Weapon equipment text processing method and device combining AI and RPA and electronic equipment

Abstract

The invention provides aweapon equipment text processing method and device combining AI and RPA and electronic equipment, and relates to the field of AI and RPA. The method comprises the steps: obtaining a set of weapon equipment texts based on an RPA robot or an IP agent; performing type identification on the weapon equipment texts in the set; under the condition that the type is the key value pair text, inputting a preset natural language question and the key value pair text into the reading understanding model so as to determine an answer text corresponding to the natural language question from the key value pair text and semantic correlation between the natural language question and the key value pair text; and under the condition that the natural language question and the key value pair text are related in semantics, determining structured data of the weapon equipment according to the answer text and attribute words in the natural language question. Therefore, the automation degree in obtaining the weapon equipment text is improved, the purpose of accurately generating the structured data from the weapon equipment text in the unified format is achieved, and the accuracy and efficiency in constructing the knowledge graph are improved.

Description

technical field [0001] The present disclosure relates to the technical fields of Artificial Intelligence (AI for short) and Robotic Process Automation (RPA for short), in particular to a text processing method, device and electronic equipment for weapons and equipment combined with AI and RPA. Background technique [0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules. [0003] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. [0004] At present, in order to construct the knowledge graph of weapons and equipment, it is necessary to obtain the structured data of weapons and equipment from the open source weapon and equipment text, and construct the knowledge graph based on the structured data. [0005] In related te...

AI Technical Summary

Problems solved by technology

[0005] In related technologies, it is necessary to manually participate in the acquisition of structured data of weapons and equipment, and, due to the diversity of data sources, the quality of acquired weapon and equipment data is uneven, and the massive data is manually screened to retain the availability of knowledge graphs. High weapon and equipment data, however, manual participation in the acquisition of weapon and equipment data reduces the efficiency of weapon and equipment data acquisition, and the manually screened data has inconsistent data formats, which reduces the accuracy and efficiency of building knowledge graphs

Images