Multi-source data and time sequence processing method and device for construction of industry knowledge graph

Abstract

The invention discloses a multi-source data and time sequence processing method and device for construction of an industry knowledge graph. The method comprises the following steps: constructing an ontology layer of the knowledge graph, wherein the ontology layer comprises ontologies, ontology attributes and an ontology relation; extracting entities and entity attributes from multiple data sources, and conducting inconsistency check on the entities; conducting inconsistency check on the entity attributes of all the entities, wherein an entity relationship between the entities inherits the ontology relationship between the ontologies corresponding to the entities; and establishing indexes of a knowledge graph database and a time sequence database. The method has the advantages that throughthe uniqueness of a standard naming table and the relational database, entity conflict resolution accuracy is ensured to the greatest extent; by utilizing the advantage that the knowledge graph has the ontology layer, accurate classification of the entity attributes is realized by establishing similar labels, and fusion efficiency is effectively improved; and the problem that the knowledge graph is difficult to process time sequence data is solved by establishing indexes between knowledge graph database ontologies and a time sequence database form.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and in particular relates to a multi-source data and time series processing method and device for constructing industry knowledge graphs. Background technique [0002] In the context of the era of big data, with the emergence of massive data and the cross-application of multi-data source fusion, the problem of multi-source heterogeneous data fusion has become increasingly prominent, and data association is particularly important. When big data is processed and analyzed, it is limited to a small area and cannot dig out more valuable information. In recent years, knowledge graph, as a new knowledge representation method and data management model, establishes various entities or concepts and their relationships in the real world, and realizes data integration from different data sources. For knowledge graphs in vertical fields, data sources mainly include three types: one is the data of th...

AI Technical Summary

Problems solved by technology

[0003] Theoretically, knowledge graphs can solve the problems of multi-source heterogeneous data extraction, fusion and storage, but there is currently no effective multi-source data processing method for knowledge graphs in vertical fields, and some well-known domain knowledge bases are mostly manually constructed by domain experts , although the quality is high, there are problems such as low degree of automation, low knowledge coverage, and slow update. If the industry knowledge graph is constructed in a semi-automatic way, and the knowledge extraction and fusion methods of the general knowledge graph are used, the quality of the knowledge base is difficult to guarantee, and which Issues such as the need for manual participation in the link and specific processing methods have always been key issues in the implementation of domain knowledge graphs; in addition, the skyrocketing and updating of data shows that knowledge graphs are dynamic, and many knowledge in vertical fields involve time series, such as daily observations, Daily sales volume, daily stock closing price, monthly average temperature, etc. These types of data are not suitable for direct storage in graph databases, but they are necessary for analysis and research. How should knowledge graphs handle this part of time series data?

[0004] To sum up, the construction of industry knowledge graphs has disadvantages such as low efficiency of multi-source massive data processing and difficulty in time series data processing. Those skilled in the art should seek multi-source data and time series processing methods for building industry knowledge graphs

Images