碳排放信息生成方法、装置、电子设备、介质和程序产品
By inputting the text of an item into a preset entity recognition model to generate an item text vector, and using an item information vector set and a carbon emission database to determine similar item identifiers, the problem of not being able to generate carbon emission information for items that are not stored in the existing technology is solved, thus achieving efficient carbon emission information generation and reducing resource consumption.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
- Filing Date
- 2022-06-28
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for generating carbon emissions for items rely on carbon factors pre-stored in structured tables, which makes it impossible to generate carbon emission information for items that are not stored. Furthermore, retrieving carbon factors by traversing table names and fields consumes a large amount of storage and computing resources, resulting in low retrieval efficiency.
By inputting the text of an item into a preset entity recognition model, an item text vector is generated. Using the item information vector set and carbon emission database, similar item identifiers are determined, and item carbon emission information is generated. This avoids traversing and searching through structured tables, reducing storage and computing resource consumption.
This technology enables the generation of carbon emission information for items, reduces the consumption of storage and computing resources, improves retrieval efficiency, and solves the problem that existing technologies cannot generate carbon emission information for items that are not stored.
Smart Images
Figure CN115292436B_ABST