is about 30%-60%, so the existing problem-solving methods still have the following disadvantages: 1. Large training samples are required, 2. Calculation accuracy is low after training

Images