匹配数据的方法、装置、设备和计算机可读介质
By combining the Transformer model, the DeepFM model, and the residual network, the problem of mismatch in sales lead allocation was solved, achieving efficient matching between sales personnel and sales leads and increasing the number of orders.
CN115619142BActive Publication Date: 2026-07-17BEIJING JINGDONG ZHENSHI INFORMATION TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING JINGDONG ZHENSHI INFORMATION TECH CO LTD
- Filing Date
- 2022-10-12
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In existing technologies, mismatched allocation of sales leads prevents an increase in order volume.
Method used
The Transformer model and DeepFM model are combined with residual networks to extract the matching degree between sales personnel and sales leads. By encoding the business characteristics of sales personnel and the characteristics of leads, a feature set is constructed and the residual network is used to extract the feature values of lead business combination, and the matching degree is output to match sales personnel and sales leads.
Benefits of technology
This improved the matching rate between sales leads and sales personnel, thereby increasing the number of orders.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115619142B_ABST
Abstract
本发明公开了匹配数据的方法、装置、设备和计算机可读介质，涉及计算机技术领域。该方法的一具体实施方式包括：将销售人员的业务特征经Transformer模型编码后，结合销售线索的线索特征输入DeepFM模型，以获取所述线索特征的线索联合特征；将所述销售人员的业务特征输入Transformer模型中，以获取所述业务特征的业务组合特征；在所述线索联合特征与所述业务组合特征构造的特征集合中，利用残差网络，提取线索业务组合特征值，并基于所述线索业务组合特征值输出所述销售人员与所述销售线索的匹配度，以匹配所述销售人员和所述销售线索。该实施方式能够提高销售线索与销售人员的匹配程度，进而提高订单数量。
Need to check novelty before this filing date? Find Prior Art